Commit earlier refactoring

workflow/apps/matlab/easy/DMPexcel2mat.m

@@ -0,0 +1,329 @@
+%% CALLED BY EASYconsole.m %%
+
+global mpdmFile
+global masterPlateFile
+global drugMediaFile
+global matDir
+
+% If we already have mpdmFile, don't recreate
+if (exist(mpdmFile, 'file') && ~isempty(mpdmFile))
+  fprintf('The Drug Media/MasterPlate Annotation File: %s exists, skipping DMPexcel2mat.m\n', mpdmFile);
+  return
+end
+
+% Do our best to find and load a relevant MasterPlate file
+if ~exist(masterPlateFile, 'file') || isempty(masterPlateFile)
+  if exist(fullfile(matDir), 'dir')
+    % Try to find the masterPlateFile automatically (newest created first)
+    try
+      files=dir(matDir);
+      mpFiles={files(strncmp(files.name, 'MasterPlate_', 12)).name};
+      if isempty(mpFiles)
+        throw(MException('MATLAB:dir', 'No MasterPlate_ files in the default MasterPlate directory'));
+      end
+      % this sorts by date (newest first)
+      [~, sortedIndices]=sort(datenum({files(strncmp(mpFiles.name, 'MasterPlate_', 12)).date}), 'descend');
+      sortedFiles=mpFiles(sortedIndices);
+      masterPlateFile=sortedFiles{1};
+      disp('Using newest MasterPlate file: ', masterPlateFile, ', skipping directory selection');
+    catch ME
+      % This can be silent, not really an error
+    end
+
+    for i=1:5 % give users 5 chances to get it right
+      try
+        % For standalone mode
+        % GUI input for selecting a MasterPlate Excel file
+        questdlg('Select MasterPlate Directory (containing DrugMedia_ & MasterPlate_ files)','Directory Selection','OK',...
+        struct('Default','OK','Interpreter','tex'))
+        dirToScan=uigetdir();
+        files=dir(dirToScan);
+        mpFiles={files(strncmp(files.name, 'MasterPlate_', 12)).name};
+        if isempty(mpFiles)
+          throw(MException('MATLAB:dir', 'No MasterPlate_ files in directory'))
+        end
+        % this sorts by date (newest first)
+        [~, sortedIndices]=sort(datenum({files(strncmp(mpFiles.name, 'MasterPlate_', 12)).date}), 'descend');
+        sortedFiles=mpFiles{sortedIndices};
+        masterPlateFile=sortedFiles{1};
+        disp('Using newest MasterPlate file: ', masterPlateFile, ', skipping directory selection');
+        break
+      catch ME
+        h=msgbox(ME.message, 'Error', 'error');
+        disp('Rerunning directory selection');
+        % I don't know what else we'll need to do here
+      end
+    end
+  else
+    for i=1:5 % give users 5 chances to get it right
+      try
+        % For standalone mode
+        % GUI input for selecting a MasterPlate Excel file
+        questdlg('Select MasterPlate Directory (containing DrugMedia_ & MasterPlate_ files)','Directory Selection','OK',...
+        struct('Default','OK','Interpreter','tex'))
+        dirToScan=uigetdir();
+        files=dir(dirToScan);
+        mpFiles={files(strncmp(files.name, 'MasterPlate_', 12)).name};
+        if isempty(mpFiles)
+          throw (MException('MATLAB:dir', 'No MasterPlate_ files in directory'));
+        end
+        % this sorts by date (newest first)
+        [~, sortedIndices]=sort(datenum({files(strncmp(mpFiles.name, 'MasterPlate_', 12)).date}), 'descend');
+        sortedFiles=mpFiles{sortedIndices};
+        masterPlateFile=sortedFiles{1};
+        disp('Using newest MasterPlate file: ', masterPlateFile, ', skipping directory selection');
+        break
+      catch ME
+        h=msgbox(ME.message, 'Error', 'error');
+        uiwait(h);
+        disp('Rerunning directory selection');
+        % I don't know what else we'll need to do here
+      end
+    end
+  end
+else
+  fprintf('Using MasterPlate file: %s skipping directory selection\n', masterPlateFile);
+end
+
+% fid=fopen(masterPlateFile)%('exp23PrintTimes.xls'); % textread puts date and time sequentially into vector
+% TODO needs explanation, it isn't clear what it is for
+% The input files should be csv, not xlsx
+% This whole file could be much better and more portable
+if ispc
+  [num, txt, raw]=xlsread(masterPlateFile);  %,'Yor1HitsMPsetFinal');
+  fields={txt(2,1:15)}; %or 1:17 for later but dont wish to exceed and cause error ? if used  
+else
+  clear MPtbl
+  opts=detectImportOptions(masterPlateFile);
+  MPtbl=readtable(masterPlateFile,opts);
+  MPtbl=readtable(masterPlateFile);
+  fields={opts.VariableNames};  %? if used anywhere although 'saved' to MPDMmat
+  MPcell=readcell(masterPlateFile);
+end
+
+numb=0;
+clear MP;
+try
+  if ispc
+    excLnNum=3;
+    while (isequal(txt{excLnNum,1},'###'))
+      numb=numb+1;    
+      MP(numb).head={raw(excLnNum,2:6)};
+      MP(numb).recNum={raw((excLnNum+1):(excLnNum+384),1)};
+      MP(numb).orf={raw((excLnNum+1):(excLnNum+384),2)};
+      MP(numb).strain={raw((excLnNum+1):(excLnNum+384),3)};
+      MP(numb).genename={raw((excLnNum+1):(excLnNum+384),12)};
+      MP(numb).drug={raw((excLnNum+1):(excLnNum+384),8)};
+      MP(numb).media={raw((excLnNum+1):(excLnNum+384),7)};
+      if size(raw,2)>15
+        MP(numb).orfRep={raw((excLnNum+1):(excLnNum+384),16)}; % added 12_1005 to specify replicates Orfs in MP
+        MP(numb).specifics={raw((excLnNum+1):(excLnNum+384),17)}; % added 12_1008 to specify replicates Specific details in MP
+      else
+        MP(numb).orfRep=' ';   
+        MP(numb).specifics= ' ';
+      end
+      % Future MP field
+      % if size(raw,2)>17 
+      %   MP(numb).specifics2= {raw((excLnNum+1):(excLnNum+384),18)};  % added 12_1008 to specify strain Bkground in MP
+      % else
+      %   MP(numb).specifics2=' ';
+      % end
+      excLnNum=excLnNum+385;
+      msg=strcat('NumberOfMP = ',num2str(numb), '   lastLineNo. = ',num2str(excLnNum));
+    end
+  else 
+    excLnNum=1;
+    while (isequal(MPcell{(excLnNum+2),1},'###'))
+      numb=numb+1;    
+      MP(numb).head={MPtbl(excLnNum,2:6)};
+      MP(numb).head{1}=table2cell(MP(numb).head{1});
+      MP(numb).recNum={MPtbl((excLnNum+1):(excLnNum+384),1)};
+      MP(numb).recNum{1}=table2cell(MP(numb).recNum{1});
+      MP(numb).orf={MPtbl((excLnNum+1):(excLnNum+384),2)};
+      MP(numb).orf{1}=table2cell(MP(numb).orf{1});
+      MP(numb).strain={MPtbl((excLnNum+1):(excLnNum+384),3)};
+      MP(numb).strain{1}=table2cell(MP(numb).strain{1});
+      MP(numb).genename={MPtbl((excLnNum+1):(excLnNum+384),12)};
+      MP(numb).genename{1}= table2cell(MP(numb).genename{1});
+      MP(numb).media= {MPtbl((excLnNum+1):(excLnNum+384),7)};
+      MP(numb).media{1}= table2cell(MP(numb).media{1});
+      if size(MPtbl,2)>15
+        MP(numb).orfRep= {MPtbl((excLnNum+1):(excLnNum+384),16)}; % added 12_1005 to specify replicates Orfs in MP
+        MP(numb).orfRep{1}=table2cell(MP(numb).orfRep{1});
+        MP(numb).specifics={MPtbl((excLnNum+1):(excLnNum+384),17)}; % added 12_1008 to specify replicates Specific details in MP
+        MP(numb).specifics{1}=table2cell(MP(numb).specifics{1});
+      else
+        MP(numb).orfRep= ' ';   
+        MP(numb).specifics= ' ';
+      end
+      excLnNum=excLnNum+385;
+      msg=strcat('NumberOfMP = ',num2str(numb), 'lastLineNo. = ',num2str(excLnNum));
+    end
+  end
+catch ME
+  h=msgbox(ME.message, 'Error', 'error');
+  uiwait(h);
+end
+
+%DMupload
+%Drug and Media Plate setup  Upload from Excel
+excLnNum=1;
+numOfDrugs=0;
+numOfMedias=0;
+
+% Grabbing the bare filename from the MasterPlate file to see if we can automatically
+% find a matching DrugMedia file
+[mpFile, mpPath]=fullfile(masterPlateFile);
+mpFileParts=strsplit(mpFile, '_');
+mpBareFileName=strjoin(mpFileParts(2:end-1), '_');
+
+if ~exist(drugMediaFile, 'file') || isempty(drugMediaFile)
+  if exist(fullfile(matDir), 'dir')
+    try
+      dmFileToTest=fullfile(mpPath, 'DrugMedia_', mpBareFileName, '.xlsx');
+      if exist(dmFileToTest, 'file') % Try to find a matching drug media file
+        drugMediaFile=dmFileToTest;
+        fprintf('Using matching DrugMedia file: %s, skipping directory selection\n', drugMediaFile);
+      else
+        % Try to find the DrugMedia file automatically (newest created first)
+        files=dir(matDir);
+        dmFiles={files(strncmp(files.name, 'DrugMedia_', 10)).name};
+        if isempty(dmFiles)
+          throw (MException('MATLAB:dir', 'No DrugMedia_ files in directory'));
+        end
+        % this sorts by date (newest first)
+        [~, sortedIndices]=sort(datenum({files(strncmp(dmFiles.name, 'DrugMedia_', 10)).date}), 'descend');
+        sortedFiles=dmFiles{sortedIndices};
+        drugMediaFile=sortedFiles{1};
+        fprintf('Using newest DrugMedia file: %s, skipping directory selection\n', drugMediaFile);
+
+      end
+    catch Me
+      % This can be silent, not really an error
+    end
+  else
+    for i=1:5 % give users 5 chances to get it right
+      try
+        % GUI input for selecting a DrugMedia file
+        % sort by newest matching DrugMedia file and return that if we find one
+        % For standalone mode
+        % GUI input for selecting a MasterPlate Excel file
+        questdlg('Select DrugMedia directory','Directory Selection','OK',...
+        struct('Default','OK','Interpreter','tex'))
+        dirToScan=uigetdir();
+        files=dir(dirToScan);
+        dmFiles={files(strncmp(files.name, 'DrugMedia_', 10)).name};
+        if isempty(dmFiles)
+          throw (MException('MATLAB:dir', 'No DrugMedia_ files in directory'));
+        end
+        % this sorts by date (newest first)
+        [~, sortedIndices]=sort(datenum({files(strncmp(dmFiles.name, 'DrugMedia_', 10)).date}), 'descend');
+        sortedFiles=dmFiles{sortedIndices};
+        drugMediaFile=sortedFiles{1};
+      catch ME
+        h=msgbox(ME.message, 'Error', 'error');
+        uiwait(h);
+        disp('Rerunning directory selection');
+        % I don't know what else we'll need to do here
+      end
+    end
+  end
+else
+  fprintf('Using drugMediaFile: %s, skipping directory selection\n', drugMediaFile);
+end
+
+% Drug and Media Plate setup
+% TODO needs better explanation
+if ispc
+  [num, txt, raw]=xlsread(drugMediaFile);  %'Yor1HitsMPsetFinal');
+  fields={txt(2,1:5)};
+  Linked=num(1,1);
+else
+  opts=detectImportOptions(drugMediaFile); 
+  DMtbl=readtable(drugMediaFile,opts);
+  fields=opts.VariableOptions;   
+  Linked=DMtbl{1,1};
+  DMcell=readcell(drugMediaFile);
+end
+
+% TODO needs better explanation
+numb=0;
+if isequal(Linked,1) % Drugs and Media are linked 1 to 1; else they are combinatorial
+  clear DM;
+  excLnNum=2;
+  if ispc
+    while (~isequal(txt{excLnNum,2},'###'))
+      numb=numb+1;    
+      DM.drug(numb)={raw(excLnNum,2)};
+      DM.conc(numb)={raw(excLnNum,3)};
+      DM.media(numb)={raw(excLnNum,4)};
+      DM.mod1(numb)={raw(excLnNum,5)};
+      DM.conc1(numb)={raw(excLnNum,6)};
+      DM.mod2(numb)={raw(excLnNum,7)};
+      DM.conc2(numb)={raw(excLnNum,8)};
+      excLnNum=excLnNum+1;
+      msg=strcat('NumberOf1:1DrugMediaPlates = ',num2str(numb), '   lastLineNo. = ',num2str(excLnNum));
+    end
+  else
+    clear DM
+    excLnNum=1;
+    while (~isequal(DMcell{excLnNum+1,2},'###'))
+      numb=numb+1;    
+      DM.drug(numb)={DMtbl(excLnNum,2)};
+      DM.drug(numb)=table2cell(DM.drug{numb});
+      DM.conc(numb)={DMtbl(excLnNum,3)};
+      DM.conc(numb)=table2cell(DM.conc{numb});
+      DM.media(numb)={DMtbl(excLnNum,4)};
+      DM.media(numb)=table2cell(DM.media{numb});
+      DM.mod1(numb)={DMtbl(excLnNum,5)};
+      DM.mod1(numb)=table2cell(DM.mod1{numb});
+      DM.conc1(numb)={DMtbl(excLnNum,6)};
+      DM.conc1(numb)=table2cell(DM.conc1{numb});
+      DM.mod2(numb)={DMtbl(excLnNum,7)};
+      DM.mod2(numb)=table2cell(DM.mod2{numb});
+      DM.conc2(numb)={DMtbl(excLnNum,8)};
+      DM.conc2(numb)=table2cell(DM.conc2{numb});
+      excLnNum=excLnNum+1;
+      msg=strcat('NumberOf1:1DrugMediaPlates = ',num2str(numb), '   lastLineNo. = ',num2str(excLnNum));
+    end
+  end
+end
+% Legacy contengency: not ever used
+if isequal(Linked,0) % 0 indicates Drugs and Media are combinatorial
+  clear DM;
+  excLnNum=2;
+  drgCnt=0;
+  medCnt=0;
+  if ispc
+    while (~isequal(txt{excLnNum,2},'###'))
+      drgCnt=drgCnt+1;    
+      DM.drug(drgCnt)={raw(excLnNum,2)};
+      DM.conc(drgCnt)={raw(excLnNum,3)};
+      excLnNum=excLnNum+1;
+    end
+
+    while (~isequal(txt{excLnNum,4},'###'))
+      medCnt=medCnt+1;    
+      DM.media(medCnt)={raw(excLnNum,4)};
+      excLnNum=excLnNum+1;
+    end
+  else
+    excLnNum=1;
+    while (~isequal(DMcell{excLnNum+1,2},'###'))
+      drgCnt=drgCnt+1;    
+      DM.drug(drgCnt)={DMtbl(excLnNum,2)};
+      DM.conc(drgCnt)={DMtbl(excLnNum,3)};
+      excLnNum=excLnNum+1;
+    end
+
+    while (~isequal(DMcel{excLnNum+1,4},'###'))
+      medCnt=medCnt+1;    
+      DM.media(medCnt)={DMtbl(excLnNum,4)};
+      excLnNum=excLnNum+1;
+    end
+  end
+  msg=strcat('NumberOfDrugs = ',num2str(drgCnt), '     NumberOfMedias = ',num2str(medCnt)  );
+end
+
+save(mpdmFile, 'fields','MP','DM','Linked');
+msgbox(sprintf('Drug-Media-MasterPlate Annotation File %s Generation Complete', mpdmFile))

workflow/apps/matlab/easy/DgenResults.m

@@ -0,0 +1,668 @@
+%% CALLED BY EASYconsole.m %%
+% Updated 240724 Bryan C Roessler to improve file operations and portability
+%
+global scansDir
+global matFile
+global defImParMat
+global printResultsDir
+global fotosResultsDir
+global pointMapsFile
+global pointMapsResultsDir
+
+ln=1;
+
+% Version compatability fixes
+if verLessThan('matlab','8.3')
+  fd4=diff(sym('K / (1 +  exp(-r* (t - l )))'),4);
+  sols=solve(fd4);
+else % accomodate new matlab changes after 2014a
+  syms t K r l;
+  fd4=diff(K / (1 +  exp(-r* (t - l ))),t,4);
+  sols=solve(fd4);
+  tmpswap=sols(1);
+  sols(1)=sols(3);
+  sols(3)=tmpswap;
+end
+
+% MPnum=ImParMat(1);
+% opt=questdlg('Print Results Only (RES), DB Only (DB), or Both','Results Printout Options','Res','DB','Both','Both');
+opt='Res';
+if ~exist('defImParMat','var') || isempty(defImParMat) % TODO needs better explanation
+  load(pointMapsFile);
+end
+destPerMP=ImParMat(2); % TODO this is weird, needs explanation
+load(matFile);
+load(mpdmFile)
+numOfDrgs=length(DM.drug);
+numOfMeds=length(DM.media);
+destPerMP=numOfDrgs;
+
+% TODO this should be rewritten or is uncessary, what is this for
+% Determine the longest set of intensity(tPts) for the Experiment Data Set
+maxNumIntens=0;
+for n=1:size(scan,2)
+  for m=1:size(scan(n).plate,2)
+    maxNumIntens=max(maxNumIntens,size(scan(n).plate(m).intens,2));
+  end
+end
+
+% if length(scansDir) == max(strfind(scansDir,'\'))
+%   localscansDir=scansDir(1:end-1);
+% else
+%   localscansDir=scansDir;
+% end
+
+% TODO this seems weird
+expNm=scansDir(max(strfind(scansDir,'/'))+1:end);
+drivePos=min(strfind(scansDir,'/'));
+drive=scansDir(1:(drivePos-1));
+DBupload=fullfile(drive,'EZdbFiles','DBupLOADfiles');
+
+% Added to allow backward compatability
+% Test for CFoutStd as indication of 2018version with r_refined fit code;If
+% earlier version with only a standard composite fite, Print results to !!ResultsStd_...txt only
+try
+  scan(1).plate(1).CFoutStd(1,1);
+  resultsFilename=fullfile(printResultsDir, strcat('!!ResultsELr_',expNm,'.txt'));
+  DBfilename=fullfile(printResultsDir, strcat('!!DbaseELr_',expNm,'.txt'));
+catch
+  resultsFilename=fullfile(printResultsDir, strcat('!!ResultsStd_',expNm,'.txt'));
+  DBfilename=fullfile(printResultsDir, strcat('!!DbaseStd_',expNm,'.txt'));
+end
+
+if isequal(opt,'Res')||isequal(opt,'Both'),fid=fopen(resultsFilename,'w');end
+if isequal(opt,'DB')||isequal(opt,'Both'),fid2=fopen(DBfilename,'w');end
+
+if isequal(opt,'Res')||isequal(opt,'Both')
+  fprintf(fid,'%d\t',ln); % Results header
+  fprintf(fid,'%s\t\n',scansDir);
+  ln=ln+1;
+  fprintf(fid,'%d\t',ln);
+end
+
+mpCnt=0;
+totPlCnt=0;
+drgCnt=0;
+medCnt=0;
+
+try
+  load(fullfile(fotosResultsDir,'Nbdg')) % Convolute scan array data into plates
+catch
+  load(fullfile(pointMapsResultsDir,'Nbdg')) % Convolute scan array data into plates
+end
+
+for s=1:size(scan,2)
+  % Convolute scan array data into plates DconB for DBcombo
+  clear Diag
+  try
+    Diag(:,:,:,1)=sbdg{s}(1:1:24,16:-1:1,:);
+  catch
+    sbdg{s};
+  end
+
+  for p=1:size((scan(s).plate),2)
+    totPlCnt=totPlCnt+1;
+    if destPerMP>1 && rem(totPlCnt,destPerMP)==1
+      mpCnt=mpCnt+1;
+    end
+    if destPerMP==1
+      mpCnt=mpCnt+1;
+    end
+    pertCnt=rem(totPlCnt,destPerMP);
+    if pertCnt==0
+      pertCnt=destPerMP;
+    end
+    pert=strcat('Perturb_',num2str(pertCnt));
+    s % TODO seems wrong
+    p % TODO seems wrong
+    clear outCmat
+    outCmat=scan(s).plate(p).CFout;
+
+    %Print Time Point HEADER for each plate for newly added intensity data
+    if isequal(opt,'Res')||isequal(opt,'Both')
+      fprintf(fid, '\n'); 
+      ln=ln+1;
+      fprintf(fid,'%d\t',ln);
+      fprintf(fid,'Scan\tPlate\tRow\tCol\t');
+      try
+        asd=cell2mat(scan(s).plate(1).CFparameters(1));
+        aucEndPt=strcat('AUC',num2str(asd(9)));
+      catch
+        asd=cell2mat(scan(s).plate(1).CFparameters{1,1}(1,384));
+        aucEndPt=strcat('AUC',num2str(asd(9)));
+      end
+      
+      fprintf(fid, 'Num.\tDiagnostics\tDrug\tConc\tMedia\tModifier1\tConc1\tModifier2\tConc2\tORF\tGene');
+      fprintf(fid, '\t %s',aucEndPt);
+      fprintf(fid, '\triseTm\tK\tr\tl\tR-squared\tK-lower\tK-upper\tr-lower\tr-upper\tl-lower\tl-upper\tArea\tLastInten\tSplineMaxRateTm\tLastFitTm\t1stFitTm\tMedianBase\tFitBase\tMinTm\tThreshTm');
+  
+      if size(outCmat,2)==27     
+        fprintf(fid, '\ttc11Cut\ttc12Cut\ttc21Cut\ttc22Cut');  %'\tEarly1\tEarly2\tLate1\tLate2'); 17_0629 MinBaseIntens update for MedianBase label
+      end
+      fprintf(fid, '\tTotFitPts\tPostThreshFitPts\t1stBackgrd\tLstBackgrd\t1stMeanTotBackgrd\tLstMeanTotBackgrd');
+    end
+
+    clear outTseries
+    outTseries=[];
+    outTseries=scan(s).plate(p).tSeries;
+    TseriesSize=size(outTseries,1);
+                    
+    clear outIntens
+    outIntens=[];
+    RawIntens=[];
+    RawIntens=scan(s).plate(p).intens;
+    RawIntensSize=size(RawIntens,2)
+    
+    clear Ag;  %Ag is Growth Area
+    Ag=scan(s).plate(p).Ag;
+    AgSize=size(Ag);
+  
+    dataLength=min(TseriesSize,RawIntensSize);
+    if isequal(opt,'Res')||isequal(opt,'Both')   
+      for j=1:dataLength
+        fprintf(fid, '\t%.5f', outTseries(j));
+      end
+    end   
+
+    numBlkCol=(maxNumIntens - dataLength); %size(outTseries,1));
+    if isequal(opt,'Res')||isequal(opt,'Both')  
+      for nn=1:numBlkCol  %extend to col beyond longest rawDataSet    
+        fprintf(fid, '\t');
+      end
+      fprintf(fid,'\tOrfRep');        
+      fprintf(fid,'\tSpecifics');
+      fprintf(fid,'\tStrainBkGrd');
+      fprintf(fid, '\n');
+      ln=ln+1;
+      fprintf(fid,'%d\t',ln);
+    end
+
+    % Data
+    n=0;
+    for r=1:16      
+      for c=1:24
+        n=n+1; 
+        clear selcode;
+        Kval=outCmat(n,3);
+        rSq=outCmat(n,6);
+        lval=outCmat(n,5);
+        if Kval>160, selcode='K_Hi'; else selcode=' ';end
+        if Kval<40, selcode=strcat(selcode,' K_Lo');end
+        if rSq<.97 && rSq>0, selcode=strcat(selcode,' rSqLo');end
+        if lval>(0.85*(max(outTseries))), selcode=strcat(selcode,' late');end
+        if isnan(outCmat(n,7))||isnan(outCmat(n,8))||isnan(outCmat(n,9))...
+          ||isnan(outCmat(n,10))||isnan(outCmat(n,11))...
+          ||isnan(outCmat(n,12)), selcode=strcat(selcode,' NaN');
+        end
+        
+        % RiseTime Calculation
+        K=(outCmat(n,3));  
+        R=(outCmat(n,4));  
+        L=(outCmat(n,5));  
+        if R>0 && L>0 && K>0
+          rr=R; ll=L; 
+          tc1=eval(sols(2));
+          tc2=eval(sols(3));
+          LL=eval(sols(1));
+          riseTm=LL-tc1;
+        else
+          riseTm=0;    
+        end
+    
+        if Ag(n)< .30*(scan(s).Awindow),selcode=strcat(selcode,' smArea'); end        
+        if outCmat(n,3)==0,selcode=strcat('0 ',selcode);end
+        
+        orf=cell2mat(MP(mpCnt).orf{1}(n));
+        gene=cell2mat(MP(mpCnt).genename{1}(n));
+        orfRep=cell2mat(MP(mpCnt).orfRep{1}(n));
+        specifics=cell2mat(MP(mpCnt).specifics{1}(n));
+        strain=cell2mat(MP(mpCnt).strain{1}(n));
+        drug=char(DM.drug{pertCnt}); 
+        conc=char(DM.conc{pertCnt});
+        media=char(DM.media{pertCnt});
+        try
+          mod1=char(DM.mod1{pertCnt});
+          conc1=char(DM.conc1{pertCnt});
+        catch
+          mod1=' ';
+          conc1=' ';
+        end
+        try
+          mod2=char(DM.mod2{pertCnt});
+          conc2=char(DM.conc2{pertCnt});
+        catch
+          mod2=' ';
+          conc2=' ';    
+        end
+        
+        if ~isempty(outCmat)  
+          if isequal(opt,'Res')||isequal(opt,'Both')  
+            fprintf(fid,'%d\t %d\t %d\t %d\t %d\t %s\t %s\t %s\t %s\t %s\t %s\t %s\t %s\t %s\t %s\t',s,p,r,c,n,selcode,drug,conc,media,mod1,conc1,mod2,conc2,orf,gene);
+            fprintf(fid, '%.5f\t %.5f\t %.5f\t %.5f\t %.5f\t %.5f\t%.5f\t%.5f\t%.5f\t%.5f\t%.5f\t%.5f\t%.5f\t%.5f\t%.5f\t%.5f',...
+              outCmat(n,1),riseTm,outCmat(n,3),outCmat(n,4),...
+              outCmat(n,5),outCmat(n,6),outCmat(n,7),outCmat(n,8),...
+              outCmat(n,9),outCmat(n,10),outCmat(n,11),outCmat(n,12),...
+              outCmat(n,13),outCmat(n,14),outCmat(n,15),outCmat(n,16));
+            
+            fprintf(fid, '\t%.5f\t%.5f\t%.5f\t%.5f\t%.5f',...
+              outCmat(n,17),outCmat(n,18),outCmat(n,19),...
+              outCmat(n,20),outCmat(n,21));
+
+            % Added for data cut times used in 'r'optomized method 06/14/2018
+            if (size(outCmat,2) == 27)
+              fprintf(fid, '\t%.5f\t%.5f\t%.5f\t%.5f',...
+                outCmat(n,24),outCmat(n,25),outCmat(n,26),outCmat(n,27));
+            end
+
+            fprintf(fid, '\t%d\t%d\t%d\t%d\t%d\t%d',...    
+              outCmat(n,22),outCmat(n,23),Diag(c,r,1,p),Diag(c,r,2,p),Diag(c,r,3,p),Diag(c,r,4,p)); %,Diag(r,c,3,p),Diag(r,c,4,p));
+          end 
+
+          % DBfile
+          if isequal(opt,'DB')||isequal(opt,'Both')
+            dbRsq=0;dbKup=0; dbKlo=0; dbrup=0; dbrlo=0; dbLlo=0; dbLup=0;
+            if isnumeric(outCmat(n,6)), dbRsq=outCmat(n,6);end
+            if isnumeric(outCmat(n,7)), dbKup=outCmat(n,7);end
+            if isnumeric(outCmat(n,8)), dbKlo=outCmat(n,8);end
+            if isnumeric(outCmat(n,9)), dbrup=outCmat(n,9);end
+            if isnumeric(outCmat(n,10)), dbrlo=outCmat(n,10);end
+            if isnumeric(outCmat(n,11)), dbLlo=outCmat(n,11);end
+            if isnumeric(outCmat(n,12)), dbLup=outCmat(n,12);end
+          end 
+
+          if isequal(opt,'DB')||isequal(opt,'Both')
+            fprintf(fid2,'%s\t %d\t %d\t %d\t %d\t %d\t %s\t %s\t %s\t %s\t %s\t %s\t %s\t %s\t %s\t %s\t',expNm,s,p,r,c,n,selcode,drug,conc,media,mod1,conc1,mod2,conc2,orf,gene);
+            fprintf(fid2, '%.5f\t %.5f\t %.5f\t %.5f\t %.5f\t %.5f\t%.5f\t%.5f\t%.5f\t%.5f\t%.5f\t%.5f',...
+                outCmat(n,1),riseTm,outCmat(n,3),outCmat(n,4),...
+                outCmat(n,5),dbRsq,dbKup,dbKlo,dbrup,dbrlo,dbLlo,dbLup);   %\t%.5f\t%.5f\t%.5f\t%.5f
+          end
+
+          % Add Intensities series to end of curve fit data
+          outIntens=[];
+          outIntens=zeros(384,dataLength);
+          intensBlob='';
+          tmBlob ='';
+        
+          for j=1:dataLength  %size(RawIntens,2)  %size(outTseries,1)
+            if Ag(n)==0,Ag(n)=scan(s).Awindow;end
+            outIntens(n,j)=RawIntens(n,j)/Ag(n);
+              if isequal(opt,'Res')||isequal(opt,'Both')
+                fprintf(fid, '\t%.5f', outIntens(n,j));  % Results print Intens
+              end
+            if isequal(opt,'DB')||isequal(opt,'Both') 
+              if j<dataLength
+                intensBlob=strcat(intensBlob,num2str(outIntens(n,j)),';');  
+              else
+                intensBlob=strcat(intensBlob,num2str(outIntens(n,j)));
+              end
+              if outTseries(j)<.0001,outTseries(j)=0;end
+              if j<dataLength
+                tmBlob=strcat(tmBlob,num2str(outTseries(j)),';');
+              else
+                tmBlob=strcat(tmBlob,num2str(outTseries(j))); 
+              end
+            end
+          end
+
+          % Results
+          if isequal(opt,'Res')||isequal(opt,'Both')
+            for nn=1:numBlkCol  %extend to col beyond longest rawDataSet    
+              fprintf(fid, '\t');
+            end
+            % Masterplate sheet
+            if ~isnan(orfRep)
+              fprintf(fid, '\t%s', orfRep);  %print OrfRep
+            else
+              fprintf(fid, '\t%s', ' ');
+            end
+            if ~isnan(specifics)    
+              fprintf(fid, '\t%s', specifics);  
+            else
+              fprintf(fid, '\t%s', ' ');  
+            end
+            if ~isnan(strain)
+              fprintf(fid, '\t%s', strain);  
+            else
+              fprintf(fid, '\t%s', ' '); 
+            end
+            fprintf(fid, '\n');
+            ln=ln+1;
+            fprintf(fid,'%d\t',ln);
+          end
+
+          %DB Raw Intensities and Timepoints
+          if isequal(opt,'DB')||isequal(opt,'Both')
+            fprintf(fid2, '\t%s\t%s',intensBlob,tmBlob );
+            % Masterplate sheet
+            if ~isnan(orfRep)
+              fprintf(fid2, '\t%s',orfRep );
+            else
+              fprintf(fid2, '\t%s', ' '); 
+            end
+            if ~isnan(specifics)
+              fprintf(fid2, '\t%s',specifics );
+            else
+              fprintf(fid2, '\t%s', ' '); 
+            end
+            if ~isnan(strain)
+              fprintf(fid2, '\t%s',strain );
+            else
+              fprintf(fid2, '\t%s', ' '); 
+            end
+            fprintf(fid2, '\n');
+          end
+        end %if ~isempty(outCmat)
+      end  %c
+    end  %r   
+  end  %p
+end  %s
+
+if isequal(opt,'Res')||isequal(opt,'Both')
+  fclose(fid); 
+end
+
+if isequal(opt,'DB')||isequal(opt,'Both')
+  fclose(fid2);
+  try
+    copyfile(DBfilename,DBupload)
+  catch ME
+    fprintf('DB upload failed with error: %s\n', getReport(ME, 'basic'));
+    rep=sprintf('Failed copyfile to %s - %s', DBupload, rep);
+    errordlg(rep);
+  end
+end
+
+% Print results using the standard method
+try
+  scan(1).plate(1).CFoutStd(1,1) %Test for 2018 r_refined version 
+
+  ln=1;
+  resultsFilename=fullfile(printResultsDir, strcat('!!ResultsStd_',expNm,'.txt'));
+  DBfilename=fullfile(printResultsDir, strcat('!!DbaseStd_',expNm,'.txt'));
+  if isequal(opt,'Res')||isequal(opt,'Both'),fid=fopen(resultsFilename,'w');end
+  if isequal(opt,'DB')||isequal(opt,'Both'),fid2=fopen(DBfilename,'w');end  %121012 Combo
+  if isequal(opt,'Res')||isequal(opt,'Both') %print Results
+    fprintf(fid,'%d\t',ln); %Results header
+    fprintf(fid,'%s\t\n',scansDir);
+    ln=ln+1;
+    fprintf(fid,'%d\t',ln);
+  end
+
+  mpCnt=0;
+  totPlCnt=0;
+  drgCnt=0;
+  medCnt=0;
+
+  for s=1:size(scan,2)
+    %Convolute scan array data into plates DconB for DBcombo
+    clear Diag
+    try
+      Diag(:,:,:,1)= sbdg{s}(1:1:24,16:-1:1,:);
+    catch
+      sbdg{s};
+    end
+
+    for p=1:size((scan(s).plate),2)
+      totPlCnt=totPlCnt+1;
+      if destPerMP>1 &&rem(totPlCnt,destPerMP)==1, mpCnt=mpCnt+1; end
+      if destPerMP==1,mpCnt=mpCnt+1; end
+      pertCnt=rem(totPlCnt,destPerMP);
+      if pertCnt==0, pertCnt= destPerMP;end
+      pert=strcat('Perturb_',num2str(pertCnt));
+      s % BCR seems wrong
+        
+      %Print Time Point HEADER for each plate for newly added intensity data
+      if isequal(opt,'Res')||isequal(opt,'Both')
+        fprintf(fid, '\n'); 
+        ln=ln+1;
+        fprintf(fid,'%d\t',ln);
+        fprintf(fid,'Scan\tPlate\tRow\tCol\t');
+        
+        try
+          asd=cell2mat(scan(s).plate(1).CFparameters(1));
+          aucEndPt=strcat('AUC',num2str(asd(9)));
+        catch
+          asd=cell2mat(scan(s).plate(1).CFparameters{1,1}(1,384));
+          aucEndPt=strcat('AUC',num2str(asd(9)));
+        end
+        fprintf(fid, 'Num.\tDiagnostics\tDrug\tConc\tMedia\tModifier1\tConc1\tModifier2\tConc2\tORF\tGene');
+        fprintf(fid, '\t %s',aucEndPt);
+        fprintf(fid, '\triseTm\tK\tr\tl\tR-squared\tK-lower\tK-upper\tr-lower\tr-upper\tl-lower\tl-upper\tArea\tLastInten\tSplineMaxRateTm\tLastFitTm\t1stFitTm\tMedianBase\tFitBase\tMinTm\tThreshTm\tTotFitPts\tPostThreshFitPts\t1stBackgrd\tLstBackgrd\t1stMeanTotBackgrd\tLstMeanTotBackgrd'); %17_0629 MinBaseIntens update for MedianBase label
+      end     
+      clear outTseries
+      outTseries=[];
+      outTseries=scan(s).plate(p).tSeries;
+      TseriesSize= size(outTseries,1);
+      clear outCmat
+      outCmat=scan(s).plate(p).CFoutStd;
+      clear outIntens
+      outIntens=[];
+      RawIntens=[];
+      RawIntens=scan(s).plate(p).intens;
+      RawIntensSize=size(RawIntens,2);
+      clear Ag;  %Ag is Growth Area
+      Ag=scan(s).plate(p).Ag;
+      AgSize= size(Ag);
+      
+      dataLength= min(TseriesSize,RawIntensSize);
+      if isequal(opt,'Res')||isequal(opt,'Both')   
+        for j=1:dataLength
+          fprintf(fid, '\t%.5f', outTseries(j));
+        end
+      end   
+
+      numBlkCol=(maxNumIntens - dataLength); %size(outTseries,1));
+
+      if isequal(opt,'Res')||isequal(opt,'Both')  
+        for nn=1:numBlkCol  %extend to col beyond longest rawDataSet    
+          fprintf(fid, '\t');
+        end
+        fprintf(fid,'\tOrfRep');        
+        fprintf(fid,'\tSpecifics');
+        fprintf(fid,'\tStrainBkGrd');
+        fprintf(fid, '\n');
+        ln=ln+1;
+        fprintf(fid,'%d\t',ln);
+      end
+
+      % Data  
+      n=0;     
+      for r=1:16      
+        for c=1:24
+          n=n+1; 
+          clear selcode;
+          Kval=outCmat(n,3);
+          rSq=outCmat(n,6);
+          lval=outCmat(n,5);
+          if Kval>160, selcode='K_Hi'; else selcode=' ';end
+          if Kval<40, selcode=strcat(selcode,' K_Lo');end  % TODO sprintf if you want a space
+          if rSq<.97 && rSq>0, selcode=strcat(selcode,' rSqLo');end
+          if lval>(0.85*(max(outTseries))), selcode=strcat(selcode,' late');end
+          if isnan(outCmat(n,7))||isnan(outCmat(n,8))||isnan(outCmat(n,9))...
+            ||isnan(outCmat(n,10))||isnan(outCmat(n,11))...
+            ||isnan(outCmat(n,12)), selcode=strcat(selcode,' NaN');
+          end
+              
+          % RiseTime Calculation
+          K=(outCmat(n,3));
+          R=(outCmat(n,4));
+          L=(outCmat(n,5));
+          if R>0 && L>0 && K>0
+            rr=R; ll=L;
+            tc1=eval(sols(2));
+            tc2=eval(sols(3));
+            LL=eval(sols(1));
+            riseTm= LL-tc1;
+          else
+            riseTm=0;    
+          end
+         
+          if Ag(n)< .30*(scan(s).Awindow),selcode=strcat(selcode,' smArea'); end  % same, need sprintf for space       
+          if outCmat(n,3)==0,selcode=strcat('0 ',selcode); end
+          orf=cell2mat(MP(mpCnt).orf{1}(n));
+          gene=cell2mat(MP(mpCnt).genename{1}(n));
+          orfRep=cell2mat(MP(mpCnt).orfRep{1}(n));
+          specifics=cell2mat(MP(mpCnt).specifics{1}(n));
+          strain=cell2mat(MP(mpCnt).strain{1}(n));
+          drug=char(DM.drug{pertCnt}); 
+          conc=char(DM.conc{pertCnt});
+          media=char(DM.media{pertCnt});
+          try
+            mod1=char(DM.mod1{pertCnt});
+            conc1=char(DM.conc1{pertCnt});
+          catch
+            mod1=' ';
+            conc1=' ';
+          end
+          try
+            mod2=char(DM.mod2{pertCnt});
+            conc2=char(DM.conc2{pertCnt});
+          catch
+            mod2=' ';
+            conc2=' ';    
+          end
+              
+          if ~isempty(outCmat)  
+            if isequal(opt,'Res')||isequal(opt,'Both')  
+              fprintf(fid,'%d\t %d\t %d\t %d\t %d\t %s\t %s\t %s\t %s\t %s\t %s\t %s\t %s\t %s\t %s\t',s,p,r,c,n,selcode,drug,conc,media,mod1,conc1,mod2,conc2,orf,gene);
+              fprintf(fid, '%.5f\t %.5f\t %.5f\t %.5f\t %.5f\t %.5f\t%.5f\t%.5f\t%.5f\t%.5f\t%.5f\t%.5f\t%.5f\t%.5f\t%.5f\t%.5f',...
+                outCmat(n,1),riseTm,outCmat(n,3),outCmat(n,4),...
+                outCmat(n,5),outCmat(n,6),outCmat(n,7),outCmat(n,8),...
+                outCmat(n,9),outCmat(n,10),outCmat(n,11),outCmat(n,12),...
+                outCmat(n,13),outCmat(n,14),outCmat(n,15),outCmat(n,16));
+            
+              fprintf(fid, '\t%.5f\t%.5f\t%.5f\t%.5f\t%.5f\t%d\t%d',...
+                outCmat(n,17),outCmat(n,18),outCmat(n,19),...
+                outCmat(n,20),outCmat(n,21),outCmat(n,22),outCmat(n,23));
+            
+              fprintf(fid, '\t%d\t%d\t%d\t%d',...    
+                Diag(c,r,1,p),Diag(c,r,2,p),Diag(c,r,3,p),Diag(c,r,4,p)); %,Diag(r,c,3,p),Diag(r,c,4,p));
+            end
+
+            % DBFile
+            % RiseTime calculation
+            if isequal(opt,'DB')||isequal(opt,'Both')
+              dbRsq= 0;dbKup= 0; dbKlo= 0; dbrup= 0; dbrlo= 0; dbLlo= 0; dbLup= 0;
+              if isnumeric(outCmat(n,6)), dbRsq= outCmat(n,6);end
+              if isnumeric(outCmat(n,7)), dbKup= outCmat(n,7);end
+              if isnumeric(outCmat(n,8)), dbKlo= outCmat(n,8);end
+              if isnumeric(outCmat(n,9)), dbrup= outCmat(n,9);end
+              if isnumeric(outCmat(n,10)), dbrlo= outCmat(n,10);end
+              if isnumeric(outCmat(n,11)), dbLlo= outCmat(n,11);end
+              if isnumeric(outCmat(n,12)), dbLup= outCmat(n,12);end
+            end
+
+            if isequal(opt,'DB')||isequal(opt,'Both')
+              fprintf(fid2,'%s\t %d\t %d\t %d\t %d\t %d\t %s\t %s\t %s\t %s\t %s\t %s\t %s\t %s\t %s\t %s\t',expNm,s,p,r,c,n,selcode,drug,conc,media,mod1,conc1,mod2,conc2,orf,gene);
+              fprintf(fid2, '%.5f\t %.5f\t %.5f\t %.5f\t %.5f\t %.5f\t%.5f\t%.5f\t%.5f\t%.5f\t%.5f\t%.5f',...
+                outCmat(n,1),riseTm,outCmat(n,3),outCmat(n,4),...
+                outCmat(n,5),dbRsq,dbKup,dbKlo,...
+                dbrup,dbrlo,dbLlo,dbLup);
+            end
+
+            % DB Analysis      
+            % Add Intensities series to end of curve fit data
+            outIntens=[];
+            outIntens=zeros(384,dataLength);
+            intensBlob='';
+            tmBlob ='';
+
+            for j=1:dataLength  %size(RawIntens,2)  %size(outTseries,1)
+              if Ag(n)==0,Ag(n)=scan(s).Awindow;end
+              outIntens(n,j)= RawIntens(n,j)/Ag(n);
+              if isequal(opt,'Res')||isequal(opt,'Both')
+                fprintf(fid, '\t%.5f', outIntens(n,j));  % Results print Intens
+              end
+              if isequal(opt,'DB')||isequal(opt,'Both') 
+                if j<dataLength
+                  intensBlob=strcat(intensBlob,num2str(outIntens(n,j)),';');  
+                else
+                  intensBlob=strcat(intensBlob,num2str(outIntens(n,j)));
+                end
+                if outTseries(j)<.0001,outTseries(j)=0;end
+                if j<dataLength
+                  tmBlob=strcat(tmBlob,num2str(outTseries(j)),';');
+                else
+                  tmBlob=strcat(tmBlob,num2str(outTseries(j))); 
+                end
+              end
+            end
+
+            % Results fprint
+            if isequal(opt,'Res')||isequal(opt,'Both')
+              for nn=1:numBlkCol  %extend to col beyond longest rawDataSet    
+                fprintf(fid, '\t');
+              end
+
+              % Masterplate sheet
+              if ~isnan(orfRep)
+                fprintf(fid, '\t%s', orfRep);  %print OrfRep
+              else
+                fprintf(fid, '\t%s', ' ');
+              end
+              if ~isnan(specifics)    
+                fprintf(fid, '\t%s', specifics);  
+              else
+                fprintf(fid, '\t%s', ' ');  
+              end
+              if ~isnan(strain)
+                fprintf(fid, '\t%s', strain);  
+              else
+                fprintf(fid, '\t%s', ' '); 
+              end
+
+              fprintf(fid, '\n');
+              ln=ln+1;
+              fprintf(fid,'%d\t',ln);
+            end
+
+
+            % Raw Intensities and Timepoints
+            if isequal(opt,'DB')||isequal(opt,'Both')
+              fprintf(fid2, '\t%s\t%s',intensBlob,tmBlob );
+
+              % Masterplate sheet
+              if ~isnan(orfRep)
+                fprintf(fid2, '\t%s',orfRep );
+              else
+                fprintf(fid2, '\t%s', ' '); 
+              end
+              if ~isnan(specifics)
+                fprintf(fid2, '\t%s',specifics );
+              else
+                fprintf(fid2, '\t%s', ' '); 
+              end
+              if ~isnan(strain)
+                fprintf(fid2, '\t%s',strain );
+              else
+                fprintf(fid2, '\t%s', ' '); 
+              end
+              fprintf(fid2, '\n');
+            end  %DB print
+          end %if ~isempty(outCmat)
+        end  %c
+      end  %r   
+    end  %p
+  end  %s
+
+  if isequal(opt,'Res')||isequal(opt,'Both')
+    fclose(fid); 
+  end
+
+  if isequal(opt,'DB')||isequal(opt,'Both')
+    fclose(fid2);
+    try
+      copyfile(DBfilename,DBupload)
+    catch ME
+      fsprintf('DB upload failed with error: %s\n', getReport(ME, 'basic'));
+      rep=sprintf('Failed copyfile to %s - %s\n', DBupload, rep);
+      errordlg(rep)
+    end
+  end
+
+  msgbox([sprintf('Printing Script complete. Check !!Results sheets in %s for results.', printResultsDir)])
+
+catch ME
+  fprintf('Printing Script failed with error: %s\n', getReport(ME, 'basic'));
+end
+

