bryan/hartman-server
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

More progress on initial commit

Browse Source
This commit is contained in:
Bryan Roessler
2024-07-22 15:54:36 -04:00
parent 06dd700680
commit 8cf3703b0c
1 changed files with 273 additions and 169 deletions
Download Patch File Download Diff File Expand all files Collapse all files

442
workflow/script-run-workflow
View File

@@ -1,7 +1,9 @@
#!/usr/bin/env bash #!/usr/bin/env bash
# Copyright 2024 Bryan C. Roessler # Copyright 2024 Bryan C. Roessler
# This is currently a code scratchpad for organizing the Hartman Lab Server workflow #
# This is a code scratchpad for organizing the Hartman Lab Server workflow
# It contains a mixture of code/pseudocode and shouldn't be run until this message is removed # It contains a mixture of code/pseudocode and shouldn't be run until this message is removed
#
# Allow indirect functions # Allow indirect functions
# shellcheck disable=SC2317 # shellcheck disable=SC2317
# #
@@ -9,8 +11,14 @@
# @name HartmanLabWorkflow # @name HartmanLabWorkflow
# @brief One script to rule them all (see: xkcd #927) # @brief One script to rule them all (see: xkcd #927)
# @description Executes the Hartman Lab image analysis workflow # @description Executes the Hartman Lab image analysis workflow
# @arg $1 string A project name # @option -p<value> | --project=<value> Include one or more projects in the analysis
# # @option -i<value> | --include=<value> Include one or more modules in the analysis (default: all modules)
# @option -x<value> | --exclude=<value> Exclude one or more modules in the analysis
# @option -y | --yes | --auto Assume yes answer to all questions (non-interactive mode)
# @option -d | --debug Turn on extra debugging output
# @option -h | --help Print help message and exit (overrides other options)
DEBUG=1 # Turn debugging ON by default during development
shopt -s extglob shopt -s extglob
# @section Libraries # @section Libraries
@@ -22,42 +30,53 @@ PERL="${PERL:-perl}"
# @section Help # @section Help
# @description Print a helpful message # @description Print a helpful message
print_help() { print_help() {
echo "Running: ${FUNCNAME[0]}" debug "Running: ${FUNCNAME[0]}"
install_dependencies --get-depends # Loads the dependency arrays
cat <<-EOF cat <<-EOF
USAGE: USAGE:
script-run-workflow [[OPTION] [VALUE]]... script-run-workflow [[OPTION] [VALUE]]...
Some options (--project, --module) can be passed multiple times for batch operations. Some options (--project, --include, --exclude) can be passed multiple times or
by using comma deliminated strings (see EXAMPLES below)
OPTIONS: OPTIONS:
--project, -p PROJECT --project, -p PROJECT
PROJECT should follow the pattern ${PROJECT_PREFIX}_UNIQUE_PROJECT_NAME PROJECT should follow the pattern ${PROJECT_PREFIX}_PROJECT_NAME
--include, -i MODULE --include, -i MODULE
See MODULES section below for list of available modules See MODULES section below for list of available modules
If no --module is specified, all modules are run If no --include is specified, all modules are run
--exclude, -x MODULE --exclude, -x MODULE
See MODULES section below for list of available modules See MODULES section below for list of modules to exclude
--yes, -y, --auto --yes, -y, --auto
