if __name__ == '__main__':
""" This script creates a file which needs to be filled with information required for a methylSeq project.
- It takes one argument, the 'outfile', which is the name of the output file. The default is 'analysis_info.txt'"""
parser=argparse.ArgumentParser(prog='create_sampleNames.py', description='Creates sample_names.txt with sample names')
parser.add_argument('-v','--version',action='version',version='%(prog)s-'+__version__)
parser.add_argument('--analysis_info_file', help='Text file with details of the analysis. Default=analysis_info.txt', default='analysis_info.txt')
parser.add_argument('--in_dir', help='Directory saving the fastq files', default='bcl2fastq_output')
parser.add_argument('--out_file', help='Output dir to save sample_names.txt', default='./sample_names.txt')
args=parser.parse_args()
# Collect info from analysis_info_file
if args.in_dir == 'bcl2fastq_output':
ai=functions.read_analysis_info_file(args.analysis_info_file)
allFiles=functions.get_filepaths(ai[args.in_dir])
fastq=[allFiles[y] for y, x in enumerate(allFiles) if re.findall("fastq.gz", x)]
fastq=[fastq[y] for y,x in enumerate(fastq) if not re.findall('Undetermined', x)]
elif args.in_dir != 'bcl2fastq_output':
allFiles=os.listdir(args.in_dir)
fastq=[allFiles[y] for y, x in enumerate(allFiles) if re.findall("fastq.gz", x)]
fastq=[re.sub('.*/','', f) for f in fastq]
fastq=[re.sub('_R[0-9_].*','',f) for f in fastq]
fastq=list(set(fastq))
#fastq=[f.replace('.fastq.gz', '') for f in fastq]
#print fastq
#fastq=[f.replace('.','') for f in fastq]
#print fastq
params_file = args.analysis_info_file
path = functions.read_parameters_file(params_file)['Working directory']
os.chdir(path)
# Read sample names text file
sampleNames = functions.read_sample_names()
# Set input and output directories if not 'rawReads/'
in_dir = args.in_dir
out_dir = args.out_dir
out_dir_plots = args.out_dir_plots
readType = args.readType
suffix_name = args.suffix_name
files = functions.get_filepaths(in_dir)
files = [
files[y] for y, x in enumerate(files)
if re.findall("fastqc_data.txt", x)
]
Parallel(n_jobs=8)(delayed(tables)(i) for i in files)
functions.make_sure_path_exists(out_dir_plots)
Parallel(n_jobs=8)(delayed(plots)(i) for i in sampleNames)
os.system('Rscript /usr/local/bin/fastqc_plots_all_part2.R ' + in_dir +
' ' + 'sample_names.txt' + ' ' + readType + ' ' + out_dir_plots +
' ' + suffix_name)
#os.system('ls rawReads/*/*fastqc | grep -v trimmed | grep ":" | sed \'s/://g\' > sample_names2.txt')
#os.system('fastqc_summary.py ./sample_names2.txt ./summary_fastqc.txt')
os.chdir(ai['project_location'])
# Read sample names
sample_names_file = args.sample_names_file
sampleNames = functions.read_sample_names(sample_names_file)
# Create rawReads folder
# Check if rawReads exists
project_location=ai['project_location']
folders = os.listdir(project_location)
readsFiles = [folders[i] for i, x in enumerate(folders) if re.findall('rawReads',x)]
# print readsFiles
# Collect fastq files analysis_info_file
if args.in_dir == 'bcl2fastq_output':
allFiles=functions.get_filepaths(ai['project_location'] + '/' + ai[args.in_dir])
fastq=[allFiles[y] for y, x in enumerate(allFiles) if re.findall("fastq.gz", x)]
fastq=[fastq[y] for y,x in enumerate(fastq) if not re.findall('Undetermined', x)]
elif args.in_dir != 'bcl2fastq_output':
allFiles=os.listdir(args.in_dir)
fastq=[allFiles[y] for y, x in enumerate(allFiles) if re.findall("fastq.gz", x)]
fastq=[args.in_dir + x for x in fastq]
# print fastq
# Move reads
if not readsFiles:
functions.make_sure_path_exists('rawReads')
sampleDir = []
for sample in sampleNames:
reads = [fastq[i] for i,x in enumerate(fastq) if re.findall(sample,x)]
if sample not in sampleDir:
# Get wd
path=os.getcwd()
#Ncores
ncores=int(args.ncores)
# Read sample names text file
ai=functions.read_analysis_info_file(args.analysis_info_file)
sample_names_file=args.sample_names_file
sampleNames = functions.read_sample_names(sample_names_file)
# Set input and output directories if not 'rawReads/'
in_dir=path + '/' + args.in_dir
out_dir_report=path + '/' + args.out_dir_report
readType=ai['readType']
suffix_name=args.suffix_name
# Create tables
files=functions.get_filepaths(in_dir)
files = [files[y] for y, x in enumerate(files) if re.findall("fastqc_data.txt", x)]
Parallel(n_jobs=8)(delayed(tables)(i) for i in files)
print "Got data from fastqc output... \n"
# Create plots
functions.make_sure_path_exists(out_dir_report)
Parallel(n_jobs=8)(delayed(plots)(i) for i in sampleNames)
print "Made plots per sample... \n"
os.system('Rscript bin/create_fastqcPlots_allSamples.R ' + in_dir + ' ' + sample_names_file + ' ' + readType + ' ' + out_dir_report + ' ' + suffix_name + ' ' + args.plot_device)
print "Made plots all samples... \n"