workflow/apps/matlab/easy/EASYconsole.m

@@ -0,0 +1,527 @@
+% Launch the MATLAB EASY console
+% Updated 240727 Bryan C Roessler to improve file operations and portability
+
+function varargout = EASYconsole(varargin)
+  global easyDir
+  global easySuffix
+  global scansDir
+  global easyResultsDir
+  global easyResultsDirName
+  global fotosResultsDir
+  global figsResultsDir
+  global pointMapsResultsDir
+  global pointMapsFile
+  global printResultsDir
+  global matDir
+  global matFile
+  global drugMediaFile
+  global masterPlateFile
+  global mpdmFile
+  global userName
+  global srchRange
+  global searchRangeFile
+
+  % Initialize some variables from matlab
+  easyPath=which(mfilename);
+  [easyDir,easyFileName]=fileparts(easyPath);
+  easyDir=fullfile(easyDir);
+  [parentDir, ~]=fileparts(easyDir);
+  parentDir=fullfile(parentDir); % ../easy/apps
+  userName=getenv('USER');
+  dt=datetime;
+  todayStr=char(dt, 'yyyyMMdd'); % This should match the parent workflow script
+
+  demo=1;
+  if demo
+    disp('Running in demo mode');
+    disp('Initialized variables:');
+    whos;
+  end
+
+  fprintf('This script name: %s\n', easyFileName);
+
+  % Set scansDir (project scans directory) intelligently
+  if exist('PROJECT', 'var') && ~isempty(getenv('PROJECT'))
+    scansDir=getenv('PROJECT');
+    fprintf('Using project path: %s from environment variable PROJECT\n', scansDir);
+    disp('This usually indicates that we are in standalone mode');
+  elseif exist('SCANS_DIR', 'var') && ~isempty(getenv('SCANS_DIR'))
+    scansDir=getenv('SCANS_DIR');
+    fprintf('Using scans directory: %s from environment variable SCANS_DIR\n', scansDir);
+    disp('This usually indicates that we are in module mode');
+  else
+    % TODO Lots of this is hardcoded logic, this TODO is just a reminder to change this block
+    % when changing EASY and other variables in the parent script
+    fprintf('Beginning parent scans directory search\n');
+    fprintf('This usually indicates that we are in stand-alone mode without PROJECT or SCANS_DIR environment variables\n');
+    dirsToScan={
+      fullfile(parentDir,'..', '..', 'scans'),
+      fullfile(parentDir, '..', '..', 'ExpJobs'),
+      fullfile('/mnt/data/scans'),
+      fullfile('/mnt/data/ExpJobs'),
+      fullfile(parentDir, '..', '..', 'templates', 'scans-demo')
+    };
+    for d=dirsToScan
+      if exist(d, 'dir')
+        subDirs=dir(d);
+        if ~isempty(subDirs)
+          fprintf('Found a non-empty parent scans directory in our list: %s\n', d);
+          fprintf('Scanning inside for a project scan directory\n');
+          [~, sortedIndices]=sort(datenum({dirs.date}), 'descend'); % sort by newest first
+          sortedDirs=dirs{sortedIndices};
+          scansDir=sortedDirs{1};
+          fprintf('Selected newest project scans directory: %s\n', scansDir);
+        end
+      end
+    end
+  end
+
+  % Sanity check and warning
+  if exist('PROJECT_USER', 'var') && ~isempty(getenv('PROJECT_USER'))
+    if ~equal(getenv('PROJECT_USER'), userName)
+      disp("WARNING: PROJECT_USER does not match the current namespace");
+    end
+  end
+
+  % Allow module to override hardcoded default EASY directory
+  if exist('EASY_DIR','var') && ~isempty(getenv('EASY_DIR'))
+    EASY_DIR=fullfile(getenv('EASY_DIR'));
+    if ~strcmp(easyDir, EASY_DIR) % sanity check
+      disp("WARNING: EASY_DIR does not match this script's hardcoded EASY location");
+      disp("This is probably OK but if strange beahvior arises, we'll need to fix it in code");
+      easyDir=EASY_DIR;
+    end
+    fprintf('Using EASY script directory: %s from environment variable EASY_DIR\n', easyDir);
+  else
+    fprintf('Using EASY script directory: %s from hardcoded default\n', easyDir);
+  end
+
+  % If we don't have tan EASY_SUFFIX from the module, generate it from scansDir
+  if exist('EASY_SUFFIX', 'var') && ~isempty(getenv('EASY_SUFFIX'))
+    easySuffix=getenv('EASY_SUFFIX');
+  else
+    % The following is a way to parse the project name from the scansDir
+    [ ~, dirName]=fileparts(scansDir);
+    parts=strsplit(dirName, '_');
+    scansDate=parts{1};
+    scansUserName=parts{2};
+    easySuffix=strjoin(parts(3:end), '_');
+    % Might as well check this too for fun
+    if ~strcmp(userName, scansUserName)
+      disp('WARNING: userName does not match scansUserName');
+      disp("This usually means that you are attempting to run an EASY analysis on another user's project data scans");
+    end
+    % For happiness
+    if strcmp(todayStr, scansDate)
+      disp("Early bird gets the worm");
+    end
+  end
+
+  if (exist('EASY_RESULTS_DIR', 'var') && ~isempty(getenv('EASY_RESULTS_DIR')))
+    easyResultsDir=fullfile(getenv('EASY_RESULTS_DIR'));
+    if exist(easyResultsDir, 'dir')
+      fprintf('WARNING: EASY results dir %s already exists\n', easyResultsDir);
+      disp('Files in this directory may be overwritten');
+    end
+    fprintf('Using output directory: %s from environment variable EASY_RESULTS_DIR\n', easyResultsDir);
+  else
+    easyResultsDirName=strcat('Results_',todayStr,'_',userName,'_',easySuffix);
+    easyResultsDir=fullfile(scansDir,easyResultsDirName);
+    if exist(easyResultsDir, 'dir')
+      fprintf('WARNING: EASY results dir %s already exists\n', easyResultsDir);
+      disp('Files in this directory may be overwritten')
+      fprintf('Using output directory: %s\n', easyResultsDir);
+    end
+  end
+
+  if exist('MASTER_PLATE_FILE', 'var') && ~isempty(getenv('MASTER_PLATE_FILE'))
+    masterPlateFile=fullfile(getenv('MASTER_PLATE_FILE'));
+    fprintf('Using drug media file: %s from environment variable MASTER_PLATE_FILE\n', masterPlateFile);
+  else
+    % Try to find MasterPlate_ file on our own
+    mp=fullfile(scansDir,'MasterPlateFiles',strcat('MasterPlate_', easySuffix,'.xlsx'));
+    if exist(mp, 'file')
+      masterPlateFile=mp;
+      fprintf('Using drug media file: %s from internal logic\n', masterPlateFile);
+    else
+      fprintf('WARNING: Have you created a MasterPlate_ file in %s/MasterPlateFiles/?\n', scansDir);
+    end
+  end
+
+  if exist('DRUG_MEDIA_FILE', 'var') && ~isempty(getenv('DRUG_MEDIA_FILE'))
+    drugMediaFile=fullfile(getenv('DRUG_MEDIA_FILE'));
+    fprintf('Using drug media file: %s from environment variable DRUG_MEDIA_FILE\n', drugMediaFile);
+  else
+    % Try to find MasterPlate_ file on our own
+    dm=fullfile(scansDir,'MasterPlateFiles',strcat('DrugMedia_', easySuffix,'.xlsx'));
+    if exist(mp, 'file')
+      drugMediaFile=dm;
+      fprintf('Using drug media file: %s from internal logic\n', drugMediaFile);
+    else
+      fprintf('WARNING: Have you created a DrugMedia_ file in %s/MasterPlateFiles/?\n', scansDir);
+    end
+  end
+
+  matDir=fullfile(easyResultsDir,'matResults');
+  if ~exist(matDir, 'dir')
+    mkdir(matDir);
+  end
+  matFile=fullfile(matDir,strcat(easyResultsDirName,'.mat'));
+  % Pulled these out of par4GblFnc8c
+  printResultsDir=fullfile(easyResultsDir,'PrintResults');
+  fotosResultsDir=fullfile(easyResultsDir,'Fotos');
+  figsResultsDir=fullfile(easyResultsDir,'figs');
+  pointMapsResultsDir=fullfile(easyResultsDir,'PTmats');
+  pointMapsFile=fullfile(pointMapsResultsDir,'NImParameters.mat');
+  oldPointMapsFile=fullfile(pointMapsResultsDir,'ImParameters.mat');
+  searchRangeFile=fullfile(fotosResultsDir,'CSearchRange.mat');
+  mpdmFile=fullfile(matDir,'MPDM.mat');
+
+  % Decent time to print some helpful vars
+  if demo
+    disp('Vars at end of main loop:')
+    whos;
+  end
+
+  % This can be removed, I think it should add the previous search range?
+  % Might be nice feature but can remove if it causes issues
+  % We are using searchRangeNum to hold old CSrchRange value(s)
+  if exist(searchRangeFile, 'file')
+    searchRangeNum=load(searchRangeFile);
+  end
+  % Add easyDir to the MATLAB path
+  % I have not idea if this is necessary or works but theoretically should
+  % reduce directory scoping issues when calling scripts w/o a path
+  addpath(easyDir);
+
+  % GUI interface design
+  gui_Singleton=1;
+  gui_State=struct( 'gui_Name',       mfilename, ...
+                    'gui_Singleton',  gui_Singleton, ...
+                    'gui_OpeningFcn', @EASYconsole_OpeningFcn, ...
+                    'gui_OutputFcn',  @EASYconsole_OutputFcn, ...
+                    'gui_LayoutFcn',  [] , ...
+                    'gui_Callback',   []);
+  if nargin && ischar(varargin{1})
+    gui_State.gui_Callback=str2func(varargin{1});
+  end
+
+  if nargout
+    [varargout{1:nargout}]=gui_mainfcn(gui_State, varargin{:});
+  else
+    gui_mainfcn(gui_State, varargin{:});
+  end
+end
+
+% GUI
+% Easyconcole_OpeningFcn executes just before the EASYconsole GUI is made visible.
+% This function has no output args, see OutputFcn.
+% hObject--handle to figure
+% eventdata reserved - to be defined in a future version of MATLAB
+% handles--structure with handles and user data (see GUIDATA)
+% varargin--input arguments to EASYconsole (see VARARGIN)
+function EASYconsole_OpeningFcn(hObject, ~, handles, varargin)
+  global fhconsole
+  global scansDir
+
+  % Choose default command line output for EASYconsole
+  handles.output=hObject;
+
+  % Update handles structure
+  guidata(hObject, handles);
+
+  %Figure header, Toolbar, etc. Setup
+  fhconsole=gcf;
+  set(fhconsole,'Toolbar','none');
+  fhconsole=gcf;
+
+  % Pulled this out of the opening function
+  % Seems better to wait until we have our vars set though?
+  if exist('scansDir','var') && ~isempty(scansDir)
+    set(fhconsole,'Name', sprintf('EASYconsole - %s', scansDir));
+  else
+    set(fhconsole,'Name','EASYconsole - No Active Experiment.')
+  end
+end
+
+% EASYconsole output
+% Outputs from this function are returned to the command line.
+% varargout--cell array for returning output args (see VARARGOUT);
+% hObject--handle to figure
+% eventdata reserved - to be defined in a future version of MATLAB
+% handles--structure with handles and user data (see GUIDATA)
+function varargout = EASYconsole_OutputFcn(~, ~, handles) 
+  % Get default command line output from handles structure
+  varargout{1}=handles.output;
+end
+
+%% CONSOLE BUTTON INTERFACES %%
+% File Button Interface
+function FileMenu_Callback(~, ~, ~)
+    %returnStartDir
+end
+
+% Load Experiment Button Interface
+function LoadExp_Callback(~, ~, ~)
+    %returnStartDir
+end
+
+% New Experiment Button Interface
+function NewExpDat_Callback(~, ~, ~)
+  global matDir
+  global matFile
+  global easyResultsDir
+  global easyResultsDirName
+  global fhconsole
+  global scan
+  global userName
+
+  % Create a new experiment
+  try
+    questdlg('\fontsize{20} NAME the file and NAVIGATE to the directory with the image folders.','File Creation','OK', struct('Default','OK','Interpreter','tex'));
+    [inputFile,inputPath]=uiputfile('.mat');
+    inputFileName=strrep(inputFile,'.mat','');
+    easyResultsDirName=strcat('Results_',todayStr,'_',userName,'_',inputFileName);
+
+    % Set paths
+    scansDir=fullfile(inputPath);
+    easyResultsDir=fullfile(scansDir,easyResultsDirName);
+    matDir=fullfile(easyResultsDir,'matResults');
+    matFile=fullfile(matDir,strcat(todayStr,'_',userName,'_',inputFile));
+    
+    %***Added for 'parfor global' to preallocate 'scan' structure 20-0123***** 
+    nlist=dir(fullfile(scansDir,'*'));
+    nnn=0;
+    for n=1:size(nlist,1)
+      if (~isempty(str2num(nlist(n).name)))
+        nnn=nnn+1;
+        PnumLst(nnn)= (str2num(nlist(n).name));
+        sl(nnn,1)={(nlist(n).name)};
+      end
+    end
+    scanSize=size(sl,1);
+    scanMax=max(str2double(sl));
+    clear scan;
+    scan(scanMax)=struct(); % changed for parfor global 20_0118
+    save(matFile,'scan')
+
+    % create supporting dirs
+    % this is also in the workflow script but here for standalone mode
+    dirs={'PrintResults', 'CFfigs', 'Fotos', 'Fotos/BkUp'};
+    for i=1:length(dirs)
+      d=dirs{i};
+      if ~exist(fullfile(easyResultsDir, d), 'dir')
+        mkdir(fullfile(easyResultsDir, d));
+      end
+    end
+
+    % templateDirs are stored in the easy template directory
+    templates={'figs', 'PTmats'};
+    for i=1:length(templates)
+      d=dirs{i};
+      if ~exist(fullfile(easyResultsDir, d), 'dir')
+        copyfile((fullfile(easyDir,d)), (fullfile(easyResultsDir,d)));
+      end
+    end
+
+    clear sbdg % reduce possible retention of a previous job sdbg
+    sbdg= cell(1,scanMax); 
+    save((fullfile(easyResultsDir,'Fotos','Nbdg')),'sbdg'); 
+  catch ME
+    fprintf('ERROR: %s\n', ME.message);
+  end
+
+  % set the title for fhconsole depending on existence
+  if exist('easyResultsDir','var')&&~isempty(easyResultsDir)
+    set(fhconsole,'Name',sprintf('EASYconsole - %s', easyResultsDir));
+  else
+    set(fhconsole,'Name','EASYconsole - Master Plate directory not selected.');
+  end
+end
+
+
+% Load a previous experiment
+function LoadDatFile_Callback(~, ~, ~)
+  global matDir
+  global matFile
+  global easyResultsDir
+  global easyPath
+  global fhconsole
+
+  try
+    questdlg('Load results .mat from ../ExpJobs/YourJob/Results/matResults/','File Creation','OK', struct('Default','OK','Interpreter','tex'));
+    [inputFile,inputPath]=uigetfile('.mat','Open Experiment folder and data storage .mat file name','MultiSelect','off');
+    matDir=fullfile(inputPath);
+    matFile=fullfile(inputPath,inputFile);
+    load(matFile);
+    easyResultsDir=fullfile(matDir,'..');
+    scansDir=fullfile(matDir,'..', '..');
+    point
+
+    % TODO this is pretty hacky and needs something more explicit
+    if isfolder(fullfile(matDir, '..','..','1')) % If Inovation Vrobot Then
+      try 
+        exist(pointMapsFile, 'file')
+        load(pointMapsFile);
+      catch
+        try 
+          load(fullfile(easyPath,'NImParameters.mat')); % hardcoded default
+        catch
+          disp("Could not load the NImParameters.mat file")
+        end
+      end
+    else % If Epson 10Plate Scans Then>
+      if exist(fullfile(pointMapsResultsDir,'ImParameters.mat'), 'file')
+        load(fullfile(pointMapsResultsDir,'ImParameters.mat'));
+      else
+        try
+          load(fullfile(easyPath,'ImParameters.mat'));
+        catch
+          disp("Could not load the ImParameters.mat file");
+        end
+      end
+    else
+      disp('WARNING: cannot find project scans');
+    end
+
+    bkupDir=fullfile(matDir,'BkUp');
+    if ~exist(bkupDir, 'dir')
+      mkkdir(bkupDir);
+    end
+
+    % Create supporting dirs
+    dirs={'PrintResults', 'figs', 'CFfigs', 'PTmats', 'Fotos'};
+    for i=1:length(dirs)
+      d=dirs{i};
+      if ~exist(fullfile(easyResultsDir, d), 'dir')
+        mkdir(fullfile(easyResultsDir, d));
+      end
+    end
+  catch
+  end
+
+  clear scan   
+
+  if exist('easyResultsDir','var') && ~isempty(easyResultsDir)
+    fhconsole=gcf;
+    set(fhconsole,'Name',sprintf('EASYconsole - %s', easyResultsDir));
+  else
+    set(fhconsole,'Name','EASYconsole - Exp. Analysis NOT selected.');
+  end
+end
+
+% Callbacks
+% 'Run' in the dropdown menu
+function run_Callback(~, ~, ~)
+end
+
+function runPlateMapPintool_Callback(~, ~, ~)
+  try   
+    NImapPT
+  catch
+    EASYconsole
+  end
+end
+
+function NImCFcombo_Callback(~, ~, ~)
+  try   
+    par4Gbl_Main8c
+    EASYconsole
+  catch 
+    EASYconsole
+  end
+end
+
+function runPlateImAnal_Callback(~, ~, ~)
+  try   
+    NImStartupOnly
+  catch
+    EASYconsole
+  end
+end
+
+function PlateCFit_Callback(~, ~, ~)
+  % global matFile % TODO BCR not sure if needed
+  try
+    NCstart  
+  catch
+    EASYconsole
+  end
+end
+
+function GenPrintouts_Callback(~, ~, ~)
+end
+
+function uploadExcelMP2DB_Callback(~, ~, ~)
+end
+
+function runDMPexcel_Callback(~, ~, ~)
+  try
+    DMPexcel2mat
+  catch
+    EASYconsole
+  end
+end
+
+function runResults_DBcombo_Callback(~, ~, ~)
+  try
+    DgenResults %similar but semicolons removed to restore so cmdLine display info.
+    %Dgen241010qhtcp %par4global -convert 1x1cell of 384cells to be like previous 1x384 cells CFparameter
+  catch ME
+    fprintf('Error in DgenResults: %s\n', ME.message);
+    EASYconsole
+  end
+end
+
+function Tools_Callback(~, ~, ~)
+end
+
+function runOverlayPlots_Callback(~, ~, ~)
+  try   
+    DoverlayPlots2
+    EASYconsole
+  catch 
+    EASYconsole
+  end
+end
+
+function runFotoStrip_Callback(~, ~, ~)
+  try   
+    F_NImStartup_CentCir
+    EASYconsole
+  catch
+    EASYconsole
+  end
+end
+
+function runDisplayFig_Callback(~, ~, ~)
+  try 
+    UfigDisplay 
+  catch
+    EASYconsole
+  end
+end
+
+function runViewParameters_Callback(~, ~, ~)
+  try
+  catch
+    EASYconsole
+  end
+end
+
+function QkviewN_Callback(~, ~, ~)
+  try 
+    QkviewImages
+  catch
+    EASYconsole
+  end
+end
+
+function CFdisplay_Callback(~, ~, ~)
+  try   
+    NCsingleDisplay
+    EASYconsole
+  catch
+    EASYconsole
+  end
+end

workflow/apps/matlab/easy/NCdisplayGui.m

@@ -0,0 +1,458 @@
+%% CALLED WHEN ACCESSING 'CurveFit Display' %%
+function [scLst, row, col] = NCdisplayGui(scansDir)
+  xPos=0.05;
+  btnWid=0.10;
+  btnHt=0.05;
+  spacing=0.02; % Spacing between the button and the next command's label
+      
+  % Figure
+  % The ADD Groups button
+  btnNumber=1;
+  yPos=0.85-(btnNumber-1)*(btnHt+spacing);
+  btnPos=[xPos yPos-spacing btnWid btnHt];
+
+  row=1;
+  hedit=uicontrol(...
+    'Style', 'edit',...
+    'String',row,...
+    'Units','normalized',...   
+    'Position', btnPos,... % [.002 .70 .08 .10],...
+    'callback',{@editRowNum});  % 'Position', [5 100 60 20])
+
+  function editRowNum(source,~)
+    user_entry=str2double(get(source,'string'));
+    if (isnan(user_entry)||(user_entry<0)||(user_entry>17) )
+      errordlg('Enter a Row between 1 and 16','Bad Input','modal')
+      return
+    end
+    row=user_entry;
+  end
+
+  btnNumber=2;
+  yPos=0.85-(btnNumber-1)*(btnHt+spacing);
+  btnPos=[xPos yPos-spacing btnWid btnHt];
+  col=1;
+  hedit=uicontrol(...
+    'Style', 'edit',...
+    'String',col,...
+    'Units','normalized',...
+    'Position', btnPos,... % [.002 .70 .08 .10],...
+    'callback',{@entryColNum});  % 'Position', [5 100 60 20])
+
+  function entryColNum(source,~)
+    user_entry=str2double(get(source,'string'));
+    if (isnan(user_entry)||(user_entry<0)||(user_entry>25))
+      errordlg('Enter a Column between 1 and 24','Bad Input','modal')
+      return
+    end
+    col=user_entry;
+  end
+
+  % Read in numeric folder names
+  nlist=dir(fullfile(scansDir,'*'));
+  nnn=0;
+  for n=1:size(nlist,1)
+    if (~isempty(str2num(nlist(n).name)))
+      nnn=nnn+1;
+      PnumLst(nnn)=(str2num(nlist(n).name));
+      slst(nnn,1)={nlist(n).name};
+      slst(nnn,1)={(nlist(n).name)};
+    end
+  end
+
+  hListbox=uicontrol(...
+    'Style', 'listbox',...
+    'String',sort(slst),...
+    'value',[],...
+    'max',1000,...
+    'min',1,...
+    'Units','normalized',...   
+    'Position', [.40 .40 .10 .60],...
+    'callback',{@load_listbox});  %'uiresume(gcbf)'); 'Position', [5 100 60 20])
+  
+  function load_listbox(source,~)  
+    userIndx=(get(source,'value'));
+    userStr=(get(source,'string'));
+    %scLstIndx=str2num(char(strrep(userStr(userIndx), 'Scan', '')))
+    user_entry=userStr(userIndx);
+    scLst=user_entry;
+  end 
+      
+  btnNumber=10;
+  yPos=0.85-(btnNumber-1)*(btnHt+spacing);
+  btnPos=[xPos yPos-spacing btnWid btnHt];
+
+  hedit8=uicontrol(...
+    'Style', 'pushbutton',...
+    'String',{'Continue'},...
+    'Units','normalized',...   
+    'Position', btnPos,... 
+    'callback','uiresume(gcbf)');  
+
+  % Labels
+  xLPos=0.175;
+  yPos=0;
+  btnWid=0.20;
+  lblNumber=1;
+  yPos=0.85-(lblNumber-1)*(btnHt+spacing);
+  btnPos=[xLPos yPos-spacing btnWid btnHt];
+  htxt=uicontrol(...
+    'Style', 'text',...
+    'String','Row',...
+    'Units','normalized',...   
+    'Position', btnPos);
+
+  lblNumber=2;
+  yPos=0.85-(lblNumber-1)*(btnHt+spacing);
+  btnPos=[xLPos yPos-spacing btnWid btnHt];
+    
+  htxt=uicontrol(...
+    'Style', 'text',...
+    'String','Column',...
+    'Units','normalized',...   
+    'Position', btnPos);
+
+  %  Not needed for Ncode ImRobot
+  uiwait(gcf);
+end %function end $$$$$[/INST]
+
+%}
+ %{
+%-------------------333333-----------
+
+   lblNumber=3;
+   yPos=0.85-(lblNumber-1)*(btnHt+spacing);
+   btnPos=[xLPos yPos-spacing btnWid btnHt];
+
+htxt=uicontrol(...
+      'Style', 'text',...
+      'String','BG Threshold (%above) Detection',...
+      'Units','normalized',...   
+   	 'Position', btnPos);
+
+%-------------------4-----------
+
+   lblNumber=4;
+   yPos=0.85-(lblNumber-1)*(btnHt+spacing);
+   btnPos=[xLPos yPos-spacing btnWid btnHt];
+  
+htxt=uicontrol(...
+      'Style', 'text',...
+      'String','SpotDetThres(1-60%)',...
+      'Units','normalized',...   
+   	 'Position', btnPos);  
+
+%-------------------55555-----------
+  lblNumber=5;
+   yPos=0.85-(lblNumber-1)*(btnHt+spacing);
+   btnPos=[xLPos yPos-spacing btnWid btnHt];
+  
+htxt=uicontrol(...
+      'Style', 'text',...
+            'String','Radius',...   %'String','Width',...
+      'Units','normalized',...   
+   	 'Position', btnPos);  
+%-------------------66666-----------
+lblNumber=6;
+   yPos=0.85-(lblNumber-1)*(btnHt+spacing);
+   btnPos=[xLPos yPos-spacing btnWid btnHt];
+  
+htxt=uicontrol(...
+      'Style', 'text',...
+      'String','Dither',...
+      'Units','normalized',...   
+   	 'Position', btnPos);  
+%-------------------77777-----------
+
+lblNumber=7;
+   yPos=0.85-(lblNumber-1)*(btnHt+spacing);
+   btnPos=[xLPos yPos-spacing btnWid btnHt];
+  
+htxt=uicontrol(...
+      'Style', 'text',...
+      'String','SearchRange',...
+      'Units','normalized',...   
+   	 'Position', btnPos);  
+
+%-------------------88888-----------
+%{
+lblNumber=8;
+   yPos=0.85-(lblNumber-1)*(btnHt+spacing);
+   btnPos=[xLPos yPos-spacing btnWid btnHt];
+  
+htxt=uicontrol(...
+      'Style', 'text',...
+      'String','Blank2',...
+      'Units','normalized',...   
+   	 'Position', btnPos);  
+%----------------------------------------
+ %}
+%}
+
+
+
+%{
+ 
+
+%-------------------66666-----------
+btnNumber=6;
+   yPos=0.85-(btnNumber-1)*(btnHt+spacing);
+   btnPos=[xPos yPos-spacing btnWid btnHt];
+srcExtendFactor=ImParMat(7);
+hedit=uicontrol(...
+      'Style', 'edit',...
+      'String',srcLoIntensThres,...
+      'Units','normalized',...   
+   	 'Position', btnPos,... 
+     'callback',{@entryExtendFactor});  
+
+ function entryExtendFactor(source,eventdata)
+user_entry=str2double(get(source,'string'));
+    if (isnan(user_entry)||(user_entry<1.8)||(user_entry>4.0))
+	errordlg('You must enter a numeric value between 1.8 and 2.1','Bad Input','modal')
+	return
+    end
+    ExtendFactor=user_entry
+    ImParMat(7)= ExtendFactor
+    ExtendFactor
+ end
+%}
+
+
+%{ 
+%-------------------333333-----------
+
+   btnNumber=3;
+   yPos=0.85-(btnNumber-1)*(btnHt+spacing);
+   btnPos=[xPos yPos-spacing btnWid btnHt];
+srcBGthreshold=ImParMat(3);
+hedit=uicontrol(...
+      'Style', 'edit',...
+      'String',srcBGthreshold,...
+      'Units','normalized',...   
+   	 'Position', btnPos,... % [.002 .70 .08 .10],...
+     'callback',{@entryBGthreshold});  % 'Position', [5 100 60 20])
+
+ function entryBGthreshold(source,eventdata)
+user_entry=str2double(get(source,'string'));
+    if (isnan(user_entry)||(user_entry<1)||(user_entry>100))
+	errordlg('Enter a numeric value between 1 and 100 percent to produce a Background Threshold value as a percent above the time series average background for each spot.','Bad Input','modal')
+	return
+    end
+    BGthresInput=user_entry
+    ImParMat(3)= BGthresInput
+BGthresInput
+ end
+
+%-------------------444444-----------
+
+btnNumber=4; %Enter spot detection threshold (lock-in Image frame)
+   yPos=0.85-(btnNumber-1)*(btnHt+spacing);
+   btnPos=[xPos yPos-spacing btnWid btnHt];
+srcSpotThres=ImParMat(4);
+hedit=uicontrol(...
+      'Style', 'edit',...
+      'String',srcSpotThres,...
+      'Units','normalized',...   
+   	 'Position', btnPos,... 
+     'callback',{@entrySpotThres});  
+
+ function entrySpotThres(source,eventdata)
+user_entry=str2double(get(source,'string'));
+    if (isnan(user_entry)||(user_entry<1)||(user_entry>60))
+	errordlg('You must enter a numeric value between 1 and 60','Bad Input','modal')
+	return
+    end
+    spotThres=user_entry
+    ImParMat(4)= spotThres
+    spotThres 
+ end
+%
+%---------555555 Radius Entry After Sept.2014---------------------------------**
+
+btnNumber=5;
+   yPos=0.85-(btnNumber-1)*(btnHt+spacing);
+   btnPos=[xPos yPos-spacing btnWid btnHt];
+srcRadius=ImParMat(10);
+hedit=uicontrol(...
+      'Style', 'edit',...
+      'String',srcRadius,...
+      'Units','normalized',...   
+   	 'Position', btnPos,... % [.002 .70 .08 .10],...
+     'callback',{@entryRadius});  % 'Position', [5 100 60 20])
+
+ function entryRadius(source,eventdata)
+user_entry=str2double(get(source,'string'));
+    if (isnan(user_entry)||(user_entry<12)||(user_entry>17))
+	errordlg('You must enter a numeric value between 12 and 17','Bad Input','modal')
+	return
+    end
+    Radius=user_entry
+    ImParMat(10)= Radius
+    Radius
+ end
+
+%---------555555  Width Entry prior the Sept.2014---------------------------------**
+%{
+btnNumber=5;
+   yPos=0.85-(btnNumber-1)*(btnHt+spacing);
+   btnPos=[xPos yPos-spacing btnWid btnHt];
+srcWidth=ImParMat(5);
+hedit=uicontrol(...
+      'Style', 'edit',...
+      'String',srcWidth,...
+      'Units','normalized',...   
+   	 'Position', btnPos,... % [.002 .70 .08 .10],...
+     'callback',{@entryWidth});  % 'Position', [5 100 60 20])
+
+ function entryWidth(source,eventdata)
+user_entry=str2double(get(source,'string'));
+    if (isnan(user_entry)||(user_entry<5)||(user_entry>41))
+	errordlg('You must enter a numeric value between 5 and 40','Bad Input','modal')
+	return
+    end
+    Width=user_entry
+    ImParMat(5)= Width
+    Width
+ end
+%}
+%-------------------66666 Dither unnecessary after Sept.2014-----------
+
+   btnNumber=6;
+   yPos=0.85-(btnNumber-1)*(btnHt+spacing);
+   btnPos=[xPos yPos-spacing btnWid btnHt];
+srcDither= ImParMat(6);
+hedit=uicontrol(...
+      'Style', 'edit',...
+      'String',srcDither,...
+      'Units','normalized',...   
+   	 'Position', btnPos,... 
+     'callback',{@entryDither});  
+
+ function entryDither(source,eventdata)
+user_entry=str2double(get(source,'string'));
+    if (isnan(user_entry)||(user_entry<0)||(user_entry>5))
+	errordlg('You must enter a numeric value between 1 and 4','Bad Input','modal')
+	return
+    end
+    Dither=user_entry
+    ImParMat(6)= Dither
+    Dither
+ end
+%-------------------77777----------- Added July 7,2015 to allow Search Range constraint
+btnNumber=7;
+   yPos=0.85-(btnNumber-1)*(btnHt+spacing);
+   btnPos=[xPos yPos-spacing btnWid btnHt];
+   try
+   srchRange=ImParMat(12);
+   searchRangeNum=ImParMat(12)
+   catch  %Legacy default value was 18 before being made a user input variable (ImParMat(12)). A preferable value now might be 12 or 14.
+       srchRange=18;
+       ImParMat(12)=18
+       searchRangeNum=ImParMat(12)
+   end
+   
+   %{
+   if size(scLst)>1
+      srchRange=ImParMat(12);
+   else
+      try
+         srchRange=CSearchRange(str2double(scLst))
+      catch
+          srchRange=ImParMat(12); 
+       end
+   end
+   %}
+hSearchRange=uicontrol(...
+      'Style', 'edit',...
+      'String',srchRange,...
+      'Units','normalized',...   
+   	 'Position', btnPos,... 
+     'callback',{@CsearchRange});  
+
+ function CsearchRange(source,eventdata)
+   user_entry=str2double(get(source,'string'));
+    if (isnan(user_entry)||(user_entry<1)||(user_entry>50))  %originally 18; 19_0729 increased
+	errordlg('You must enter a numeric value between 1 and 18 12->18 recommended. (ImParMat(12)))','Bad Input','modal')
+	return
+    end
+    searchRangeNum=user_entry
+        
+ end
+
+%-------------------77777-----------
+%{
+btnNumber=7;
+   yPos=0.85-(btnNumber-1)*(btnHt+spacing);
+   btnPos=[xPos yPos-spacing btnWid btnHt];
+srcExtend=ImParMat(7);
+
+hedit=uicontrol(...
+      'Style', 'edit',...
+      'String',srcExtend,...
+      'Units','normalized',...   
+   	 'Position', btnPos,... 
+     'callback',{@entryExtend});  
+
+ function entryExtend(source,eventdata)
+user_entry=str2double(get(source,'string'));
+    if (isnan(user_entry)||(user_entry<-0.10)||(user_entry>0.4))
+	errordlg('You must enter a numeric value between 0 and 0.4. 0.10 recommended','Bad Input','modal')
+	return
+    end
+    extend=user_entry
+    ImParMat(7)= extend
+    extend
+ end
+%-------------------888888-----------
+
+btnNumber=8;
+   yPos=0.85-(btnNumber-1)*(btnHt+spacing);
+   btnPos=[xPos yPos-spacing btnWid btnHt];
+%ImParMat(8)=1;
+   srcpointExtend=ImParMat(8);
+hedit=uicontrol(...
+      'Style', 'edit',...
+      'String',srcpointExtend,...
+      'Units','normalized',...   
+   	 'Position', btnPos,... 
+     'callback',{@entrypointExtend});  
+
+ function entrypointExtend(source,eventdata)
+user_entry=str2double(get(source,'string'));
+user_entry= floor(user_entry);
+    if (isnan(user_entry)||(user_entry<-3)||(user_entry>5))
+	errordlg('You must enter an integer value between 0 and 5.  1 recommended','Bad Input','modal')
+	return
+    end
+    pointExtend=user_entry
+    ImParMat(8)= pointExtend
+    pointExtend
+ end
+%}
+%-------------------999999-----------
+
+btnNumber=9;
+   yPos=0.85-(btnNumber-1)*(btnHt+spacing);
+   btnPos=[xPos yPos-spacing btnWid btnHt];
+ 
+hedit=uicontrol(...
+      'Style', 'popupmenu',...
+      'String',{'GrowthArea','FixedArea'},...
+      'Units','normalized',...   
+   	 'Position', btnPos,... 
+     'callback',{@grwArea});  
+
+ function grwArea(source,eventdata)
+         str=get(source, 'String');
+         val=get(source,'Value');
+         % Set current data to the selected data set.
+         switch str{val};
+         case 'GrowthArea' ;% User selects Peaks.
+            SWgrowthArea=1
+         case 'FixedArea' % User selects Membrane.
+            SWgrowthArea=0
+         end
+ end
+%}
+