Always answer yes to questions (non-interactive mode) Always answer yes to questions (non-interactive mode)
--debug, -d --debug, -d
Print extra debugging info Print extra debugging info
--help, -h --help, -h
Print this help message and exit Print this help message and exit
MODULES: MODULES:
${ALL_MODULES[*]} ${ALL_MODULES[*]}
SUBMODULES:
${ALL_SUBMODULES[*]}
DEPENDENCIES: DEPENDENCIES:
binaries (system): graphviz pandoc pdftk-java gd-devel deb: ${depends_deb[@]}
perl (cpan): File::Map ExtUtils::PkgConfig GD GO::TermFinder rpm: ${depends_rpm[@]}
R (default): BiocManager ontologyIndex ggrepel tidyverse sos openxlsx ggplot2 plyr extrafont gridExtra gplots stringr plotly ggthemes pandoc rmarkdown brew: ${depends_brew[@]}
R (BiocManager): perl: ${depends_perl[@]}
R: ${depends_r[@]}
BiocManager: ${depends_bioc[@]}
EXAMPLES: EXAMPLES:
script-run-workflow --module ${ALL_MODULES[0]} --module ${ALL_MODULES[1]} script-run-workflow --module ${ALL_MODULES[0]} --module ${ALL_MODULES[1]}
script-run-workflow --project ${PROJECT_PREFIX}_MY_PROJECT --module ${ALL_MODULES[0]} --module ${ALL_MODULES[1]} script-run-workflow --project ${PROJECT_PREFIX}_MY_PROJECT --module ${ALL_MODULES[0]} --module ${ALL_MODULES[1]}
script-run-workflow --project ${PROJECT_PREFIX}_MY_PROJECT --module ${ALL_MODULES[1]} --module ${ALL_MODULES[2]} --yes script-run-workflow --project ${PROJECT_PREFIX}_MY_PROJECT --module ${ALL_MODULES[1]} --module ${ALL_MODULES[2]} --yes
script-run-workflow --module=${ALL_MODULES[0]},${ALL_MODULES[1]}
script-run-workflow --project=${PROJECT_PREFIX}_MY_PROJECT,${PROJECT_PREFIX}_MY_OTHER_PROJECT
script-run-workflow --project=${PROJECT_PREFIX}_MY_PROJECT,${PROJECT_PREFIX}_MY_OTHER_PROJECT --module=${ALL_MODULES[1]},${ALL_MODULES[2]} --yes --debug
EOF EOF
} }
@@ -65,10 +84,9 @@ print_help() {
# @section User Input # @section User Input
# @description Creates array and switches from user input # @description Creates array and switches from user input
parse_input() { parse_input() {
echo "Running: ${FUNCNAME[0]}" "$@" debug "Running: ${FUNCNAME[0]}" "$@"
long_opts="project:,include:,exclude:,yes,auto,debug,help" long_opts="project:,include:,exclude:,yes,auto,debug,help"
#long_opts+="restorefile:,betapass:,"
short_opts="+p:i:x:yhd" short_opts="+p:i:x:yhd"
if input=$(getopt -o $short_opts -l $long_opts -- "$@"); then if input=$(getopt -o $short_opts -l $long_opts -- "$@"); then
@@ -77,15 +95,27 @@ parse_input() {
case $1 in case $1 in
--project|-p) --project|-p)
shift shift
declare -ga PROJECT_NAMES+=("$1") if [[ $1 == *','* ]] ; then # check for commas
IFS=',' read -ra PROJECTS <<< "$1"
else
PROJECTS+=("$1")
fi
;; ;;
--include|-i) --include|-i)
shift shift
declare -ga MODULES+=("$1") if [[ $1 == *','* ]] ; then # check for commas
IFS=',' read -ra INCLUDE_MODULES <<< "$1"
else
INCLUDE_MODULES+=("$1")
fi
;; ;;
--exclude|-x) --exclude|-x)
shift shift
declare -ga EXCLUDE_MODULES+=("$1") if [[ $1 == *','* ]] ; then # check for commas
IFS=',' read -ra EXCLUDE_MODULES <<< "$1"
else
EXCLUDE_MODULES+=("$1")
fi
;; ;;
--yes|-y|--auto) --yes|-y|--auto)
declare -g YES=1 declare -g YES=1
@@ -109,12 +139,118 @@ parse_input() {
} }
# @section Helper functions
# @internal
module() {
debug "Adding $1 module"
ALL_MODULES+=("$1")
declare -gA "$1"
}
submodule() {
debug "Adding $1 submodule"
ALL_SUBMODULES+=("$1")
