Files
hartman-server/workflow/.old/apps/remc/GTF/Concatenate_GTF_results.py

72 lines
2.0 KiB
Python

#!/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 sys, os, string, glob
# return the file list
def list_all_files(Path):
list_all_files = []
list_all_files = glob.glob(Path +'/*.txt.tsv')
return list_all_files
# Main function
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)
# Open the output file
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_all_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()