workflow/apps/matlab/easy/NCfitImCFparforFailGbl2.m

@@ -0,0 +1,232 @@
+%% CALLED BY par4GblFnc8c.m %%
+function [par4scanselIntensStd,par4scanselTimesStd,par4scanTimesELr,par4scanIntensELr,par4scanCFparameters,par4scanCFdate,outC,outCstd]= ...
+  NCfitImCFparforFailGbl2(parMat,times, values, timeOffsets, fileSuffix, AUCfinalTime, ~, spotAreas, printResultsDir, ~,~, sols, ~)  %,scan)
+
+  % Preallocation for parfor loop
+  st(1,1:size(times,2))=1111;
+  resMat(1,1:27)=0; 
+  resMatStd=resMat;
+  outC=zeros(384,27);  
+  outCstd=zeros(384,27);  
+  for m=1:384
+    pa{m}=st; 
+    par4scanCFparameters{m}=parMat; 
+    par4scanCFdate{m}=datestr((now),31); 
+  end
+  par4scanselTimesStd=pa;   
+  par4scanselIntensStd=pa;
+  par4scanTimesELr=pa;
+  par4scanIntensELr=pa;
+  par4resMat=zeros(384,27);
+  par4resMatStd=zeros(384,27);
+
+  % Spot (cultures) loop
+  for ii=1:384   % startSpot:numCultures
+    ii; % db print out the culture number 
+    timepts=[];
+    currValues=[];
+    currSpotAreas=[];
+    currSpotArea=[];
+    dataMatrix=[];
+    selTimesStd=[]; % 191024 parfor
+    selIntensStd=[]; % 191024 parfor
+    FiltTimesELr=[]; % 191024 parfor
+    NormIntensELr=[]; % 191024 parfor
+    
+    % add offset...1 offset PER PLATE
+    timepts=times + timeOffsets;  % (floor((ii-1)/arrayFormat) + 1);    
+    currValues=values(ii,:); % change values(spotNum,:);
+    % get spot areas for this culture
+    currSpotArea=spotAreas(:,ii);
+      
+    % just use the area at the last time point
+    % currSpotArea=currSpotAreas(1);
+  
+    % Preallocate to accomodate parfor loop 
+    resMatStd=zeros(1,27);
+    resMat=zeros(1,27);
+    currNormIntens=currValues/currSpotArea;
+    tmpx=find(currNormIntens>5); %15jh % 2.3);
+    validSpot=true;
+    if(isempty(tmpx) || length(tmpx)<3)
+        validSpot=false;
+        normIntens=currNormIntens;
+        filterTimes=timepts; %filterTimes; %currTimes;
+        selTimesStd=timepts;
+        selIntensStd=currNormIntens;
+        FiltTimesELr=timepts;
+        NormIntensELr=currNormIntens;
+    else
+      % NCfilImCF.m
+      % Preallocate incase something bails in NCscurImCFparfor
+      resMatStd=zeros(1,27);
+      resMat=zeros(1,27);
+      hold off;
+      dataMatrix=[];
+      K=0;r=0;l=0;Klow=0;Kup=0;rlow=0;rup=0;llow=0;lup=0;AUC=0;MSR=0;rsquare=0; 
+      bl=0;
+      Tpt1=0;numFitTpts=0;thresGT2=0;minTime=0;fitbl=0; % diagnostic outputs only 
+      
+      timepts=timepts; % timepts=currTimes; parfor
+      normIntens=currNormIntens;
+
+      dataMatrix=[]; % arfor move clear from NCfitImCF...m
+      loIntensThres=parMat(4);
+      stdLoIntLim=parMat(5);
+          
+      % Basic filtering
+      % [loInten Thres,stdbased Trim before Scurve start, and dropout detection]    
+      if(max(normIntens) > 2.29)
+        threshold=loIntensThres; %1.9; %Increase this value to reduce low data point (flag=2)
+      else
+        threshold=0;
+      end
+
+      dropThreshold=-0.0001*max(normIntens);
+
+      % Initialize dataMatrix
+      dataMatrix(1,:)=timepts;
+      dataMatrix(2,:)=normIntens;
+      dataMatrix(3,:)=ones;
+      dataMatrix(4,:)=normIntens;
+          
+      % Determine a mean Intensity Index point and assoc'd TimePt    
+      a=min(normIntens(normIntens>=0));   %(find(normIntens>=0)));
+      b=max(normIntens(normIntens>=0));   %(find(normIntens>=0)));
+      c=0.5*(b-a);
+      d=b-c;
+      meanIntIndPt=find(normIntens>d,1);
+      meanInt=normIntens(meanIntIndPt);
+      meanTime=times(meanIntIndPt);
+
+      % NCLoIntstdTrim
+      % NCLoSstdTrim.m called by NCfilImCF and NCfil.m
+      flg1=0;
+      loScurvLim=stdLoIntLim;
+      loStimeN=1;
+      last2n=1;
+      stdDev=[];
+      nrmIntens0=normIntens;
+      for n=1:meanIntIndPt
+        if nrmIntens0(n)<=0
+          nrmIntens0(n)=0;
+        end    
+        if(nrmIntens0(n)<threshold)
+          if (loStimeN-2)>0
+            dataMatrix(3,1:(n-2))=2; % add to lowIntensity cull flags, the pre S cull data
+          else 
+            dataMatrix(3,1:n)=2;
+          end
+          dataMatrix(3,1:(n-2))=2;
+          last2n=n; 
+        end
+        if n<(length(nrmIntens0)-3)
+          x=nrmIntens0(n:(n+3));
+          stdDev(n)=std(x);
+          if (stdDev(n)<loScurvLim && flg1~=1)
+            loStime=timepts(n); 
+            loStimeN=n;
+          end
+          if stdDev(n)>6
+            flg1=1;
+          end
+        end
+      end
+
+      % TODO repetitive code
+      if (loStimeN-2)>0
+        dataMatrix(3,1:(loStimeN-2))=2; % add to lowIntensity cull flags, the pre S cull data
+      else 
+        dataMatrix(3,1:(loStimeN-2))=2
+      end
+
+      qcutoff=2;
+      qind=find(normIntens>2);  %,:,'first');
+      if ~isempty(qind(3))
+        qcutoff=qind(3);
+      end
+      [minInt,I]=min(normIntens(2:qcutoff));
+      bl=minInt;
+      minTime=dataMatrix(1,I);
+
+      if (length(qind)>5)&&I>1
+        dataMatrix(3,1:(I-1))=5;
+      end
+
+      tGT2Flg=0;
+      for n=1:length(normIntens)
+        dataMatrix(4,n)=normIntens(n)-bl; 
+        if n>I && dataMatrix(4,n)>=2 && tGT2Flg==0
+          thresGT2=n;thresGT2Tm=dataMatrix(1,n);tGT2Flg=1;
+        end   
+      end
+
+      resMat(18)=bl;
+      resMatStd(18)=bl;   
+      resMatStd(20)=minTime;
+      resMat(20)=minTime;
+
+      % DropOut cull section (single drop points)
+      DropOutStartPt=length(normIntens);   
+      for n=1:length(normIntens) 
+        if(n>1)
+          if(((normIntens(n)- normIntens(n-1))< dropThreshold)) && ...
+            (n > max(meanIntIndPt,thresGT2) )
+            dataMatrix(3,n)=6;
+          end
+        end
+      end
+
+      % TODO should/could this be removed as recreated in%NCscurImCF_3parfor.m
+      % Post Stdtest cull for low intensities inclusion of additional low value points 
+      % selTimes=[--,--] %don't know size before as it is a filtered output
+      tmpIndx=0;
+      for n=1:length(normIntens) 
+        if (dataMatrix(3,n)==1)
+          tmpIndx=tmpIndx+1;
+          selTimes(tmpIndx)=dataMatrix(1,n); % selTimes(nn)=dataMatrix(1,n);
+          selIntens(tmpIndx)=dataMatrix(4,n); %s elIntens(nn)=dataMatrix(4,n);
+        
+        end
+      end
+
+      selTimes=selTimes';
+      selIntens=selIntens';
+      filtNormIntens=normIntens;
+      dataMatrix0=dataMatrix;
+      filterTimes=timepts; % parfor
+      
+      %NCscurImCF
+      %NCscurImCF_1
+      %NCscurImCF_2
+      %NCscurImCF_3
+      %NCscurImCF_3parfor
+      %NCscurImCF_3parfor(dataMatrix, AUCfinalTime)
+      %dataMatrix  %debugging parfor gbl  ok 85.7145; 126.4579,6, 124.5264  37tPt
+      %adsfj  %debugging parfor gbl
+
+      [resMatStd, resMat, selTimesStd, selIntensStd, FiltTimesELr, NormIntensELr] =...
+        NCscurImCF_3parfor(dataMatrix0, AUCfinalTime, currSpotArea, sols, bl, minTime); 
+
+    end
+
+    par4scanselTimesStd{ii}=selTimesStd  %timepts'; %filterTimes';
+    par4scanselIntensStd{ii}=selIntensStd;  %normIntens';
+    par4scanTimesELr{ii}=FiltTimesELr; % 19_1021 preserve for CurveDisplay and EZview
+    par4scanIntensELr{ii}=NormIntensELr; % 19_1021 preserve for CurveDisplay and EZview
+
+    outC(ii,:)=resMat; %{ii, par4resMat};
+    outCstd(ii,:)=resMatStd; %{ii, par4resMatStd};
+  end  
+
+  % To accomodate parfor 
+  % Copy par4scan thru global p4 functions inside of parfor loop --then outside to par4Gbl_Main8b.m
+  fileExt='.txt';
+  filePrefix='FitResultsComplete_';
+  fileNamePlate=[filePrefix fileSuffix fileExt];
+  fileName=fullfile(printResultsDir, fileNamePlate);  %[printResultsDir fileNamePlate];
+  fid=fopen(fileName,'w');
+  fprintf(fid, 'Fit Results Complete\n');
+  %fprintf(fid, 'Num.\tAUC\tMSR\tK\tr\tl\tR-squared\tK-lower\tK-upper\tr-lower\tr-upper\tl-upper\tl-lower\tArea\tLastInten\tSpineMaxRateTimePt\tLastFitTimePt\n');
+  fclose(fid);
+end

workflow/apps/matlab/easy/NCscurImCF_3parfor.m

@@ -0,0 +1,353 @@
+%% CALLED BY NCfitImCFparforFailGbl2.m %%
+function [resMatStd, resMat, selTimesStd, selIntensStd, FiltTimesELr, NormIntensELr] =...
+  NCscurImCF_3parfor(dataMatrix, AUCfinalTime, currSpotArea, sols, bl, minTime)
+
+  % Preallocate
+  resMatStd=zeros(1,27);
+  resMat=zeros(1,27);
+
+  % Set internal variables sent to matlab fit function 
+  me=200;
+  meL=750;
+  mi=25;
+  miL=250;
+  rmsStg1=0;
+  rmsStg1I(1)=0;
+  slps=1;
+  filterTimes=[];
+  normIntens=[];
+  nn=1;
+  numFitTpts=0;
+
+  % Build filterTimes and normIntens from spot dataMatrix selection codes produced in filter section  
+  for n=1:size(dataMatrix,2)
+    if (((dataMatrix(3,n)==1))||(dataMatrix(3,n)==3)||(dataMatrix(3,n)==2)...
+      ||(dataMatrix(3,n)==0))
+      filterTimes(nn)=dataMatrix(1,n);
+      normIntens(nn)=dataMatrix(4,n);  
+      nn=nn+1;
+    end
+  end
+  filterTimes=filterTimes';  
+  selTimesStd=filterTimes; 
+  normIntens=normIntens';  
+  selIntensStd=normIntens;
+  lastTptUsed=1;
+  lastIntensUsed=1;
+  thresGT2TmStd=0;  
+  try
+    lastTptUsed=max(filterTimes);
+    lastIntensUsed=normIntens(length(normIntens));
+    lastIntensUsedStd=lastIntensUsed;
+    lastTptUsedStd=lastTptUsed;
+    Tpt1Std=filterTimes(1);    
+    numFitTptsStd=nnz((normIntens(:)>=0)==1);
+    thresGT2=find(((normIntens(:)>2)==1), 1);
+    if isempty(thresGT2)
+     thresGT2TmStd=0;
+    else
+      thresGT2TmStd=filterTimes(thresGT2);
+    end
+    numTptsGT2Std=nnz((normIntens(:)>=2)==1); % nnz(filterTimes(find(filterTimes>=thresGT2Tm)));
+    K_Guess=max(normIntens);
+    numTimePts=length(filterTimes);
+    opts=fitoptions('Method','Nonlinear','Robust','On','DiffMinChange',1.0E-11,'DiffMaxChange',0.001,...
+      'MaxFunEvals',me, 'MaxIter', mi, 'TolFun', 1.0E-12, 'TolX', 1.0E-10, 'Lower', [K_Guess*0.5,0,0],...
+      'StartPoint', [K_Guess,filterTimes(floor(numTimePts/2)),0.30], 'Upper', [K_Guess*2.0,max(filterTimes),1.0],'Display','off');
+    ftype=fittype('K / (1 +  exp(-r* (t - l )))','independent','t','dependent',['K','r','l'],'options',opts);
+    
+    % Carry out the curve fitting process
+    [fitObject, errObj]=fit(filterTimes,normIntens,ftype);
+    coeffsArray=coeffvalues(fitObject);
+    rmsStg1=errObj.rsquare;
+    rmsStg1I(slps)=errObj.rsquare;
+    sDat(slps,1)=errObj.rsquare; 
+    K=coeffsArray(1); sDat(slps,2)=coeffsArray(1);  % Carrying Capacity
+    l=coeffsArray(2); sDat(slps,3)=coeffsArray(2); % lag time
+    r=coeffsArray(3); sDat(slps,4)=coeffsArray(3); % rateS
+
+    % Integrate (from first to last time point)
+    numVals=size(filterTimes);
+    numVals=numVals(1);
+    t_begin=0;
+    t_end=AUCfinalTime;
+    AUC=(K/r*log(1+exp(-r*(t_end-l)))-K/r*log(exp(-r*(t_end-l)))) - (K/r*log(1+exp(-r*(t_begin-l)))-K/r*log(exp(-r*(t_begin-l))));
+    MSR=r;
+    rsquare=errObj.rsquare;  
+    confObj=confint(fitObject,0.9); % get the 90% confidence 
+    NANcond=0; stdNANcond=0;  % stdNANcond added to relay not to attempt ELr as there is no curve to find critical point
+    confObj_filtered=confObj; 
+    Klow=confObj(1,1); sDat(slps,5)=confObj(1,1);
+    Kup=confObj(2,1); sDat(slps,6)=confObj(2,1);
+    llow=confObj(1,2); sDat(slps,7)=confObj(1,2);
+    lup=confObj(2,2); sDat(slps,8)=confObj(2,2);
+    rlow=confObj(1,3); sDat(slps,9)=confObj(1,3);
+    rup=confObj(2,3); sDat(slps,10)=confObj(2,3);
+    if(isnan(Klow)||isnan(Kup)||isnan(llow)||isnan(lup)||isnan(rlow)||isnan(rup))
+      NANcond=1; stdNANcond=1; % stdNANcond added to relay not to attempt ELr as there is no curve to find critical point
+    end  
+  catch
+    % if no data is given, return zeros
+    AUC=0;MSR=0;K=0;r=0;l=0;rsquare=0;Klow=0;Kup=0;
+    rlow=0;rup=0;lup=0;llow=0; 
+    NANcond=1; stdNANcond=1;  %stdNANcond added to relay not to attempt ELr as there is no curve to find critical point
+  end
+
+  if (exist('K','var')&& exist('r','var') && exist('l','var'))
+    t=(0:1:200);   
+    Growth=K ./ (1 +  exp(-r.* (t - l )));
+    fitblStd=min(Growth);
+  end
+   
+  cutTm(1:4)=1000;  %-1 means cuts not used or NA
+  
+  % Preserve for ResultsStd
+  resMatStd(1)=AUC;
+  resMatStd(2)=MSR;
+  resMatStd(3)=K;
+  resMatStd(4)=r;
+  resMatStd(5)=l;
+  resMatStd(6)=rsquare;
+  resMatStd(7)=Klow;
+  resMatStd(8)=Kup;
+  resMatStd(9)=rlow;
+  resMatStd(10)=rup;
+  resMatStd(11)=llow;
+  resMatStd(12)=lup;
+  resMatStd(13)=currSpotArea;
+  resMatStd(14)=lastIntensUsedStd; % filtNormIntens(length(filtNormIntens));
+  maxRateTime=0; %[];  %Std shows []; ELr shows 0;  %parfor
+  resMatStd(15)=0; %maxRateTimestdMeth;
+  resMatStd(16)=lastTptUsedStd;
+  if isempty(Tpt1Std)
+    Tpt1Std=777;
+  end
+  resMatStd(17)=Tpt1Std;
+  resMatStd(18)=bl; % perform in the filter section of NCfitImCFparfor
+  resMatStd(19)=fitblStd; % taken from NCfil... and not affected by NCscur...changes
+  resMatStd(20)=minTime; % not affected by changes made in NCscur...for refined 'r'
+  resMatStd(21)=thresGT2TmStd;
+  resMatStd(22)=numFitTptsStd;
+  resMatStd(23)=numTptsGT2Std;
+  resMatStd(24)=999; % yhe Standard method has no cuts .:.no cutTm  
+  resMatStd(25)=999;
+  resMatStd(26)=999;
+  resMatStd(27)=999;
+
+  % ELr New Experimental data through L+deltaS Logistic fit for 'Improved r'  Fitting
+  FiltTimesELr=[];  %{ii}=filterTimes;
+  NormIntensELr=[];  %{ii}=normIntens;  
+  normIntens=selIntensStd;
+  filterTimes=selTimesStd;
+  stdIntens=selIntensStd;
+  tmpIntens=selIntensStd;
+  stdTimes=selTimesStd;
+
+  if stdNANcond==0
+    % Determine critical points and offsets for selecting Core Data based on 
+    % Standard curve fit run.  Put diff into NImStartupImCF02.m calling source
+    % to reduce repeated execution since it doesn't change.
+    % fd4=diff(sym('K / (1 +  exp(-r* (t - l )))'),4);
+    % sols=solve(fd4);
+    tc1=eval(sols(2));
+    tc2=eval(sols(3));
+    LL=l;  %eval(sols(1));  %exactly the same as 'l' from std. fit method-Save time
+    rsTmStd=LL-tc1;   %%riseTime (first critical point to L)
+    deltS=rsTmStd/2;
+    tc1Early=tc1-deltS;    %AKA- tc1AdjTm %2*tc1 -LL
+    L_Late=LL+deltS;
+    tc1EdatPt=find(filterTimes>(tc1Early),1,'first');
+    cutTm(1)=filterTimes(2);
+    cutDatNum(1)=2;
+    cutTm(2)=tc1Early;
+    cutDatNum(2)=tc1EdatPt-1;
+    L_LDatPt=find(filterTimes< L_Late,1,'last');
+    tc2LdatPt=find(filterTimes< tc2+rsTmStd,1,'last');
+    cutTm(3)=L_Late;
+    cutDatNum(3)=L_LDatPt;
+    
+    % Select Core Data Set  (Remove Early data before critical point)         
+    ints=[];
+    ints(1:L_LDatPt-tc1EdatPt+2)=(tmpIntens(L_LDatPt));
+    ints(2:end)=tmpIntens(tc1EdatPt:L_LDatPt);
+    ints(1)=tmpIntens(1);
+    tms=[];
+    tms(1:L_LDatPt-tc1EdatPt+2)=(stdTimes(L_LDatPt));
+    tms(2:end)=stdTimes(tc1EdatPt:L_LDatPt);
+    tms(1)=stdTimes(1);
+
+    % Include/Keep late data that define K
+    if length(tmpIntens(tc2LdatPt:end))> 4
+      KlastInts=tmpIntens(tc2LdatPt:end);
+      KlastTms=stdTimes(tc2LdatPt:end);
+      lengthKlast=length(tmpIntens(tc2LdatPt:end));
+      ints(end:(end+ lengthKlast-1))=KlastInts;
+      tms(end:(end+ lengthKlast-1 ))=KlastTms;
+      cutTm(4)=tc2+rsTmStd;
+      cutDatNum(4)=tc2LdatPt-1;
+    else
+      lengthKlast=length(tmpIntens(tc2LdatPt-1:end)); 
+      if lengthKlast>1
+        KlastInts=tmpIntens(end-(lengthKlast-1):end);
+        KlastTms=stdTimes(end-(lengthKlast-1):end);
+        ints(end:(end+ lengthKlast-1 ))=KlastInts;
+        tms(end:(end+ lengthKlast-1 ))=KlastTms;
+      end
+      cutTm(4)=stdTimes(tc2LdatPt-1);
+      cutDatNum(4)=tc2LdatPt-2;   %length(stdTimes(end-(lengthKlast-1):end)); 
+    end
+    Ints=[];
+    Tms=[];
+    Ints=ints';
+    Tms=tms';
+    try
+      filterTimes=Tms; filterTimes4=Tms; 
+      normIntens=Ints;   normIntens4=Ints;
+
+      % Classic symmetric logistic curve fit setup restated as COMMENTS for reference convenience
+      % opts=fitoptions is the same as for Std and so is redundant     
+      % opts=fitoptions('Method','Nonlinear','Robust','On',...
+      % 'DiffMinChange',1.0E-11,'DiffMaxChange',0.001,...
+      % 'MaxFunEvals',me, 'MaxIter', mi, 'TolFun', 1.0E-12, 'TolX', 1.0E-10, 'Lower', [K_Guess*0.5,0,0], 'StartPoint', [K_Guess,filterTimes(floor(numTimePts/2)),0.30], 'Upper', [K_Guess*2.0,max(filterTimes),1.0]);
+    
+      ftype=fittype('K / (1 +  exp(-r* (t - l )))','independent','t','dependent',['K','l','r'],'options',opts);
+      fitObject=[]; errObj=[];
+      % carry out the curve fitting process
+      [fitObject, errObj]=fit(Tms,Ints,ftype);
+      coeffsArray=coeffvalues(fitObject);
+      r3=coeffsArray(3); % sDat(slps,4)=coeffsArray(3); % rateS
+    
+      if (exist('K','var')&& exist('r','var') && exist('l','var'))
+        t=(0:1:200);   
+        GrowthELr=K ./ (1 +  exp(-r.* (t - l )));
+        fitblELr=min(GrowthELr);   %jh diag
+      end
+    catch
+      % if no data is given, return zeros
+      AUC=0;MSR=0;K=0;r=0;l=0;rsquare=0;Klow=0;Kup=0;
+      rlow=0;rup=0;lup=0;llow=0; %normIntens=[];
+    end
+  end
+
+  % Update values if r is better(higher) with removal of early data
+  try
+    if r3>r && stdNANcond==0 
+      r=r3; sDat(slps,4)=sDat(slps,4); % rateS 
+      K=coeffsArray(1); sDat(slps,2)=coeffsArray(1);  % Carrying Capacity
+      l=coeffsArray(2); sDat(slps,3)=coeffsArray(2); % lag time
+      coeffsArray=coeffvalues(fitObject);
+      rmsStg1=errObj.rsquare;
+      rmsStg1I(slps)=errObj.rsquare;
+      sDat(slps,1)=errObj.rsquare; 
+    
+      % JH diagnostics   
+      numFitTpts=nnz((normIntens(:)>=0)==1);
+      thresGT2=find(((normIntens(:)>2)==1), 1);
+      thresGT2Tm=filterTimes(thresGT2); 
+      numTptsGT2=nnz((normIntens(:)>=2)==1);
+      numTimePts=length(filterTimes);
+    
+      AUC=(K/r*log(1+exp(-r*(t_end-l)))-K/r*log(exp(-r*(t_end-l)))) - (K/r*log(1+exp(-r*(t_begin-l)))-K/r*log(exp(-r*(t_begin-l))));
+      MSR=r3;
+      rsquare=errObj.rsquare;  
+      confObj=confint(fitObject,0.9); % get the 90% confidence 
+      NANcond=0;
+      confObj_filtered=confObj; 
+      Klow=confObj(1,1); sDat(slps,5)=confObj(1,1);
+      Kup=confObj(2,1); sDat(slps,6)=confObj(2,1);
+      llow=confObj(1,2); sDat(slps,7)=confObj(1,2);
+      lup=confObj(2,2); sDat(slps,8)=confObj(2,2);
+      rlow=confObj(1,3); sDat(slps,9)=confObj(1,3);
+      rup=confObj(2,3); sDat(slps,10)=confObj(2,3);
+      if(isnan(Klow)||isnan(Kup)||isnan(llow)||isnan(lup)||isnan(rlow)||isnan(rup))
+        NANcond=1;    
+      end
+      filterTimes=Tms; 
+      normIntens=Ints;   
+      resMat(17)=.00002;  
+      resMat(18)=bl;  
+      resMat(19)=fitblELr; 
+      resMat(20)=minTime; 
+    else % r is better than r3 so use the Std data in the ELr result sheet
+      filterTimes=selTimesStd; 
+      normIntens=selIntensStd;
+      lastTptUsed=lastTptUsedStd; % Reinstall Std values for jh diags
+      Tpt1=filterTimes(1);
+      try
+        if isempty(Tpt1)
+          Tpt1=0.00002;  %777;
+        end
+      catch
+        Tpt1=0.00002;  %777;
+      end
+     
+      resMat(17)=Tpt1;
+      numFitTpts=numFitTptsStd;
+      numTptsGT2=numTptsGT2Std;
+      thresGT2Tm=thresGT2TmStd;
+      cutTm(1:4)=1000;  % 1 means cuts not used or NA
+      resMat(18)=bl;  % only applicable to Std curve Fit; ELr superceeds and makes meaningless
+      resMat(19)=fitblStd; % only applicable to Std curve Fit; ELr superceeds and makes meaningless
+      resMat(20)=minTime; % only applicable to Std curve Fit; ELr superceeds and makes meaningless
+    end  % if r3>r1
+  catch
+    % if no data is given, return zeros
+    AUC=0;MSR=0;K=0;r=0;l=0;rsquare=0;Klow=0;Kup=0;
+    rlow=0;rup=0;lup=0;llow=0; % normIntens=[];
+  end
+   
+  resMat(1)=AUC;
+  resMat(2)=MSR;
+  resMat(3)=K;
+  resMat(4)=r;
+  resMat(5)=l;
+  resMat(6)=rsquare;
+  resMat(7)=Klow;
+  resMat(8)=Kup;
+  resMat(9)=rlow;
+  resMat(10)=rup;
+  resMat(11)=llow;
+  resMat(12)=lup;
+  resMat(13)=currSpotArea;
+  resMat(14)=lastIntensUsed;  %filtNormIntens(length(filtNormIntens));
+  % spline fit unneccessary and removed therfor no max spline rate time->set 0
+  maxRateTime=0; % ELr will show 0; Std will show [] 
+  resMat(15)=maxRateTime;
+  resMat(16)=lastTptUsed; % filterTimes(length(filterTimes));
+  try % if Std fit used no cuts .:. no cutTm 
+    resMat(24)=cutTm(1);
+    resMat(25)=cutTm(2);
+    resMat(26)=cutTm(3);
+    resMat(27)=cutTm(4);
+  catch
+    resMat(24)=999; % if Std fit used no cuts .:. no cutTm  
+    resMat(25)=999;
+    resMat(26)=999;
+    resMat(27)=999;
+  end
+
+  FiltTimesELr=filterTimes;
+  NormIntensELr=normIntens;
+  lastTptUsed=max(filterTimes);
+  lastIntensUsed=normIntens(length(normIntens));  
+  
+  if (exist('K','var')&& exist('r','var') && exist('l','var'))
+    t=(0:1:200);   
+    Growth=K ./ (1 +  exp(-r.* (t - l )));
+    fitbl=min(Growth);  % jh diag
+  end 
+  try % jh diag
+    if isempty(thresGT2Tm)
+      thresGT2Tm=0
+    end
+  catch
+    thresGT2Tm=0;
+    numTptsGT2=0;
+  end
+
+  resMat(21)=thresGT2Tm;
+  resMat(22)=numFitTpts;
+  resMat(23)=numTptsGT2;
+end
+
+ 

workflow/apps/matlab/easy/NCsingleDisplay.m

@@ -0,0 +1,89 @@
+%% CALLED WHEN ACCESSING 'CurveFit Display' %%
+global scLst
+global scan
+
+hf=figure;
+% Parameter Entry
+[scLst, row, col]=NCdisplayGui(scansDir);
+close(hf)
+selSpot=(row-1)*24 + col;
+for iPlate=1:length(scLst)
+  scanPltNum=str2double(scLst(iPlate));
+  K=scan(scanPltNum).plate(1).CFout((selSpot),3);
+  r=scan(scanPltNum).plate(1).CFout((selSpot),4);
+  l=scan(scanPltNum).plate(1).CFout((selSpot),5);
+  suffix=strcat('Scan-Plate', scLst(iPlate)); % char(QspLst(n));
+  % fileSpotSuffix=strcat('-Spot#',num2str(selSpot),'-Row=',selSpotRC(1),'-Col=',selSpotRC(2),'-FitData','-L=',num2str(l),'-r=',num2str(r),'-K=',num2str(K));    
+  fileSpotSuffix=strcat('-Spot#',num2str(selSpot),'-Row=',num2str(row),'-Col=',num2str(col),'-FitData','-L=',num2str(l),'-r=',num2str(r),'-K=',num2str(K));    
+  filenameNoExt=[suffix fileSpotSuffix];
+  timeArr=scan(scanPltNum).plate(1).tSeries;
+  rawIntens=scan(scanPltNum).plate(1).intens((selSpot),:)/scan(scanPltNum).plate(1).Ag((selSpot));
+  try
+    filterTms=scan(scanPltNum).plate(1).filterTimes{(selSpot)};
+    normInts=scan(scanPltNum).plate(1).normIntens{(selSpot)};
+  catch
+  end
+  if (exist('K','var')&& exist('r','var') && exist('l','var'))
+    t=(0:1:200);   
+    Growth=K ./ (1 +  exp(-r.* (t - l )));
+  end 
+  if length(scLst)>1 
+    figure
+  else
+    cla
+  end
+  hold on
+  plot(timeArr,rawIntens,'g*');
+  try
+    plot(filterTms,normInts,'o');
+  catch
+  end
+  hold on;
+  title(filenameNoExt); % this didn't make sense so changed
+  xlabel('Hours');
+  ylabel('Intensities Normalized by Area');
+  grid on;
+  if (exist('K','var')&& exist('r','var') && exist('l','var'))
+    plot(t, Growth,'b-');
+    % Plot L on curvefit figure
+    grL=Growth(round(l)); % growthCurve timePT for l in hours 
+    plot(l,0:grL,'-b') % to display position of l 
+    plot(l,grL,'^b') % to display l position on curve as an arrowhead
+
+    % Plot Arbitrary User Entry AUC "finalTimePt"  
+    % plot(finalTimePt,0,'+m')
+    % plot(0:finalTimePt,bl,'-m')
+  end  
+end
+
+%Spot entry form------------------------------------------------------
+%{
+prompt={'Enter spot to analyse:'};
+dlg_title='Input spot to curve fit';
+num_lines=1;
+def={'1'};
+selSpot=inputdlg(prompt,dlg_title,num_lines,def);
+K=scan(scanPltNum).plate(1).CFout(str2double(selSpot),3);
+r=scan(scanPltNum).plate(1).CFout(str2double(selSpot),4);
+l=scan(scanPltNum).plate(1).CFout(str2double(selSpot),5);
+
+suffix=strcat('Scan-Plate', scLst);    %char(QspLst(n));
+fileSpotSuffix=strcat('-Spot#',selSpot,'-FitData','-L=',num2str(l),'-r=',num2str(r),'-K=',num2str(K));    
+filenameNoExt=[suffix fileSpotSuffix];
+
+timeArr=scan(scanPltNum).plate(1).tSeries;
+rawIntens=scan(scanPltNum).plate(1).intens(str2double(selSpot),:)/scan(scanPltNum).plate(1).Ag(str2double(selSpot));
+filterTms=scan(scanPltNum).plate(1).filterTimes{str2double(selSpot)};
+normInts=scan(scanPltNum).plate(1).normIntens{str2double(selSpot)};
+
+%}
+%-----------------------------------------------------------------------
+%{
+prompt={'Enter Spot row:','Enter Spot column:'};
+dlg_title='Input spot to curve fit';
+num_lines=2;
+def={'1','1'};
+selSpotRC=inputdlg(prompt,dlg_title,num_lines,def);
+row=str2double(selSpotRC(1));  col=str2double(selSpotRC(2));
+%}
+%row=cell2mat(row);

workflow/apps/matlab/easy/NIcircle.m

@@ -0,0 +1,59 @@
+%% CALLED BY par4Gbl_Main8c.m %%
+%{
+%Imaging ToolBox method
+r=14;
+A=zeros(70,70);  %(fIntsc(refPtR:(refPtRExt),refPtC:(refPtCExt)))
+m={40,40};
+A(m{:})=1;
+B=imdilate(A,strel('disk',r,0) );
+imshow(B)
+
+area=pi*r^2
+
+clear all
+%}
+
+%without Image Proc. Toolbox
+%r=14;
+%A=zeros(70,70);
+%A=zeros(r,r);
+%P=[40,40];
+%center=[refPtR+ round(.5*width), refPtC+ round(.5*width)];
+%A=zeros(70,70);
+%---------------------------------------------------------------------
+%radius=14;
+diaExt=2*(radius+1);
+circBoxA=zeros(diaExt,diaExt);
+center=[radius+2, radius+2];
+[m,n]=size(circBoxA);
+X=bsxfun(@plus,(1:m)', zeros(1,n));
+Y=bsxfun(@plus,(1:n), zeros(m,1));
+cirMask=sqrt(sum(bsxfun(@minus,cat(3,X,Y),reshape(center,1,1,[])) .^2,3))<=radius;
+area=pi*radius^2;
+cirPixA=nnz(cirMask);
+optCirMask=double(cirMask);
+optCirMask(optCirMask==0)=0.8;
+% Foto Circle Fram(e)
+expansion=2;
+radExpan=radius+expansion;
+FdiaExt=2*(radExpan);
+circBoxA=zeros(FdiaExt,FdiaExt);
+center=[radExpan+1, radExpan+1];
+[m, n ]=size(circBoxA);
+X=bsxfun(@plus,(1:m)', zeros(1,n));
+Y=bsxfun(@plus,(1:n), zeros(m,1));
+FcirMask=sqrt(sum(bsxfun(@minus,cat(3,X,Y),reshape(center,1,1,[])) .^2,3))<=radExpan;
+
+%FcirPixA=nnz(cirMask);
+FoptCirMask=double(FcirMask);
+FoptCirMask(FoptCirMask==1)=2;
+%FoptCirMask(FoptCirMask==0)=1;
+%********Combine Masks to create circular boundry************
+padOptCirMask=padarray(optCirMask,[expansion-1 expansion-1],0.8);
+FoptCirMask=FoptCirMask .* padOptCirMask;
+FoptCirMask(FoptCirMask==1.6)=0.8;
+FoptCirMask(FoptCirMask==0)=1;
+FoptCirMask(FoptCirMask==2)=1;
+
+%---------------------------------------------------
+%imagesc(cirMask)

workflow/apps/matlab/easy/NImParamRadiusGui.m

@@ -0,0 +1,247 @@
+%% CALLED BY par4Gbl_Main8c.m %%
+% TODO Should some of these vars be pulled out higher so they are easier to change?
+%
+function NImParamRadiusGui(scansDir)
+  global SWsingleSc
+  global SWgrowthArea
+  global scan
+  global scLst
+  global ImParMat
+  global searchRangeNum
+  global defImParMat
+  global fhImRun
+  global fhconsole
+  global easyResultsDir
+  global fotosResultsDir
+  global pointMapsResultsDir
+  global pointMapsFile
+  global matFile
+  global numRows
+  global numCols
+  global scanSize
+  global scanMax
+  global searchRangeFile
+
+  % Ncode ImRobot adaptation
+  % TODO this code block and variables needs explanation
+  defImParMat=[1,1,15,34,24,1,0,0,1,14,1,18];  
+  if ImParMat(3)==0 || ImParMat(4)==0 ||ImParMat(5)==0 || ImParMat(10)==0 ||ImParMat(11)==0 
+    ImParMat=defImParMat;
+  end
+  if size(ImParMat,2)<12
+    ImParMat(12)=18; % default before user input CsearchRange value
+    msg='Data made before SearchRange user entry added (ImParMat(12). 18 was the set value and the current default.)';
+  end
+  % ImParMat=defImParMat; %Activate for INITIAL USE only
+  MPnum=1;
+  destPerMP=1;
+  selScan=1;
+  SWgrowthArea=1;
+
+  if exist(pointMapsFile, 'file')
+    load(pointMapsFile);
+  else
+    load(fullfile(easyDir, 'PTmats', 'NImParameters')) % hardcoded default
+    disp('WARNING: Using hardcoded NImParameters.mat')
+  end
+  ImParMat;
+  % if ~exist('searchRangeNum','var') || isempty(searchRangeNum)
+  if exist(searchRangeFile, 'file')
+    load(searchRangeFile);
+    CSearchRange; % TODO, might be an issue, figure out what this is doing
+  end
+      
+  % yInitPos=0.30;
+  xPos=0.05;
+  btnWid=0.10;
+  btnHt=0.05;
+  spacing=0.02;% Spacing between the button and the next command's label
+  
+  % The ADD Groups button
+  btnNumber=1;
+  yPos=0.85-(btnNumber-1)*(btnHt+spacing);
+  btnPos=[xPos yPos-spacing btnWid btnHt];
+  fhImParm=gcf;
+  if exist('easyResultsDir','var')&& ~isempty(easyResultsDir)
+    set(fhImParm,'NumberTitle','off')
+    set(fhImParm,'Name',strcat('ImageAnalysis- ',char(easyResultsDir)))
+  else
+    set(fhImParm,'NumberTitle','off')
+    set(fhImParm,'Name','EASYconsole - Exp. Analysis NOT selected.')
+  end
+
+  btnNumber=5;
+  yPos=0.85-(btnNumber-1)*(btnHt+spacing);
+  btnPos=[xPos yPos-spacing btnWid btnHt];
+  srcRadius=ImParMat(10);
+  hedit=uicontrol(...
+    'Style', 'edit',...
+    'String',srcRadius,...
+    'Units','normalized',...   
+    'Position', btnPos,... % [.002 .70 .08 .10],...
+    'callback',{@entryRadius}); % 'Position', [5 100 60 20])
+
+  function entryRadius(source,~)
+    user_entry=str2double(get(source,'string'));
+    if (isnan(user_entry)||(user_entry<12)||(user_entry>17))
+      errordlg('You must enter a numeric value between 12 and 17','Bad Input','modal')
+      return
+    end
+    Radius=user_entry;
+    ImParMat(10)=Radius;
+    Radius;
+  end
+
+  btnNumber=6;
+  yPos=0.85-(btnNumber-1)*(btnHt+spacing);
+  btnPos=[xPos yPos-spacing btnWid btnHt];
+  srcDither=ImParMat(6);
+  hedit=uicontrol(...
+    'Style', 'edit',...
+    'String',srcDither,...
+    'Units','normalized',...   
+    'Position', btnPos,... 
+    'callback',{@entryDither});  
+
+  function entryDither(source,~)
+    user_entry=str2double(get(source,'string'));
+    if (isnan(user_entry)||(user_entry<0)||(user_entry>5))
+      errordlg('You must enter a numeric value between 1 and 4','Bad Input','modal')
+      return
+    end
+    Dither=user_entry;
+    ImParMat(6)=Dither;
+    Dither;
+  end
+
+  btnNumber=7;
+  yPos=0.85-(btnNumber-1)*(btnHt+spacing);
+  btnPos=[xPos yPos-spacing btnWid btnHt];
+
+  % TODO, I don't think these are defined?
+  try
+    srchRange=ImParMat(12);
+  catch  % Legacy default value was 18 before being made a user input variable (ImParMat(12)). A preferable value now might be 12 or 14.
+    srchRange=18;
+    ImParMat(12)=18;
+  end
+    
+  hSearchRange=uicontrol(...
+    'Style', 'edit',...
+    'Value',searchRangeNum,...
+    'Units','normalized',...   
+    'Position', btnPos,... 
+    'callback',{@searchRangeCallback});  
+
+  function searchRangeCallback(source,~)
+    user_entry=str2double(get(source,'string'));
+    if (isnan(user_entry)||(user_entry<1)||(user_entry>50))  %originally 18; 19_0729 increased
+      errordlg('You must enter a numeric value between 1 and 18 12->18 recommended. (ImParMat(12)))','Bad Input','modal')
+      return
+    end
+    searchRangeNum=user_entry;  
+  end
+
+  % Ncode 12_0120 for reading in numeric folder names
+  nlist=dir(fullfile(scansDir,'*'));
+  nnn=0;
+  for n=1:size(nlist,1)
+    if (~isempty(str2num(nlist(n).name)))
+      nnn=nnn+1;
+      PnumLst(nnn)=(str2num(nlist(n).name));
+      sl(nnn,1)={(nlist(n).name)};
+    end
+  end
+  scanSize=size(sl,1);
+  scanMax=max(str2double(sl));
+
+  hListbox=uicontrol(...
+    'Style', 'listbox',...
+    'String',sort(sl),...
+    'value',[],...
+    'max',1000,...
+    'min',1,...
+    'Units','normalized',...   
+    'Position', [.70 .40 .10 .60],...
+    'callback',{@load_listbox});  %'uiresume(gcbf)'); 'Position', [5 100 60 20])
+  
+  function load_listbox(source,~)
+    userIndx=(get(source,'value'));
+    userStr=(get(source,'string'));
+    %scLstIndx=str2num(char(strrep(userStr(userIndx), 'Scan', '')))
+
+    user_entry=userStr(userIndx);
+    scLst=user_entry;
+    if size(scLst,1)>1
+      % searchRangeNum=num2str(ImParMat(12))
+      set(hSearchRange,'string',num2str(ImParMat(12)))
+    else
+      try
+        searchRangeNum=CSearchRange(str2double(scLst));
+        set(hSearchRange,'string',CSearchRange(str2double(scLst)))
+      catch
+        % CSrchRng=num2str(ImParMat(12))
+        % set(hSearchRange,'string',num2str(ImParMat(12)))
+      end
+    end
+  end
+
+  scLst;
+      
+  btnNumber=10;
+  yPos=0.85-(btnNumber-1)*(btnHt+spacing);
+  btnPos=[xPos yPos-spacing btnWid btnHt];
+  hedit8=uicontrol(...
+    'Style', 'pushbutton',...
+    'String',{'Continue'},...
+    'Units','normalized',...   
+    'Position', btnPos,... 
+    'callback','uiresume(gcbf)');  
+
+  % Labels
+  xLPos=0.175;
+  yPos=0;
+  btnWid=0.20;
+
+  lblNumber=5;
+  yPos=0.85-(lblNumber-1)*(btnHt+spacing);
+  btnPos=[xLPos yPos-spacing btnWid btnHt];
+  htxt=uicontrol(...
+    'Style', 'text',...
+    'String','Radius',...  %'String','Width',...
+    'Units','normalized',...   
+    'Position', btnPos);  
+
+  lblNumber=6;
+  yPos=0.85-(lblNumber-1)*(btnHt+spacing);
+  btnPos=[xLPos yPos-spacing btnWid btnHt];
+  htxt=uicontrol(...
+    'Style', 'text',...
+    'String','Dither',...
+    'Units','normalized',...   
+    'Position', btnPos);  
+
+  lblNumber=7;
+  yPos=0.85-(lblNumber-1)*(btnHt+spacing);
+  btnPos=[xLPos yPos-spacing btnWid btnHt]; 
+  htxt=uicontrol(...
+    'Style', 'text',...
+    'String','SearchRange',...
+    'Units','normalized',...   
+    'Position', btnPos);  
+
+  uiwait(gcf);
+  for i=1:length(scLst)
+    CSearchRange(str2double(scLst(i)))=CSrchRng;
+    ImParMat(12)=CSrchRng;
+  end    
+    
+  ImParMat;
+  searchRangeNum;
+
+  save(pointMapsFile, 'ImParMat');
+  save(searchRangeFile,'searchRangeNum');
+
+  close
+  return
+end

workflow/apps/matlab/easy/datatipp.m

@@ -0,0 +1,15 @@
+%% PART OF GUI FUNCTIONALITY %%
+
+% Display the position of the data cursor
+function output_txt = datatipp(~,event_obj)
+% obj          Currently not used (empty)
+% event_obj    Handle to event object
+% output_txt   Data cursor text string (string or cell array of strings).
+  pos=get(event_obj,'Position');
+  output_txt={['X: ',num2str(pos(1),4)],['Y: ',num2str(pos(2),4)]};
+
+  % If there is a Z-coordinate in the position, display it as well
+  if length(pos) > 2
+    output_txt{end+1}=['Z: ',num2str(pos(3),4)];
+  end
+end