declare -gA "$1"
}
# This function will only work if users have an actual name registered on the server
# TODO for now just use username
# user_initials() {
# user_record="$(getent passwd "$(whoami)")"
# user_gecos_field="$(echo "$user_record" | cut -d ':' -f 5)"
# user_full_name="$(echo "$user_gecos_field" | cut -d ',' -f 1)"
# last="${user_full_name#* }"
# echo "${user_full_name:0:1}${last:0:1}"
# }
ask() {
declare response
(( YES )) && return 0
read -r -p "$* [y/N]: " response
[[ ${response,,} =~ ^(yes|y)$ ]]
}
err() { echo "Error: $*" >&2; }
ask_pn() {
declare -g PROJECT
read -r -p "Enter a full project name (ex. ${PROJECT_PREFIX}_PROJECT_NAME): " PROJECT
}
debug() { (( DEBUG )) && echo "Debug: $*"; }
# @section Modules
# @description A module contains a cohesive set of actions/experiments to run on a project
# Use a module when:
# * Building a new type of analysis
# * Combining submodules
#
#
module install_dependencies
# @description Installs dependencies for the workflow
install_dependencies() {
debug "Running: ${FUNCNAME[0]}" "$@"
# Dependency arrays
depends_rpm=(graphviz pandoc pdftk-java gd-devel)
depends_deb=(graphviz pandoc pdftk-java libgd-dev)
depends_brew=(graphiz pandoc gd pdftk-java)
depends_perl=(File::Map ExtUtils::PkgConfig GD GO::TermFinder)
depends_r=(BiocManager ontologyIndex ggrepel tidyverse sos openxlsx ggplot2
plyr extrafont gridExtra gplots stringr plotly ggthemes pandoc rmarkdown)
depends_bioc=(org.Sc.sgd.db)
[[ $1 == "--get-depends" ]] && return 0 # if we just want to read the depends vars
# Install system-wide dependencies
echo "Installing system dependencies"
case "$(uname -s)" in
Linux*|CYGWIN*|MINGW*)
ask "Detected Linux platform, continue?" || return 1
echo "You may be prompted for your sudo password to install system packages"
if hash dnf &>/dev/null; then
sudo dnf install "${depends_rpm[@]}"
elif hash apt &>/dev/null; then
sudo apt install "${depends_deb[@]}"
fi
;;
Darwin*)
ask "Detected Mac platform, continue?" || return 1
export HOMEBREW_BREW_GIT_REMOTE="https://github.com/Homebrew/brew"
curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh|bash
brew install "${depends_brew[@]}"
;;
*)
echo "Your system could not be detected, please install dependencies manually"
;;
esac
# Install perl CPAN modules
echo "Installing perl CPAN modules"
debug "cpan" "${depends_perl[@]}"
cpan "${depends_perl[@]}"
# Install R packages
echo "Installing R packages"
depends_r_str=""
depends_r_to_string() {
for d in "${depends_r[@]}"; do
depends_r_str+="$d\", \""
done
depends_r_str="${depends_r_str::-3}" # strip last , " (comma and quote)
}
depends_r_to_string
debug "Rscript -e install.packages(c(\"$depends_r_str), dep=TRUE, repos=\"https://cloud.r-project.org\")"
Rscript -e "install.packages(c(\"$depends_r_str), dep=TRUE, repos=\"https://cloud.r-project.org\")"
Rscript -e "BiocManager::install(\"${depends_bioc[0]}\")"
}
module init_job
# @section Initialize a new job in the scans directory # @section Initialize a new job in the scans directory
# @description Create a new ExpJobs project # @description Create a new ExpJobs project
# TODO Copy over source image directories from robot - are these alse named by the ExpJobs name? # TODO Copy over source image directories from robot - are these alse named by the ExpJobs name?