workflow/apps/matlab/easy/p4loop8c.m

@@ -0,0 +1,36 @@
+%% CALLED BY par4Gbl_Main8c.m %%
+function[p4L4,...
+ TmpexpScanIntens4,TmpFexpScanSpots4,TmpFexpScanBMtp4,TmpanlZoneRefs4,Tmpsbdg4]= ...
+    p4loop8c(parMat,tptLength,numScans,selScanNumLst,SWsingleSc,Fflg,PTmapPos,optCirMask,diaExt,doCircle,cirPixA,cirMask,width, ... 
+    TmpexpScanIntens00,TmpFexpScanSpots00,TmpFexpScanBMtp00,TmpanlZoneRefs00,~,tifFileLstP4,pathname,ImParMat, ...
+    numRows,numCols,scLst,easyResultsDir,scansDir, p4L00,TmpexpScanIntens4,TmpFexpScanSpots4,TmpFexpScanBMtp4,TmpanlZoneRefs4, Tmpsbdg00, Tmpsbdg4)
+p4L0=p4L00;
+TmpexpScanIntens0=TmpexpScanIntens00;
+TmpFexpScanSpots0=TmpFexpScanSpots00;
+TmpFexpScanBMtp0=TmpFexpScanBMtp00;
+TmpanlZoneRefs0=TmpanlZoneRefs00;
+Tmpsbdg0= Tmpsbdg00;
+
+% for scCount=1:numScans
+if SWsingleSc==1
+  parforArg=0;
+else
+  parforArg=inf;
+end
+
+% for (scCount=1:numScans)
+parfor (scCount=1:numScans,parforArg)
+  scCount % for debugging
+  p4L0=cell(18,1);
+  [p4L3,TmpexpScanIntens3,TmpFexpScanSpots3,TmpFexpScanBMtp3,TmpanlZoneRefs3,Tmpsbdg3]= ...
+  par4GblFnc8c(parMat,tptLength,numScans,selScanNumLst,SWsingleSc,Fflg,PTmapPos,optCirMask,diaExt,doCircle,cirPixA,cirMask,width, ... 
+  TmpexpScanIntens0,TmpFexpScanSpots0,TmpFexpScanBMtp0,TmpanlZoneRefs0,scCount,tifFileLstP4,pathname,ImParMat, ...
+  numRows,numCols, scLst,easyResultsDir,scansDir, p4L0,Tmpsbdg0);
+
+  p4L4(:,scCount)=p4L3; % (:,scCount);
+  TmpexpScanIntens4(scCount)=TmpexpScanIntens3;
+  TmpFexpScanSpots4(scCount)=TmpFexpScanSpots3;
+  TmpFexpScanBMtp4(scCount)=TmpFexpScanBMtp3;
+  TmpanlZoneRefs4(scCount)=TmpanlZoneRefs3;
+  Tmpsbdg4(scCount)=Tmpsbdg3;
+end

workflow/apps/matlab/easy/par4GblFnc8c.m

@@ -0,0 +1,300 @@
+%% CALLED By p4loop8c.m %%
+function [p4L2, TmpexpScanIntens3,TmpFexpScanSpots3,TmpFexpScanBMtp3,TmpanlZoneRefs3,Tmpsbdg3]= ...
+  par4GblFnc8c(parMat,tptLength,~,selScanNumLst,~,Fflg,PTmapPos,optCirMask,diaExt,doCircle,cirPixA,cirMask,~,...
+  TmpexpScanIntens,TmpFexpScanSpots,TmpFexpScanBMtp,TmpanlZoneRefs,scCount,tifFileLstP4,~,ImParMat, ...
+  numRows,numCols,scLst,easyResultsDir,scansDir,~, Tmpsbdg)
+
+  global printResultsDir
+
+  selScan=selScanNumLst(scCount);
+  tptLength0=length(tifFileLstP4{scCount});  
+  % tptLength=numFiles;
+  tifFileLst={tifFileLstP4(scCount)}; 
+      
+  % Extract the Imaging time stamps from selected tif files
+  % clear('e','f'); %can't use clear inside a parfor loop. Preallocation
+  % can be larger than useable .bmp files! Therefore must be small and
+  % increased during for loop to maintain cell size integrity between e & f
+  e=cell(1,2); f=cell(1,2);  %(tptLength,2); f=cell(tptLength,2);
+  nndx=0;
+
+  for tPt=1:tptLength0   %size(tifFileLst,1)  %length(tifFileLst) 
+    tifFileLstP4{scCount}(tPt)
+    scLst;
+    scLst(scCount)
+    char(scLst(scCount))
+    char(fullfile(scansDir,char(scLst(scCount))))
+    scansDir;
+    swCatch=0;
+    nndx=nndx+1;
+    tifFile=char(fullfile(scansDir,char(scLst(scCount)), tifFileLstP4{scCount}(tPt)));
+    try
+      info=imfinfo(tifFile);  % D:\jwrDevel\DevelCurveFittingJWR\ImageScans\Scan2\020hr002.tif
+    catch ME 
+      % Note: During parallel operation Matlab will not open file (fid)
+      % etc. Therefore error message text will not be written.The only way
+      % to get it out would be to pass variable through called function to
+      % the ..Main8c script outside the parfor loop and print to file from
+      % there.  Consequently for now it only prints error to file when one
+      % edits p4loop8c.m from 'parfor' to ordinary 'for' loop
+      fFail=((fullfile(printResultsDir,'ImageFileReadFailure.txt')));  
+      fid=fopen(fFail,'a'); %create,open and append
+      % fprintf(fid,'%s \n',char(tifFile))
+      fclose(fid);
+      nndx=nndx-1;
+      swCatch=1;
+      rep=getReport(ME, 'basic');
+      rep=strcat('Read info failure for-',tifFile,' -', rep);
+      % fprintf(fid,'%s \n',rep) %See Note:    
+    end
+    tptLength=nndx;
+    scTmNumeric=1;  %initialize for parfor 
+    if swCatch==0
+      scTmNumeric(nndx)=datenum(info.FileModDate);
+      e(nndx,:)={tifFile, scTmNumeric(nndx)};
+      % newtifFileLst(nndx)=tifFileLst(tPt);
+    end
+  end
+
+  % Clear tifFileLst;
+  tifFileLst=cell(nndx,1);
+  f={sortrows(e,2)};
+  tifFileLst=f{1,1}(:,1);
+  areaOfIntensAboveBG=zeros(24,16,length(tifFileLst));
+
+  % Calculate Time series for each Plate of Selected Scan
+  lastPlateOnScan=1;  %Ncode
+  tSeriesv=[]; t0Seriesv=[];
+  if tptLength>0  % added to jump over and fill data for invalid Sscan(plate runs    
+    scTmNumv=cell2mat(f{1,1}(:,2));  % (:,2))120613 fix for variant length data
+    prtTmNumv=min(scTmNumv)-.000001;
+    tSeriesv=((scTmNumv-prtTmNumv)*24);
+    t0Seriesv=((scTmNumv-scTmNumv(1))*24);
+  end  
+
+  % Added to jump over and fill data for invalid Sscan(plate runs
+  if tptLength>=3 
+    % Create blank scan
+    ImHeigth=2075;
+    ImWidth=1400;
+    Empsc=zeros(ImHeigth,ImWidth);  %Ncode
+
+    % Start scan loop
+    lastPlateOnScan=1;  %Ncode
+    disp('Before call to NIscanIntens.....')
+
+    % Execute Image conversion into Intensity Data
+    [Tmpsbdg2, scanIntens, ~, ~, ~, TmpexpScanIntens2, TmpFexpScanSpots2, TmpFexpScanBMtp2, TmpanlZoneRefs2,areaOfIntensAboveBG]= ... 
+        NIscanIntensBGpar4GblFnc(Fflg,tifFileLst, ImParMat, PTmapPos,optCirMask,diaExt,doCircle,cirPixA,numRows,numCols,ImHeigth,ImWidth,cirMask, ...
+        tptLength,selScan,Empsc,TmpexpScanIntens,TmpFexpScanSpots,TmpFexpScanBMtp,TmpanlZoneRefs,easyResultsDir, Tmpsbdg);
+
+    TmpexpScanIntens3=TmpexpScanIntens2;
+    TmpFexpScanSpots3=TmpFexpScanSpots2;
+    TmpFexpScanBMtp3=TmpFexpScanBMtp2;
+    TmpanlZoneRefs3=TmpanlZoneRefs2;
+    Tmpsbdg3=Tmpsbdg2;
+
+    % clear plate
+    CFscanIntens=zeros(384,1); % zeros(16,24);
+    plate=[];
+    plate=zeros(24,16,tptLength);
+    plate(:,:,:,1)=scanIntens(1:1:24,16:-1:1,:); % TmpexpScanIntens2(1:1:24,16:-1:1,:);%Ncode Dev3Vertical Similar to below
+
+    % NIcheck: Check for bad scans at time points (swapped plates etc.)
+    % Set up cell arrays for storing each plate in each Scan ..(scan,plate)
+    SWprint=0;
+
+    % Construct Legacy ...Intens.txt file
+    if SWprint==1
+      filename=fullfile(easyResultsDir,'PrintResults',(strcat('Plate',num2str(selScan),'_Intens.txt')));
+      fid=fopen(filename,'w');
+    end
+
+    if length(size(plate))==2 % only two dims if only one image
+      numOfImages=1;
+    else
+      numOfImages=size(plate,3);
+    end
+
+    CFscanIntens=zeros(384,numOfImages);        
+    locIndx=0; pl=1;
+    for n=1:numCols % Ncode changed to 16 for Vert
+      for m=1:numRows % Ncode change to 24 for Vert
+        locIndx=locIndx+1;      
+        for k=1:numOfImages
+          if SWprint==1
+            if k==1 && numOfImages==1, fprintf(fid,'%.2f\n',plate(m,n,k,pl));end
+            if k==1 && numOfImages~=1, fprintf(fid,'%.2f',plate(m,n,k,pl));end
+            if k>1  && k<numOfImages, fprintf(fid,'\t%.2f',plate(m,n,k,pl));end  %
+            if k~=1 && k==numOfImages,fprintf(fid,'\t%.2f\n',plate(m,n,k,pl));end
+          end    
+          CFscanIntens(locIndx,k)=plate(m,n,k,pl);
+        end
+      end
+    end
+
+    if SWprint==1
+      fclose(fid);
+    end
+
+    % printGrwAreas
+    % Area as the max number of pixels with intensities greater than the Background 
+    % grArea(row,col,tPt,Plate) Note that images r and c are 90 degrees shifted
+    % and then mirror imaged.  Thus data must be inverted and rotated to get
+    % for the rows a-p and col 1-24 (and the EMS expected 1-384) orientation
+    % clear grArea
+    grArea=ones(24,16,tptLength);
+    grArea(:,:,:,1)=areaOfIntensAboveBG(1:1:24,16:-1:1,:);  %for Ncode dev3vert
+
+    % for p=1:lastPlateOnScan
+    if SWprint==1    
+      if SWgrowthArea==1
+        filename=fullfile(printResultsDir,(strcat('Plate',num2str(selScan),'_Areas.txt')));
+      else
+        filename=fullfile(printResultsDir,(strcat('ALTgrowthA_Scan',num2str(selScan),'_Plate',num2str(1),'_Areas.txt')));
+        filename=fullfile(printResultsDir,(strcat('ALTgrowthA_Plate',num2str(selScan),'_Plate','_Areas.txt')));
+      end
+      fid=fopen(filename,'w');
+    end
+    locIndx=0;
+    Ag=zeros(1,384);
+    for m=1:16 % Ncode change from 16  %Vert back to 16
+      for n=1:24 % Ncode change from  24 %Vert back to 24
+        growthArea=max(grArea(n,m,:,1));
+        if SWprint==1
+          fprintf(fid,'%3.f\n',growthArea);
+        end
+        locIndx=locIndx+1;
+        Ag(locIndx)=growthArea;
+      end
+    end
+
+    if SWprint==1
+      fclose(fid);
+      % fclose('all'); % TODO do we need this? 
+    end
+
+    % AutoImCF curveFit kickoff setup
+    autoImCFlag=1;
+    if autoImCFlag==1, SWgrowthArea=1;end
+    times=tSeriesv;     
+    scanAreas=Ag; % growthArea;
+    offsets=0; 
+    suffix=strcat('Scan', num2str(selScan),'_Plate', num2str(1)); % char(QspLst(n));
+    AUCfinalTime=96;
+    arrayFormat=384;
+        
+    % Version compatability fixes
+    %{
+    v11a='7.12.0.635 (R2011a)';
+    v14a='8.3.0.532 (R2014a)';
+    %v14b='8.4.0.150421 (R2014b)';
+    v18a='9.4.0.813654 (R2018a)';
+    v18b='9.5.0.944444 (R2018b)';
+    % Fourth order derivative of logistic equation
+    if isequal(v18a,version)||isequal(v18b,version)
+      syms t K r l;
+      fd4=diff(K / (1 +  exp(-r* (t - l ))),t,4);  
+    else
+      fd4=diff(sym('K / (1 +  exp(-r* (t - l )))'),4);   
+    end
+    sols=solve(fd4);
+    if isequal(v11a,version) || isequal(v14a,version)
+    else
+      tmpswap=sols(1);
+      sols(1)=sols(3);
+      sols(3)=tmpswap;
+    end
+    %}
+
+    if verLessThan('matlab','8.3') % original work 23_0227 updated 23_0525 (8.4 changed to 8.3)
+      fd4=diff(sym('K / (1 +  exp(-r* (t - l )))'),4);
+      sols=solve(fd4);
+    else % accomodate new matlab changes after 2014a  fix 2nd update 23_0227
+      syms t K r l;
+      fd4=diff(K / (1 +  exp(-r* (t - l ))),t,4);
+      sols=solve(fd4);
+      tmpswap=sols(1);
+      sols(1)=sols(3);
+      sols(3)=tmpswap;
+    end
+
+    % CFscanIntens
+    % Call CurveFit routine
+    % NCfitImCF(times, CFscanIntens, offsets, suffix, AUCfinalTime, arrayFormat, scanAreas, printResultsDir, autoImCFlag, selScan,sols) %,scan)%, scPltList) outputDirectory;   
+    % [scanTmp2]=NCfitImCFparforFailGbl(times, CFscanIntens, offsets, suffix, AUCfinalTime, arrayFormat, scanAreas, printResultsDir, autoImCFlag, selScan, sols, scanTmp); %,scan)%, scPltList) outputDirectory;
+    [par4scanselIntensStd,par4scanselTimesStd,par4scanTimesELr,par4scanIntensELr,par4scanCFparameters,par4scanCFdate,outC2,outCstd2]= ...
+        NCfitImCFparforFailGbl2(parMat,times, CFscanIntens, offsets, suffix, AUCfinalTime, arrayFormat, scanAreas, printResultsDir, autoImCFlag, selScan, sols); %,scan)%, scPltList) outputDirectory;
+  else  %fill with default values when an invalid plate scan occurs
+    CFscanIntens=zeros(16,24);
+    Ag=zeros(1,384);
+
+    % Preallocation for parfor loop
+    times=tSeriesv;
+    st(1,1:size(times,2))=1111;
+    resMat(1,1:27)=0; 
+    resMatStd=resMat;      
+    outC2=zeros(384,27); 
+    outCstd2=zeros(384,27);  
+    for m=1:384
+        pa{m}=st;
+        par4scanCFparameters{m}=parMat; 
+        par4scanCFdate{m}=datestr((now),31); 
+    end
+    par4scanselTimesStd=pa;   
+    par4scanselIntensStd=pa;
+    par4scanTimesELr=pa;
+    par4scanIntensELr=pa;
+    par4resMat=zeros(384,27);
+    par4resMatStd=zeros(384,27);
+    %{ 
+    TmpexpScanIntens00=cell(1);  %cell(1,scanMax);
+    TmpFexpScanSpots00=cell(1);  %cell(1,scanMax);
+    TmpFexpScanBMtp00=cell(1);  %cell(1,scanMax);
+    TmpanlZoneRefs00=cell(1);  %cell(1,scanMax);
+    Tmpsbdg00=cell(1); 
+    %}
+    TmpexpScanIntens3=cell(1);  %TmpexpScanIntens2;
+    TmpFexpScanSpots3=cell(1);  %TmpFexpScanSpots2;
+    TmpFexpScanBMtp3=cell(1);  %TmpFexpScanBMtp2;
+    TmpanlZoneRefs3=cell(1);  %TmpanlZoneRefs2;
+    Tmpsbdg3=cell(1);  %Tmpsbdg2;
+  end  %if tptLenth>=3  line19  20_0928 
+
+  tSeriesv;  %debuggin parfor
+  p4L1{1}=tSeriesv;  
+  p4L1{2}=t0Seriesv;  
+  p4L1{3}=datestr(prtTmNumv,31);  
+  p4L1{4}=CFscanIntens;
+
+  locIndx=0;
+  for n=1:numCols % Ncode changed to 16 for Vert
+    for m=1:numRows % Ncode change to 24 for Vert
+      locIndx=locIndx+1;
+      rc=[n,m];
+        p4rcTmp(locIndx)={rc};
+        p4pIndxTmp(locIndx)=locIndx;
+    end
+  end
+
+  p4L1{5}=p4rcTmp;
+  p4L1{6}=p4pIndxTmp;
+  p4L1{7}=Ag;
+
+  p4L1{8}=par4scanselIntensStd; 
+  p4L1{9}=par4scanselTimesStd; 
+  p4L1{10}=par4scanTimesELr; 
+  p4L1{11}=par4scanIntensELr; 
+
+  p4L1{12}=par4scanCFparameters;
+  p4L1{13}=par4scanCFdate;
+
+  p4L1{14}=outC2; 
+  p4L1{15}=outCstd2;
+  p4L1{16}=selScan; 
+
+  p4L1{17}=cirPixA;
+  p4L1{18}=datestr((now),31); % TODO this seems bad
+
+  p4L2=p4L1;
+end

workflow/apps/matlab/easy/par4Gbl_Main8c.m

@@ -0,0 +1,246 @@
+%% CALLED BY EASYconsole.m %%
+
+global SWgrowthArea
+global scLst
+global ImParMat
+global scansDir
+global matFile
+global fhconsole
+global easyResultsDir
+global printResultsDir
+global pointMapsResultsDir
+global fotosResultsDir
+global matDir
+global ImWidth
+global ImHeigth
+global numRows
+global numCols
+global scan
+global scanMax
+global tptLength
+global easyDir
+
+numRows=24; % for Single Vertical 
+numCols=16; % for Single Vertical 
+
+% CIRCLE related
+doCircle=1; % use Circle area analysis 14_0807
+radius=14;
+ImParMat(10)=radius;
+ImParMat(11)=doCircle;
+
+% TODO what is this for?
+Fflg=1;
+
+% Don't think we need this
+% fclose('all');  % close all open files
+
+% Unset some vars just in case they are already set
+clear('scanIntens','Scanfiles','pathname','tifFileLstP4');
+
+try
+  clf(fhconsole,'reset');
+catch
+end
+
+% No idea why we're doing this so commenting out
+% close
+% EASYconsole
+
+if exist(matFile, 'file')
+  bkUpMatFile=fullfile(matDir,'BkUp',matFile);
+  copyfile(matFile,bkUpMatFile);
+end
+
+% Reloacated from 'PTmats' to prevent potential overwrite when PTmats is
+% copied into new job when the PT template is about the same.  We also
+% now have a default template if one is not made. i.e., when the images
+% from the new experiment are too sketchy to make a good pintool
+% template. By moving it to 'Fotos' we avoid possible issues due to
+% copying the Nbdg.mat file along with the default template '.mat' files.
+% A copy of Ndbg.mat is placed also saved to the 'PTmats' directory
+% after each run to allow previous version of EASY to access data made
+% by EASY versions after 20_0819.
+try
+  load(fullfile(fotosResultsDir,'Nbdg')); %Modified to load from 'Fotos' 20_0819
+catch
+  load(fullfile(pointMapsResultsDir,'Nbdg')); %Left in to accomodate loads of work before 20_0819
+end
+% Load Fotos stored data
+fotosToLoad = {'Coordinates', 'BGatTpts', 'anlZones', 'NCFparms'};
+for i=1:length(fotosToLoad)
+  try
+    load(fullfile(fotosResultsDir, fotosToLoad{i}));
+  catch
+    load(fullfile(easyDir,'parameters'));
+  end
+end
+
+% Get Print Times
+PrintTimes=[];
+scLst={};
+
+% Parameter Entry
+NImParamRadiusGui(scansDir); % Ncode 122111replaced removed  ,numOfPrtTimes)
+width=24;
+widthEx=width-1; % width extention from reference point
+dither=ImParMat(6);
+radius=ImParMat(10);
+NIcircle;
+
+% Load Stuff
+lastPlateOnLastScan=1; % Ncode
+
+if size(scLst,1)==1
+  SWsingleSc=1;
+else 
+  SWsingleSc=0;
+end
+
+dvec=datevec(datestr(floor(now))); %method to get current offset year '01-Jan-"currentyr"'
+dvec(2)=1;
+dvec(3)=1;
+% yrOffset=datenum('01-Jan-2012');%(dvec); %('01-Jan-2009'); %time num default is currentyear jan1
+numScans=size(scLst,1);
+
+if(isequal(SWsingleSc,1))
+  selScan=str2double(char(scLst(1)));
+else
+  % startScan=1;
+end
+
+SWgrowthArea=ImParMat(9);
+load(fullfile(pointMapsResultsDir,'NPTmapSearch'));
+PTmapPos=detPos;
+selScanNumLst=[];
+Scanfiles=[];
+pathname=[];
+
+for ii=1:length(scLst)
+  if (SWsingleSc == 1)
+    % TODO proably need to make this more explicit with paths
+    [Scanfiles, pathname]=uigetfile('*.bmp', 'Select files','MultiSelect','on'); % change '*hr*.bmp' 12/20/2011 
+    if ischar(Scanfiles)    
+      scd=imread(char(Scanfiles));
+      tptLength=1;
+    else
+      scd=imread(char(Scanfiles(1,1)));
+      tptLength=length(Scanfiles);
+    end
+  ImHeigth=size(scd,1);
+  ImWidth=size(scd,2);
+  sc=scd(1:ImHeigth,1:ImWidth);
+  end
+
+  numFiles=size(Scanfiles,2);
+
+  % Initialize tifFilesLst for parfor loop
+  dir(fullfile(scansDir, char(scLst(ii)), '*.bmp'));
+  numFiles=length(tifFileLst4MultiT);  
+  tptLength=numFiles;
+  tifFileLstP4{ii}={tifFileLst4MultiT.name};
+end
+
+for jj=1:numScans % startScan:numScans
+  selScan=str2double(char(scLst(jj)));
+  selScanNumLst(jj)=selScan;
+end
+selScanNumLst2=selScanNumLst; % function passthrough, passback to par4gbl_Main 20_0205
+
+% Preallocation
+scCount=[];
+TmpexpScanIntens00=cell(1); % cell(1,scanMax);
+TmpFexpScanSpots00=cell(1); % cell(1,scanMax);
+TmpFexpScanBMtp00=cell(1); % cell(1,scanMax);
+TmpanlZoneRefs00=cell(1); % cell(1,scanMax);
+Tmpsbdg00=cell(1); 
+TmpexpScanIntens4=cell(1,numScans);
+TmpFexpScanSpots4=cell(1,numScans);
+TmpFexpScanBMtp4=cell(1,numScans);
+TmpanlZoneRefs4=cell(1,numScans);
+Tmpsbdg4=cell(1,numScans);
+TmpexpScanIntens5=cell(1,numScans);
+TmpFexpScanSpots5=cell(1,numScans);
+TmpFexpScanBMtp5=cell(1,numScans);
+TmpanlZoneRefs5=cell(1,numScans);
+Tmpsbdg5=cell(1,numScans);
+p4L00=cell(18,1);
+p4L0=p4L00;
+p4L4=cell(18,numScans);
+p4L5=p4L4;
+Ag=ones(384);
+CFscanIntens=zeros(16,24);
+ 
+[p4L4,TmpexpScanIntens5,TmpFexpScanSpots5,TmpFexpScanBMtp5,TmpanlZoneRefs5,Tmpsbdg5]= ...
+  p4loop8c(parMat,tptLength,numScans,selScanNumLst,SWsingleSc,Fflg,PTmapPos,optCirMask,diaExt,doCircle,cirPixA,cirMask,width, ... 
+  TmpexpScanIntens00,TmpFexpScanSpots00,TmpFexpScanBMtp00,TmpanlZoneRefs00,scCount,tifFileLstP4,pathname,ImParMat, ...
+  numRows,numCols,scLst,easyResultsDir,scansDir, p4L00,TmpexpScanIntens4,TmpFexpScanSpots4,TmpFexpScanBMtp4,TmpanlZoneRefs4, ...
+  Tmpsbdg00,Tmpsbdg4);
+
+for scanCnt=1:numScans
+  selScan=p4L4{16,scanCnt}; % determine the actual scan in the scanCnt parfor distributed "id"
+  scan(selScan).plate(1).tSeries=cell2mat(p4L4(1,scanCnt));
+  scan(selScan).plate(1).t0Series=cell2mat(p4L4(2,scanCnt));
+  scan(selScan).plate(1).printTm=cell2mat(p4L4(3,scanCnt));
+  scan(selScan).plate(1).intens=cell2mat(p4L4(4,scanCnt));
+  scan(selScan).plate(1).rc=p4L4(5,scanCnt);
+  scan(selScan).plate(1).pIndx=cell2mat(p4L4(6,scanCnt));
+  scan(selScan).plate(1).Ag=cell2mat(p4L4(7,scanCnt));
+  scan(selScan).plate(1).selIntens=p4L4(8,scanCnt); 
+  scan(selScan).plate(1).selTimes=p4L4(9,scanCnt); 
+  scan(selScan).plate(1).filterTimes=p4L4(10,scanCnt); 
+  scan(selScan).plate(1).normIntens=p4L4(11,scanCnt); 
+  % scan(selScan).plate(1).CFparameters=p4L4(12,scanCnt); %Need to convert to a matrix form like Old versions
+  CFparm(1:384)=p4L4{12,scanCnt}(1:384);
+  scan(selScan).plate(1).CFparameters=CFparm;
+  scan(selScan).plate(1).CFdate=p4L4(13,scanCnt);
+  scan(selScan).plate(1).CFout=cell2mat(p4L4(14,scanCnt)); 
+  scan(selScan).plate(1).CFoutStd=cell2mat(p4L4(15,scanCnt));
+  scan(selScan).Awindow=cell2mat(p4L4(17,scanCnt));
+  scan(selScan).Idate=cell2mat(p4L4(18,scanCnt)); 
+  expScanIntens(selScan)=TmpexpScanIntens5(scanCnt);
+  FexpScanSpots(selScan)=TmpFexpScanSpots5(scanCnt);
+  FexpScanBMtp(selScan)=TmpFexpScanBMtp5(scanCnt);
+  anlZoneRefs(selScan)=TmpanlZoneRefs5(scanCnt);
+  if ~isempty(Tmpsbdg5{scanCnt})
+    sbdg(selScan)=Tmpsbdg5(scanCnt);
+  else
+    sbdg{selScan}=uint8(zeros(24,16,4));
+  end
+end 
+
+% Save data in .mat files
+save(matFile,'scan');
+% save((fullfile(easyResultsDir,'PTmats','Nbdg')), 'sbdg'); %legacy location can probably get rid of in time
+save((fullfile(fotosResultsDir,'Nbdg')), 'sbdg');
+save((fullfile(fotosResultsDir,'Coordinates')),'FexpScanSpots') %Saves frames at each tPt
+save((fullfile(fotosResultsDir,'BGatTpts')),'FexpScanBMtp')
+save((fullfile(fotosResultsDir,'anlZones')),'anlZoneRefs')%Saves anl Positions at each tPt
+
+% Print FitResults
+fileExt='.txt';
+filePrefix='FitResults_';
+for scanCnt=1:numScans
+  selScan=p4L4{16,scanCnt}; % determine the actual scan in the scanCnt parfor distributed "id"
+  fileSuffix=sprintf('Scan%d_Plate%d', selScan, 1);
+  fileNamePlate=[filePrefix fileSuffix fileExt];
+  fileName=fullfile(printResultsDir, fileNamePlate); % [outputDirectory fileNamePlate];
+
+  % This,fprint for loop,is an very old legacy feature which slows processing. Could be
+  % removed but allows easy observation of how a run is progressing and can be
+  % used as a diagnostic tool.
+  outCprint=p4L4;
+
+  fid=fopen(fileName,'w');
+  fprintf(fid, 'Num.\tAUC\tMSR\tK\tr\tl\tR-squared\tK-lower\tK-upper\tr-lower\tr-upper\tl-upper\tl-lower\tArea\tLastInten\tSpineMaxRateTimePt\tLastFitTimePt\n');
+  for n=1:384 % startCount:numCultures
+    fprintf(fid,'%d\t',n);
+    fprintf(fid, '%.5f\t%.5f\t%.5f\t%.5f\t%.5f\t%.5f\t%.5f\t%.5f\t%.5f\t%.5f\t%.5f\t%.5f\t%.5f\t%.5f\t%.5f\t%.5f\n',...
+    outCprint{14,scanCnt}(n,1),outCprint{14,scanCnt}(n,2),outCprint{14,scanCnt}(n,3),outCprint{14,scanCnt}(n,4),...
+    outCprint{14,scanCnt}(n,5),outCprint{14,scanCnt}(n,6),outCprint{14,scanCnt}(n,7),outCprint{14,scanCnt}(n,8),...
+    outCprint{14,scanCnt}(n,9),outCprint{14,scanCnt}(n,10),outCprint{14,scanCnt}(n,11),outCprint{14,scanCnt}(n,12),...
+    outCprint{14,scanCnt}(n,13),outCprint{14,scanCnt}(n,14),outCprint{14,scanCnt}(n,15),outCprint{14,scanCnt}(n,16));
+  end
+  fclose(fid);
+end
+

workflow/apps/perl/analyze_v2.pl

@@ -0,0 +1,390 @@
+#!/usr/bin/perl
+
+# $Id: analyze.pl,v 1.9 2008/05/14 20:45:37 sherlock Exp $
+
+# Date   : 16th October 2003
+# Author : Gavin Sherlock
+
+# License information (the MIT license)
+
+# Copyright (c) 2003 Gavin Sherlock; Stanford University
+
+# Permission is hereby granted, free of charge, to any person
+# obtaining a copy of this software and associated documentation files
+# (the "Software"), to deal in the Software without restriction,
+# including without limitation the rights to use, copy, modify, merge,
+# publish, distribute, sublicense, and/or sell copies of the Software,
+# and to permit persons to whom the Software is furnished to do so,
+# subject to the following conditions:
+
+# The above copyright notice and this permission notice shall be
+# included in all copies or substantial portions of the Software.
+
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+# NONINFRINGEMENT.  IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+# BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+# ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+# CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+# SOFTWARE.
+
+use strict;
+use warnings;
+use diagnostics;
+
+use Data::Dumper;
+
+use Getopt::Long;
+
+use IO::File;
+
+use GO::TermFinder;
+use GO::AnnotationProvider::AnnotationParser;
+use GO::OntologyProvider::OboParser;
+
+use GO::TermFinderReport::Text;
+
+use GO::Utils::File    qw (GenesFromFile);
+use GO::Utils::General qw (CategorizeGenes);
+
+$|=1;
+
+###################################################################################
+sub Usage{
+###################################################################################
+
+    my $message = shift;
+
+    if (defined $message){
+
+	print $message, "\n";
+
+    }
+
+    print <<USAGE;
+
+This program takes a list of files, each of which contain a list of
+genes, with one gene per line.  It will findTerms for the lists of
+genes in each of the GO aspects, outputting the results to a file
+named for the original file, but with a .terms extension.  It will only
+output terms with a corrected P-value of <= 0.05.
+
+It will use the first supplied argument as the annotation file, the
+second argument as the expected number of genes within the organism,
+the third argument is the name of the obo file, and all subsequent
+files as ones containing lists of genes.
+
+Usage:
+
+analyze.pl <annotation_file> <numGenes> <obofile> <file1> <file2> <file3> ... <fileN>
+
+e.g.
+
+analyze.pl -a ../t/gene_association.sgd -n 7200 -o ../t/gene_ontology_edit.obo genes.txt genes2.txt
+
+USAGE
+
+    exit;
+
+}
+
+# we need at least 3 arguments, an annotation file, the number of
+# genes in the genome, and a file of input genes to test
+
+&Usage if (@ARGV < 3);
+
+# now get our annotation file and number of genes
+
+my $annotationFile = '';
+my $totalNum       = '';
+my $oboFile        = '';
+my $background	   = '';
+my $aspect	   = '';
+
+GetOptions(	"annotations=s"	=> \$annotationFile,
+		"obofile=s"	=> \$oboFile,
+		"background=s"	=> \$background,
+		"numGenes=i"	=> \$totalNum,
+		"aspect=s"	=> \$aspect
+	);
+
+if ($oboFile !~ /\.obo$/){
+
+    # require the obo file to have a .obo extension
+
+    &Usage("Your obo file does not have a .obo extension.");
+
+}
+
+if ($annotationFile !~ /\.sgd$/){
+	&Usage("Perhaps we are missing an annotation file.");
+}
+
+my @population = ();
+if ($background) {
+	@population = GenesFromFile($background)
+}
+
+# now set up the objects we need
+
+my $process   = GO::OntologyProvider::OboParser->new(ontologyFile => $oboFile,
+						     aspect       => 'P');
+my $component = GO::OntologyProvider::OboParser->new(ontologyFile => $oboFile,
+						     aspect       => 'C');
+my $function  = GO::OntologyProvider::OboParser->new(ontologyFile => $oboFile,
+						     aspect       => 'F');
+
+my $annotation = GO::AnnotationProvider::AnnotationParser->new(annotationFile=>$annotationFile);
+
+my @termFinders = ();
+
+if ($background) {
+	if ($aspect =~ /^P$|^$/) {
+		push @termFinders, GO::TermFinder->new(annotationProvider=> $annotation,
+		   				   ontologyProvider  => $process,
+						   population	     => \@population,
+						   aspect            => 'P');
+	}
+	
+	if ($aspect =~ /^C$|^$/) {
+		push @termFinders, GO::TermFinder->new(annotationProvider=> $annotation,
+						   ontologyProvider  => $component,
+						   population	     => \@population,
+						   aspect            => 'C');
+	}
+	
+	if ($aspect =~ /^F$|^$/) {
+		push @termFinders, GO::TermFinder->new(annotationProvider=> $annotation,
+						   ontologyProvider  => $function,
+						   population	     => \@population,
+						   aspect            => 'F');
+	}
+} else {
+	if ($aspect =~ /^P$|^$/) {
+		push @termFinders, GO::TermFinder->new(annotationProvider=> $annotation,
+		   				   ontologyProvider  => $process,
+						   totalNumGenes     => $totalNum,
+						   aspect            => 'P');
+	}
+	
+	if ($aspect =~ /^C$|^$/) {
+		push @termFinders, GO::TermFinder->new(annotationProvider=> $annotation,
+						   ontologyProvider  => $component,
+						   totalNumGenes     => $totalNum,
+						   aspect            => 'C');
+	}
+	
+	if ($aspect =~ /^F$|^$/) {
+		push @termFinders, GO::TermFinder->new(annotationProvider=> $annotation,
+						   ontologyProvider  => $function,
+						   totalNumGenes     => $totalNum,
+						   aspect            => 'F');
+	}
+}
+
+
+my $report = GO::TermFinderReport::Text->new();
+
+my $cutoff = 0.1;
+
+# now go through each file
+
+foreach my $file (@ARGV){
+
+    print "Analyzing $file\n";
+
+    my @genes = GenesFromFile($file); 
+
+    my (@list, @notFound, @ambiguous);
+
+    CategorizeGenes(annotation  => $annotation,
+		    genes       => \@genes,
+		    ambiguous   => \@ambiguous,
+		    unambiguous => \@list,
+		    notFound    => \@notFound);
+
+    my $outfile = $file.".terms";
+
+    my $fh = IO::File->new($outfile, q{>} )|| die "Cannot make $outfile : $!";
+
+    print "Results being put in $outfile\n";
+
+    if (@list){
+
+	print $fh "The following gene(s) will be considered:\n\n";
+
+	foreach my $gene (@list){
+
+	    print $fh $gene, "\t", $annotation->standardNameByName($gene), "\n";
+
+	}
+
+	print $fh "\n";
+
+    }else{
+
+	print $fh "None of the gene names were recognized\n";
+	print $fh "They were:\n\n";
+	print $fh join("\n", @notFound), "\n";
+	$fh->close;
+
+	next;
+
+    }
+
+    if (@ambiguous){
+
+	# note, some of these ambiguous names would be perfectly fine
+	# if put into GO::TermFinder if they are also standard names.
+	# Currently the behavior of analyze.pl differs from the
+	# default behavior of GO::TermFinder
+
+	print $fh "The following gene(s) are ambiguously named, and so will not be used:\n";
+	print $fh join("\n", @ambiguous), "\n\n";
+
+    }
+
+    if (@notFound){
+
+	print $fh "The following gene(s) were not recognized, and will not be considered:\n\n";
+	print $fh join("\n", @notFound), "\n\n";
+
+    }
+
+    foreach my $termFinder (@termFinders){
+
+	# it's possible that the supplied number of genes on the
+	# command line was less than indicated by the annotation
+	# provider, and thus the TermFinder may have used a larger
+	# number than was entered on the command line.
+
+	my $totalNumGenesUsedInBackground = $termFinder->totalNumGenes;
+
+	print $fh "Finding terms for ", $termFinder->aspect, "\n\n";
+
+	my @pvalues = $termFinder->findTerms(genes => \@list, calculateFDR => 1);
+  if($#pvalues == 0) {
+    print "WARNIING: NO p-value structures returned by findTerms(";
+    print join ",", @list;
+    print ")\n";
+  	print $fh "\n\n";
+    $fh->close;
+    exit();
+  }
+	my $numHypotheses = $report->print(pvalues  => \@pvalues,
+					   numGenes => scalar(@list),
+					   totalNum => $totalNumGenesUsedInBackground,
+					   cutoff   => $cutoff,
+					   fh       => $fh);
+
+  my $numProcesses = $#pvalues + 1;
+  print "Number of GO processes found: $numProcesses\n";
+  print "Number of hypotheses passed cutoff: $numHypotheses\n";
+
+	# if they had no significant P-values
+
+	if ($numHypotheses == 0){
+
+	    print $fh "No terms were found for this aspect with a corrected P-value <= $cutoff.\n";
+
+	}
+
+	print $fh "\n\n";
+
+    }
+
+    $fh->close;    
+    
+}
+
+=pod
+
+=head1 NAME
+
+analyze.pl - batch processor to find terms for lists of genes in various files
+
+=head1 SYNOPSIS
+
+This program takes a list of files, each of which contain a list of
+genes, with one gene per line.  It will findTerms for the lists of
+genes in each of the GO aspects, outputting the results to a file
+named for the original file, but with a .terms extension.  It will
+only output terms with a corrected P-value of <= 0.05.
+
+It will use the first supplied argument as the annotation file, the
+second argument as the expected number of genes within the organism,
+the third argument is the name of the obo file, and all subsequent
+files as ones containing lists of genes.
+
+Usage:
+
+    analyze.pl <annotation_file> <numGenes> <obofile> <file1> <file2> <file3> ... <fileN>
+
+e.g.
+
+    analyze.pl ../t/gene_association.sgd 7200 ../t/gene_ontology_edit.obo genes.txt genes2.txt
+
+An example output file might look like this:
+
+    The following gene(s) will be considered:
+    
+    YDL235C YPD1
+    YDL224C WHI4
+    YDL225W SHS1
+    YDL226C GCS1
+    YDL227C HO
+    YDL228C YDL228C
+    YDL229W SSB1
+    YDL230W PTP1
+    YDL231C BRE4
+    YDL232W OST4
+    YDL233W YDL233W
+    YDL234C GYP7
+    
+    Finding terms for P
+    
+    
+    Finding terms for C
+    
+    
+    Finding terms for F
+    
+    -- 1 of 15--
+    GOID    GO:0005096
+    TERM    GTPase activator activity
+    CORRECTED P-VALUE       0.0113038452336839
+    UNCORRECTED P-VALUE     0.00113038452336839
+    NUM_ANNOTATIONS 2 of 12 in the list, vs 31 of 7272 in the genome
+    The genes annotated to this node are:
+    YDL234C, YDL226C
+    -- 2 of 15--
+    GOID    GO:0008047
+    TERM    enzyme activator activity
+    CORRECTED P-VALUE       0.0316194107645226
+    UNCORRECTED P-VALUE     0.00316194107645226
+    NUM_ANNOTATIONS 2 of 12 in the list, vs 52 of 7272 in the genome
+    The genes annotated to this node are:
+    YDL234C, YDL226C
+    -- 3 of 15--
+    GOID    GO:0005083
+    TERM    small GTPase regulatory/interacting protein activity
+    CORRECTED P-VALUE       0.0340606972468798
+    UNCORRECTED P-VALUE     0.00340606972468798
+    NUM_ANNOTATIONS 2 of 12 in the list, vs 54 of 7272 in the genome
+    The genes annotated to this node are:
+    YDL234C, YDL226C
+    -- 4 of 15--
+    GOID    GO:0030695
+    TERM    GTPase regulator activity
+    CORRECTED P-VALUE       0.0475469908576535
+    UNCORRECTED P-VALUE     0.00475469908576535
+    NUM_ANNOTATIONS 2 of 12 in the list, vs 64 of 7272 in the genome
+    The genes annotated to this node are:
+    YDL234C, YDL226C
+
+=head1 AUTHORS
+
+Gavin Sherlock, sherlock@genome.stanford.edu
+
+=cut

workflow/apps/perl/gene_association.README

@@ -0,0 +1,48 @@
+gene_association.sgd.gz    This file is TAB delimited and contains all GO annotations for yeast genes (protein and RNA) 
+
+The gene_association.sgd.gz file uses the standard file format for
+gene_association files of the Gene Ontology (GO) Consortium.  A more
+complete description of the file format is found here:
+
+http://www.geneontology.org/GO.format.annotation.shtml
+
+Columns are:					Contents:
+
+ 1) DB						- database contributing the file (always "SGD" for this file)
+ 2) DB_Object_ID				- SGDID
+ 3) DB_Object_Symbol				- see below
+ 4) NOT 			(optional)	- 'NOT', 'contributes_to', or 'colocalizes_with' qualifier for a GO annotation, when needed
+ 5) GO ID					- unique numeric identifier for the GO term
+ 6) DB:Reference(|DB:Reference)			- the reference associated with the GO annotation
+ 7) Evidence					- the evidence code for the GO annotation
+ 8) With (or) From 		(optional)	- any With or From qualifier for the GO annotation
+ 9) Aspect					- which ontology the GO term belongs in
+10) DB_Object_Name(|Name) 	(optional)	- a name for the gene product in words, e.g. 'acid phosphatase'
+11) DB_Object_Synonym(|Synonym) (optional)	- see below
+12) DB_Object_Type				- type of object annotated, e.g. gene, protein, etc.
+13) taxon(|taxon)				- taxonomic identifier of species encoding gene product
+14) Date					- date GO annotation was made
+15) Assigned_by					- source of the annotation (e.g. SGD, UniProtKB, YeastFunc, bioPIXIE_MEFIT)
+
+Note on SGD nomenclature (pertaining to columns 3 and 11):
+
+Column 3 - When a Standard Gene Name (e.g. CDC28, COX2) has been
+        conferred, it will be present in Column 3. When no Gene Name
+        has been conferred, the Systematic Name (e.g. YAL001C,
+        YGR116W, YAL034W-A) will be present in column 3.
+
+Column 11 - The Systematic Name (e.g. YAL001C, YGR116W, YAL034W-A,
+	Q0010) will be the first name present in Column 11. Any other
+	names (except the Standard Name, which will be in Column 3 if
+	one exists), including Aliases used for the gene will also be
+	present in this column.
+
+Please note that ORFs classified as 'Dubious' are not included in this file, as there is currently 
+no experimental evidence that a gene product is produced in S. cerevisiae.
+
+This file is updated weekly. 
+
+For more information on the Gene Ontology (GO) project, see: 
+
+  http://www.geneontology.org/
+

workflow/apps/perl/terms2tsv.pl

@@ -0,0 +1,54 @@
+#!/usr/bin/env perl
+use strict;
+use warnings;
+use diagnostics;
+use File::Map qw(map_file);
+
+my $infile = shift;
+
+my $input;
+
+map_file $input, $infile;
+
+{
+	local $_	= $input;
+	(my $f		= $infile) =~ s/(.*\/)?(.*)(\.[^\.]*){2}/$2/;
+	my %orfgene	= (/(Y\w+)\s+(\w+)\n/g);
+	my @indices	= (/\Q-- \E(\d+) of \d+\Q --\E/g);
+	my @ids		= (/GOID\s+GO:(\d+)/g);
+	my @terms	= (/TERM\s+(.*?)\n/g);
+	my @pvalues	= (/\nCORRECTED P-VALUE\s+(\d.*?)\n/g);
+	my @clusterf	= (/NUM_ANNOTATIONS\s+(\d+ of \d+)/g);
+	my @bgfreq	= (/, vs (\d+ of \d+) in the genome/g);
+	my @orfs	= (/The genes annotated to this node are:\n(.*?)\n/g);
+	
+	s/, /:/g for @orfs;
+
+	my @genes;
+	for my $orf (@orfs) {
+		my @otmp = split /:/, $orf;
+		my @gtmp = map { $orfgene{$_} } @otmp;
+		push @genes, (join ':', @gtmp);
+	}
+
+	&header();
+	for my $i (0 .. (@ids - 1)) {
+		&report($f, $ids[$i], $terms[$i], $pvalues[$i], $clusterf[$i], $bgfreq[$i], $orfs[$i], $genes[$i]);
+	}
+}
+
+sub header {
+	print "REMc ID\tGO_term ID\tGO-term\tCluster frequency\tBackground frequency\tP-value\tORFs\tGenes\n";
+}
+
+sub report {
+	my ($f, $id, $term, $p, $cfreq, $bgfreq, $orfs, $genes) = @_;
+
+	$cfreq =~ /(\d+) of (\d+)/;
+	$cfreq = sprintf "%d out of %d genes, %.1f%%", $1, $2, (100*$1/$2);
+
+	$bgfreq =~ /(\d+) of (\d+)/;
+	$bgfreq = sprintf "%d out of %d genes, %.1f%%", $1, $2, (100*$1/$2);
+
+	print "$f\t$id\t$term\t$cfreq\t$bgfreq\t$p\t$orfs\t$genes\n";
+}

workflow/apps/python/DconJG2.py

@@ -0,0 +1,130 @@
+#!/usr/bin/env python
+"""
+Improved code to determine the origin column (OligCol) without user input of the argument
+and removed the former sys.argv[2]. JWR 22_0816
+"""
+"""
+this code can be used for the parse of the REMc "-finalTable.csv" output file 
+to make a series of subdatasets, which reflect the pedigree structure 
+of the way cluters breaking up. 
+"""
+
+import sys, os, string, glob
+
+try:
+   data_file_Path = sys.argv[1]
+   #print data_file_Path
+   #cluster_ori_col_num = sys.argv[2]
+   output_path = sys.argv[2]
+except: 
+   print ('Usage: python parse_clustering_result_to_Pedigree_Dataset_and_genelist.py /datasetPath/datasetfilename cluster_origin_column_num output_path_name')
+   print ('Data file not found')
+   sys.exit(1)
+
+#define a function to reading files and generate the list
+def read_file(file_path):
+    with open(file_path, 'r') as file:
+        attributes = file.readline().strip().split(',')
+        gene_list = [elements[1] for line in file for elements in [line.strip().split(',')]]
+    return gene_list
+
+# define a function to write the list into a file named in hierarchical series
+def write_cluster_orf_list(orf_list, output_dir, cluster_name):
+    cluster_file_path = os.path.join(output_dir, f"cluster_name, 'txt')
+    with open(cluster_file_path, 'w') as outfile:
+        for orf in orf_list:
+            outfile.write(orf.strip() + '\n')
+
+# define a function to write the clusters information into a series of files
+def write_cluster_results(attributes, orf_list, data_dict, output_directory, cluster_name):
+    file_path = os.path.join(output_directory, f"{cluster_name}-finaltable.csv")
+    with open(file_path, 'w') as output_file:
+        output_file.write(attributes)
+        output_file.write('\n')
+        for orf in orf_list:
+            output_file.write(data_dict[orf.strip()].strip())
+            output_file.write('\n')
+
+# define a function to write the cluster name origina extensive final table 
+def write_extended_final_table(attributes, data, ori_name_column_number, output_directory, output_file_name):
+    output_file_path = os.path.join(output_directory, f"{output_file_name}-oriExtFinalTable.csv")
+    with open(output_file_path, 'w') as output_file:
+        output_file.write(attributes)
+        output_file.write('\n')
+        for orf in data:
+            elements = data[orf].split(',')
+            ori_name_list = elements[int(ori_name_column_number)-1].strip().split(';')
+            for ori_name in ori_name_list:
+                elements.append(orii_name.strip())
+            output_file.write(','.join(elements))
+            output_file.write('\n')
+
+# Read the data file
+try:
+   data = open(data_file_Path,'r')
+except OSError:
+   print ('input file does not exists')
+
+ 
+# first the title line would be read and kept
+attributes = data.readline().strip().split(',')
+print(attributes)
+print(len(attributes))
+OrigCol= len(attributes) - 1
+print(OrigCol)
+
+# then the data
+data_dict = {}
+for data_line in data:
+    data_line = data_line.strip()
+    line_elements = data_line.split(',')
+    orf_identifier = line_elements[1].strip().upper()
+    data_dict[orf_identifier] = ','.join(line_elements).upper()
+data.close()
+#print dataDic
+   
+print ("OrigCol is ", str(OrigCol))
+fileDic = {}
+for orf in dataDic:
+    line = dataDic[orf].split(',')
+    #read the cluster name len(attributes)
+    clusterOrigin = line[int(OrigCol) - 1]
+    
+    #clusterOrigin = line[int(cluster_ori_col_num) - 1]
+    #print clusterOrigin
+    clusterOrigin = clusterOrigin.strip()
+    #print clusterOrigin
+    clusterIdentifier = clusterOrigin.split(';')[0:-1]
+    #print clusterIdentifier
+    
+    for identifier in clusterIdentifier:
+        identifier = identifier.strip()
+        upper_identifier = identifier.upper()
+        if upper_identifier not in fileDic:
+            fileDic[upper_identifier] = line[1]
+        else:
+            fileDic[upper_identifier] += ',' + line[1]
+	    
+input_file_identifier = data_file_Path.strip().split('/')[-1].strip().split('.csv')[-3]
+
+#make the output folder
+try:
+    os.mkdir(str(output_path)+str(input_file_identifier))
+except OSError:
+	
+	
+print ('dir exists')
+
+#Writing the extensive ori name finaltable
+Writing_ext_final_table(attributeLine, dataDic,str(OrigCol),str(output_path)+str(input_file_identifier), str(input_file_identifier))
+#Writing_ext_final_table(attributeLine, dataDic,cluster_ori_col_num,str(output_path)+str(input_file_identifier), str(input_file_identifier))
+
+#write the genelist files
+for cluster_name in fileDic:
+    #print fileDic[cluster_name].split(',')
+    Writing_clusterORF_list(fileDic[cluster_name].split(','), str(output_path)+str(input_file_identifier), cluster_name)                        
+    #write the cluster result files
+    Writing_cluster_results(attributeLine, fileDic[cluster_name].split(','), dataDic,str(output_path)+str(input_file_identifier),cluster_name)
+        
+
+

workflow/apps/python/concatGTFResults.py

@@ -0,0 +1,103 @@
+#!/usr/bin/env python
+# This code is to concatenate the batch GO Term Finder results (.tsv) generated from batch GTF perl code(Chris Johnson, U of Tulsa) into a list table
+
+import os
+import glob
+
+def list_files(directory):
+    """Return a list of all files in the given directory."""
+    return glob.glob(os.path.join(directory, '*.txt.tsv'))
+
+def concatenate_gtf_results(data_dir, output_file):
+    """Concatenate the GTF results into a single file."""
+    output = open(output_file, 'w')
+
+    files = list_files(data_dir)
+    files.sort()
+
+    for file_path in files:
+        file_name = os.path.basename(file_path).rstrip('.txt.tsv')
+        with open(file_path, 'r') as f:
+            labels = f.readline().strip().split('\t')
+            output.write('\t'.join(labels) + '\n')
+
+            for line in f:
+                line = line.strip().strip('\t')
+                if line:
+                    output.write(line + '\n')
+
+    output.close()
+
+if __name__ == '__main__':
+    if len(sys.argv) != 3:
+        print('Usage: python Concatenate_GTF_results.py data_dir output_file')
+        sys.exit(1)
+
+    data_dir = sys.argv[1]
+    output_file = sys.argv[2]
+
+    concatenate_gtf_results(data_dir, output_file)
+
+
+
+
+
+# Old version
+# def list_files(directory):
+#     """Return a list of all files in the given directory."""
+#     return glob.glob(os.path.join(directory, '*.txt.tsv'))
+
+# try:
+#    data_file_Path = sys.argv[1]
+#    output_file_Path = sys.argv[2]
+# except: 
+#    print ('Usage: python Concatenate_GTF_results.py /datasetPath /outputFilePath_and_Name')
+#    print ('Data file not found, error in given directory')
+#    sys.exit(1)
+
+# try:
+#     output = open(output_file_Path, 'w')
+# except OSError:
+#     print ('output file error')
+
+# # get all the GTF result files in given directory
+# File_list = []
+# File_list = list_files(data_file_Path)
+# File_list.sort()
+
+# i = 0
+# for file in File_list:
+#     #parse the file names given in absolute path
+#     file_name = file.strip().split('/')[-1]
+#     file_name = file_name.rstrip('.txt.tsv')
+#     # function to read tsv files from a given directory
+#     #open the file
+#     data = open(file,'r')
+#     #reading the label line
+#     labelLine = data.readline()
+#     label = labelLine.strip().split('\t')
+#     #write the label
+#     #updates2010July26: update following label writing code	
+#     if i == 0:
+#     #    output.write('cluster origin')
+#         for element in label:
+#             output.write(element)
+#             output.write('\t')
+#     i = i + 1
+#     #updates2010July26 End
+#     #switch to the next line
+#     output.write('\n')
+
+#     #read the GO terms
+#     GOTermLines = data.readlines()
+#     for GOTerm in GOTermLines:
+#         GOTerm = GOTerm.strip().strip('\t')
+#         if GOTerm != '':
+# 	    #updates2010July26: remove the code to write the first column 'REMc cluster ID'
+#             #output.write(file_name)
+#             #output.write('\t')
+# 	    ##updates2010July26 update end
+#             output.write(GOTerm + '\n')
+#             #output.write('\n')
+# output.close()
+

workflow/apps/python/dCon.py

@@ -0,0 +1,131 @@
+#!/usr/bin/env python
+"""
+Reads the REMc "-finalTable.csv" output file and makes a series of subdatasets
+that reflect the pedigree structure of the way clusters break up.
+"""
+
+import sys
+import os
+import string
+import glob
+
+
+def reading_single_file(file_path):
+    """
+    Reads a file and generates a list of gene names.
+    """
+    with open(file_path, 'r') as data:
+        attribute_line = data.readline().strip()
+        attributes = attribute_line.split(',')
+
+        gene_list = []
+        for dataline in data:
+            dataline = dataline.strip()
+            elements = dataline.split(',')
+            gene_list.append(elements[1])
+
+    return gene_list
+
+
+def writing_cluster_orf_list(list, output_dir, real_cluster_ori_name):
+    """
+    Writes a list of ORF names into a file in hierarchical series.
+    """
+    outfile_path = os.path.join(output_dir, f"{real_cluster_ori_name}.txt")
+    with open(outfile_path, 'w') as outfile:
+        for orf in list:
+            outfile.write(orf.strip())
+            outfile.write('\n')
+
+
+def writing_cluster_results(attributes, orf_list, dic, output_dir, real_cluster_ori_name):
+    """
+    Writes clusters information into a series of files.
+    """
+    outfile_path = os.path.join(output_dir, f"{real_cluster_ori_name}-finaltable.csv")
+    with open(outfile_path, 'w') as outfile:
+        outfile.write(attributes)
+        outfile.write('\n')
+        for orf in orf_list:
+            outfile.write(dic[orf.strip()].strip())
+            outfile.write('\n')
+
+
+def writing_ext_final_table(attributes, dic, ori_name_col_num, output_dir, output_file_name):
+    """
+    Writes the cluster name extensive final table.
+    """
+    outfile_path = os.path.join(output_dir, f"{output_file_name}-oriExtFinalTable.csv")
+    with open(outfile_path, 'w') as outfile:
+        outfile.write(attributes)
+        outfile.write('\n')
+        for orf in dic:
+            elements = dic[orf].split(',')
+            ori_name_list = elements[int(ori_name_col_num) - 1].strip().split(';')
+            for ori_name in ori_name_list:
+                elements.append(ori_name.strip())
+            outfile.write(','.join(elements))
+            outfile.write('\n')
+
+
+def main():
+    """
+    Main function to parse the REMc -finalTable.csv output file.
+    """
+    try:
+        data_file_path = sys.argv[1]
+        output_path = sys.argv[2]
+    except IndexError:
+        print('Usage: python parse_clustering_result_to_Pedigree_Dataset_and_genelist.py '
+              '/datasetPath/datasetfilename cluster_origin_column_num output_path_name')
+        print('Data file not found')
+        sys.exit(1)
+
+    try:
+        with open(data_file_path, 'r') as data:
+            attribute_line = data.readline().strip()
+            attributes = attribute_line.split(',')
+            orig_col = len(attributes) - 1
+
+            data_dict = {}
+            for dataline in data:
+                dataline = dataline.strip()
+                elements = dataline.split(',')
+                data_dict[str.upper(elements[1].strip())] = ','.join(elements).upper()
+
+    except FileNotFoundError:
+        print('Input file does not exist')
+        sys.exit(1)
+
+    file_dict = {}
+    for orf in data_dict:
+        line = data_dict[orf].split(',')
+        cluster_origin = line[int(orig_col) - 1].strip()
+        cluster_identifier = cluster_origin.split(';')[0:-1]
+
+        for i, identifier in enumerate(cluster_identifier):
+            identifier = identifier.strip()
+            if identifier not in file_dict:
+                file_dict[identifier] = line[1]
+            else:
+                file_dict[identifier] = f"{file_dict[identifier]},{line[1]}"
+
+    input_file_identifier = os.path.basename(data_file_path).split('.csv')[0]
+    output_dir = os.path.join(output_path, input_file_identifier)
+    os.makedirs(output_dir, exist_ok=True)
+
+    # Writing the extensive ori name finaltable
+    writing_ext_final_table(attribute_line, data_dict, orig_col, output_dir, input_file_identifier)
+
+    # Writing the genelist files
+    for cluster_name in file_dict:
+        writing_cluster_orf_list(file_dict[cluster_name].split(','), output_dir, cluster_name)
+
+        # Writing the cluster result files
+        writing_cluster_results(attribute_line, file_dict[cluster_name].split(','), data_dict,
+                                output_dir, cluster_name)
+
+
+if __name__ == '__main__':
+    main()
+

workflow/apps/r/CompileGTF.R

@@ -0,0 +1,55 @@
+#!/usr/bin/env Rscript
+
+# Load the openxlsx package
+library(openxlsx)
+
+args <- commandArgs(TRUE)
+
+outDir <- args[1]
+
+# Function to combine CSV and TXT files into a workbook with named sheets
+combineFilesToWorkbook <- function(file_list, output_file) {
+  # Create a new workbook
+  wb <- createWorkbook()
+  
+  # Loop through the file list
+  for (i in seq_along(file_list)) {
+    file <- file_list[i]
+    
+    # Extract the sheet name from the file name based on the extension
+    ext <- tools::file_ext(file)
+    sheet_name <- tools::file_path_sans_ext(basename(file))
+    
+    # Read the data based on the file extension
+    if (ext %in% c("csv", "txt")) {
+      if (ext == "csv") {
+        data <- read.csv(file)
+      } else if (ext == "txt") {
+        data <- readLines(file)
+      }
+      
+      # Create a new sheet in the workbook with the extracted sheet name
+      addWorksheet(wb, sheetName = sheet_name)
+      
+      # Write the data to the sheet
+      writeData(wb, sheet = sheet_name, x = data)
+    }
+  }
+  
+  # Save the workbook as an Excel file
+  saveWorkbook(wb, output_file)
+}
+
+Component <- file.path(outDir, "Component", "ComponentResults.txt")
+Function <- file.path(outDir, "Function", "FunctionResults.txt")
+Process <- file.path(outDir, "Process", "ProcessResults.txt")
+
+# Specify the list of input files (both CSV and TXT)
+file_list <- c(Component,Process,Function)
+
+# Specify the output file name
+output_file <- file.path(outDir, "GTFCombined.xlsx")
+
+# Call the function to combine the files into a workbook with named sheets
+combineFilesToWorkbook(file_list, output_file)
+