init_job() { init_job() {
echo "Running: ${FUNCNAME[0]}" debug "Running: ${FUNCNAME[0]}"
if [[ -d $SCAN_DIR ]]; then if [[ -d $SCAN_DIR ]]; then
ask "$SCAN_DIR already exists, re-initialize?" || return 0 ask "$SCAN_DIR already exists, re-initialize?" || return 0
else else
@@ -124,17 +260,17 @@ init_job() {
[[ -d $SCAN_DIR/MasterPlateFiles ]] || mkdir -p "$SCAN_DIR/MasterPlateFiles" [[ -d $SCAN_DIR/MasterPlateFiles ]] || mkdir -p "$SCAN_DIR/MasterPlateFiles"
DRUG_MEDIA_FILE="$SCAN_DIR/MasterPlateFiles/DrugMedia_$PROJECT_NAME.xls" DRUG_MEDIA_FILE="$SCAN_DIR/MasterPlateFiles/DrugMedia_$PROJECT.xls"
MASTER_PLATE_FILE="$SCAN_DIR/MasterPlateFiles/MasterPlate_$PROJECT_NAME.xls" MASTER_PLATE_FILE="$SCAN_DIR/MasterPlateFiles/MasterPlate_$PROJECT.xls"
# TODO Where are the actual templates? # TODO Where are the actual templates?
for f in $DRUG_MEDIA_FILE $MASTER_PLATE_FILE; do for f in $DRUG_MEDIA_FILE $MASTER_PLATE_FILE; do
touch "$f" touch "$f"
done done
} }
module easy
# @section EASY # @section EASY
# @description Start an EASY analysis # @description Start an EASY analysis
# The QHTCPImageFolders and ‘MasterPlateFiles’ folder are the inputs for image analysis with EASY software. # The QHTCPImageFolders and ‘MasterPlateFiles’ folder are the inputs for image analysis with EASY software.
@@ -142,7 +278,7 @@ init_job() {
# The ‘Results’ directory is created and entered, using the “File >> New Experiment” dropdown in EASY. # The ‘Results’ directory is created and entered, using the “File >> New Experiment” dropdown in EASY.
# Multiple ‘Results’ files may be created (and uniquely named) within an ‘ExperimentJob’ folder. # Multiple ‘Results’ files may be created (and uniquely named) within an ‘ExperimentJob’ folder.
easy() { easy() {
echo "Running: ${FUNCNAME[0]}" debug "Running: ${FUNCNAME[0]}"
EASY="/mnt/data/EASY/EasyDev2024/BU/EASY240430AppExported/EstartConsole.m" EASY="/mnt/data/EASY/EasyDev2024/BU/EASY240430AppExported/EstartConsole.m"
pushd "$SCAN_DIR" || return 1 pushd "$SCAN_DIR" || return 1
@@ -172,22 +308,35 @@ easy() {
echo "EASY OUTPUT ARRAY: " "${EASY_OUT_ARRAY[@]}" echo "EASY OUTPUT ARRAY: " "${EASY_OUT_ARRAY[@]}"
} }
module ezview
# @section EZView # @section EZView
ezview() { ezview() {
echo "Running: ${FUNCNAME[0]}" debug "Running: ${FUNCNAME[0]}"
EZVIEW_DIR="/mnt/data/EZVIEW" EZVIEW_DIR="/mnt/data/EZVIEW"
echo "$EZVIEW_DIR" echo "$EZVIEW_DIR"
} }
# @section StudiesQHTCP module qhtcp
# @ description This section is derived from the earliest work of Jinyu Guo. As such it uses Perl scripts. Without porting these two Perl scripts into a new intergrated R script or Python script, one is contrained to use the rather crude copy-paste and and shell script inherient in the original procedures. These two Perl scripts are analyze_v2.pl and terms2tsv_v4.pl which were written in 2003 by Gavin Sherlock for the SGD gene ontology system and require perl installations of such files. These also require that the gene_ontology_edit.obo, SGD_features.tab files used in the ../Code also be included here. Without rewriting the code, one must compromise directory convenience. # @section QHTCP
# @description Main QHTCP module (functional rewrite of REMcMaster3.sh)
# @description Main loop for qhtcp modules (rewrite of REMcMaster3.sh)
qhtcp() { qhtcp() {