workflow/apps/r/PairwiseLK.R

@@ -0,0 +1,658 @@
+#!/usr/bin/env Rscript
+# This R script performs GTA L and K Pairwise Compares for user specified pairs of Experiments 
+#
+# Updated 240724 Bryan C Roessler to improve file operations and portability
+# NOTE: The two required arguments are the same and now there are two optional arguments
+#   1. Exp1
+#   2. Exp2
+#   3. StudyInfo.csv file
+#   4. Output Directory
+
+library("ggplot2")
+library("plotly")
+library("htmlwidgets")
+library("extrafont")
+library("grid")
+library("ggthemes")
+
+args <- commandArgs(TRUE)
+exp_name <- args[1]
+exp_name2 <- args[2]
+
+if (length(args) > 3) {
+  study_info_file  <- args[3]
+} else {
+  study_info_file  <- "StudyInfo.csv" 
+}
+
+if (length(args) > 4) {
+  output_dir <- args[4]
+} else {
+  output_dir <- "gta"
+}
+
+# if (length(args) > 3) {
+#   sgd_terms_file <- args[3]
+# } else {
+#   sgd_terms_file <- "../Code/go_terms.tab"
+# }
+
+# if (length(args) > 4) {
+#   sgd_features_file <- args[4]
+# } else {
+#   sgd_features_file <- "../Code/gene_association.sgd"
+# }
+
+expNumber1<- as.numeric(sub("^.*?(\\d+)$", "\\1", exp_name))
+expNumber2<- as.numeric(sub("^.*?(\\d+)$", "\\1", exp_name2))
+Labels<- read.csv(file=study_info_file,stringsAsFactors = FALSE)
+Name1 <- Labels[expNumber1,2]
+Name2 <- Labels[expNumber2,2]
+
+go_terms_file <- "Average_GOTerms_All.csv"
+input_file1 <- file.path(output_dir,exp_name,go_terms_file)
+input_file2 <- file.path(output_dir,exp_name2,go_terms_file)
+
+pairDirL= file.path(output_dir,"PairwiseCompareL_",exp_name,"-",exp_name2)
+pairDirK= file.path(output_dir,"PairwiseCompareK_",exp_name,"-",exp_name2)
+outPathGTAcompare= file.path(output_dir,"PairwiseCompareL")
+outPathGTAcompare[2]= file.path(output_dir,"PairwiseCompareK")
+#dir.create(outPathGTAcompare[1])
+dir.create(pairDirL)  #(outPathGTAcompare[1])
+dir.create(pairDirK)  #(outPathGTAcompare[2])
+
+###########BEGIN PAIRWISE L-----LLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLL
+outputpath <- pairDirL  #outPathGTAcompare[1]   #Args[5]
+#outputPlotly <- "../GTAresults/PairwiseCompareL/" #"/GTAresults/PairwiseCompareL/"
+print("39")
+#theme elements for plots
+theme_Publication <- function(base_size=14, base_family="sans") {
+  (theme_foundation(base_size=base_size, base_family=base_family)
+   + theme(plot.title = element_text(face = "bold",
+                                     size = rel(1.2), hjust = 0.5),
+           text = element_text(),
+           panel.background = element_rect(colour = NA),
+           plot.background = element_rect(colour = NA),
+           panel.border = element_rect(colour = NA),
+           axis.title = element_text(face = "bold",size = rel(1)),
+           axis.title.y = element_text(angle=90,vjust =2),
+           axis.title.x = element_text(vjust = -0.2),
+           axis.text = element_text(), 
+           axis.line = element_line(colour="black"),
+           axis.ticks = element_line(),
+           panel.grid.major = element_line(colour="#f0f0f0"),
+           panel.grid.minor = element_blank(),
+           legend.key = element_rect(colour = NA),
+           legend.position = "bottom",
+           legend.direction = "horizontal",
+           legend.key.size= unit(0.2, "cm"),
+           legend.spacing = unit(0, "cm"),
+           legend.title = element_text(face="italic"),
+           plot.margin=unit(c(10,5,5,5),"mm"),
+           strip.background=element_rect(colour="#f0f0f0",fill="#f0f0f0"),
+           strip.text = element_text(face="bold")
+   ))
+  
+}
+
+scale_fill_Publication <- function(...){
+  library(scales)
+  discrete_scale("fill","Publication",manual_pal(values = c("#386cb0","#fdb462","#7fc97f","#ef3b2c","#662506","#a6cee3","#fb9a99","#984ea3","#ffff33")), ...)
+}
+
+scale_colour_Publication <- function(...){
+  discrete_scale("colour","Publication",manual_pal(values = c("#386cb0","#fdb462","#7fc97f","#ef3b2c","#662506","#a6cee3","#fb9a99","#984ea3","#ffff33")), ...)
+}
+
+theme_Publication_legend_right <- function(base_size=14, base_family="sans") {
+  (theme_foundation(base_size=base_size, base_family=base_family)
+   + theme(plot.title = element_text(face = "bold",
+                                     size = rel(1.2), hjust = 0.5),
+           text = element_text(),
+           panel.background = element_rect(colour = NA),
+           plot.background = element_rect(colour = NA),
+           panel.border = element_rect(colour = NA),
+           axis.title = element_text(face = "bold",size = rel(1)),
+           axis.title.y = element_text(angle=90,vjust =2),
+           axis.title.x = element_text(vjust = -0.2),
+           axis.text = element_text(), 
+           axis.line = element_line(colour="black"),
+           axis.ticks = element_line(),
+           panel.grid.major = element_line(colour="#f0f0f0"),
+           panel.grid.minor = element_blank(),
+           legend.key = element_rect(colour = NA),
+           legend.position = "right",
+           legend.direction = "vertical",
+           legend.key.size= unit(0.5, "cm"),
+           legend.spacing = unit(0, "cm"),
+           legend.title = element_text(face="italic"),
+           plot.margin=unit(c(10,5,5,5),"mm"),
+           strip.background=element_rect(colour="#f0f0f0",fill="#f0f0f0"),
+           strip.text = element_text(face="bold")
+   ))
+}
+
+scale_fill_Publication <- function(...){
+  discrete_scale("fill","Publication",manual_pal(values = c("#386cb0","#fdb462","#7fc97f","#ef3b2c","#662506","#a6cee3","#fb9a99","#984ea3","#ffff33")), ...)
+}
+
+scale_colour_Publication <- function(...){
+  discrete_scale("colour","Publication",manual_pal(values = c("#386cb0","#fdb462","#7fc97f","#ef3b2c","#662506","#a6cee3","#fb9a99","#984ea3","#ffff33")), ...)
+}
+
+X1 <- read.csv(file = input_file1,stringsAsFactors=FALSE,header = TRUE)
+X2 <- read.csv(file = input_file2,stringsAsFactors=FALSE,header = TRUE)
+print(117)
+
+X <- merge(X1,X2,by ="Term_Avg",all=TRUE,suffixes = c("_X1","_X2"))
+gg <- ggplot(data = X,aes(x=Z_lm_L_Avg_X1,y=Z_lm_L_Avg_X2,color=Ontology_Avg_X1,Term=Term_Avg,Genes=Genes_Avg_X1,NumGenes=NumGenes_Avg_X1,AllPossibleGenes=AllPossibleGenes_Avg_X1,SD_1=Z_lm_L_SD_X1,SD_2=Z_lm_L_SD_X2)) + 
+  xlab(paste("GO Term Avg lm Z for ",Name1,sep="")) +
+  geom_rect(aes(xmin=-2,xmax=2,ymin=-2,ymax=2),color="grey20",size=0.25,alpha=0.1,inherit.aes = FALSE,fill=NA) + geom_point(shape=3) +
+  ylab(paste("GO Term Avg lm Z for ",Name2,sep="")) + ggtitle(paste("Comparing Average GO Term Z lm for ",Name1," vs. ",Name2,sep = "")) +
+  theme_Publication_legend_right()
+pdf(paste(outputpath,"/","Scatter_lm_GTA_Averages_",Name1,"_vs_",Name2,"_All_ByOntology.pdf",sep=""),width = 12,height = 8)
+gg
+dev.off()
+pgg <- ggplotly(gg)
+#pgg
+print("130")
+fname <- paste("Scatter_lm_GTA_Averages_",Name1,"_vs_",Name2,"_All_byOntology.html",sep="")
+print(fname)
+htmlwidgets::saveWidget(pgg, file.path(getwd(),fname))
+file.rename(from = file.path(getwd(),fname), to =  file.path(pairDirL,fname))
+
+
+#ID aggravators and alleviators, regardless of whether they meet 2SD threshold
+X1_Specific_Aggravators <- X[which(X$Z_lm_L_Avg_X1 >= 2 & X$Z_lm_L_Avg_X2 < 2),]
+X1_Specific_Alleviators <- X[which(X$Z_lm_L_Avg_X1 <= -2 & X$Z_lm_L_Avg_X2 > -2),]
+
+X2_Specific_Aggravators <- X[which(X$Z_lm_L_Avg_X2 >= 2 & X$Z_lm_L_Avg_X1 < 2),]
+X2_Specific_Alleviators <- X[which(X$Z_lm_L_Avg_X2 <= -2 & X$Z_lm_L_Avg_X1 > -2),]
+
+Overlap_Aggravators <- X[which(X$Z_lm_L_Avg_X1 >= 2 & X$Z_lm_L_Avg_X2 >= 2),]
+Overlap_Alleviators <- X[which(X$Z_lm_L_Avg_X1 <= -2 & X$Z_lm_L_Avg_X2 <= -2),]
+
+X2_Specific_Aggravators_X1_Alleviatiors <- X[which(X$Z_lm_L_Avg_X2 >= 2 & X$Z_lm_L_Avg_X1 <= -2),]
+X2_Specific_Alleviators_X1_Aggravators <- X[which(X$Z_lm_L_Avg_X2 <= -2 & X$Z_lm_L_Avg_X1 >= 2),]
+print("155")
+X$Overlap_Avg <- NA
+
+try(X[X$Term_Avg %in% X1_Specific_Aggravators$Term_Avg,]$Overlap_Avg <- paste(Name1,"Specific_Deletion_Enhancers",sep="_"))
+try(X[X$Term_Avg %in% X1_Specific_Alleviators$Term_Avg,]$Overlap_Avg <- paste(Name1,"Specific_Deletion_Suppresors",sep="_"))
+try(X[X$Term_Avg %in% X2_Specific_Aggravators$Term_Avg,]$Overlap_Avg <- paste(Name2,"Specific_Deletion_Enhancers",sep="_"))
+try(X[X$Term_Avg %in% X2_Specific_Alleviators$Term_Avg,]$Overlap_Avg <- paste(Name2,"Specific_Deletion_Suppressors",sep="_"))
+try(X[X$Term_Avg %in% Overlap_Aggravators$Term_Avg,]$Overlap_Avg <- "Overlapping_Deletion_Enhancers")
+try(X[X$Term_Avg %in% Overlap_Alleviators$Term_Avg,]$Overlap_Avg <- "Overlapping_Deletion_Suppressors")
+try(X[X$Term_Avg %in% X2_Specific_Aggravators_X1_Alleviatiors$Term_Avg,]$Overlap_Avg <- paste(Name2,"Deletion_Enhancers",Name1,"Deletion_Suppressors",sep="_"))
+try(X[X$Term_Avg %in% X2_Specific_Alleviators_X1_Aggravators$Term_Avg,]$Overlap_Avg <- paste(Name2,"Deletion_Suppressors",Name1,"Deletion_Enhancers",sep="_"))
+
+
+gg <- ggplot(data = X,aes(x=Z_lm_L_Avg_X1,y=Z_lm_L_Avg_X2,color=Overlap_Avg,Term=Term_Avg,Genes=Genes_Avg_X1,NumGenes=NumGenes_Avg_X1,AllPossibleGenes=AllPossibleGenes_Avg_X1,SD_1=Z_lm_L_SD_X1,SD_2=Z_lm_L_SD_X2)) + 
+  xlab(paste("GO Term Avg lm Z for ",Name1,sep="")) +
+  geom_rect(aes(xmin=-2,xmax=2,ymin=-2,ymax=2),color="grey20",size=0.25,alpha=0.1,inherit.aes = FALSE,fill=NA) + geom_point(shape=3) +
+  ylab(paste("GO Term Avg lm Z for ",Name2,sep="")) + ggtitle(paste("Comparing Average GO Term Z lm for ",Name1," vs. ",Name2,sep="")) +
+  theme_Publication_legend_right()
+pdf(paste(outputpath,"/","Scatter_lm_GTA_Averages_",Name1,"_vs_",Name2,"_All_ByOverlap.pdf",sep=""),width = 12,height = 8)
+gg
+dev.off()
+pgg <- ggplotly(gg)
+
+#pgg
+print("#2-174")
+#2
+fname <- paste("/Scatter_lm_GTA_Averages_",Name1,"_vs_",Name2,"_All_byOverlap.html",sep="")
+print(fname)
+htmlwidgets::saveWidget(pgg, file.path(getwd(),fname))
+file.rename(from = file.path(getwd(),fname), to =  file.path(pairDirL,fname))
+
+x_rem2_gene <- X[X$NumGenes_Avg_X1 >= 2 & X$NumGenes_Avg_X2 >= 2,]
+#3
+gg <- ggplot(data = x_rem2_gene,aes(x=Z_lm_L_Avg_X1,y=Z_lm_L_Avg_X2,color=Overlap_Avg,Term=Term_Avg,Genes=Genes_Avg_X1,NumGenes=NumGenes_Avg_X1,AllPossibleGenes=AllPossibleGenes_Avg_X1,SD_1=Z_lm_L_SD_X1,SD_2=Z_lm_L_SD_X2)) + 
+  xlab(paste("GO Term Avg lm Z for ",Name1,sep="")) +
+  geom_rect(aes(xmin=-2,xmax=2,ymin=-2,ymax=2),color="grey20",size=0.25,alpha=0.1,inherit.aes = FALSE,fill=NA) + geom_point(shape=3) +
+  ylab(paste("GO Term Avg lm Z for ",Name2,sep="")) + ggtitle(paste("Comparing Average GO Term Z lm for ",Name1," vs. ",Name2,sep="")) +
+  theme_Publication_legend_right()
+pdf(paste(outputpath,"/","Scatter_lm_GTA_Averages_",Name1,"_vs_",Name2,"_All_ByOverlap_above2genes.pdf",sep=""),width = 12,height = 8)
+gg
+dev.off()
+pgg <- ggplotly(gg)
+#pgg
+print("#3")
+fname <- paste("Scatter_lm_GTA_Averages_",Name1,"_vs_",Name2,"_All_byOverlap_above2genes.html",sep="")
+print(fname)
+htmlwidgets::saveWidget(pgg, file.path(getwd(),fname))
+file.rename(from = file.path(getwd(),fname), to =  file.path(pairDirL,fname))
+
+#4
+X_overlap_nothresold <- X[!(is.na(X$Overlap_Avg)),]
+gg <- ggplot(data = X_overlap_nothresold,aes(x=Z_lm_L_Avg_X1,y=Z_lm_L_Avg_X2,color=Overlap_Avg,Term=Term_Avg,Genes=Genes_Avg_X1,NumGenes=NumGenes_Avg_X1,AllPossibleGenes=AllPossibleGenes_Avg_X1,SD_1=Z_lm_L_SD_X1,SD_2=Z_lm_L_SD_X2)) + 
+  xlab(paste("GO Term Avg lm Z for ",Name1,sep="")) +
+  geom_rect(aes(xmin=-2,xmax=2,ymin=-2,ymax=2),color="grey20",size=0.25,alpha=0.1,inherit.aes = FALSE,fill=NA) + geom_point(shape=3) +
+  ylab(paste("GO Term Avg lm Z for ",Name2,sep="")) + ggtitle(paste("Comparing Average GO Term Z lm for ",Name1," vs. ",Name2,sep = "")) +
+  theme_Publication_legend_right()
+pdf(paste(outputpath,"/","Scatter_lm_GTA_Averages_",Name1,"_vs_",Name2,"_Above2SD_ByOverlap.pdf",sep=""),width = 12,height = 8)
+gg
+dev.off()
+pgg <- ggplotly(gg)
+#pgg
+print("#4")
+fname <- paste("Scatter_lm_GTA_Averages_",Name1,"_vs_",Name2,"_Above2SD_ByOverlap.html",sep="")
+print(fname)
+htmlwidgets::saveWidget(pgg, file.path(getwd(),fname))
+file.rename(from = file.path(getwd(),fname), to =  file.path(pairDirL,fname))
+
+
+#only output GTA terms where average score is still above 2 after subtracting the SD
+#Z1 will ID aggravators, Z2 alleviators
+Z1 <- X
+Z1$L_Subtract_SD_X1 <- Z1$Z_lm_L_Avg_X1 - Z1$Z_lm_L_SD_X1
+Z1$L_Subtract_SD_X2 <- Z1$Z_lm_L_Avg_X2 - Z1$Z_lm_L_SD_X2
+
+Z2 <- X
+Z2$L_Subtract_SD_X1 <- Z1$Z_lm_L_Avg_X1 + Z1$Z_lm_L_SD_X1
+Z2$L_Subtract_SD_X2 <- Z1$Z_lm_L_Avg_X2 + Z1$Z_lm_L_SD_X2
+
+X1_Specific_Aggravators2 <- Z1[which(Z1$L_Subtract_SD_X1 >= 2 & Z1$L_Subtract_SD_X2 < 2),]
+X1_Specific_Alleviators2 <- Z2[which(Z2$L_Subtract_SD_X1 <= -2 & Z2$L_Subtract_SD_X2 > -2),]
+
+X2_Specific_Aggravators2 <- Z1[which(Z1$L_Subtract_SD_X2 >= 2 & Z1$L_Subtract_SD_X1 < 2),]
+X2_Specific_Alleviators2 <- Z2[which(Z2$L_Subtract_SD_X2 <= -2 & Z2$L_Subtract_SD_X1 > -2),]
+
+Overlap_Aggravators2 <- Z1[which(Z1$L_Subtract_SD_X1 >= 2 & Z1$L_Subtract_SD_X2 >= 2),]
+Overlap_Alleviators2 <- Z2[which(Z2$L_Subtract_SD_X2 <= -2 & Z2$L_Subtract_SD_X1 <= -2),]
+
+X2_Specific_Aggravators2_X1_Alleviatiors2 <- Z1[which(Z1$L_Subtract_SD_X2 >= 2 & Z2$L_Subtract_SD_X1 <= -2),]
+X2_Specific_Alleviators2_X1_Aggravators2 <- Z2[which(Z2$L_Subtract_SD_X2 <= -2 & Z1$L_Subtract_SD_X1 >= 2),]
+
+X$Overlap <- NA
+
+try(X[X$Term_Avg %in% X1_Specific_Aggravators2$Term_Avg,]$Overlap <- paste(Name1,"Specific_Deletion_Enhancers",sep="_"))
+try(X[X$Term_Avg %in% X1_Specific_Alleviators2$Term_Avg,]$Overlap <- paste(Name1,"Specific_Deletion_Suppresors",sep="_"))
+try(X[X$Term_Avg %in% X2_Specific_Aggravators2$Term_Avg,]$Overlap <- paste(Name2,"Specific_Deletion_Enhancers",sep="_"))
+try(X[X$Term_Avg %in% X2_Specific_Alleviators2$Term_Avg,]$Overlap <- paste(Name2,"Specific_Deletion_Suppressors",sep="_"))
+try(X[X$Term_Avg %in% Overlap_Aggravators2$Term_Avg,]$Overlap <- "Overlapping_Deletion_Enhancers")
+try(X[X$Term_Avg %in% Overlap_Alleviators2$Term_Avg,]$Overlap <- "Overlapping_Deletion_Suppressors")
+try(X[X$Term_Avg %in% X2_Specific_Aggravators2_X1_Alleviatiors2$Term_Avg,]$Overlap <- paste(Name2,"Deletion_Enhancers",Name1,"Deletion_Suppressors",sep="_"))
+try(X[X$Term_Avg %in% X2_Specific_Alleviators2_X1_Aggravators2$Term_Avg,]$Overlap <- paste(Name2,"Deletion_Suppressors",Name1,"Deletion_Enhancers",sep="_"))
+
+#5
+X_abovethreshold <- X[!(is.na(X$Overlap)),]
+
+gg <- ggplot(data = X_abovethreshold,aes(x=Z_lm_L_Avg_X1,y=Z_lm_L_Avg_X2,color=Overlap,Term=Term_Avg,Genes=Genes_Avg_X1,NumGenes=NumGenes_Avg_X1,AllPossibleGenes=AllPossibleGenes_Avg_X1,SD_1=Z_lm_L_SD_X1,SD_2=Z_lm_L_SD_X2)) + 
+  xlab(paste("GO Term Avg lm Z for ",Name1,sep="")) +
+  geom_rect(aes(xmin=-2,xmax=2,ymin=-2,ymax=2),color="grey20",size=0.25,alpha=0.1,inherit.aes = FALSE,fill=NA) + geom_point(shape=3) +
+  ylab(paste("GO Term Avg lm Z for ",Name2,sep="")) + ggtitle(paste("Comparing Average GO Term Z lm for ",Name1," vs. ",Name2,sep="")) +
+  theme_Publication_legend_right()
+pdf(paste(outputpath,"/","Scatter_lm_GTA_Averages_",Name1,"_vs_",Name2,"_All_ByOverlap_AboveThreshold.pdf",sep=""),width = 12,height = 8)
+gg
+dev.off()
+pgg <- ggplotly(gg)
+#pgg
+print("#5")
+fname <- paste("Scatter_lm_GTA_Averages_",Name1,"_vs_",Name2,"_All_ByOverlap_AboveThreshold.html",sep="")
+print(fname)
+htmlwidgets::saveWidget(pgg, file.path(getwd(),fname))
+file.rename(from = file.path(getwd(),fname), to =  file.path(pairDirL,fname))
+#6
+gg <- ggplot(data = X_abovethreshold,aes(x=Z_lm_L_Avg_X1,y=Z_lm_L_Avg_X2,color=Overlap,Term=Term_Avg,Genes=Genes_Avg_X1,NumGenes=NumGenes_Avg_X1,AllPossibleGenes=AllPossibleGenes_Avg_X1,SD_1=Z_lm_L_SD_X1,SD_2=Z_lm_L_SD_X2)) + 
+  xlab(paste("GO Term Avg lm Z for ",Name1,sep="")) +
+  geom_text(aes(label=Term_Avg),nudge_y = 0.25,size=2) + 
+  geom_rect(aes(xmin=-2,xmax=2,ymin=-2,ymax=2),color="grey20",size=0.25,alpha=0.1,inherit.aes = FALSE,fill=NA) + geom_point(shape=3,size=3) +
+  ylab(paste("GO Term Avg lm Z for ",Name2,sep="")) + ggtitle(paste("Comparing Average GO Term Z lm for ",Name1," vs. ",Name2,sep="")) +
+  theme_Publication_legend_right()
+pdf(paste(outputpath,"/","Scatter_lm_GTA_Averages_",Name1,"_vs_",Name2,"_All_ByOverlap_AboveThreshold_names.pdf",sep=""),width = 20,height = 20)
+gg
+dev.off()
+pgg <- ggplotly(gg)
+#pgg
+print("#6")
+fname <- paste("Scatter_lm_GTA_Averages_",Name1,"_vs_",Name2,"_All_ByOverlap_AboveThreshold_names.html",sep="")
+print(fname)
+htmlwidgets::saveWidget(pgg, file.path(getwd(),fname))
+file.rename(from = file.path(getwd(),fname), to =  file.path(pairDirL,fname))
+
+X_abovethreshold$X1_Rank <- NA
+X_abovethreshold$X1_Rank <- rank(-X_abovethreshold$Z_lm_L_Avg_X1,ties.method = "random")
+X_abovethreshold$X2_Rank <- NA
+X_abovethreshold$X2_Rank <- rank(-X_abovethreshold$Z_lm_L_Avg_X2,ties.method = "random")
+
+#7
+gg <- ggplot(data = X_abovethreshold,aes(x=Z_lm_L_Avg_X1,y=Z_lm_L_Avg_X2,color=Overlap,Term=Term_Avg,Genes=Genes_Avg_X1,NumGenes=NumGenes_Avg_X1,AllPossibleGenes=AllPossibleGenes_Avg_X1,SD_1=Z_lm_L_SD_X1,SD_2=Z_lm_L_SD_X2)) + 
+  xlab(paste("GO Term Avg lm Z for ",Name1,sep="")) +
+  geom_text(aes(label=X1_Rank),nudge_y = 0.25,size=4) + 
+  geom_rect(aes(xmin=-2,xmax=2,ymin=-2,ymax=2),color="grey20",size=0.25,alpha=0.1,inherit.aes = FALSE,fill=NA) + geom_point(shape=3,size=3) +
+  ylab(paste("GO Term Avg lm Z for ",Name2,sep="")) + ggtitle(paste("Comparing Average GO Term Z lm for ",Name1," vs. ",Name2,sep="")) +
+  theme_Publication_legend_right()
+pdf(paste(outputpath,"/","Scatter_lm_GTA_Averages_",Name1,"_vs_",Name2,"_All_ByOverlap_AboveThreshold_numberedX1.pdf",sep=""),width = 15,height = 15)
+gg
+dev.off()
+pgg <- ggplotly(gg)
+#pgg
+print("#7")
+fname <- paste("Scatter_lm_GTA_Averages_",Name1,"_vs_",Name2,"_All_ByOverlap_AboveThreshold_numberedX1.html",sep="")
+print(fname)
+htmlwidgets::saveWidget(pgg, file.path(getwd(),fname))
+file.rename(from = file.path(getwd(),fname), to =  file.path(pairDirL,fname))
+
+#8
+gg <- ggplot(data = X_abovethreshold,aes(x=Z_lm_L_Avg_X1,y=Z_lm_L_Avg_X2,color=Overlap,Term=Term_Avg,Genes=Genes_Avg_X1,NumGenes=NumGenes_Avg_X1,AllPossibleGenes=AllPossibleGenes_Avg_X1,SD_1=Z_lm_L_SD_X1,SD_2=Z_lm_L_SD_X2)) + 
+  xlab(paste("GO Term Avg lm Z for ",Name1,sep="")) +
+  geom_text(aes(label=X2_Rank),nudge_y = 0.25,size=4) + 
+  geom_rect(aes(xmin=-2,xmax=2,ymin=-2,ymax=2),color="grey20",size=0.25,alpha=0.1,inherit.aes = FALSE,fill=NA) + geom_point(shape=3,size=3) +
+  ylab(paste("GO Term Avg lm Z for ",Name2,sep="")) + ggtitle(paste("Comparing Average GO Term Z lm for ",Name1," vs. ",Name2,sep="")) +
+  theme_Publication_legend_right()
+pdf(paste(outputpath,"/","Scatter_lm_GTA_Averages_",Name1,"_vs_",Name2,"_All_ByOverlap_AboveThreshold_numberedX2.pdf",sep=""),width = 15,height = 15)
+gg
+dev.off()
+pgg <- ggplotly(gg)
+#pgg
+print("#8")
+fname <- paste("Scatter_lm_GTA_Averages_",Name1,"_vs_",Name2,"_All_ByOverlap_AboveThreshold_numberedX2.html",sep="")
+print(fname)
+htmlwidgets::saveWidget(pgg, file.path(getwd(),fname))
+file.rename(from = file.path(getwd(),fname), to =  file.path(pairDirL,fname))
+
+print("write csv files L")
+write.csv(x=X,file = paste(outputpath,"/All_GTA_Avg_Scores_",Name1,"_vs_",Name2,".csv",sep=""),row.names = FALSE)
+write.csv(x=X_abovethreshold,file = paste(getwd(),"/",outputpath,"/","AboveThreshold_GTA_Avg_Scores_",Name1,"_vs_",Name2,".csv",sep=""),row.names = FALSE)
+#End of L GTA Pairwise Compare
+
+
+
+###########BEGIN PAIRWISE K-----KKKKKKKKKKKKKKKKKKKKKKKKKKKKKKKKKKKKKKKKKKKKKKKKKKKKK
+#define the output path (as fourth argument from Rscript)
+outputpath <- pairDirK #outPathGTAcompare[2]   #Args[5]
+
+#theme elements for plots
+theme_Publication <- function(base_size=14, base_family="sans") {
+  (theme_foundation(base_size=base_size, base_family=base_family)
+   + theme(plot.title = element_text(face = "bold",
+                                     size = rel(1.2), hjust = 0.5),
+           text = element_text(),
+           panel.background = element_rect(colour = NA),
+           plot.background = element_rect(colour = NA),
+           panel.border = element_rect(colour = NA),
+           axis.title = element_text(face = "bold",size = rel(1)),
+           axis.title.y = element_text(angle=90,vjust =2),
+           axis.title.x = element_text(vjust = -0.2),
+           axis.text = element_text(), 
+           axis.line = element_line(colour="black"),
+           axis.ticks = element_line(),
+           panel.grid.major = element_line(colour="#f0f0f0"),
+           panel.grid.minor = element_blank(),
+           legend.key = element_rect(colour = NA),
+           legend.position = "bottom",
+           legend.direction = "horizontal",
+           legend.key.size= unit(0.2, "cm"),
+           legend.spacing = unit(0, "cm"),
+           legend.title = element_text(face="italic"),
+           plot.margin=unit(c(10,5,5,5),"mm"),
+           strip.background=element_rect(colour="#f0f0f0",fill="#f0f0f0"),
+           strip.text = element_text(face="bold")
+   ))
+}
+
+scale_fill_Publication <- function(...){
+  library(scales)
+  discrete_scale("fill","Publication",manual_pal(values = c("#386cb0","#fdb462","#7fc97f","#ef3b2c","#662506","#a6cee3","#fb9a99","#984ea3","#ffff33")), ...)
+}
+scale_colour_Publication <- function(...){
+  discrete_scale("colour","Publication",manual_pal(values = c("#386cb0","#fdb462","#7fc97f","#ef3b2c","#662506","#a6cee3","#fb9a99","#984ea3","#ffff33")), ...)
+}
+
+theme_Publication_legend_right <- function(base_size=14, base_family="sans") {
+  (theme_foundation(base_size=base_size, base_family=base_family)
+   + theme(plot.title = element_text(face = "bold",
+                                     size = rel(1.2), hjust = 0.5),
+           text = element_text(),
+           panel.background = element_rect(colour = NA),
+           plot.background = element_rect(colour = NA),
+           panel.border = element_rect(colour = NA),
+           axis.title = element_text(face = "bold",size = rel(1)),
+           axis.title.y = element_text(angle=90,vjust =2),
+           axis.title.x = element_text(vjust = -0.2),
+           axis.text = element_text(), 
+           axis.line = element_line(colour="black"),
+           axis.ticks = element_line(),
+           panel.grid.major = element_line(colour="#f0f0f0"),
+           panel.grid.minor = element_blank(),
+           legend.key = element_rect(colour = NA),
+           legend.position = "right",
+           legend.direction = "vertical",
+           legend.key.size= unit(0.5, "cm"),
+           legend.spacing = unit(0, "cm"),
+           legend.title = element_text(face="italic"),
+           plot.margin=unit(c(10,5,5,5),"mm"),
+           strip.background=element_rect(colour="#f0f0f0",fill="#f0f0f0"),
+           strip.text = element_text(face="bold")
+   ))
+}
+
+scale_fill_Publication <- function(...){
+  discrete_scale("fill","Publication",manual_pal(values = c("#386cb0","#fdb462","#7fc97f","#ef3b2c","#662506","#a6cee3","#fb9a99","#984ea3","#ffff33")), ...)
+}
+scale_colour_Publication <- function(...){
+  discrete_scale("colour","Publication",manual_pal(values = c("#386cb0","#fdb462","#7fc97f","#ef3b2c","#662506","#a6cee3","#fb9a99","#984ea3","#ffff33")), ...)
+}
+
+X1 <- read.csv(file = input_file1,stringsAsFactors=FALSE,header = TRUE)
+
+X2 <- read.csv(file = input_file2,stringsAsFactors=FALSE,header = TRUE)
+
+#1
+X <- merge(X1,X2,by ="Term_Avg",all=TRUE,suffixes = c("_X1","_X2"))
+
+gg <- ggplot(data = X,aes(x=Z_lm_K_Avg_X1,y=Z_lm_K_Avg_X2,color=Ontology_Avg_X1,Term=Term_Avg,Genes=Genes_Avg_X1,NumGenes=NumGenes_Avg_X1,AllPossibleGenes=AllPossibleGenes_Avg_X1,SD_1=Z_lm_K_SD_X1,SD_2=Z_lm_K_SD_X2)) + 
+  xlab(paste("GO Term Avg lm Z for ",Name1,sep="")) +
+  geom_rect(aes(xmin=-2,xmax=2,ymin=-2,ymax=2),color="grey20",size=0.25,alpha=0.1,inherit.aes = FALSE,fill=NA) + geom_point(shape=3) +
+  ylab(paste("GO Term Avg lm Z for ",Name2,sep="")) + ggtitle(paste("Comparing Average GO Term Z lm for ",Name1," vs. ",Name2,sep = "")) +
+  theme_Publication_legend_right()
+pdf(paste(getwd(),"/",outputpath,"/","Scatter_lm_GTF_Averages_",Name1,"_vs_",Name2,"_All_ByOntology.pdf",sep=""),width = 12,height = 8)
+gg
+dev.off()
+pgg <- ggplotly(gg)
+#pgg
+print("127")
+fname <- paste("Scatter_lm_GTA_Averages_",Name1,"_vs_",Name2,"_All_byOntology.html",sep="")
+print(fname)
+htmlwidgets::saveWidget(pgg, file.path(getwd(),fname))
+file.rename(from = file.path(getwd(),fname), to =  file.path(pairDirK,fname))
+
+#2
+#ID aggravators and alleviators, regardless of whether they meet 2SD threshold
+X1_Specific_Aggravators <- X[which(X$Z_lm_K_Avg_X1 >= 2 & X$Z_lm_K_Avg_X2 < 2),]
+X1_Specific_Alleviators <- X[which(X$Z_lm_K_Avg_X1 <= -2 & X$Z_lm_K_Avg_X2 > -2),]
+
+X2_Specific_Aggravators <- X[which(X$Z_lm_K_Avg_X2 >= 2 & X$Z_lm_K_Avg_X1 < 2),]
+X2_Specific_Alleviators <- X[which(X$Z_lm_K_Avg_X2 <= -2 & X$Z_lm_K_Avg_X1 > -2),]
+
+Overlap_Aggravators <- X[which(X$Z_lm_K_Avg_X1 >= 2 & X$Z_lm_K_Avg_X2 >= 2),]
+Overlap_Alleviators <- X[which(X$Z_lm_K_Avg_X1 <= -2 & X$Z_lm_K_Avg_X2 <= -2),]
+
+X2_Specific_Aggravators_X1_Alleviatiors <- X[which(X$Z_lm_K_Avg_X2 >= 2 & X$Z_lm_K_Avg_X1 <= -2),]
+X2_Specific_Alleviators_X1_Aggravators <- X[which(X$Z_lm_K_Avg_X2 <= -2 & X$Z_lm_K_Avg_X1 >= 2),]
+
+X$Overlap_Avg <- NA
+
+try(X[X$Term_Avg %in% X1_Specific_Aggravators$Term_Avg,]$Overlap_Avg <- paste(Name1,"Specific_Deletion_Suppressors",sep="_"))
+try(X[X$Term_Avg %in% X1_Specific_Alleviators$Term_Avg,]$Overlap_Avg <- paste(Name1,"Specific_Deletion_Enhancers",sep="_"))
+try(X[X$Term_Avg %in% X2_Specific_Aggravators$Term_Avg,]$Overlap_Avg <- paste(Name2,"Specific_Deletion_Suppressors",sep="_"))
+try(X[X$Term_Avg %in% X2_Specific_Alleviators$Term_Avg,]$Overlap_Avg <- paste(Name2,"Specific_Deletion_Enhancers",sep="_"))
+try(X[X$Term_Avg %in% Overlap_Aggravators$Term_Avg,]$Overlap_Avg <- "Overlapping_Deletion_Suppressors")
+try(X[X$Term_Avg %in% Overlap_Alleviators$Term_Avg,]$Overlap_Avg <- "Overlapping_Deletion_Enhancers")
+try(X[X$Term_Avg %in% X2_Specific_Aggravators_X1_Alleviatiors$Term_Avg,]$Overlap_Avg <- paste(Name2,"Deletion_Suppressors",Name1,"Deletion_Enhancers",sep="_"))
+try(X[X$Term_Avg %in% X2_Specific_Alleviators_X1_Aggravators$Term_Avg,]$Overlap_Avg <- paste(Name2,"Deletion_Enhancers",Name1,"Deletion_Suppressors",sep="_"))
+
+
+plotly_path <- paste(getwd(),"/",outputpath,"/","Scatter_lm_GTF_Averages_",Name1,"_vs_",Name2,"_All_byOverlap.html",sep="")
+gg <- ggplot(data = X,aes(x=Z_lm_K_Avg_X1,y=Z_lm_K_Avg_X2,color=Overlap_Avg,Term=Term_Avg,Genes=Genes_Avg_X1,NumGenes=NumGenes_Avg_X1,AllPossibleGenes=AllPossibleGenes_Avg_X1,SD_1=Z_lm_K_SD_X1,SD_2=Z_lm_K_SD_X2)) + 
+  xlab(paste("GO Term Avg lm Z for ",Name1,sep="")) +
+  geom_rect(aes(xmin=-2,xmax=2,ymin=-2,ymax=2),color="grey20",size=0.25,alpha=0.1,inherit.aes = FALSE,fill=NA) + geom_point(shape=3) +
+  ylab(paste("GO Term Avg lm Z for ",Name2,sep="")) + ggtitle(paste("Comparing Average GO Term Z lm for ",Name1," vs. ",Name2,sep="")) +
+  theme_Publication_legend_right()
+pdf(paste(getwd(),"/",outputpath,"/","Scatter_lm_GTF_Averages_",Name1,"_vs_",Name2,"_All_ByOverlap.pdf",sep=""),width = 12,height = 8)
+gg
+dev.off()
+pgg <- ggplotly(gg)
+#pgg
+print("#2-170")
+#2
+fname <- paste("/Scatter_lm_GTA_Averages_",Name1,"_vs_",Name2,"_All_byOverlap.html",sep="")
+print(fname)
+htmlwidgets::saveWidget(pgg, file.path(getwd(),fname))
+file.rename(from = file.path(getwd(),fname), to =  file.path(pairDirK,fname))
+
+#3
+x_rem2_gene <- X[X$NumGenes_Avg_X1 >= 2 & X$NumGenes_Avg_X2 >= 2,]
+plotly_path <- paste(getwd(),"/",outputpath,"/","Scatter_lm_GTF_Averages_",Name1,"_vs_",Name2,"_All_byOverlap_above2genes.html",sep="")
+gg <- ggplot(data = x_rem2_gene,aes(x=Z_lm_K_Avg_X1,y=Z_lm_K_Avg_X2,color=Overlap_Avg,Term=Term_Avg,Genes=Genes_Avg_X1,NumGenes=NumGenes_Avg_X1,AllPossibleGenes=AllPossibleGenes_Avg_X1,SD_1=Z_lm_K_SD_X1,SD_2=Z_lm_K_SD_X2)) + 
+  xlab(paste("GO Term Avg lm Z for ",Name1,sep="")) +
+  geom_rect(aes(xmin=-2,xmax=2,ymin=-2,ymax=2),color="grey20",size=0.25,alpha=0.1,inherit.aes = FALSE,fill=NA) + geom_point(shape=3) +
+  ylab(paste("GO Term Avg lm Z for ",Name2,sep="")) + ggtitle(paste("Comparing Average GO Term Z lm for ",Name1," vs. ",Name2,sep="")) +
+  theme_Publication_legend_right()
+pdf(paste(getwd(),"/",outputpath,"/","Scatter_lm_GTF_Averages_",Name1,"_vs_",Name2,"_All_ByOverlap_above2genes.pdf",sep=""),width = 12,height = 8)
+gg
+dev.off()
+pgg <- ggplotly(gg)
+#pgg
+print("#3")
+fname <- paste("Scatter_lm_GTA_Averages_",Name1,"_vs_",Name2,"_All_byOverlap_above2genes.html",sep="")
+print(fname)
+htmlwidgets::saveWidget(pgg, file.path(getwd(),fname))
+file.rename(from = file.path(getwd(),fname), to =  file.path(pairDirK,fname))
+
+#4
+X_overlap_nothresold <- X[!(is.na(X$Overlap_Avg)),]
+gg <- ggplot(data = X_overlap_nothresold,aes(x=Z_lm_K_Avg_X1,y=Z_lm_K_Avg_X2,color=Overlap_Avg,Term=Term_Avg,Genes=Genes_Avg_X1,NumGenes=NumGenes_Avg_X1,AllPossibleGenes=AllPossibleGenes_Avg_X1,SD_1=Z_lm_K_SD_X1,SD_2=Z_lm_K_SD_X2)) + 
+  xlab(paste("GO Term Avg lm Z for ",Name1,sep="")) +
+  geom_rect(aes(xmin=-2,xmax=2,ymin=-2,ymax=2),color="grey20",size=0.25,alpha=0.1,inherit.aes = FALSE,fill=NA) + geom_point(shape=3) +
+  ylab(paste("GO Term Avg lm Z for ",Name2,sep="")) + ggtitle(paste("Comparing Average GO Term Z lm for ",Name1," vs. ",Name2,sep = "")) +
+  theme_Publication_legend_right()
+pdf(paste(getwd(),"/",outputpath,"/","Scatter_lm_GTF_Averages_",Name1,"_vs_",Name2,"_Above2SD_ByOverlap.pdf",sep=""),width = 12,height = 8)
+gg
+dev.off()
+pgg <- ggplotly(gg)
+#pgg
+print("#4")
+fname <- paste("Scatter_lm_GTA_Averages_",Name1,"_vs_",Name2,"_Above2SD_ByOverlap.html",sep="")
+print(fname)
+htmlwidgets::saveWidget(pgg, file.path(getwd(),fname))
+file.rename(from = file.path(getwd(),fname), to =  file.path(pairDirK,fname))
+
+#5
+#only output GTA terms where average score is still above 2 after subtracting the SD
+#Z1 will ID aggravators, Z2 alleviators
+Z1 <- X
+Z1$L_Subtract_SD_X1 <- Z1$Z_lm_K_Avg_X1 - Z1$Z_lm_K_SD_X1
+Z1$L_Subtract_SD_X2 <- Z1$Z_lm_K_Avg_X2 - Z1$Z_lm_K_SD_X2
+
+Z2 <- X
+Z2$L_Subtract_SD_X1 <- Z1$Z_lm_K_Avg_X1 + Z1$Z_lm_K_SD_X1
+Z2$L_Subtract_SD_X2 <- Z1$Z_lm_K_Avg_X2 + Z1$Z_lm_K_SD_X2
+
+
+X1_Specific_Aggravators2 <- Z1[which(Z1$L_Subtract_SD_X1 >= 2 & Z1$L_Subtract_SD_X2 < 2),]
+X1_Specific_Alleviators2 <- Z2[which(Z2$L_Subtract_SD_X1 <= -2 & Z2$L_Subtract_SD_X2 > -2),]
+
+X2_Specific_Aggravators2 <- Z1[which(Z1$L_Subtract_SD_X2 >= 2 & Z1$L_Subtract_SD_X1 < 2),]
+X2_Specific_Alleviators2 <- Z2[which(Z2$L_Subtract_SD_X2 <= -2 & Z2$L_Subtract_SD_X1 > -2),]
+
+Overlap_Aggravators2 <- Z1[which(Z1$L_Subtract_SD_X1 >= 2 & Z1$L_Subtract_SD_X2 >= 2),]
+Overlap_Alleviators2 <- Z2[which(Z2$L_Subtract_SD_X2 <= -2 & Z2$L_Subtract_SD_X1 <= -2),]
+
+X2_Specific_Aggravators2_X1_Alleviatiors2 <- Z1[which(Z1$L_Subtract_SD_X2 >= 2 & Z2$L_Subtract_SD_X1 <= -2),]
+X2_Specific_Alleviators2_X1_Aggravators2 <- Z2[which(Z2$L_Subtract_SD_X2 <= -2 & Z1$L_Subtract_SD_X1 >= 2),]
+
+X$Overlap <- NA
+
+try(X[X$Term_Avg %in% X1_Specific_Aggravators2$Term_Avg,]$Overlap <- paste(Name1,"Specific_Deletion_Suppressors",sep="_"))
+try(X[X$Term_Avg %in% X1_Specific_Alleviators2$Term_Avg,]$Overlap <- paste(Name1,"Specific_Deletion_Enhancers",sep="_"))
+try(X[X$Term_Avg %in% X2_Specific_Aggravators2$Term_Avg,]$Overlap <- paste(Name2,"Specific_Deletion_Suppressors",sep="_"))
+try(X[X$Term_Avg %in% X2_Specific_Alleviators2$Term_Avg,]$Overlap <- paste(Name2,"Specific_Deletion_Enhancers",sep="_"))
+try(X[X$Term_Avg %in% Overlap_Aggravators2$Term_Avg,]$Overlap <- "Overlapping_Deletion_Suppressors")
+try(X[X$Term_Avg %in% Overlap_Alleviators2$Term_Avg,]$Overlap <- "Overlapping_Deletion_Enhancers")
+try(X[X$Term_Avg %in% X2_Specific_Aggravators2_X1_Alleviatiors2$Term_Avg,]$Overlap <- paste(Name2,"Deletion_Suppressors",Name1,"Deletion_Enhancers",sep="_"))
+try(X[X$Term_Avg %in% X2_Specific_Alleviators2_X1_Aggravators2$Term_Avg,]$Overlap <- paste(Name2,"Deletion_Enhancers",Name1,"Deletion_Suppressors",sep="_"))
+
+X_abovethreshold <- X[!(is.na(X$Overlap)),]
+gg <- ggplot(data = X_abovethreshold,aes(x=Z_lm_K_Avg_X1,y=Z_lm_K_Avg_X2,color=Overlap,Term=Term_Avg,Genes=Genes_Avg_X1,NumGenes=NumGenes_Avg_X1,AllPossibleGenes=AllPossibleGenes_Avg_X1,SD_1=Z_lm_K_SD_X1,SD_2=Z_lm_K_SD_X2)) + 
+  xlab(paste("GO Term Avg lm Z for ",Name1,sep="")) +
+  geom_rect(aes(xmin=-2,xmax=2,ymin=-2,ymax=2),color="grey20",size=0.25,alpha=0.1,inherit.aes = FALSE,fill=NA) + geom_point(shape=3) +
+  ylab(paste("GO Term Avg lm Z for ",Name2,sep="")) + ggtitle(paste("Comparing Average GO Term Z lm for ",Name1," vs. ",Name2,sep="")) +
+  theme_Publication_legend_right()
+pdf(paste(getwd(),"/",outputpath,"/","Scatter_lm_GTF_Averages_",Name1,"_vs_",Name2,"_All_ByOverlap_AboveThreshold.pdf",sep=""),width = 12,height = 8)
+gg
+dev.off()
+pgg <- ggplotly(gg)
+#pgg
+print("#5")
+fname <- paste("Scatter_lm_GTA_Averages_",Name1,"_vs_",Name2,"_All_ByOverlap_AboveThreshold.html",sep="")
+print(fname)
+htmlwidgets::saveWidget(pgg, file.path(getwd(),fname))
+file.rename(from = file.path(getwd(),fname), to =  file.path(pairDirK,fname))
+
+#6
+gg <- ggplot(data = X_abovethreshold,aes(x=Z_lm_K_Avg_X1,y=Z_lm_K_Avg_X2,color=Overlap,Term=Term_Avg,Genes=Genes_Avg_X1,NumGenes=NumGenes_Avg_X1,AllPossibleGenes=AllPossibleGenes_Avg_X1,SD_1=Z_lm_K_SD_X1,SD_2=Z_lm_K_SD_X2)) + 
+  xlab(paste("GO Term Avg lm Z for ",Name1,sep="")) +
+  geom_text(aes(label=Term_Avg),nudge_y = 0.25,size=2) + 
+  geom_rect(aes(xmin=-2,xmax=2,ymin=-2,ymax=2),color="grey20",size=0.25,alpha=0.1,inherit.aes = FALSE,fill=NA) + geom_point(shape=3,size=3) +
+  ylab(paste("GO Term Avg lm Z for ",Name2,sep="")) + ggtitle(paste("Comparing Average GO Term Z lm for ",Name1," vs. ",Name2,sep="")) +
+  theme_Publication_legend_right()
+pdf(paste(getwd(),"/",outputpath,"/","Scatter_lm_GTF_Averages_",Name1,"_vs_",Name2,"_All_ByOverlap_AboveThreshold_names.pdf",sep=""),width = 20,height = 20)
+gg
+dev.off()
+pgg <- ggplotly(gg)
+#pgg
+print("#6")
+fname <- paste("Scatter_lm_GTA_Averages_",Name1,"_vs_",Name2,"_All_ByOverlap_AboveThreshold_names.html",sep="")
+print(fname)
+htmlwidgets::saveWidget(pgg, file.path(getwd(),fname))
+file.rename(from = file.path(getwd(),fname), to =  file.path(pairDirK,fname))
+
+#7
+X_abovethreshold$X1_Rank <- NA
+X_abovethreshold$X1_Rank <- rank(-X_abovethreshold$Z_lm_K_Avg_X1,ties.method = "random")
+X_abovethreshold$X2_Rank <- NA
+X_abovethreshold$X2_Rank <- rank(-X_abovethreshold$Z_lm_K_Avg_X2,ties.method = "random")
+
+
+gg <- ggplot(data = X_abovethreshold,aes(x=Z_lm_K_Avg_X1,y=Z_lm_K_Avg_X2,color=Overlap,Term=Term_Avg,Genes=Genes_Avg_X1,NumGenes=NumGenes_Avg_X1,AllPossibleGenes=AllPossibleGenes_Avg_X1,SD_1=Z_lm_K_SD_X1,SD_2=Z_lm_K_SD_X2)) + 
+  xlab(paste("GO Term Avg lm Z for ",Name1,sep="")) +
+  geom_text(aes(label=X1_Rank),nudge_y = 0.25,size=4) + 
+  geom_rect(aes(xmin=-2,xmax=2,ymin=-2,ymax=2),color="grey20",size=0.25,alpha=0.1,inherit.aes = FALSE,fill=NA) + geom_point(shape=3,size=3) +
+  ylab(paste("GO Term Avg lm Z for ",Name2,sep="")) + ggtitle(paste("Comparing Average GO Term Z lm for ",Name1," vs. ",Name2,sep="")) +
+  theme_Publication_legend_right()
+pdf(paste(getwd(),"/",outputpath,"/","Scatter_lm_GTF_Averages_",Name1,"_vs_",Name2,"_All_ByOverlap_AboveThreshold_numberedX1.pdf",sep=""),width = 15,height = 15)
+gg
+dev.off()
+pgg <- ggplotly(gg)
+#pgg
+print("#7")
+fname <- paste("Scatter_lm_GTA_Averages_",Name1,"_vs_",Name2,"_All_ByOverlap_AboveThreshold_numberedX1.html",sep="")
+print(fname)
+htmlwidgets::saveWidget(pgg, file.path(getwd(),fname))
+file.rename(from = file.path(getwd(),fname), to =  file.path(pairDirK,fname))
+
+#8
+gg <- ggplot(data = X_abovethreshold,aes(x=Z_lm_K_Avg_X1,y=Z_lm_K_Avg_X2,color=Overlap,Term=Term_Avg,Genes=Genes_Avg_X1,NumGenes=NumGenes_Avg_X1,AllPossibleGenes=AllPossibleGenes_Avg_X1,SD_1=Z_lm_K_SD_X1,SD_2=Z_lm_K_SD_X2)) + 
+  xlab(paste("GO Term Avg lm Z for ",Name1,sep="")) +
+  geom_text(aes(label=X2_Rank),nudge_y = 0.25,size=4) + 
+  geom_rect(aes(xmin=-2,xmax=2,ymin=-2,ymax=2),color="grey20",size=0.25,alpha=0.1,inherit.aes = FALSE,fill=NA) + geom_point(shape=3,size=3) +
+  ylab(paste("GO Term Avg lm Z for ",Name2,sep="")) + ggtitle(paste("Comparing Average GO Term Z lm for ",Name1," vs. ",Name2,sep="")) +
+  theme_Publication_legend_right()
+pdf(paste(getwd(),"/",outputpath,"/","Scatter_lm_GTF_Averages_",Name1,"_vs_",Name2,"_All_ByOverlap_AboveThreshold_numberedX2.pdf",sep=""),width = 15,height = 15)
+gg
+dev.off()
+pgg <- ggplotly(gg)
+#pgg
+print("#8")
+fname <- paste("Scatter_lm_GTA_Averages_",Name1,"_vs_",Name2,"_All_ByOverlap_AboveThreshold_numberedX2.html",sep="")
+print(fname)
+htmlwidgets::saveWidget(pgg, file.path(getwd(),fname))
+file.rename(from = file.path(getwd(),fname), to =  file.path(pairDirK,fname))
+
+print("write csv files")
+write.csv(x=X,file = paste(getwd(),"/",outputpath,"/","All_GTF_Avg_Scores_",Name1,"_vs_",Name2,".csv",sep=""),row.names = FALSE)
+write.csv(x=X_abovethreshold,file = paste(getwd(),"/",outputpath,"/","AboveThreshold_GTF_Avg_Scores_",Name1,"_vs_",Name2,".csv",sep=""),row.names = FALSE)
+
+#End of GTA Pairwise compare for K values