echo "Running: ${FUNCNAME[0]}" debug "Running: ${FUNCNAME[0]}"
TEMPLATE_DIR="$SCRIPT_DIR/templates/qhtcp" TEMPLATE_DIR="$SCRIPT_DIR/templates/qhtcp"
QHTCP_DIR="/mnt/data/StudiesQHTCP/$PROJECT_NAME" QHTCP_DIR="/mnt/data/StudiesQHTCP/$PROJECT"
# Our list of submodules (functions) to run for this module
# Put these in the appropriate order of operations
submodules=(
r_join_interact
java_extract
r_add_shift_values
r_heat_maps_zscores
r_heat_maps_homology
py_gtf
r_compile_gtf
)
while [[ -d $QHTCP_DIR ]]; do while [[ -d $QHTCP_DIR ]]; do
echo "A project already exists at $QHTCP_DIR" echo "A project already exists at $QHTCP_DIR"
@@ -202,24 +351,38 @@ qhtcp() {
echo "New project created at $QHTCP_DIR" echo "New project created at $QHTCP_DIR"
fi fi
# Create StudyInfo.csv
# Right now this is identical to the template but we can change it later
cat <<-EOF > "$QHTCP_DIR/Code/StudyInfo.csv"
ExpNumb,ExpLabel,BackgroundSD,ZscoreJoinSD,AnalysisBy
1,ExpName1,NA,NA,UserInitials
2,ExpName2,NA,NA,UserInitials
3,ExpName3,NA,NA,UserInitials
4,ExpName4,NA,NA,UserInitials
EOF
# Enter REMc directory to run the scripts there # Enter REMc directory to run the scripts there
pushd "$QHTCP_DIR/REMc" || return 1 pushd "$QHTCP_DIR/REMc" || return 1
r_join_interact && # Run each submodule
java_jingyu_extract && for s in "${submodules[@]}"; do "$s"; done
r_add_shift_values &&
r_heat_maps_zscores &&
r_heat_maps_homology &&
py_gtf &&
r_compile_gtf
popd || return 1 popd || return 1
} }
# @section Submodules
# @description Submodules provide functionaility to modules and are reusable between modules
# Use a submodule when:
# * Calling external scripts
# * Performing repetitive tasks
# *
#
submodule r_join_interact
# @description JoinInteractExps3dev.R creates REMcRdy_lm_only.csv and Shift_only.csv # @description JoinInteractExps3dev.R creates REMcRdy_lm_only.csv and Shift_only.csv
r_join_interact() { r_join_interact() {
echo "Running: ${FUNCNAME[0]}" debug "Running: ${FUNCNAME[0]}"
echo "Rscript JoinInteractExps3dev.R" echo "Rscript JoinInteractExps3dev.R"
Rscript JoinInteractExps3dev.R Rscript JoinInteractExps3dev.R
out_file="REMcRdy_lm_only.csv" out_file="REMcRdy_lm_only.csv"
@@ -230,10 +393,11 @@ r_join_interact() {
} }
submodule java_extract
# @description Jingyu's REMc java utility using file input file REMcRdy_lm_only.csv # @description Jingyu's REMc java utility using file input file REMcRdy_lm_only.csv
# and output REMcRdy_lm_only.csv-finalTable.csv # and output REMcRdy_lm_only.csv-finalTable.csv
java_jingyu_extract() { java_extract() {
echo "Running: ${FUNCNAME[0]}" debug "Running: ${FUNCNAME[0]}"
classpath="jingyuJava_1_7_extractLib.jar" classpath="jingyuJava_1_7_extractLib.jar"
out_file="REMcRdy_lm_only.csv-finalTable.csv" out_file="REMcRdy_lm_only.csv-finalTable.csv"
@@ -253,10 +417,11 @@ java_jingyu_extract() {
} }
submodule r_add_shift_values
# @description Add shift values back to REMcRdy_lm_only.csv-finalTable.csv # @description Add shift values back to REMcRdy_lm_only.csv-finalTable.csv
# and output "REMcWithShift.csv" for use with the REMc heat maps # and output "REMcWithShift.csv" for use with the REMc heat maps
r_add_shift_values() { r_add_shift_values() {
echo "Running: ${FUNCNAME[0]}" debug "Running: ${FUNCNAME[0]}"
out_file="REMcHeatmaps/REMcWithShift.csv" out_file="REMcHeatmaps/REMcWithShift.csv"
echo "Rscript AddShiftVals2.R" echo "Rscript AddShiftVals2.R"
Rscript AddShiftVals2.R Rscript AddShiftVals2.R
@@ -265,9 +430,10 @@ r_add_shift_values() {
} }
submodule r_heat_maps_zscores
# @description Execute REMcHeatmaps_zscores.R # @description Execute REMcHeatmaps_zscores.R
r_heat_maps_zscores() { r_heat_maps_zscores() {
echo "Running: ${FUNCNAME[0]}" debug "Running: ${FUNCNAME[0]}"
out_file="REMcHeatmaps/compiledREMcHeatmaps.pdf" out_file="REMcHeatmaps/compiledREMcHeatmaps.pdf"
echo "Rscript REMcHeatmaps_zscores.R" echo "Rscript REMcHeatmaps_zscores.R"
Rscript REMcHeatmaps_zscores.R Rscript REMcHeatmaps_zscores.R
@@ -278,9 +444,10 @@ r_heat_maps_zscores() {
} }
submodule r_heat_maps_homology
# @description Execute REMcHeatmaps_Z_lm_wDAmPs_andHomology_221212.R # @description Execute REMcHeatmaps_Z_lm_wDAmPs_andHomology_221212.R
r_heat_maps_homology() { r_heat_maps_homology() {
echo "Running: ${FUNCNAME[0]}" debug "Running: ${FUNCNAME[0]}"
work_dir="REMcHeatmapsWithHomology" work_dir="REMcHeatmapsWithHomology"
source_file="REMcHeatmaps/REMcWithShift.csv" source_file="REMcHeatmaps/REMcWithShift.csv"
target_file="$work_dir/REMcWithShift.csv" target_file="$work_dir/REMcWithShift.csv"
@@ -307,9 +474,10 @@ r_heat_maps_homology() {
} }
submodule py_gtf
# @description Perform GTF # @description Perform GTF
py_gtf() { py_gtf() {
echo "Running: ${FUNCNAME[0]}" debug "Running: ${FUNCNAME[0]}"
process_dir="GTF/Process" process_dir="GTF/Process"
function_dir="GTF/Function" function_dir="GTF/Function"
component_dir="GTF/Component" component_dir="GTF/Component"
@@ -325,7 +493,7 @@ py_gtf() {
# @description Not sure what to name this # @description Not sure what to name this
# @arg $1 string directory name # @arg $1 string directory name
_process() { _process() {
echo "Running: ${FUNCNAME[0]}" "$@" debug "Running: ${FUNCNAME[0]}" "$@"
pushd "$1" || return 1 pushd "$1" || return 1
shopt -s nullglob shopt -s nullglob
@@ -350,6 +518,27 @@ py_gtf() {
popd || return 1 popd || return 1
} }
# @description Perl analyze submodule
# @arg $1 string "Set 1"
# @arg $@ string
pl_analyze() {
:
}
pl_terms2tsv() {