workflow/apps/r/TSHeatmaps5dev2.R

@@ -0,0 +1,696 @@
+#!/usr/bin/env Rscript
+# Makes heat maps of multiple experiments
+#
+# Updated 240724 Bryan C Roessler to improve file operations and portability
+# I tried to leave as much logic intact as possible, just feeding in vars in a better way
+# NOTE: The script now has 7 required arguments and a variable number of input experiments
+# @arg $1 string StudyInfo.csv file
+# @arg $2 string gene_ontology_edit.obo file
+# @arg $3 string go_terms.tab file
+# @arg $4 string All_SGD_GOTerms_for_QHTCPtk.csv
+# @arg $5 string ZScores_interaction.csv
+# @arg $6 string base directory
+# @arg $7 string output directory
+
+library("ontologyIndex")
+library("ggplot2")
+library("RColorBrewer")
+library("grid")
+library("ggthemes")
+#library("plotly")
+#library("htmlwidgets")
+library("extrafont")
+library("stringr")
+library("org.Sc.sgd.db")
+library("ggrepel")
+library("gplots")
+
+# Load arguments
+args <- commandArgs(TRUE)
+study_info_file <- args[1]
+ontology_file <- args[2]
+sgd_terms_tfile <- args[3]
+all_sgd_terms_csv <- args[4]
+zscores_file <- args[5]
+base_dir <- args[6]
+output_dir <- args[7]
+study_nums <- args[8:length(args)]
+
+#import standard tables used in Sean's code That should be copied to each ExpStudy
+labels<- read.csv(file=study_info_file,stringsAsFactors = FALSE)
+Ontology <- get_ontology(file=ontology_file,propagate_relationships = "is_a",extract_tags = "minimal")
+GO2ALLORFs <- as.list(org.Sc.sgdGO2ALLORFS) #all ORFs associated with GO term
+Terms <- read.delim(file=sgd_terms_tfile,header=FALSE,quote = "",col.names = c("GO_ID","GO_Term","GO_Aspect","GO_Term_Definition"))
+XX3 <- read.csv(file=all_sgd_terms_csv,stringsAsFactors=FALSE,header = TRUE)
+XX3[,1] <- paste("GO:",formatC(XX3[,1],width=7,flag="0"),sep="")
+XX3[,2] <- gsub(pattern = " ",replacement = "_",x = XX3[,2])
+XX3[,2] <- gsub(pattern = "/",replacement = "_",x = XX3[,2])
+
+# Load input files
+for (study_num in study_nums) {
+  input_file <- file.path(base_dir,paste('Exp',study_num),zscores_file)
+  if (file.exists(input_file)) {
+    assign(paste(X, study_num), read.csv(file=input_file,stringsAsFactors=FALSE,header=TRUE))
+    assign(paste(Name, study_num), labels[study_num,2])
+  }
+}
+
+for (study_num in study_nums) {
+  eval(paste("function",study_num))
+}
+
+if (length(study_nums) > 0) {
+  X1$ORF <- X1$OrfRep
+  X1$ORF <- gsub("_1","",x=X1$ORF)
+  X1$ORF <- gsub("_2","",x=X1$ORF)
+  X1$ORF <- gsub("_3","",x=X1$ORF)
+  X1$ORF <- gsub("_4","",x=X1$ORF)
+  
+  X1$Score_L <- "No Effect"
+  try(X1[is.na(X1$Z_lm_L),]$Score_L <- "No Growth")
+  try(X1[!is.na(X1$Z_lm_L) & X1$Z_lm_L >= 2,]$Score_L <- "Deletion Enhancer")
+  try(X1[!is.na(X1$Z_lm_L) & X1$Z_lm_L <= -2,]$Score_L <- "Deletion Suppressor")
+  
+  X1$Score_K <- "No Effect"
+  try(X1[is.na(X1$Z_lm_K),]$Score_K <- "No Growth")
+  try(X1[!is.na(X1$Z_lm_K) & X1$Z_lm_K >= 2,]$Score_K <- "Deletion Suppressor")
+  try(X1[!is.na(X1$Z_lm_K) & X1$Z_lm_K <= -2,]$Score_K <- "Deletion Enhancer")
+  
+  #express the na data as 0.001 in X1 for K and L
+  X1[is.na(X1$Z_lm_L),]$Z_lm_L <- 0.001
+  X1[is.na(X1$Z_lm_K),]$Z_lm_K <- 0.001
+  X1$Rank_L <- rank(X1$Z_lm_L)
+  X1$Rank_K <- rank(X1$Z_lm_K)
+  
+  X1 <- X1[order(X1$OrfRep,decreasing = FALSE),]
+  colnames(X1) <- paste(colnames(X1),"_X1",sep="")
+}
+
+if (length(study_nums) > 1) {
+  X2$ORF <- X2$OrfRep
+  X2$ORF <- gsub("_1","",x=X2$ORF)
+  X2$ORF <- gsub("_2","",x=X2$ORF)
+  X2$ORF <- gsub("_3","",x=X2$ORF)
+  X2$ORF <- gsub("_4","",x=X2$ORF)
+  
+  X2$Score_L <- "No Effect"
+  try(X2[is.na(X2$Z_lm_L),]$Score_L <- "No Growth")
+  try(X2[!is.na(X2$Z_lm_L) & X2$Z_lm_L >= 2,]$Score_L <- "Deletion Enhancer")
+  try(X2[!is.na(X2$Z_lm_L) & X2$Z_lm_L <= -2,]$Score_L <- "Deletion Suppressor")
+  
+  X2$Score_K <- "No Effect"
+  try(X2[is.na(X2$Z_lm_K),]$Score_K <- "No Growth")
+  try(X2[!is.na(X2$Z_lm_K) & X2$Z_lm_K >= 2,]$Score_K <- "Deletion Suppressor")
+  try(X2[!is.na(X2$Z_lm_K) & X2$Z_lm_K <= -2,]$Score_K <- "Deletion Enhancer")
+  #express the na data as 0.001 in X2
+  X2[is.na(X2$Z_lm_L),]$Z_lm_L <- 0.001
+  X2[is.na(X2$Z_lm_K),]$Z_lm_K <- 0.001
+  
+  X2$Rank_L <- rank(X2$Z_lm_L)
+  X2$Rank_K <- rank(X2$Z_lm_K)
+  
+  X2 <- X2[order(X2$OrfRep,decreasing = FALSE),]
+  colnames(X2) <- paste(colnames(X2),"_X2",sep="")
+  X <- cbind(X1,X2)
+}
+
+if (length(study_nums) > 2) {
+  X3$ORF <- X3$OrfRep
+  X3$ORF <- gsub("_1","",x=X3$ORF)
+  X3$ORF <- gsub("_2","",x=X3$ORF)
+  X3$ORF <- gsub("_3","",x=X3$ORF)
+  X3$ORF <- gsub("_4","",x=X3$ORF)
+  
+  X3$Score_L <- "No Effect"
+  try(X3[is.na(X3$Z_lm_L),]$Score_L <- "No Growth")
+  try(X3[!is.na(X3$Z_lm_L) & X3$Z_lm_L >= 2,]$Score_L <- "Deletion Enhancer")
+  try(X3[!is.na(X3$Z_lm_L) & X3$Z_lm_L <= -2,]$Score_L <- "Deletion Suppressor")
+  
+  X3$Score_K <- "No Effect"
+  try(X3[is.na(X3$Z_lm_K),]$Score_K <- "No Growth")
+  try(X3[!is.na(X3$Z_lm_K) & X3$Z_lm_K >= 2,]$Score_K <- "Deletion Suppressor")
+  try(X3[!is.na(X3$Z_lm_K) & X3$Z_lm_K <= -2,]$Score_K <- "Deletion Enhancer")
+  #express the na data as 0.001 in X3
+  X3[is.na(X3$Z_lm_L),]$Z_lm_L <- 0.001
+  X3[is.na(X3$Z_lm_K),]$Z_lm_K <- 0.001
+  
+  X3$Rank_L <- rank(X3$Z_lm_L)
+  X3$Rank_K <- rank(X3$Z_lm_K)
+  
+  X3 <- X3[order(X3$OrfRep,decreasing = FALSE),]
+  colnames(X3) <- paste(colnames(X3),"_X3",sep="")
+  X <- cbind(X,X3)
+}  
+
+if (length(study_nums) > 3) {
+  X4$ORF <- X4$OrfRep
+  X4$ORF <- gsub("_1","",x=X4$ORF)
+  X4$ORF <- gsub("_2","",x=X4$ORF)
+  X4$ORF <- gsub("_3","",x=X4$ORF)
+  X4$ORF <- gsub("_4","",x=X4$ORF)
+  
+  X4$Score_L <- "No Effect"
+  try(X4[is.na(X4$Z_lm_L),]$Score_L <- "No Growth")
+  try(X4[!is.na(X4$Z_lm_L) & X4$Z_lm_L >= 2,]$Score_L <- "Deletion Enhancer")
+  try(X4[!is.na(X4$Z_lm_L) & X4$Z_lm_L <= -2,]$Score_L <- "Deletion Suppressor")
+  
+  X4$Score_K <- "No Effect"
+  try(X4[is.na(X4$Z_lm_K),]$Score_K <- "No Growth")
+  try(X4[!is.na(X4$Z_lm_K) & X4$Z_lm_K >= 2,]$Score_K <- "Deletion Suppressor")
+  try(X4[!is.na(X4$Z_lm_K) & X4$Z_lm_K <= -2,]$Score_K <- "Deletion Enhancer")
+  #express the na data as 0.001 in X4
+  X4[is.na(X4$Z_lm_L),]$Z_lm_L <- 0.001
+  X4[is.na(X4$Z_lm_K),]$Z_lm_K <- 0.001
+  
+  X4$Rank_L <- rank(X4$Z_lm_L)
+  X4$Rank_K <- rank(X4$Z_lm_K)
+  
+  X4 <- X4[order(X4$OrfRep,decreasing = FALSE),]
+  colnames(X4) <- paste(colnames(X4),"_X4",sep="")
+  X <- cbind(X,X4)
+}
+
+if (length(study_nums) > 4) {
+  X5$ORF <- X5$OrfRep
+  X5$ORF <- gsub("_1","",x=X5$ORF)
+  X5$ORF <- gsub("_2","",x=X5$ORF)
+  X5$ORF <- gsub("_3","",x=X5$ORF)
+  X5$ORF <- gsub("_4","",x=X5$ORF)
+  
+  X5$Score_L <- "No Effect"
+  try(X5[is.na(X5$Z_lm_L),]$Score_L <- "No Growth")
+  try(X5[!is.na(X5$Z_lm_L) & X5$Z_lm_L >= 2,]$Score_L <- "Deletion Enhancer")
+  try(X5[!is.na(X5$Z_lm_L) & X5$Z_lm_L <= -2,]$Score_L <- "Deletion Suppressor")
+  
+  X5$Score_K <- "No Effect"
+  try(X5[is.na(X5$Z_lm_K),]$Score_K <- "No Growth")
+  try(X5[!is.na(X5$Z_lm_K) & X5$Z_lm_K >= 2,]$Score_K <- "Deletion Suppressor")
+  try(X5[!is.na(X5$Z_lm_K) & X5$Z_lm_K <= -2,]$Score_K <- "Deletion Enhancer")
+  #express the na data as 0.001 in X5
+  X5[is.na(X5$Z_lm_L),]$Z_lm_L <- 0.001
+  X5[is.na(X5$Z_lm_K),]$Z_lm_K <- 0.001
+  
+  X5$Rank_L <- rank(X5$Z_lm_L)
+  X5$Rank_K <- rank(X5$Z_lm_K)
+  
+  X5 <- X5[order(X5$OrfRep,decreasing = FALSE),]
+  colnames(X5) <- paste(colnames(X5),"_X5",sep="")
+  X <- cbind(X,X5)
+}
+
+X$ORF <- X$OrfRep_X1
+
+if (length(study_nums) > 1) {
+
+  X$ORF <- gsub("_1","",x=X$ORF)
+  
+  try(X[X$Gene_X1 == "",]$Gene_X1 <- X[X$Gene_X1 == "",]$OrfRep_X1)
+  try(X[X$Gene_X2 == "",]$Gene_X2 <- X[X$Gene_X2 == "",]$OrfRep_X2)
+  X_heatmap <- X[colnames(X) == "ORF" | colnames(X) == "Gene_X1" |
+                   colnames(X) == "Z_Shift_K_X1" | colnames(X) == "Z_lm_K_X1" |
+                   colnames(X) == "Z_Shift_K_X2" | colnames(X) == "Z_lm_K_X2" |
+                   colnames(X) == "Z_Shift_L_X1" | colnames(X) == "Z_lm_L_X1" |
+                   colnames(X) == "Z_Shift_L_X2" | colnames(X) == "Z_lm_L_X2" ]
+  
+  X_heatmap <- X_heatmap[,c(10,1,4,5,8,9,2,3,6,7)]
+  colnames(X_heatmap) <- gsub(pattern = "X1",replacement = Name1,colnames(X_heatmap))
+  colnames(X_heatmap) <- gsub(pattern = "X2",replacement = Name2,colnames(X_heatmap))
+  colnames(X_heatmap)[2] <- "Gene"
+}
+
+
+if (length(study_nums) > 2) {
+  X$ORF <- gsub("_1","",x=X$ORF)
+  X$ORF <- gsub("_2","",x=X$ORF)
+  
+  try(X[X$Gene_X1 == "",]$Gene_X1 <- X[X$Gene_X1 == "",]$OrfRep_X1)
+  try(X[X$Gene_X2 == "",]$Gene_X2 <- X[X$Gene_X2 == "",]$OrfRep_X2)
+  try(X[X$Gene_X3 == "",]$Gene_X3 <- X[X$Gene_X3 == "",]$OrfRep_X3)
+  
+  X_heatmap <- X[colnames(X) == "ORF" | colnames(X) == "Gene_X1" |
+                   colnames(X) == "Z_Shift_K_X1" | colnames(X) == "Z_lm_K_X1" |
+                   colnames(X) == "Z_Shift_K_X2" | colnames(X) == "Z_lm_K_X2" | 
+                   colnames(X) == "Z_Shift_K_X3" | colnames(X) == "Z_lm_K_X3" |
+                   colnames(X) == "Z_Shift_L_X1" | colnames(X) == "Z_lm_L_X1" |
+                   colnames(X) == "Z_Shift_L_X2" | colnames(X) == "Z_lm_L_X2" |
+                   colnames(X) == "Z_Shift_L_X3" | colnames(X) == "Z_lm_L_X3" ]
+  #Reorder columns
+  X_heatmap <- X_heatmap[,c(14,1,4,5,8,9,12,13,2,3,6,7,10,11)]  #Three
+  colnames(X_heatmap) <- gsub(pattern = "X1",replacement = Name1,colnames(X_heatmap))
+  colnames(X_heatmap) <- gsub(pattern = "X2",replacement = Name2,colnames(X_heatmap))
+  colnames(X_heatmap) <- gsub(pattern = "X3",replacement = Name3,colnames(X_heatmap))
+  colnames(X_heatmap)[2] <- "Gene"
+}
+
+if (length(study_nums) > 3) {
+  X$ORF <- gsub("_1","",x=X$ORF)
+  X$ORF <- gsub("_2","",x=X$ORF)
+  X$ORF <- gsub("_3","",x=X$ORF)
+  
+  try(X[X$Gene_X1 == "",]$Gene_X1 <- X[X$Gene_X1 == "",]$OrfRep_X1)
+  try(X[X$Gene_X2 == "",]$Gene_X2 <- X[X$Gene_X2 == "",]$OrfRep_X2)
+  try(X[X$Gene_X3 == "",]$Gene_X3 <- X[X$Gene_X3 == "",]$OrfRep_X3)
+  try(X[X$Gene_X4 == "",]$Gene_X4 <- X[X$Gene_X4 == "",]$OrfRep_X4)
+  
+  X_heatmap <- X[colnames(X) == "ORF" | colnames(X) == "Gene_X1" |
+                   colnames(X) == "Z_Shift_K_X1" | colnames(X) == "Z_lm_K_X1" |
+                   colnames(X) == "Z_Shift_K_X2" | colnames(X) == "Z_lm_K_X2" | 
+                   colnames(X) == "Z_Shift_K_X3" | colnames(X) == "Z_lm_K_X3" |
+                   colnames(X) == "Z_Shift_K_X4" | colnames(X) == "Z_lm_K_X4" |
+                   colnames(X) == "Z_Shift_L_X1" | colnames(X) == "Z_lm_L_X1" |
+                   colnames(X) == "Z_Shift_L_X2" | colnames(X) == "Z_lm_L_X2" |
+                   colnames(X) == "Z_Shift_L_X3" | colnames(X) == "Z_lm_L_X3" |
+                   colnames(X) == "Z_Shift_L_X4" | colnames(X) == "Z_lm_L_X4" ]
+  #Reorder columns
+  X_heatmap <- X_heatmap[,c(18,1,4,5,8,9,12,13,16,17,2,3,6,7,10,11,14,15)]  #Four
+  colnames(X_heatmap) <- gsub(pattern = "X1",replacement = Name1,colnames(X_heatmap))
+  colnames(X_heatmap) <- gsub(pattern = "X2",replacement = Name2,colnames(X_heatmap))
+  colnames(X_heatmap) <- gsub(pattern = "X3",replacement = Name3,colnames(X_heatmap))
+  colnames(X_heatmap) <- gsub(pattern = "X4",replacement = Name4,colnames(X_heatmap))
+  colnames(X_heatmap)[2] <- "Gene"
+}
+
+
+if (length(study_nums) > 4) {
+  X$ORF <- gsub("_1","",x=X$ORF)
+  X$ORF <- gsub("_2","",x=X$ORF)
+  X$ORF <- gsub("_3","",x=X$ORF)
+  X$ORF <- gsub("_4","",x=X$ORF)
+  
+  try(X[X$Gene_X1 == "",]$Gene_X1 <- X[X$Gene_X1 == "",]$OrfRep_X1)
+  try(X[X$Gene_X2 == "",]$Gene_X2 <- X[X$Gene_X2 == "",]$OrfRep_X2)
+  try(X[X$Gene_X3 == "",]$Gene_X3 <- X[X$Gene_X3 == "",]$OrfRep_X3)
+  try(X[X$Gene_X4 == "",]$Gene_X4 <- X[X$Gene_X4 == "",]$OrfRep_X4)
+  try(X[X$Gene_X5 == "",]$Gene_X5 <- X[X$Gene_X5 == "",]$OrfRep_X5)
+  
+  X_heatmap <- X[colnames(X) == "ORF" | colnames(X) == "Gene_X1" |
+                   colnames(X) == "Z_Shift_K_X1" | colnames(X) == "Z_lm_K_X1" |
+                   colnames(X) == "Z_Shift_K_X2" | colnames(X) == "Z_lm_K_X2" | 
+                   colnames(X) == "Z_Shift_K_X3" | colnames(X) == "Z_lm_K_X3" |
+                   colnames(X) == "Z_Shift_K_X4" | colnames(X) == "Z_lm_K_X4" |
+                   colnames(X) == "Z_Shift_K_X5" | colnames(X) == "Z_lm_K_X5" |
+                   colnames(X) == "Z_Shift_L_X1" | colnames(X) == "Z_lm_L_X1" |
+                   colnames(X) == "Z_Shift_L_X2" | colnames(X) == "Z_lm_L_X2" |
+                   colnames(X) == "Z_Shift_L_X3" | colnames(X) == "Z_lm_L_X3" |
+                   colnames(X) == "Z_Shift_L_X4" | colnames(X) == "Z_lm_L_X4" |
+                   colnames(X) == "Z_Shift_L_X5" | colnames(X) == "Z_lm_L_X5"]
+  #Reorder columns
+  X_heatmap <- X_heatmap[,c(22,1,4,5,8,9,12,13,16,17,20,21,2,3,6,7,10,11,14,15,18,19)]
+  colnames(X_heatmap) <- gsub(pattern = "X1",replacement = Name1,colnames(X_heatmap))
+  colnames(X_heatmap) <- gsub(pattern = "X2",replacement = Name2,colnames(X_heatmap))
+  colnames(X_heatmap) <- gsub(pattern = "X3",replacement = Name3,colnames(X_heatmap))
+  colnames(X_heatmap) <- gsub(pattern = "X4",replacement = Name4,colnames(X_heatmap))
+  colnames(X_heatmap) <- gsub(pattern = "X5",replacement = Name5,colnames(X_heatmap))
+  
+  colnames(X_heatmap)[2] <- "Gene"
+}
+
+
+#theme elements for plots
+theme_Publication <- function(base_size=14, base_family="sans") {
+  (theme_foundation(base_size=base_size, base_family=base_family)
+   + theme(plot.title = element_text(face = "bold",
+                                     size = rel(1.2), hjust = 0.5),
+           text = element_text(),
+           panel.background = element_rect(colour = NA),
+           plot.background = element_rect(colour = NA),
+           panel.border = element_rect(colour = NA),
+           axis.title = element_text(face = "bold",size = rel(1)),
+           axis.title.y = element_text(angle=90,vjust =2),
+           axis.title.x = element_text(vjust = -0.2),
+           axis.text = element_text(), 
+           axis.line = element_line(colour="black"),
+           axis.ticks = element_line(),
+           panel.grid.major = element_line(colour="#f0f0f0"),
+           panel.grid.minor = element_blank(),
+           legend.key = element_rect(colour = NA),
+           legend.position = "bottom",
+           legend.direction = "horizontal",
+           legend.key.size= unit(0.2, "cm"),
+           legend.spacing = unit(0, "cm"),
+           legend.title = element_text(face="italic"),
+           plot.margin=unit(c(10,5,5,5),"mm"),
+           strip.background=element_rect(colour="#f0f0f0",fill="#f0f0f0"),
+           strip.text = element_text(face="bold")
+   ))
+  
+}
+
+scale_fill_Publication <- function(...){
+  library(scales)
+  discrete_scale("fill","Publication",manual_pal(values = c("#386cb0","#fdb462","#7fc97f","#ef3b2c","#662506","#a6cee3","#fb9a99","#984ea3","#ffff33")), ...)
+  
+}
+
+scale_colour_Publication <- function(...){
+  discrete_scale("colour","Publication",manual_pal(values = c("#386cb0","#fdb462","#7fc97f","#ef3b2c","#662506","#a6cee3","#fb9a99","#984ea3","#ffff33")), ...)
+  
+}
+
+
+theme_Publication_legend_right <- function(base_size=14, base_family="sans") {
+  (theme_foundation(base_size=base_size, base_family=base_family)
+   + theme(plot.title = element_text(face = "bold",
+                                     size = rel(1.2), hjust = 0.5),
+           text = element_text(),
+           panel.background = element_rect(colour = NA),
+           plot.background = element_rect(colour = NA),
+           panel.border = element_rect(colour = NA),
+           axis.title = element_text(face = "bold",size = rel(1)),
+           axis.title.y = element_text(angle=90,vjust =2),
+           axis.title.x = element_text(vjust = -0.2),
+           axis.text = element_text(), 
+           axis.line = element_line(colour="black"),
+           axis.ticks = element_line(),
+           panel.grid.major = element_line(colour="#f0f0f0"),
+           panel.grid.minor = element_blank(),
+           legend.key = element_rect(colour = NA),
+           legend.position = "right",
+           legend.direction = "vertical",
+           legend.key.size= unit(0.5, "cm"),
+           legend.spacing = unit(0, "cm"),
+           legend.title = element_text(face="italic"),
+           plot.margin=unit(c(10,5,5,5),"mm"),
+           strip.background=element_rect(colour="#f0f0f0",fill="#f0f0f0"),
+           strip.text = element_text(face="bold")
+   ))
+  
+}
+
+scale_fill_Publication <- function(...){
+  discrete_scale("fill","Publication",manual_pal(values = c("#386cb0","#fdb462","#7fc97f","#ef3b2c","#662506","#a6cee3","#fb9a99","#984ea3","#ffff33")), ...)
+  
+}
+
+scale_colour_Publication <- function(...){
+  discrete_scale("colour","Publication",manual_pal(values = c("#386cb0","#fdb462","#7fc97f","#ef3b2c","#662506","#a6cee3","#fb9a99","#984ea3","#ffff33")), ...)
+  
+}
+
+
+Ontology <- get_ontology(file=ontology_file,propagate_relationships = "is_a",extract_tags = "minimal")
+print(Ontology)
+#all ORFs associated with GO term
+GO2ALLORFs <- as.list(org.Sc.sgdGO2ALLORFS)
+
+#Terms is the GO term list jwr moved up to TAABLES
+Terms <- read.delim(file=sgd_terms_tfile,header=FALSE,quote = "",col.names = c("GO_ID","GO_Term","GO_Aspect","GO_Term_Definition"))
+
+
+#BIG LOOP BIG LOOP ------------------------------------------------------
+colormapbreaks <- c(-12,-10,-8,-6,-4,-2,2,4,6,8,10,12)
+for(s in 1:dim(XX3)[1]){
+  #Ontology <- get_ontology(file="Documents/Hartman_Lab/SGD_Downloads/gene_ontology_edit.obo",propagate_relationships = "is_a",extract_tags = "minimal")
+  #Ontology_Everything <- get_ontology(file="Documents/Hartman_Lab/SGD_Downloads/gene_ontology_edit.obo",propagate_relationships = "is_a",extract_tags = "everything")
+  #GO_ID_Arg <- "GO:0006325"
+  GO_ID_Arg_loop <- as.character(XX3[s,1])
+  GOTerm_parent <- get_descendants(Ontology,roots = GO_ID_Arg_loop)
+  #GOTerm_parent <- get_descendants(Ontology,roots = "GO:0006325")
+  #only make plots if parent term has fewer than 500 children
+ 
+  Parent_Size <- length(as.vector(GO2ALLORFs[GO_ID_Arg_loop][[1]]))
+  
+  if(length(GOTerm_parent) > 100){
+    next()
+  }
+  
+  Parent_Size <- length(as.vector(GO2ALLORFs[GO_ID_Arg_loop][[1]]))
+  if(Parent_Size < 2){
+    next()
+  }
+  if(Parent_Size > 2000){
+    pdf(file=paste(output_dir,XX3[s,2],".pdf",sep=""),width = 12, height = 45, onefile = TRUE)
+    for(i in 1:length(GOTerm_parent)){
+      GO_Term <- GOTerm_parent[i]
+      GO_Term_Num <- as.integer(str_split_fixed(as.character(GO_Term),"\\:",2)[,2])
+      GO_Term_Name <- as.character(Terms[Terms$GO_ID == GO_Term_Num,]$GO_Term)
+      #Genes_Annotated_to_Term <- Gene_Association[Gene_Association$GO_ID == GO_Term,]
+      All_Genes_Annotated_to_Term <- as.vector(GO2ALLORFs[GO_Term][[1]])
+      Genes_Annotated_to_Term <- X_heatmap[X_heatmap$ORF %in% All_Genes_Annotated_to_Term,]
+      X0 <- as.matrix(Genes_Annotated_to_Term[,3:dim(Genes_Annotated_to_Term)[2]])
+      if(dim(Genes_Annotated_to_Term)[1] > 2){
+        try(heatmap.2(x=X0,
+                      Rowv=TRUE, Colv=NA, distfun = dist, hclustfun = hclust,
+                      dendrogram = "row", cexCol = 0.7, cexRow = 0.5, scale = "none",
+                      breaks=colormapbreaks, symbreaks=FALSE, colsep = c(2,4,6), sepcolor= "white", offsetCol = 0.1,
+                      ylab = "Gene",
+                      cellnote = round(X0,digits=0), notecex = 0.5, key=TRUE,
+                      keysize=0.5, trace="none", density.info=c("none"), margins=c(10,8),
+                      na.color="red", col=brewer.pal(11,"PuOr"),
+                      main=GO_Term_Name, 
+                      #ColSideColors=ev_repeat,
+                      labRow=as.character(Genes_Annotated_to_Term$Gene)))
+      }
+    }
+    dev.off()
+  }
+  
+  if(Parent_Size >= 1000 && Parent_Size <= 2000){
+    pdf(file=paste(output_dir,XX3[s,2],".pdf",sep=""),width = 12, height = 35, onefile = TRUE)
+    for(i in 1:length(GOTerm_parent)){
+      GO_Term <- GOTerm_parent[i]
+      GO_Term_Num <- as.integer(str_split_fixed(as.character(GO_Term),"\\:",2)[,2])
+      GO_Term_Name <- as.character(Terms[Terms$GO_ID == GO_Term_Num,]$GO_Term)
+      #Genes_Annotated_to_Term <- Gene_Association[Gene_Association$GO_ID == GO_Term,]
+      All_Genes_Annotated_to_Term <- as.vector(GO2ALLORFs[GO_Term][[1]])
+      Genes_Annotated_to_Term <- X_heatmap[X_heatmap$ORF %in% All_Genes_Annotated_to_Term,]
+      X0 <- as.matrix(Genes_Annotated_to_Term[,3:dim(Genes_Annotated_to_Term)[2]])
+      if(dim(Genes_Annotated_to_Term)[1] > 2){
+        try(heatmap.2(x=X0,
+                      Rowv=TRUE, Colv=NA, distfun = dist, hclustfun = hclust,
+                      dendrogram = "row", cexCol = 0.7, cexRow = 0.6, scale = "none",
+                      breaks=colormapbreaks, symbreaks=FALSE, colsep = c(2,4,6), sepcolor= "white", offsetCol = 0.1,
+                      ylab = "Gene",
+                      cellnote = round(X0,digits=0), notecex = 0.5, key=TRUE,
+                      keysize=0.5, trace="none", density.info=c("none"), margins=c(10,8),
+                      na.color="red", col=brewer.pal(11,"PuOr"),
+                      main=GO_Term_Name, 
+                      #ColSideColors=ev_repeat,
+                      labRow=as.character(Genes_Annotated_to_Term$Gene)))
+      }
+    }
+    dev.off()
+  }
+  if(Parent_Size >= 500 && Parent_Size <= 1000){
+    pdf(file=paste(output_dir,XX3[s,2],".pdf",sep=""),width = 12, height = 30, onefile = TRUE)
+    for(i in 1:length(GOTerm_parent)){
+      GO_Term <- GOTerm_parent[i]
+      GO_Term_Num <- as.integer(str_split_fixed(as.character(GO_Term),"\\:",2)[,2])
+      GO_Term_Name <- as.character(Terms[Terms$GO_ID == GO_Term_Num,]$GO_Term)
+      #Genes_Annotated_to_Term <- Gene_Association[Gene_Association$GO_ID == GO_Term,]
+      All_Genes_Annotated_to_Term <- as.vector(GO2ALLORFs[GO_Term][[1]])
+      Genes_Annotated_to_Term <- X_heatmap[X_heatmap$ORF %in% All_Genes_Annotated_to_Term,]
+      X0 <- as.matrix(Genes_Annotated_to_Term[,3:dim(Genes_Annotated_to_Term)[2]])
+      if(dim(Genes_Annotated_to_Term)[1] > 2){
+        try(heatmap.2(x=X0,
+                      Rowv=TRUE, Colv=NA, distfun = dist, hclustfun = hclust,
+                      dendrogram = "row", cexCol = 0.7, cexRow = 0.6, scale = "none",
+                      breaks=colormapbreaks, symbreaks=FALSE, colsep = c(2,4,6), sepcolor= "white", offsetCol = 0.1,
+                      ylab = "Gene",
+                      cellnote = round(X0,digits=0), notecex = 0.5, key=TRUE,
+                      keysize=0.5, trace="none", density.info=c("none"), margins=c(10,8),
+                      na.color="red", col=brewer.pal(11,"PuOr"),
+                      main=GO_Term_Name, 
+                      #ColSideColors=ev_repeat,
+                      labRow=as.character(Genes_Annotated_to_Term$Gene)))
+      }
+    }
+    dev.off()
+  }
+  if(Parent_Size >= 200 && Parent_Size <= 500){
+    pdf(file=paste(output_dir,XX3[s,2],".pdf",sep=""),width = 12, height = 25, onefile = TRUE)
+    for(i in 1:length(GOTerm_parent)){
+      GO_Term <- GOTerm_parent[i]
+      GO_Term_Num <- as.integer(str_split_fixed(as.character(GO_Term),"\\:",2)[,2])
+      GO_Term_Name <- as.character(Terms[Terms$GO_ID == GO_Term_Num,]$GO_Term)
+      #Genes_Annotated_to_Term <- Gene_Association[Gene_Association$GO_ID == GO_Term,]
+      All_Genes_Annotated_to_Term <- as.vector(GO2ALLORFs[GO_Term][[1]])
+      Genes_Annotated_to_Term <- X_heatmap[X_heatmap$ORF %in% All_Genes_Annotated_to_Term,]
+      X0 <- as.matrix(Genes_Annotated_to_Term[,3:dim(Genes_Annotated_to_Term)[2]])
+      if(dim(Genes_Annotated_to_Term)[1] > 2){
+        try(heatmap.2(x=X0,
+                      Rowv=TRUE, Colv=NA, distfun = dist, hclustfun = hclust,
+                      dendrogram = "row", cexCol = 0.7, cexRow = 0.7, scale = "none",
+                      breaks=colormapbreaks, symbreaks=FALSE, colsep = c(2,4,6), sepcolor= "white", offsetCol = 0.1,
+                      ylab = "Gene",
+                      cellnote = round(X0,digits=0), notecex = 0.5, key=TRUE,
+                      keysize=0.5, trace="none", density.info=c("none"), margins=c(10,8),
+                      na.color="red", col=brewer.pal(11,"PuOr"),
+                      main=GO_Term_Name, 
+                      #ColSideColors=ev_repeat,
+                      labRow=as.character(Genes_Annotated_to_Term$Gene)))
+      }
+    }
+    dev.off()
+  }
+  if(Parent_Size >= 100 && Parent_Size <= 200){
+    pdf(file=paste(output_dir,XX3[s,2],".pdf",sep=""),width = 12, height = 20, onefile = TRUE)
+    for(i in 1:length(GOTerm_parent)){
+      GO_Term <- GOTerm_parent[i]
+      GO_Term_Num <- as.integer(str_split_fixed(as.character(GO_Term),"\\:",2)[,2])
+      GO_Term_Name <- as.character(Terms[Terms$GO_ID == GO_Term_Num,]$GO_Term)
+      #Genes_Annotated_to_Term <- Gene_Association[Gene_Association$GO_ID == GO_Term,]
+      All_Genes_Annotated_to_Term <- as.vector(GO2ALLORFs[GO_Term][[1]])
+      Genes_Annotated_to_Term <- X_heatmap[X_heatmap$ORF %in% All_Genes_Annotated_to_Term,]
+      X0 <- as.matrix(Genes_Annotated_to_Term[,3:dim(Genes_Annotated_to_Term)[2]])
+      if(dim(Genes_Annotated_to_Term)[1] > 2){
+        try(heatmap.2(x=X0,
+                      Rowv=TRUE, Colv=NA, distfun = dist, hclustfun = hclust,
+                      dendrogram = "row", cexCol = 0.7, cexRow = 0.7, scale = "none",
+                      breaks=colormapbreaks, symbreaks=FALSE, colsep = c(2,4,6), sepcolor= "white", offsetCol = 0.1,
+                      ylab = "Gene",
+                      cellnote = round(X0,digits=0), notecex = 0.5, key=TRUE,
+                      keysize=0.5, trace="none", density.info=c("none"), margins=c(10,8),
+                      na.color="red", col=brewer.pal(11,"PuOr"),
+                      main=GO_Term_Name, 
+                      #ColSideColors=ev_repeat,
+                      labRow=as.character(Genes_Annotated_to_Term$Gene)))
+      }
+    }
+    dev.off()
+  }
+  if(Parent_Size >= 60 && Parent_Size <= 100){
+    pdf(file=paste(output_dir,XX3[s,2],".pdf",sep=""),width = 12, height = 15, onefile = TRUE)
+    for(i in 1:length(GOTerm_parent)){
+      GO_Term <- GOTerm_parent[i]
+      GO_Term_Num <- as.integer(str_split_fixed(as.character(GO_Term),"\\:",2)[,2])
+      GO_Term_Name <- as.character(Terms[Terms$GO_ID == GO_Term_Num,]$GO_Term)
+      #Genes_Annotated_to_Term <- Gene_Association[Gene_Association$GO_ID == GO_Term,]
+      All_Genes_Annotated_to_Term <- as.vector(GO2ALLORFs[GO_Term][[1]])
+      Genes_Annotated_to_Term <- X_heatmap[X_heatmap$ORF %in% All_Genes_Annotated_to_Term,]
+      X0 <- as.matrix(Genes_Annotated_to_Term[,3:dim(Genes_Annotated_to_Term)[2]])
+      if(dim(Genes_Annotated_to_Term)[1] > 2){
+        try(heatmap.2(x=X0,
+                      Rowv=TRUE, Colv=NA, distfun = dist, hclustfun = hclust,
+                      dendrogram = "row", cexCol = 0.7, cexRow = 0.7, scale = "none",
+                      breaks=colormapbreaks, symbreaks=FALSE, colsep = c(2,4,6), sepcolor= "white", offsetCol = 0.1,
+                      ylab = "Gene",
+                      cellnote = round(X0,digits=0), notecex = 0.5, key=TRUE,
+                      keysize=0.5, trace="none", density.info=c("none"), margins=c(10,8),
+                      na.color="red", col=brewer.pal(11,"PuOr"),
+                      main=GO_Term_Name, 
+                      #ColSideColors=ev_repeat,
+                      labRow=as.character(Genes_Annotated_to_Term$Gene)))
+      }
+    }
+    dev.off()
+  }
+  if(Parent_Size >= 30 && Parent_Size <= 60){
+    pdf(file=paste(output_dir,XX3[s,2],".pdf",sep=""),width = 12, height = 10, onefile = TRUE)
+    for(i in 1:length(GOTerm_parent)){
+      GO_Term <- GOTerm_parent[i]
+      GO_Term_Num <- as.integer(str_split_fixed(as.character(GO_Term),"\\:",2)[,2])
+      GO_Term_Name <- as.character(Terms[Terms$GO_ID == GO_Term_Num,]$GO_Term)
+      #Genes_Annotated_to_Term <- Gene_Association[Gene_Association$GO_ID == GO_Term,]
+      All_Genes_Annotated_to_Term <- as.vector(GO2ALLORFs[GO_Term][[1]])
+      Genes_Annotated_to_Term <- X_heatmap[X_heatmap$ORF %in% All_Genes_Annotated_to_Term,]
+      X0 <- as.matrix(Genes_Annotated_to_Term[,3:dim(Genes_Annotated_to_Term)[2]])
+      if(dim(Genes_Annotated_to_Term)[1] > 2){
+        try(heatmap.2(x=X0,
+                      Rowv=TRUE, Colv=NA, distfun = dist, hclustfun = hclust,
+                      dendrogram = "row", cexCol = 0.7, cexRow = 0.7, scale = "none",
+                      breaks=colormapbreaks, symbreaks=FALSE, colsep = c(2,4,6), sepcolor= "white", offsetCol = 0.1,
+                      ylab = "Gene",
+                      cellnote = round(X0,digits=0), notecex = 0.5, key=TRUE,
+                      keysize=0.5, trace="none", density.info=c("none"), margins=c(10,8),
+                      na.color="red", col=brewer.pal(11,"PuOr"),
+                      main=GO_Term_Name, 
+                      #ColSideColors=ev_repeat,
+                      labRow=as.character(Genes_Annotated_to_Term$Gene)))
+      }
+      if(dim(Genes_Annotated_to_Term)[1] <= 2 && dim(Genes_Annotated_to_Term)[1] > 0){
+        try(heatmap.2(x=X0,
+                      Rowv=TRUE, Colv=NA, distfun = dist, hclustfun = hclust,
+                      dendrogram = "none", cexCol = 0.7, cexRow = 0.7, scale = "none",
+                      breaks=colormapbreaks, symbreaks=FALSE, colsep = c(2,4,6), sepcolor= "white", offsetCol = 0.1,
+                      ylab = "Gene",
+                      cellnote = round(X0,digits=0), notecex = 0.5, key=TRUE,
+                      keysize=0.5, trace="none", density.info=c("none"), margins=c(10,8),
+                      na.color="red", col=brewer.pal(11,"PuOr"),
+                      main=GO_Term_Name, 
+                      #ColSideColors=ev_repeat,
+                      labRow=as.character(Genes_Annotated_to_Term$Gene)))
+      }
+    }
+    
+    dev.off()
+  }
+  if(Parent_Size >= 3 && Parent_Size <= 30){
+    pdf(file=paste(output_dir,XX3[s,2],".pdf",sep=""),width = 12, height = 7, onefile = TRUE)
+    for(i in 1:length(GOTerm_parent)){
+      GO_Term <- GOTerm_parent[i]
+      GO_Term_Num <- as.integer(str_split_fixed(as.character(GO_Term),"\\:",2)[,2])
+      GO_Term_Name <- as.character(Terms[Terms$GO_ID == GO_Term_Num,]$GO_Term)
+      #Genes_Annotated_to_Term <- Gene_Association[Gene_Association$GO_ID == GO_Term,]
+      All_Genes_Annotated_to_Term <- as.vector(GO2ALLORFs[GO_Term][[1]])
+      Genes_Annotated_to_Term <- X_heatmap[X_heatmap$ORF %in% All_Genes_Annotated_to_Term,]
+      X0 <- as.matrix(Genes_Annotated_to_Term[,3:dim(Genes_Annotated_to_Term)[2]])
+      if(dim(Genes_Annotated_to_Term)[1] > 2){
+        try(heatmap.2(x=X0,
+                      Rowv=TRUE, Colv=NA, distfun = dist, hclustfun = hclust,
+                      dendrogram = "row", cexCol = 0.7, cexRow = 0.7, scale = "none",
+                      breaks=colormapbreaks, symbreaks=FALSE, colsep = c(2,4,6), sepcolor= "white", offsetCol = 0.1,
+                      ylab = "Gene",
+                      cellnote = round(X0,digits=0), notecex = 0.5, key=TRUE,
+                      keysize=0.5, trace="none", density.info=c("none"), margins=c(10,8),
+                      na.color="red", col=brewer.pal(11,"PuOr"),
+                      main=GO_Term_Name, 
+                      #ColSideColors=ev_repeat,
+                      labRow=as.character(Genes_Annotated_to_Term$Gene)))
+      }
+      if(dim(Genes_Annotated_to_Term)[1] <= 2 && dim(Genes_Annotated_to_Term)[1] > 0){
+        try(heatmap.2(x=X0,
+                      Rowv=TRUE, Colv=NA, distfun = dist, hclustfun = hclust,
+                      dendrogram = "none", cexCol = 0.7, cexRow = 0.7, scale = "none",
+                      breaks=colormapbreaks, symbreaks=FALSE, colsep = c(2,4,6), sepcolor= "white", offsetCol = 0.1,
+                      ylab = "Gene",
+                      cellnote = round(X0,digits=0), notecex = 0.5, key=TRUE,
+                      keysize=0.5, trace="none", density.info=c("none"), margins=c(10,8),
+                      na.color="red", col=brewer.pal(11,"PuOr"),
+                      main=GO_Term_Name, 
+                      #ColSideColors=ev_repeat,
+                      labRow=as.character(Genes_Annotated_to_Term$Gene)))
+      }
+    }
+    dev.off()
+  }
+  if(Parent_Size == 2){
+    pdf(file=paste(output_dir,XX3[s,2],".pdf",sep=""),width = 12, height = 7, onefile = TRUE)
+    for(i in 1:length(GOTerm_parent)){
+      GO_Term <- GOTerm_parent[i]
+      GO_Term_Num <- as.integer(str_split_fixed(as.character(GO_Term),"\\:",2)[,2])
+      GO_Term_Name <- as.character(Terms[Terms$GO_ID == GO_Term_Num,]$GO_Term)
+      #Genes_Annotated_to_Term <- Gene_Association[Gene_Association$GO_ID == GO_Term,]
+      All_Genes_Annotated_to_Term <- as.vector(GO2ALLORFs[GO_Term][[1]])
+      Genes_Annotated_to_Term <- X_heatmap[X_heatmap$ORF %in% All_Genes_Annotated_to_Term,]
+      X0 <- as.matrix(Genes_Annotated_to_Term[,3:dim(Genes_Annotated_to_Term)[2]])
+      if(dim(Genes_Annotated_to_Term)[1] > 2){
+        try(heatmap.2(x=X0,
+                      Rowv=TRUE, Colv=NA, distfun = dist, hclustfun = hclust,
+                      dendrogram = "row", cexCol = 0.7, cexRow = 0.7, scale = "none",
+                      breaks=colormapbreaks, symbreaks=FALSE, colsep = c(2,4,6), sepcolor= "white", offsetCol = 0.1,
+                      ylab = "Gene",
+                      cellnote = round(X0,digits=0), notecex = 0.5, key=TRUE,
+                      keysize=0.5, trace="none", density.info=c("none"), margins=c(10,8),
+                      na.color="red", col=brewer.pal(11,"PuOr"),
+                      main=GO_Term_Name, 
+                      #ColSideColors=ev_repeat,
+                      labRow=as.character(Genes_Annotated_to_Term$Gene)))
+      }
+      if(dim(Genes_Annotated_to_Term)[1] <= 2 && dim(Genes_Annotated_to_Term)[1] > 0){
+        try(heatmap.2(x=X0,
+                      Rowv=TRUE, Colv=NA, distfun = dist, hclustfun = hclust,
+                      dendrogram = "none", cexCol = 0.7, cexRow = 0.7, scale = "none",
+                      breaks=colormapbreaks, symbreaks=FALSE, colsep = c(2,4,6), sepcolor= "white", offsetCol = 0.1,
+                      ylab = "Gene",
+                      cellnote = round(X0,digits=0), notecex = 0.5, key=TRUE,
+                      keysize=0.5, trace="none", density.info=c("none"), margins=c(10,8),
+                      na.color="red", col=brewer.pal(11,"PuOr"),
+                      main=GO_Term_Name, 
+                      #ColSideColors=ev_repeat,
+                      labRow=as.character(Genes_Annotated_to_Term$Gene)))
+      }
+    }
+    dev.off()
+  }
+}

workflow/apps/r/addShiftVals.R

@@ -0,0 +1,91 @@
+#!/usr/bin/env Rscript
+# This script will add the shift data to the finalTable.csv file
+#
+# May want to reorder columns in excel before making heatmaps - otherwise all the shift data will be plotted next to each other.
+
+library(plyr)
+library(dplyr)
+library(sos)
+
+args=commandArgs(TRUE)
+
+if (length(args) > 1) {
+  finalTable <- args[1]
+} else {
+  finalTable <- "REMcRdy_lm_only.csv-finalTable.csv"  # for legacy workflow
+}
+
+if (length(args) > 2) {
+  shiftFile <- args[2]
+} else {
+  shiftFile <- "Shift_only.csv"  # for legacy workflow
+}
+
+if (length(args) > 3) {
+  studyInfo <- args[3]
+} else {
+  studyInfo <- "../Code/StudyInfo.csv" # for legacy workflow
+}
+
+if (length(args) > 4) {
+  output <- args[4]
+} else {
+  output<- "REMcHeatmaps/REMcWithShift.csv" # for legacy workflow
+}
+
+
+# Read in the REMc finalTable data
+X = data.frame(read.csv(file=finalTable,header=TRUE,stringsAsFactors = FALSE))
+# Read in the shift data From ../JoinInteractions
+Y = data.frame(read.csv(file=shiftFile,header=TRUE,stringsAsFactors = FALSE))
+Labels <- read.delim(studyInfo,skip=0,as.is=T,row.names=1,strip.white=TRUE)
+
+# Determine the number of cols - needed to create the correct number of new cols
+Xcolnum <- length(X[1,])
+ADDnum <- Xcolnum + length(Y[1,]) - 2
+
+# Create new columns filled with NAs to be filled with data
+Xtemp= X
+Xtemp[,(Xcolnum+1):ADDnum] <- NA
+
+# Match the orf names in each row to a orf name in the shift data file and then add the shift data to the finalTable file
+shiftTbl <-as.data.frame(matrix(nrow=1,ncol=length(Y)-2)) #the df shiftTbl must be initialized before for loop
+
+for(i in 1:length(X[,1])){
+  Shiftrownum = match(X[i,2],Y[,1])
+  shiftTbl[i,]= Y[Shiftrownum,3:length(Y[1,])]
+  Xtemp[i,(Xcolnum+1):ADDnum] <- Y[Shiftrownum,3:length(Y[1,])]
+}
+headerX= colnames(Xtemp)
+headerY= colnames(Y)
+shfHdr= headerY[3:length(headerY)]
+combTbl<- X[,1:3]
+lmTbl= select(Xtemp,  contains('Z_lm'))  #X[,(4:Xcolnum-2)]
+shiftTbl<- select(Xtemp,  contains('V'))
+clustTbl<- select(Xtemp, contains('cluster.'))
+
+# Give the new column names the same names as in the shift file
+Xcols = colnames(X)
+Ycols = colnames(Y)[3:length(Y[1,])]
+newCols = c(Xcols[1:Xcolnum],Ycols)
+
+# Reorder columns for generating heatmaps
+combI= combTbl  #Starting Template orf, Genename columns
+headersRemc<-newCols  #colnames(X)
+newHeaders= newCols[1:3]
+lmHdr= colnames(lmTbl)   #newCols[4:(length(Xcols)-2)]
+clstHdr= colnames(clustTbl)  #select(newCols, contains('cluster.'))  #newCols[3+length(lmHdr):2]
+
+intLvHdr= vector()
+#Reorder columns to produce an interleaved set of Z_lm and Shift data for all the cpps.
+for(i in 1:(length(shiftTbl[1,]))){
+  combI=cbind.data.frame(combI, shiftTbl[i])
+  combI=cbind.data.frame(combI, lmTbl[i])
+  intLvHdrx= c(shfHdr[i],lmHdr[i] )
+  intLvHdr= c(intLvHdr,intLvHdrx)
+}
+
+combIHdr= c(colnames(combTbl),intLvHdr,clstHdr)
+combI=cbind.data.frame(combI, clustTbl)
+colnames(combI)= combIHdr
+write.csv(combI,file=output, row.names=FALSE)