:
}
# Perform operations in each directory # Perform operations in each directory
for d in "$process_dir" "$function_dir" "$component_dir"; do for d in "$process_dir" "$function_dir" "$component_dir"; do
set1="ORF_List_Without_DAmPs.txt" set1="ORF_List_Without_DAmPs.txt"
@@ -361,141 +550,56 @@ py_gtf() {
# @description Compile GTF in R # @description Compile GTF in R
r_compile_gtf() { r_compile_gtf() {
echo "Running: ${FUNCNAME[0]}" debug "Running: ${FUNCNAME[0]}"
echo "Rscript CompileGTF.R" echo "Rscript CompileGTF.R"
Rscript CompileGTF.R Rscript CompileGTF.R
} }
# @description Installs dependencies for the workflow
install_dependencies() {
echo "Running: ${FUNCNAME[0]}"
# Install system-wide dependencies
echo "Installing system dependencies"
case "$(uname -s)" in
Linux*|CYGWIN*|MINGW*)
ask "Detected Linux platform, continue?" || return 1
echo "You may be prompted for your sudo password to install system packages"
if hash dnf &>/dev/null; then
sudo dnf install graphviz pandoc pdftk-java gd-devel
elif hash apt &>/dev/null; then
sudo apt install graphviz pandoc pdftk-java libgd-dev
fi
;;
Darwin*)
ask "Detected Mac platform, continue?" || return 1
export HOMEBREW_BREW_GIT_REMOTE="https://github.com/Homebrew/brew"
curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh|bash
brew install graphiz
brew install gd
brew install pdftk-java
brew install pandoc
cpan File::Map ExtUtils::PkgConfig GD GO::TermFinder
;;
*)
echo "Your system could not be detected, please install dependencies manually"
;;
esac
# Install perl CPAN modules
echo "Installing perl CPAN modules"
echo "cpan File::Map ExtUtils::PkgConfig GD GO::TermFinder"
cpan File::Map ExtUtils::PkgConfig GD GO::TermFinder
# Install R packages
echo "Installing R packages"
Rscript -e 'install.packages(c(\
"BiocManager", \
"ontologyIndex" \
"ggrepel" \
"tidyverse" \
"sos" \
"openxlsx" \
"ggplot2" \
"plyr" \
"extrafont" \
"gridExtra" \
"gplots" \
"stringr" \
"plotly" \
"ggthemes" \
"pandoc" \
"rmarkdown" \
), dep=TRUE, repos="https://cloud.r-project.org")'
Rscript -e 'BiocManager::install("org.Sc.sgd.db")'
}
# @internal
ask() {
declare response
(( YES )) && return 0
read -r -p "$* [y/N]: " response
[[ ${response,,} =~ ^(yes|y)$ ]]
}
# @internal
err() { echo "Error: $*" >&2; }
# @internal
ask_pn() {
declare -g PROJECT_NAME
read -r -p "Enter a full project name (ex. ${PROJECT_PREFIX}_PROJECT_NAME): " PROJECT_NAME
}
# @internal
debug() { (( DEBUG )) && echo "Debug: $*"; }
# @description The main loop of script-run-workflow # @description The main loop of script-run-workflow
# May eventually need to add git ops # May eventually need to add git ops
# Passes on arguments # Passes on arguments
# Most variables in main() are user configurable or can be overriden by env # Most variables in main() are user configurable or can be overriden by env
main() { main() {
echo "Running: ${FUNCNAME[0]}" "$@" debug "Running: ${FUNCNAME[0]}" "$@"
# Where are we located? # Where are we located?
SCRIPT_DIR=$( cd -- "$( dirname -- "${BASH_SOURCE[0]}" )" &> /dev/null && pwd ) SCRIPT_DIR=$( cd -- "$( dirname -- "${BASH_SOURCE[0]}" )" &> /dev/null && pwd )
# Set the automatic project directory prefix # Set the automatic project directory prefix
PROJECT_PREFIX="$(whoami)_$(date +%y_%m_%d)" PROJECT_PREFIX="$(whoami)_$(date +%y_%m_%d)"
san() { [[ $1 =~ .+_[0-9][0-9]_[0-9][0-9]_[0-9][0-9]_.+ ]]; } # sanitizer regex for prefix
# When adding a module, it also should be added to this list
ALL_MODULES=(
install_dependencies
init_job
easy
ezview
qhtcp
)
declare -a PROJECT_NAMES=() # this array will hold all of the projects to run declare -ag PROJECTS=() # this array will hold all of the projects for this run
[[ $# -eq 1 ]] && PROJECT_NAMES+=("$1") # easy way to run on single dir
[[ $# -ge 2 ]] && parse_input "$@" # parse arguments with getopt
# Prompt user for the PROJECT_NAME if we still don't have one parse_input "$@" # parse arguments with getopt
if [[ ${#PROJECT_NAMES[@]} -eq 0 ]]; then # still allows for environment overrides
# Prompt user for the PROJECT if we still don't have one
if [[ ${#PROJECTS[@]} -eq 0 ]]; then # still allows for environment overrides
ask_pn ask_pn
PROJECT_NAMES+=("$PROJECT_NAME") PROJECTS+=("$PROJECT")
fi fi
# Sanitize PROJECT_NAMES for i in "${!PROJECTS[@]}"; do
# This regex should match PROJECT_PREFIX if ! san "${PROJECTS[i]}"; then
san() { [[ $1 =~ .+_[0-9][0-9]_[0-9][0-9]_[0-9][0-9]_.+ ]]; } echo "Project name ${PROJECTS[i]} is invalid"
for i in "${!PROJECT_NAMES[@]}"; do
if ! san "${PROJECT_NAME[i]}"; then
echo "Project name ${PROJECT_NAME[$i]} is invalid"
echo "Enter a replacement" echo "Enter a replacement"
ask_pn ask_pn
san "$PROJECT_NAME" || (echo "RTFM"; return 1) san "$PROJECT" || (echo "RTFM"; return 1)
PROJECT_NAME[i]="$PROJECT_NAME" PROJECTS[i]="$PROJECT"
fi fi
done done
SCANS_DIR="${SCANS_DIR:-"/mnt/data/ExpJobs"}" # TODO propose changing this to something else SCANS_DIR="${SCANS_DIR:-"/mnt/data/ExpJobs"}" # TODO propose changing this to something else
# If we don't catch with getopt or env, run all # If we don't catch with getopt or env, run all
[[ ${#MODULES[@]} -eq 0 ]] && MODULES=("${ALL_MODULES[@]}") if [[ ${#INCLUDE_MODULES[@]} -eq 0 ]]; then
MODULES=("${ALL_MODULES[@]}")
else
MODULES=("${INCLUDE_MODULES[@]}")
fi
# Exclude modules overrides include # Exclude modules from --exclude
arr=() arr=()
for m in "${MODULES[@]}"; do for m in "${MODULES[@]}"; do
[[ " ${EXCLUDE_MODULES[*]} " =~ [[:space:]]${m}[[:space:]] ]] || arr+=("$m") [[ " ${EXCLUDE_MODULES[*]} " =~ [[:space:]]${m}[[:space:]] ]] || arr+=("$m")
@@ -508,15 +612,15 @@ main() {
if ! [[ " ${ALL_MODULES[*]} " =~ [[:space:]]${MODULES[i]}[[:space:]] ]]; then if ! [[ " ${ALL_MODULES[*]} " =~ [[:space:]]${MODULES[i]}[[:space:]] ]]; then
echo "Module $m not in the module list" echo "Module $m not in the module list"
echo "Available modules: ${ALL_MODULES[*]}" echo "Available modules: ${ALL_MODULES[*]}"
read -r -p "Enter replacement name: " MODULE read -r -p "Enter replacement module name: " MODULE
! [[ " ${ALL_MODULES[*]} " =~ [[:space:]]${MODULE}[[:space:]] ]] || (echo "RTFM"; return 1) ! [[ " ${ALL_MODULES[*]} " =~ [[:space:]]${MODULE}[[:space:]] ]] || (echo "RTFM"; return 1)
MODULES[i]="$MODULE" MODULES[i]="$MODULE"
fi fi
done done
# Loop over projects # Loop over projects
for PROJECT_NAME in "${PROJECT_NAMES[@]}"; do for PROJECT in "${PROJECTS[@]}"; do
SCAN_DIR="$SCANS_DIR/$PROJECT_NAME" SCAN_DIR="$SCANS_DIR/$PROJECT"
# Run selected modules # Run selected modules
for m in "${MODULES[@]}"; do for m in "${MODULES[@]}"; do