workflow/apps/r/createHeatMaps.R

@@ -0,0 +1,288 @@
+#!/usr/bin/env Rscript
+# This script will make heatmaps for the REMc analysis
+# need to give the input "finalTable.csv" file after running REMc generated by eclipse
+
+library(RColorBrewer)
+library(gplots)
+
+args <- commandArgs(TRUE)
+
+# Set output dir
+if (length(args) > 1) {
+  input_finalTable <- args[1]
+} else {
+  input_finalTable <- "/REMcHeatmaps/REMcWithShift.csv" # for legacy workflow
+}
+
+if (length(args) > 2) {
+  outDir <- args[2]
+} else {
+  outDir <- "/REMcHeatmaps/REMcWithShift.csv" # for legacy workflow
+}
+
+hmapfile <- data.frame(read.csv(file=input_finalTable,header=TRUE,sep=",",stringsAsFactors = FALSE))
+# set NAs to NA
+hmapfile[hmapfile == -100] <- NA
+hmapfile[hmapfile == 100] <- NA
+hmapfile[hmapfile == 0.001] <- NA
+hmapfile[hmapfile == -0.001] <- NA
+
+# select the number of rows based on the number of genes
+num_total_genes <- length(hmapfile[,1])
+
+# Break out the cluster names so each part of the cluster origin can be accessed
+# line below removed because it adds to many genes to clusters when going past 1-0-10 since it cannot differentiate between 1-0-1 and 1-0-10 when using grepl.
+# hmapfile$cluster.origin = gsub(" ","",x=hmapfile$cluster.origin)
+
+hmapfile$cluster.origin = gsub(";"," ;",x=hmapfile$cluster.origin)
+hmapfile$cluster.origin = strsplit(hmapfile$cluster.origin,';')
+#use tail(x,n) for accessing the outward most cluster
+
+clust_rounds <- 0
+for(i in 1:num_total_genes){
+  if(length(hmapfile$cluster.origin[[i]]) > clust_rounds){
+    clust_rounds <- length(hmapfile$cluster.origin[[i]])
+  }
+}
+
+unique_clusts <- unique(hmapfile$cluster.origin[1:num_total_genes])
+unique_clusts <- unique_clusts[unique_clusts != " "]
+
+# Select only the unique cluster names
+unique_clusts <- sort(unique(unlist(unique_clusts,use.names= FALSE)),decreasing=FALSE)
+num_unique_clusts <- length(unique_clusts)
+
+# Base the color key on a statistical analysis of the L and K data
+# need to create "breaks" to set the color key, need to have 12 different breaks (for 11 colors)
+# scale() will calculate the mean and standard deviation of the entire vector, then "scale" each element by those values by subtracting the mean and dividing by the sd.
+# hmapfile[,4:(length(hmapfile[1,]) - 2)] <- scale(hmapfile[,4:(length(hmapfile[1,]) - 2)])
+# change so that the L data is multiplied to be on the same scale as the K data
+
+KEY_MIN <- 0
+KEY_MAX <- 0
+K_MIN <- 0
+L_MAX <- 0
+KcolumnValues <- vector()
+LcolumnValues <- vector()
+
+for(i in 4:(length(hmapfile[1,]) - 2)){
+  if(grepl("_Z_lm_K",colnames(hmapfile)[i],fixed=TRUE) == TRUE){
+    KcolumnValues <- append(KcolumnValues,i)
+  }
+  if(grepl("_Z_lm_L",colnames(hmapfile)[i],fixed=TRUE) == TRUE){
+    LcolumnValues <- append(LcolumnValues,i)
+  }
+}
+
+# L_MAX <- quantile(hmapfile[,LcolumnValues],c(0,.01,.5,.99,1),na.rm=TRUE)[4]
+# K_MIN <- quantile(hmapfile[,KcolumnValues],c(0,.01,.5,.99,1),na.rm=TRUE)[2]
+# L_MAX <- quantile(hmapfile[,LcolumnValues],c(0,.01,.5,.975,1),na.rm=TRUE)[4]
+# K_MIN <- quantile(hmapfile[,KcolumnValues],c(0,.025,.5,.99,1),na.rm=TRUE)[2]
+
+# Z scores are
+L_MAX <- 12
+K_MIN <- -12
+
+# L_Multiplier <- as.numeric(abs(K_MIN/L_MAX))
+# hmapfile[,LcolumnValues] <- hmapfile[,LcolumnValues] * L_Multiplier
+
+# if(grepl("SHIFT",colnames(hmapfile)[4],fixed=TRUE) == TRUE){
+#  print("FOUND SHIFT VALUES")
+#  hmapfile[,(LcolumnValues - 1)] <- hmapfile[,(LcolumnValues-1)] * L_Multiplier
+# }
+
+# KEY_MAX <- as.numeric(L_MAX * L_Multiplier)
+# KEY_MIN <- as.numeric(K_MIN)
+
+KEY_MAX <- as.numeric(L_MAX)
+KEY_MIN <- as.numeric(K_MIN)
+
+print(KEY_MIN)
+print(L_MAX)
+# print(L_Multiplier)
+
+colormapbreaks <- c(KEY_MIN,KEY_MIN*(5/6),KEY_MIN*(4/6),KEY_MIN*(3/6),KEY_MIN*(2/6),KEY_MIN*(1/6),KEY_MAX*(1/6),KEY_MAX*(2/6),KEY_MAX*(3/6),KEY_MAX*(4/6),KEY_MAX*(5/6),KEY_MAX)
+# print(colormapbreaks)
+
+# Probably should give a way to detect shift in case that is is not in the first row... (maybe just grepl for the whole column name?)
+# However since also using this to amend the first part. Could possibly identify all the ones that contain the word shift and then create an object containing just those numbers
+# then could just use these values and create spaces only between interaction values - possibly could get rid of redundant shift values if we don't want to view these
+# could we pool all the shift data/average it?
+if(grepl("Shift",colnames(hmapfile)[4],fixed=TRUE) == TRUE){
+  even_columns <- seq(from= 2, to= (length(hmapfile[1,]) - 7),by=2)
+  #ev_repeat = rep("white",length(even_columns))
+  #ev_repeat = rep("red",(length(hmapfile[1,]) - 5))
+  #middle_col <- (length(hmapfile[1,]) - 5)/2
+  #ev_repeat[(middle_col/2)] <- "black"
+  #print(ev_repeat)
+}
+
+if(grepl("Shift",colnames(hmapfile)[4],fixed=TRUE) == FALSE){
+  even_columns <- seq(from= 2, to= (length(hmapfile[1,]) - 7),by=1)
+  print("NO SHIFT VALS FOUND")
+}
+
+#FOR THIS SCRIPT ONLY (rap tem hu script)
+#even_columns <- c(2,5,7,10,12,15,17)
+
+#m <- 0
+colnames_edit <- as.character(colnames(hmapfile)[4:(length(hmapfile[1,]) - 2)])
+#print(colnames_edit)
+for(i in 1:length(colnames_edit)){
+  if(grepl("Shift",colnames_edit[i],fixed=TRUE) == TRUE){
+    colnames_edit[i] <- ""
+    colnames_edit[i+1] <- gsub(pattern = "_Z_lm_",replacement = " ",x = colnames_edit[i+1])
+    try(colnames_edit[i+1] <- gsub(pattern = "_",replacement = " ",x = colnames_edit[i+1]))
+    
+    # INT_store <- strsplit(colnames_edit[i+1], "Z_lm")
+    # print(length(unlist(INT_store)))
+    # if(length(unlist(INT_store)) == 4){
+    #   colnames_edit[i+1] <- paste(unlist(INT_store)[1],unlist(INT_store)[2],unlist(INT_store)[3],sep=" ")
+    # }
+    # if(length(unlist(INT_store)) == 3){
+    # 
+    #   colnames_edit[i+1] <- paste(unlist(INT_store)[1],unlist(INT_store)[2],sep=" ")
+    # }
+    # if(length(unlist(INT_store)) == 5){
+    #   colnames_edit[i+1] <- paste(unlist(INT_store)[1],unlist(INT_store)[2],unlist(INT_store)[3],unlist(INT_store)[4],sep=" ")
+    # }
+    # if(length(unlist(INT_store)) == 6){
+    #   colnames_edit[i+1] <- paste(unlist(INT_store)[1],unlist(INT_store)[2],unlist(INT_store)[6],sep=" ")
+    # }
+
+  }
+}
+print(colnames_edit)
+#break()
+#colnames_edit[5] <- "TEM HLEG K"
+#colnames_edit[10] <- "TEM HL K"
+#colnames_edit[15] <- "TEM HLEG L"
+#colnames_edit[20] <- "TEM HL L"
+
+
+# Create the heatmaps
+for(i in 1:num_unique_clusts){
+  cluster <- unique_clusts[i]
+  cluster_data <- subset(hmapfile,grepl(cluster,cluster.origin))
+  cluster_length <- length(cluster_data[,1])
+  if(cluster_length != 1){
+    X0 <- as.matrix(cluster_data[,4:(length(hmapfile[1,]) - 2)])
+    if(cluster_length >= 2001){
+      mypath = file.path(outDir,paste("cluster_",gsub(" ","",cluster), ".pdf",sep=""))
+      pdf(file=mypath,height=20,width=15)
+      heatmap.2(x=X0,
+                Rowv=TRUE, Colv=NA, distfun = dist, hclustfun = hclust,
+                dendrogram = "row", cexCol = 0.8, cexRow = 0.1, scale = "none",
+                breaks=colormapbreaks, symbreaks=FALSE, colsep = even_columns, sepcolor= "white", offsetCol = 0.1,
+                #zlim=c(-132,132), 
+                xlab = "Type of Media", ylab = "Gene Name",
+                #cellnote = round(X0,digits=0), notecex = 0.1, key=TRUE,
+                keysize=0.7, trace="none", density.info=c("none"), margins=c(10, 8),
+                na.color="red", col=brewer.pal(11,"PuOr"),
+                main=cluster, 
+                #ColSideColors=ev_repeat,
+                labRow=as.character(cluster_data$Gene), labCol=colnames_edit)
+      #abline(v=0.5467,col="black")
+      dev.off()
+    }
+    if(cluster_length >= 201 && cluster_length <= 2000){
+      mypath = file.path(outDir,paste("cluster_",gsub(" ","",cluster), ".pdf",sep=""))
+      pdf(file=mypath,height=15,width=12)
+      heatmap.2(x=X0,
+                Rowv=TRUE, Colv=NA, distfun = dist, hclustfun = hclust,
+                dendrogram = "row", cexCol = 0.8, cexRow = 0.1, scale = "none",
+                breaks=colormapbreaks, symbreaks=FALSE, colsep = even_columns, sepcolor="white", offsetCol = 0.1,
+                #zlim=c(-132,132), 
+                xlab = "Type of Media", ylab = "Gene Name",
+                cellnote = round(X0,digits=0), notecex = 0.1, key=TRUE,
+                keysize=0.7, trace="none", density.info=c("none"), margins=c(10, 8),
+                na.color="red", col=brewer.pal(11,"PuOr"),
+                main=cluster,
+                labRow=as.character(cluster_data$Gene), labCol=colnames_edit)
+      #abline(v=0.5316,col="black")
+      dev.off()
+    }
+    if(cluster_length >= 150 && cluster_length <= 200){
+      mypath = file.path(outDir,paste("cluster_",gsub(" ","",cluster), ".pdf",sep=""))
+      pdf(file=mypath,height=12,width=12)
+      heatmap.2(x=X0,
+                Rowv=TRUE, Colv=NA, distfun = dist, hclustfun = hclust,
+                dendrogram = "row", cexCol = 0.8, cexRow = 0.1, scale = "none",
+                breaks=colormapbreaks, symbreaks=FALSE, colsep = even_columns, sepcolor="white", offsetCol = 0.1,
+                #zlim=c(-132,132), 
+                xlab = "Type of Media", ylab = "Gene Name",
+                cellnote = round(X0,digits=0), notecex = 0.2, key=TRUE,
+                keysize=1, trace="none", density.info=c("none"), margins=c(10, 8),
+                na.color="red", col=brewer.pal(11,"PuOr"),
+                main=cluster,
+                labRow=as.character(cluster_data$Gene), labCol=colnames_edit)
+      dev.off()
+    }
+    if(cluster_length >= 101 && cluster_length <= 149){
+      mypath = file.path(outDir,paste("cluster_",gsub(" ","",cluster), ".pdf",sep=""))
+      pdf(file=mypath,mypath,height=12,width=12)
+      heatmap.2(x=X0,
+                Rowv=TRUE, Colv=NA, distfun = dist, hclustfun = hclust,
+                dendrogram = "row", cexCol = 0.8, cexRow = 0.2, scale = "none",
+                breaks=colormapbreaks, symbreaks=FALSE, colsep = even_columns, sepcolor="white", offsetCol = 0.1,
+                #zlim=c(-132,132), 
+                xlab = "Type of Media", ylab = "Gene Name",
+                cellnote = round(X0,digits=0), notecex = 0.3, key=TRUE,
+                keysize=1, trace="none", density.info=c("none"), margins=c(10, 8),
+                na.color="red", col=brewer.pal(11,"PuOr"),
+                main=cluster,
+                labRow=as.character(cluster_data$Gene), labCol=colnames_edit)
+      dev.off()
+    }
+    if(cluster_length >= 60 && cluster_length <= 100){
+      mypath = file.path(outDir,paste("cluster_",gsub(" ","",cluster), ".pdf",sep=""))
+      pdf(file=mypath,height=12,width=12)
+      heatmap.2(x=X0,
+                Rowv=TRUE, Colv=NA, distfun = dist, hclustfun = hclust,
+                dendrogram = "row", cexCol = 0.8, cexRow = 0.4, scale = "none",
+                breaks=colormapbreaks,symbreaks=FALSE, colsep = even_columns, sepcolor="white", offsetCol = 0.1,
+                #zlim=c(-132,132),
+                xlab = "Type of Media", ylab = "Gene Name",
+                cellnote = round(X0,digits=0), notecex = 0.3, key=TRUE,
+                keysize=1, trace="none", density.info=c("none"), margins=c(10, 8),
+                na.color="red", col=brewer.pal(11,"PuOr"),
+                main=cluster,
+                labRow=as.character(cluster_data$Gene), labCol=colnames_edit)
+      dev.off()
+    }
+    if(cluster_length <= 59 && cluster_length >= 30){
+      mypath = file.path(outDir,paste("cluster_",gsub(" ","",cluster), ".pdf",sep=""))
+      pdf(file=mypath,height=9,width=12)
+      heatmap.2(x=X0,
+                Rowv=TRUE, Colv=NA, distfun = dist, hclustfun = hclust,
+                dendrogram = "row", cexCol = 0.8, cexRow = 0.6, scale = "none",
+                breaks=colormapbreaks, symbreaks=FALSE, colsep = even_columns, sepcolor="white", offsetCol = 0.1,
+                #zlim=c(-132,132), 
+                xlab = "Type of Media", ylab = "Gene Name",
+                cellnote = round(X0,digits=0), notecex = 0.4, key=TRUE,
+                keysize=1, trace="none", density.info=c("none"), margins=c(10, 8),
+                na.color="red", col=brewer.pal(11,"PuOr"),
+                main=cluster,
+                labRow=as.character(cluster_data$Gene), labCol=colnames_edit)
+      dev.off()
+    }
+    if(cluster_length <= 29){
+      mypath = file.path(outDir,paste("cluster_",gsub(" ","",cluster), ".pdf",sep=""))
+      pdf(file=mypath,height=7,width=12)
+      heatmap.2(x=X0,
+                Rowv=TRUE, Colv=NA, 
+                distfun = dist, hclustfun = hclust,
+                dendrogram = "row", cexCol = 0.8, cexRow = 0.9, scale = "none",
+                breaks=colormapbreaks, symbreaks=FALSE, colsep = even_columns, sepcolor="white", offsetCol = 0.1,
+                #zlim=c(-132,132), 
+                xlab = "Type of Media", ylab = "Gene Name",
+                cellnote = round(X0,digits=0), notecex = 0.4, key=TRUE,
+                keysize=1, trace="none", density.info=c("none"), margins=c(10, 8),
+                na.color="red", col=brewer.pal(11,"PuOr"),
+                main=cluster,
+                labRow=as.character(cluster_data$Gene), labCol=colnames_edit)
+      dev.off()
+    }
+  }
+  #print(paste("FINISHED", "CLUSTER",cluster,sep=" "))
+}

workflow/apps/r/createHeatMapsHomology.R

@@ -0,0 +1,351 @@
+#!/usr/bin/env Rscript
+# This script will make homology heatmaps for the REMc analysis
+# This script didn't have any hard set inputs so I didn't bother
+
+library(RColorBrewer)
+library(gplots)
+library(tidyverse)
+
+args <- commandArgs(TRUE)
+# Need to give the input "finalTable.csv" file after running REMc generated by eclipse
+inputFinalTable <- args[1]
+
+# Give the DAmP_list.txt as the third argument - will color the gene names differently
+DAmPs <- Args[2]
+DAmP_list <- read.delim(file=DAmPs,header=F,stringsAsFactors = F)
+
+# Give the yeast human homology mapping as the fourth argument - will add the genes to the finalTable and use info for heatmaps
+mapFile <- Args[3]
+mapping <- read.csv(file=mapFile,stringsAsFactors = F)
+
+# Define the output path for the heatmaps - create this folder first - in linux terminal in the working folder use > mkdir filename_heatmaps
+outputPath <- Args[4]
+
+# Read in finalTablewithShift
+hmapfile <- data.frame(read.csv(file=inputFinalTable,header=TRUE,sep=",",stringsAsFactors = FALSE))
+
+# Map the finalTable to the human homolog file
+hmapfile_map <- hmapfile
+# Match using OrfRep after dropping the _1 _2 _3 _4 
+# But need to also account for some older files have ORF as column name rather than OrfRep in finalTable file
+if(colnames(hmapfile_map)[2] == "OrfRep"){
+  try(hmapfile_map$ORFMatch <- hmapfile_map$OrfRep)
+}
+if(colnames(hmapfile_map)[2] == "ORF"){
+  try(hmapfile_map$ORFMatch <- hmapfile_map$ORF)
+}
+hmapfile_map$ORFMatch <- gsub("_1","",x=hmapfile_map$ORFMatch)
+hmapfile_map$ORFMatch <- gsub("_2","",x=hmapfile_map$ORFMatch)
+hmapfile_map$ORFMatch <- gsub("_3","",x=hmapfile_map$ORFMatch)
+hmapfile_map$ORFMatch <- gsub("_4","",x=hmapfile_map$ORFMatch)
+
+# Join the hmapfile using 
+hmapfile_w_homolog <- full_join(hmapfile_map,mapping,by=c("ORFMatch"="ensembl_gene_id"))
+
+# Remove matches that are not from the finalTable
+hmapfile_w_homolog <- hmapfile_w_homolog[is.na(hmapfile_w_homolog$likelihood) == F,]
+
+# Write csv with all info from mapping file
+write.csv(hmapfile_w_homolog,file=paste(outputPath,"/",inputFinalTable,"_WithHomologAll.csv",sep=""),row.names = F)
+
+# Remove the non matches and output another mapping file - this is also one used to make heatmaps
+hmapfile_w_homolog <- hmapfile_w_homolog[is.na(hmapfile_w_homolog$external_gene_name_Human) == F,]
+write.csv(hmapfile_w_homolog,file=paste(outputPath,"/",inputFinalTable,"_WithHomologMatchesOnly.csv",sep=""),row.names = F)
+
+# Add human gene name to the Gene column
+hmapfile_w_homolog$Gene <- paste(hmapfile_w_homolog$Gene,hmapfile_w_homolog$external_gene_name_Human,sep="/")
+
+# Only keep the finalTable file columns and the homology info
+hmap_len <- dim(hmapfile)[2]
+
+hmapfile_w_homolog_remake <- cbind(hmapfile_w_homolog[,1:hmap_len], hsapiens_homolog_orthology_type=hmapfile_w_homolog$hsapiens_homolog_orthology_type)
+hmapfile <- hmapfile_w_homolog_remake
+
+# Set NAs to NA
+hmapfile[hmapfile == -100] <- NA
+hmapfile[hmapfile == 100] <- NA
+hmapfile[hmapfile == 0.001] <- NA
+hmapfile[hmapfile == -0.001] <- NA
+
+# Select the number of rows based on the number of genes
+num_total_genes <- length(hmapfile[,1])
+
+# break out the cluster names so each part of the cluster origin can be accessed
+# line below removed because it adds to many genes to clusters when going past 1-0-10 since it cannot differentiate between 1-0-1 and 1-0-10 when using grepl.
+# hmapfile$cluster.origin = gsub(" ","",x=hmapfile$cluster.origin)
+
+hmapfile$cluster.origin = gsub(";"," ;",x=hmapfile$cluster.origin)
+hmapfile$cluster.origin = strsplit(hmapfile$cluster.origin,';')
+# use tail(x,n) for accessing the outward most cluster
+
+clust_rounds <- 0
+for(i in 1:num_total_genes){
+  if(length(hmapfile$cluster.origin[[i]]) > clust_rounds){
+    clust_rounds <- length(hmapfile$cluster.origin[[i]])
+  }
+}
+
+unique_clusts <- unique(hmapfile$cluster.origin[1:num_total_genes])
+unique_clusts <- unique_clusts[unique_clusts != " "]
+
+#select only the unique cluster names
+unique_clusts <- sort(unique(unlist(unique_clusts,use.names= FALSE)),decreasing=FALSE)
+num_unique_clusts <- length(unique_clusts)
+
+# Base the color key on a statistical analysis of the L and K data
+# need to create "breaks" to set the color key, need to have 12 different breaks (for 11 colors)
+# scale() will calculate the mean and standard deviation of the entire vector, then "scale" each element by those values by subtracting the mean and dividing by the sd.
+
+# hmapfile[,4:(length(hmapfile[1,]) - 2)] <- scale(hmapfile[,4:(length(hmapfile[1,]) - 2)])
+
+# Change so that the L data is multiplied to be on the same scale as the K data
+
+KEY_MIN <- 0
+KEY_MAX <- 0
+K_MIN <- 0
+L_MAX <- 0
+KcolumnValues <- vector()
+LcolumnValues <- vector()
+
+for(i in 4:(length(hmapfile[1,]) - 3)){
+  if(grepl("_Z_lm_K",colnames(hmapfile)[i],fixed=TRUE) == TRUE){
+    KcolumnValues <- append(KcolumnValues,i)
+  }
+  if(grepl("_Z_lm_L",colnames(hmapfile)[i],fixed=TRUE) == TRUE){
+    LcolumnValues <- append(LcolumnValues,i)
+  }
+}
+
+# L_MAX <- quantile(hmapfile[,LcolumnValues],c(0,.01,.5,.99,1),na.rm=TRUE)[4]
+# K_MIN <- quantile(hmapfile[,KcolumnValues],c(0,.01,.5,.99,1),na.rm=TRUE)[2]
+# L_MAX <- quantile(hmapfile[,LcolumnValues],c(0,.01,.5,.975,1),na.rm=TRUE)[4]
+# K_MIN <- quantile(hmapfile[,KcolumnValues],c(0,.025,.5,.99,1),na.rm=TRUE)[2]
+
+# Z scores are
+L_MAX <- 12
+K_MIN <- -12
+
+# L_Multiplier <- as.numeric(abs(K_MIN/L_MAX))
+# hmapfile[,LcolumnValues] <- hmapfile[,LcolumnValues] * L_Multiplier
+
+# if(grepl("SHIFT",colnames(hmapfile)[4],fixed=TRUE) == TRUE){
+#  print("FOUND SHIFT VALUES")
+#  hmapfile[,(LcolumnValues - 1)] <- hmapfile[,(LcolumnValues-1)] * L_Multiplier
+# }
+
+#KEY_MAX <- as.numeric(L_MAX * L_Multiplier)
+#KEY_MIN <- as.numeric(K_MIN)
+KEY_MAX <- as.numeric(L_MAX)
+KEY_MIN <- as.numeric(K_MIN)
+
+print(KEY_MIN)
+print(L_MAX)
+#print(L_Multiplier)
+
+colormapbreaks <- c(KEY_MIN,KEY_MIN*(5/6),KEY_MIN*(4/6),KEY_MIN*(3/6),KEY_MIN*(2/6),KEY_MIN*(1/6),KEY_MAX*(1/6),KEY_MAX*(2/6),KEY_MAX*(3/6),KEY_MAX*(4/6),KEY_MAX*(5/6),KEY_MAX)
+#print(colormapbreaks)
+
+# Probably should give a way to detect shift in case that is is not in the first row... (maybe just grepl for the whole column name?)
+# However since also using this to amend the first part. Could possibly identify all the ones that contain the word shift and then create an object containing just those numbers
+# then could just use these values and create spaces only between interaction values - possibly could get rid of redundant shift values if we don't want to view these
+# could we pool all the shift data/average it?
+if(grepl("Shift",colnames(hmapfile)[4],fixed=TRUE) == TRUE){
+  even_columns <- seq(from= 2, to= (length(hmapfile[1,]) - 7),by=2)
+  # ev_repeat = rep("white",length(even_columns))
+  # ev_repeat = rep("red",(length(hmapfile[1,]) - 5))
+  # middle_col <- (length(hmapfile[1,]) - 5)/2
+  # ev_repeat[(middle_col/2)] <- "black"
+  # print(ev_repeat)
+}
+
+if(grepl("Shift",colnames(hmapfile)[4],fixed=TRUE) == FALSE){
+  even_columns <- seq(from= 2, to= (length(hmapfile[1,]) - 7),by=1)
+  print("NO SHIFT VALS FOUND")
+}
+
+# for this script only (rap tem hu script)
+# even_columns <- c(2,5,7,10,12,15,17)
+
+# m <- 0
+colnames_edit <- as.character(colnames(hmapfile)[4:(length(hmapfile[1,]) - 3)])
+
+colnames(DAmP_list)[1] <- "ORF"
+hmapfile$DAmPs <- "YKO"
+colnames(hmapfile)[2] <- "ORF"
+try(hmapfile[hmapfile$ORF %in% DAmP_list$ORF,]$DAmPs <- "YKD")
+# X <- X[order(X$DAmPs,decreasing = TRUE),]
+hmapfile$color2 <- NA
+try(hmapfile[hmapfile$DAmPs == "YKO",]$color2 <- "black")
+try(hmapfile[hmapfile$DAmPs == "YKD",]$color2 <- "red")
+
+hmapfile$color <- NA
+try(hmapfile[hmapfile$hsapiens_homolog_orthology_type == "ortholog_many2many",]$color <- "#F8766D")
+try(hmapfile[hmapfile$hsapiens_homolog_orthology_type == "ortholog_one2many",]$color <- "#00BA38")
+try(hmapfile[hmapfile$hsapiens_homolog_orthology_type == "ortholog_one2one",]$color <- "#619CFF")
+
+# print(colnames_edit)
+for(i in 1:length(colnames_edit)){
+  if(grepl("Shift",colnames_edit[i],fixed=TRUE) == TRUE){
+    colnames_edit[i] <- ""
+    colnames_edit[i+1] <- gsub(pattern = "_Z_lm_",replacement = " ",x = colnames_edit[i+1])
+    try(colnames_edit[i+1] <- gsub(pattern = "_",replacement = " ",x = colnames_edit[i+1]))
+    
+    # INT_store <- strsplit(colnames_edit[i+1], "Z_lm")
+    # print(length(unlist(INT_store)))
+    # if(length(unlist(INT_store)) == 4){
+    #   colnames_edit[i+1] <- paste(unlist(INT_store)[1],unlist(INT_store)[2],unlist(INT_store)[3],sep=" ")
+    # }
+    # if(length(unlist(INT_store)) == 3){
+    # 
+    #   colnames_edit[i+1] <- paste(unlist(INT_store)[1],unlist(INT_store)[2],sep=" ")
+    # }
+    # if(length(unlist(INT_store)) == 5){
+    #   colnames_edit[i+1] <- paste(unlist(INT_store)[1],unlist(INT_store)[2],unlist(INT_store)[3],unlist(INT_store)[4],sep=" ")
+    # }
+    # if(length(unlist(INT_store)) == 6){
+    #   colnames_edit[i+1] <- paste(unlist(INT_store)[1],unlist(INT_store)[2],unlist(INT_store)[6],sep=" ")
+    # }
+
+  }
+}
+
+print(colnames_edit)
+# break()
+# colnames_edit[5] <- "TEM HLEG K"
+# colnames_edit[10] <- "TEM HL K"
+# colnames_edit[15] <- "TEM HLEG L"
+# colnames_edit[20] <- "TEM HL L"
+
+# Create the heatmaps
+for(i in 1:num_unique_clusts){
+  cluster <- unique_clusts[i]
+  cluster_data <- subset(hmapfile,grepl(cluster,cluster.origin))
+  cluster_length <- length(cluster_data[,1])
+  if(cluster_length != 1){
+    X0 <- as.matrix(cluster_data[,4:(length(hmapfile[1,]) - 6)])
+    if(cluster_length >= 2001){
+      mypath = file.path(outputPath,paste("cluster_",gsub(" ","",cluster), ".pdf",sep=""))
+      pdf(file=mypath,height=20,width=15)
+      heatmap.2(
+        x=X0,
+        Rowv=TRUE, Colv=NA, distfun = dist, hclustfun = hclust,
+        dendrogram = "row", cexCol = 0.8, cexRow = 0.1, scale = "none",
+        breaks=colormapbreaks, symbreaks=FALSE, colsep = even_columns, sepcolor= "white", offsetCol = 0.1,
+        # zlim=c(-132,132), 
+        xlab = "Type of Media", ylab = "Gene Name",
+        # cellnote = round(X0,digits=0), notecex = 0.1, key=TRUE,
+        keysize=0.7, trace="none", density.info=c("none"), margins=c(10, 8),
+        na.color="red", col=brewer.pal(11,"PuOr"),
+        main=cluster, 
+        # ColSideColors=ev_repeat,
+        labRow=as.character(cluster_data$Gene), labCol=colnames_edit, colRow=cluster_data$color2,RowSideColors=cluster_data$color)
+      # abline(v=0.5467,col="black")
+      dev.off()
+    }
+    if(cluster_length >= 201 && cluster_length <= 2000){
+      mypath = file.path(outputPath,paste("cluster_",gsub(" ","",cluster), ".pdf",sep=""))
+      pdf(file=mypath,height=15,width=12)
+      heatmap.2(
+        x=X0,
+        Rowv=TRUE, Colv=NA, distfun = dist, hclustfun = hclust,
+        dendrogram = "row", cexCol = 0.8, cexRow = 0.1, scale = "none",
+        breaks=colormapbreaks, symbreaks=FALSE, colsep = even_columns, sepcolor="white", offsetCol = 0.1,
+        # zlim=c(-132,132), 
+        xlab = "Type of Media", ylab = "Gene Name",
+        cellnote = round(X0,digits=0), notecex = 0.1, key=TRUE,
+        keysize=0.7, trace="none", density.info=c("none"), margins=c(10, 8),
+        na.color="red", col=brewer.pal(11,"PuOr"),
+        main=cluster,
+        labRow=as.character(cluster_data$Gene), labCol=colnames_edit, colRow=cluster_data$color2,RowSideColors=cluster_data$color)
+      # abline(v=0.5316,col="black")
+      dev.off()
+    }
+    if(cluster_length >= 150 && cluster_length <= 200){
+      mypath = file.path(outputPath,paste("cluster_",gsub(" ","",cluster), ".pdf",sep=""))
+      pdf(file=mypath,height=12,width=12)
+      heatmap.2(
+        x=X0,
+        Rowv=TRUE, Colv=NA, distfun = dist, hclustfun = hclust,
+        dendrogram = "row", cexCol = 0.8, cexRow = 0.1, scale = "none",
+        breaks=colormapbreaks, symbreaks=FALSE, colsep = even_columns, sepcolor="white", offsetCol = 0.1,
+        # zlim=c(-132,132), 
+        xlab = "Type of Media", ylab = "Gene Name",
+        cellnote = round(X0,digits=0), notecex = 0.2, key=TRUE,
+        keysize=1, trace="none", density.info=c("none"), margins=c(10, 8),
+        na.color="red", col=brewer.pal(11,"PuOr"),
+        main=cluster,
+        labRow=as.character(cluster_data$Gene), labCol=colnames_edit, colRow=cluster_data$color2,RowSideColors=cluster_data$color)
+      dev.off()
+    }
+    if(cluster_length >= 101 && cluster_length <= 149){
+      mypath = file.path(outputPath,paste("cluster_",gsub(" ","",cluster), ".pdf",sep=""))
+      pdf(file=mypath,mypath,height=12,width=12)
+      heatmap.2(
+        x=X0,
+        Rowv=TRUE, Colv=NA, distfun = dist, hclustfun = hclust,
+        dendrogram = "row", cexCol = 0.8, cexRow = 0.2, scale = "none",
+        breaks=colormapbreaks, symbreaks=FALSE, colsep = even_columns, sepcolor="white", offsetCol = 0.1,
+        # zlim=c(-132,132), 
+        xlab = "Type of Media", ylab = "Gene Name",
+        cellnote = round(X0,digits=0), notecex = 0.3, key=TRUE,
+        keysize=1, trace="none", density.info=c("none"), margins=c(10, 8),
+        na.color="red", col=brewer.pal(11,"PuOr"),
+        main=cluster,
+        labRow=as.character(cluster_data$Gene), labCol=colnames_edit, colRow=cluster_data$color2,RowSideColors=cluster_data$color)
+      dev.off()
+    }
+    if(cluster_length >= 60 && cluster_length <= 100){
+      mypath = file.path(outputPath,paste("cluster_",gsub(" ","",cluster), ".pdf",sep=""))
+      pdf(file=mypath,height=12,width=12)
+      heatmap.2(
+        x=X0,
+        Rowv=TRUE, Colv=NA, distfun = dist, hclustfun = hclust,
+        dendrogram = "row", cexCol = 0.8, cexRow = 0.4, scale = "none",
+        breaks=colormapbreaks,symbreaks=FALSE, colsep = even_columns, sepcolor="white", offsetCol = 0.1,
+        #zlim=c(-132,132),
+        xlab = "Type of Media", ylab = "Gene Name",
+        cellnote = round(X0,digits=0), notecex = 0.3, key=TRUE,
+        keysize=1, trace="none", density.info=c("none"), margins=c(10, 8),
+        na.color="red", col=brewer.pal(11,"PuOr"),
+        main=cluster,
+        labRow=as.character(cluster_data$Gene), labCol=colnames_edit, colRow=cluster_data$color2,RowSideColors=cluster_data$color)
+      dev.off()
+    }
+    if(cluster_length <= 59 && cluster_length >= 30){
+      mypath = file.path(outputPath,paste("cluster_",gsub(" ","",cluster), ".pdf",sep=""))
+      pdf(file=mypath,height=9,width=12)
+      heatmap.2(
+        x=X0,
+        Rowv=TRUE, Colv=NA, distfun = dist, hclustfun = hclust,
+        dendrogram = "row", cexCol = 0.8, cexRow = 0.6, scale = "none",
+        breaks=colormapbreaks, symbreaks=FALSE, colsep = even_columns, sepcolor="white", offsetCol = 0.1,
+        #zlim=c(-132,132), 
+        xlab = "Type of Media", ylab = "Gene Name",
+        cellnote = round(X0,digits=0), notecex = 0.4, key=TRUE,
+        keysize=1, trace="none", density.info=c("none"), margins=c(10, 8),
+        na.color="red", col=brewer.pal(11,"PuOr"),
+        main=cluster,
+        labRow=as.character(cluster_data$Gene), labCol=colnames_edit, colRow=cluster_data$color2,RowSideColors=cluster_data$color)
+      dev.off()
+    }
+    if(cluster_length <= 29){
+      mypath = file.path(outputPath,paste("cluster_",gsub(" ","",cluster), ".pdf",sep=""))
+      pdf(file=mypath,height=7,width=12)
+      heatmap.2(
+        x=X0,
+        Rowv=TRUE, Colv=NA, 
+        distfun = dist, hclustfun = hclust,
+        dendrogram = "row", cexCol = 0.8, cexRow = 0.9, scale = "none",
+        breaks=colormapbreaks, symbreaks=FALSE, colsep = even_columns, sepcolor="white", offsetCol = 0.1,
+        #zlim=c(-132,132), 
+        xlab = "Type of Media", ylab = "Gene Name",
+        cellnote = round(X0,digits=0), notecex = 0.4, key=TRUE,
+        keysize=1, trace="none", density.info=c("none"), margins=c(10, 8),
+        na.color="red", col=brewer.pal(11,"PuOr"),
+        main=cluster,
+        labRow=as.character(cluster_data$Gene), labCol=colnames_edit, colRow=cluster_data$color2,RowSideColors=cluster_data$color)
+      dev.off()
+    }
+  }
+  # print(paste("FINISHED", "CLUSTER",cluster,sep=" "))
+}

workflow/apps/r/gtaTemplate.R

@@ -0,0 +1,199 @@
+#!/usr/bin/env R 
+# GTA (GoTermAveraging)
+# Your output  may not be reproducible as org.Sc.sgd.db is uploaded from Bioconductor R library and changes
+#
+# Updated 240724 Bryan C Roessler to improve file operations and portability
+# NOTE: The script now has 2 additional OPTIONAL arguments: 
+#   1. Path to SGD terms file (go.terms.tab)
+#   2. Path to SGD features file (gene_association.sgd)
+
+library("stringr")
+library("org.Sc.sgd.db")
+library("plyr")
+
+# Parse arguments
+args <- commandArgs(TRUE)
+
+exp_name <- args[1]
+
+if (length(args) > 2) {
+  zscores_file <- args[2]
+} else {
+  zscores_file <- "zscores/zscores_interaction.csv" # https://downloads.yeastgenome.org/curation/chromosomal_feature/gene_association.sgd
+}
+
+if (length(args) > 3) {
+  sgd_terms_file <- args[3]
+} else {
+  sgd_terms_file <- "go_terms.tab"
+}
+
+if (length(args) > 4) {
+  sgd_features_file <- args[4]
+} else {
+  sgd_features_file <- "gene_association.sgd" # https://downloads.yeastgenome.org/curation/chromosomal_feature/gene_association.sgd
+}
+
+if (length(args) > 5) {
+  output_dir <- args[5]
+} else {
+  output_dir <- "../../out/gta" # https://downloads.yeastgenome.org/curation/chromosomal_feature/gene_association.sgd
+}
+
+
+
+# # Set SGDgeneList file path
+# if (length(args) > 4) {
+#   SGDgeneList <- args[4]
+# } else {
+#   SGDgeneList <- "../Code/SGD_features.tab"
+
+
+#Begin for loop for experiments in this study-----------------ZScores_Interaction.csv
+for(m in 1:length(zscores_file)){
+  
+  #zscores_file <- paste(Wstudy,"/",expName[m],'/ZScores/ZScores_Interaction.csv',sep="")  #ArgsScore[1]
+  X <- read.csv(file = zscores_file[m],stringsAsFactors=FALSE,header = TRUE)
+  
+  if(colnames(X)[1] == "OrfRep"){
+    colnames(X)[1] <- "ORF"
+  }
+  
+  #Terms is the GO term list
+  Terms <- read.delim(file = sgd_terms_file,header=FALSE,quote = "",col.names = c("GO_ID","GO_Term","GO_Aspect","GO_Term_Definition"))
+  #all ORFs associated with GO term
+  GO2ALLORFs <- as.list(org.Sc.sgdGO2ALLORFS)
+  #Gene_Association is the gene association to GO term file
+  Gene_Association <- read.delim(sgd_features_file,skip=8,header=FALSE,quote="",col.names = c("Database","Database_Object_ID","Database_Object_Symbol","NOT","GO_ID","Database_Reference","Evidence","With_or_From","Aspect","Database_Object_Name","Database_Object_Synonym","Database_Object_Type","taxon","Date","Assigned_By","OtherInfo","Empty"))
+  #Get the ORF names associated with each gene/GO term
+  Gene_Association$ORF <- str_split_fixed(as.character(Gene_Association$Database_Object_Synonym),"\\|",2)[,1]
+  #Get the numeric GO ID for matching
+  Gene_Association$GO_ID_Numeric <- as.integer(str_split_fixed(as.character(Gene_Association$GO_ID),"\\:",2)[,2])
+  #get all unique GO terms
+  GO_Terms <- unique(Gene_Association$GO_ID)
+  #create a character vector with just the ColNames of the input file to store the scores for each GO term
+  Col_Names_X <- colnames(X)
+  #create a data_frame with header from input_file
+  GO_Term_Averages <- X[0,]
+  #fill table with NAs same length as number of GO terms
+  GO_Term_Averages[1:length(GO_Terms),] <- NA
+  #change the first and second col names to GO_ID and Term
+  colnames(GO_Term_Averages)[1] <- "GO_ID"
+  colnames(GO_Term_Averages)[2] <- "Term"
+  
+  #create new columns for Ontology, number genes (used to calculate the avg score), all possible genes in the GO term, and print genes/ORFs used
+  GO_Term_Averages$Ontology <- NA
+  GO_Term_Averages$NumGenes <- NA
+  GO_Term_Averages$AllPossibleGenes <- NA
+  GO_Term_Averages$Genes <- NA
+  GO_Term_Averages$ORFs <- NA
+  
+  #create a data.frame for the standard deviation info 
+  GO_Term_SD <- X[0,]
+  GO_Term_SD[1:length(GO_Terms),] <- NA
+  colnames(GO_Term_SD)[1] <- "GO_ID"
+  colnames(GO_Term_SD)[2] <- "Term"
+  
+  #Loop for each GO term to get an average L and K Z score
+  for(i in 1:length(GO_Terms)){
+    #get the GO_Term
+    ID <- GO_Terms[i]
+    #Get data.frame for all genes associated to the GO Term
+    ID_AllGenes <- Gene_Association[Gene_Association$GO_ID == ID,]
+    #get a vector of just the gene names
+    ID_AllGenes_vector <- as.vector(GO2ALLORFs[as.character(ID)][[1]])
+    if(length(unique(ID_AllGenes_vector)) > 4000){
+      next()
+    }
+    #get the GO term character description where numeric Terms ID matches GO_Term's ID
+    GO_Description_Term <- as.character(Terms[Terms$GO_ID %in% ID_AllGenes$GO_ID_Numeric,]$GO_Term[1])
+    #get the Z scores for all genes in the GO_ID
+    Zscores_For_ID <- X[X$ORF %in% ID_AllGenes_vector,]
+    #get the Gene names and ORFs for the term
+    GO_Term_Averages$Genes[i] <- paste(unique(Zscores_For_ID$Gene),collapse=" | ")
+    GO_Term_Averages$ORFs[i] <- paste(unique(Zscores_For_ID$ORF),collapse=" | ")
+    
+    #dataframe to report the averages for a GO term
+    #get the GO ID
+    GO_Term_Averages$GO_ID[i] <- as.character(ID)
+    #get the term name
+    GO_Term_Averages$Term[i] <- GO_Description_Term
+    #get total number of genes annotated to the Term that we have in our library
+    GO_Term_Averages$NumGenes[i] <- length(unique(Zscores_For_ID$ORF))
+    #get total number of genes annotated to the Term in SGD
+    GO_Term_Averages$AllPossibleGenes[i] <- length(unique(ID_AllGenes_vector))
+    #get the ontology of the term
+    GO_Term_Averages$Ontology[i] <- as.character(ID_AllGenes$Aspect[1])
+    
+    #calculate the average score for every column
+    for(j in 3:length(X[1,])){
+      GO_Term_Averages[i,j] <- mean(Zscores_For_ID[,j],na.rm = TRUE)
+      #GO_Scores <- colMeans(Zscores_For_ID[,3:length(X[1,])])
+    }
+    
+    #also calculate same values for the SD
+    GO_Term_SD$GO_ID[i] <- as.character(ID)
+    #get the term name
+    GO_Term_SD$Term[i] <- GO_Description_Term
+    
+    #calculate column scores for SD
+    for(j in 3:length(X[1,])){
+      GO_Term_SD[i,j] <- sd(Zscores_For_ID[,j],na.rm = TRUE)
+      #GO_Scores <- colMeans(Zscores_For_ID[,3:length(X[1,])])
+    }
+  }
+  #add either _Avg or _SD depending on if the calculated score is an average or SD
+  colnames(GO_Term_Averages) <- paste(colnames(GO_Term_Averages),"Avg", sep = "_")
+  colnames(GO_Term_SD) <- paste(colnames(GO_Term_SD),"SD", sep = "_")
+  #combine the averages with the SDs to make one big data.frame
+  X2 <- cbind(GO_Term_Averages,GO_Term_SD)
+  #test[ , order(names(test))]
+  X2 <- X2[,order(names(X2))]
+  X2 <- X2[!is.na(X2$Z_lm_L_Avg),]
+  #create output file
+  write.csv(X2,file=paste(output_dir,"/",expName[m],"/Average_GOTerms_All.csv",sep=""),row.names=FALSE)
+  #remove NAs
+  X3 <- X2[!is.na(X2$Z_lm_L_Avg),]
+  #identify redundant GO terms
+  
+  for(i in 1:length(X3[,1])){
+    #loop through each GO term - get term
+    GO_term_ID <- as.character(X3$GO_ID_Avg[i])
+    #get term in the X3
+    X3_Temp <- X3[X3$GO_ID_Avg == GO_term_ID,]
+    #get anywhere that has the same number K_Avg value
+    X3_Temp2 <- X3[X3$Z_lm_K_Avg %in% X3_Temp,]
+    if(length(X3_Temp2[,1]) > 1){
+      if(length(unique(X3_Temp2$Genes_Avg)) == 1){
+        X3_Temp2 <- X3_Temp2[1,]
+      }
+    }
+    
+    if(i == 1){
+      Y <- X3_Temp2
+    }
+    if(i > 1){
+      Y <- rbind(Y,X3_Temp2)
+    }
+  }
+  Y1 <- unique(Y)
+  
+  write.csv(Y1,file=paste(output_dir,"/",exp_name,"/Average_GOTerms_All_NonRedundantTerms.csv",sep=""),row.names = FALSE)
+  
+  Y2 <- Y1[Y1$Z_lm_L_Avg >= 2 | Y1$Z_lm_L_Avg <= -2,]
+  Y2 <- Y2[!is.na(Y2$Z_lm_L_Avg),]
+  write.csv(Y2,file=paste(output_dir,"/",exp_name,"/Average_GOTerms_NonRedundantTerms_Above2SD_L.csv",sep=""),row.names = FALSE)
+  
+  Y3 <- Y2[Y2$NumGenes_Avg > 2,]
+  write.csv(Y3,file=paste(output_dir,"/",exp_name,"/Average_GOTerms_NonRedundantTerms_Above2SD_L_Above2Genes.csv",sep=""),row.names = FALSE)
+  
+  Y4 <- Y1[Y1$Z_lm_K_Avg >= 2 | Y1$Z_lm_K_Avg <= -2,]
+  Y4 <- Y4[!is.na(Y4$Z_lm_K_Avg),]
+  write.csv(Y4,file=paste(output_dir,"/",exp_name,"/Average_GOTerms_NonRedundantTerms_Above2SD_K.csv",sep=""),row.names = FALSE)
+  
+  Y5 <- Y4[Y4$NumGenes_Avg > 2,]
+  write.csv(Y5,file=paste(output_dir,"/",exp_name,"/Average_GOTerms_NonRedundantTerms_Above2SD_K_Above2Genes.csv",sep=""),row.names = FALSE)
+  
+  #End of 'for loop'
+}
+