######################### if __name__ == '__main__': parser = argparse.ArgumentParser(description = 'Counting Reads') 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='Path to folder containing fastq files. Default=alignedReads/', default='alignedReads/') parser.add_argument('--out_dir', help='Path to output folder. Default=countedReads/', default='countedReads/') parser.add_argument('--mapping_summary_file', help='Mapping summary file. Default=mapping_summary.csv', default='mapping_summary.csv') args=parser.parse_args() params_file=args.analysis_info_file path=functions.read_parameters_file(params_file)['Working directory'] refGenome=functions.read_parameters_file(params_file)['Reference Genome'] strand=functions.read_parameters_file(params_file)['strand'] strand_piccard, strand_htseq = functions.get_strand(strand) gtfFile=functions.read_parameters_file(params_file)['GTF File'] os.chdir(path) # Read sample names text file sampleNames = functions.read_sample_names() # Set input and output directories if not '/' in_dir=args.in_dir out_dir=args.out_dir functions.make_sure_path_exists(out_dir) mapping_summary_file=args.mapping_summary_file
parser.add_argument( '--in_dir', help='Path to folder containing fastq files. Default=alignedReads/', default='alignedReads/') parser.add_argument('--out_dir', help='Path to output folder. Default=countedReads/', default='countedReads/') parser.add_argument( '--mapping_summary_file', help='Mapping summary file. Default=mapping_summary.csv', default='mapping_summary.csv') args = parser.parse_args() params_file = args.analysis_info_file path = functions.read_parameters_file(params_file)['Working directory'] refGenome = functions.read_parameters_file(params_file)['Reference Genome'] strand = functions.read_parameters_file(params_file)['strand'] strand_piccard, strand_htseq = functions.get_strand(strand) gtfFile = functions.read_parameters_file(params_file)['GTF File'] os.chdir(path) # Read sample names text file sampleNames = functions.read_sample_names() # Set input and output directories if not '/' in_dir = args.in_dir out_dir = args.out_dir functions.make_sure_path_exists(out_dir) mapping_summary_file = args.mapping_summary_file
os.system("java -jar -Xmx2g ~/picard-tools-1.127/picard.jar CollectAlignmentSummaryMetrics R="+refGenome+" I="+outdir+"/"+i+"Aligned.sortedByCoord.out.bam O="+outdir+"/stat_align"+i+".txt") ######################### if __name__ == '__main__': parser = argparse.ArgumentParser(description = 'Mapping reads with BWA') 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='Path to folder containing fastq files. Default=trimmedReads/', default='trimmedReads/') parser.add_argument('--out_dir', help='Path to out put folder. Default=alignedReads/', default='alignedReads/') args=parser.parse_args() params_file=args.analysis_info_file path=functions.read_parameters_file(params_file)['Working directory'] refGenome=functions.read_parameters_file(params_file)['Reference Genome'] os.chdir(path) # Read sample names text file sampleNames = functions.read_sample_names() # Set input and output directories if not '/' in_dir=args.in_dir out_dir=args.out_dir functions.make_sure_path_exists(out_dir) # Detect if files are gz gz = functions.check_gz(in_dir) Parallel(n_jobs=8)(delayed(sam2bam)(i) for i in sampleNames)
default='rawReads') parser.add_argument( '--readType', help='Read Type: pairedEnd or singleEnd. Default=pairedEnd', default='pairedEnd') parser.add_argument('--out_dir_plots', help='Path to out put folder. Default=Report/figure', default='Report/figure') parser.add_argument( '--suffix_name', help='Suffix to optionally put to the output name. Default=', default='') args = parser.parse_args() 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)
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='Path to folder containing fastq files. Default=trimmedReads/', default='trimmedReads/') parser.add_argument('--out_dir', help='Path to out put folder. Default=alignedReads/', default='alignedReads/') args = parser.parse_args() params_file = args.analysis_info_file path = functions.read_parameters_file(params_file)['Working directory'] refGenome = functions.read_parameters_file(params_file)['Reference Genome'] os.chdir(path) # Read sample names text file sampleNames = functions.read_sample_names() # Set input and output directories if not '/' in_dir = args.in_dir out_dir = args.out_dir functions.make_sure_path_exists(out_dir) # Detect if files are gz gz = functions.check_gz(in_dir) Parallel(n_jobs=8)(delayed(sam2bam)(i) for i in sampleNames)
os.system('macs2 callpeak --broad -s='+fragSize+' -broadCutOff '+broadCutOff+' -q' + qCutOff + ' --bw '+fragSize+' -f '+readFormat+' -c '+indir+'/'+controlSample+'Aligned.sortedByCoord.bam -t '+in_dir+'/'+treatedSample+"Aligned.sortedByCoord.dedup.removed.out.bam -g "+genomeSize+" -n "+treatedSample+"_"+controlSample+"_bampe_q_value_filtered_dedup_00001_pval -outdir "+out_dir) else: os.system('macs2 callpeak -s='+fragSize+' -q' + qCutOff + ' --bw '+fragSize+' -f '+readFormat+' -c '+indir+'/'+controlSample+'Aligned.sortedByCoord.bam -t '+in_dir+'/'+treatedSample+"Aligned.sortedByCoord.dedup.removed.out.bam -g "+genomeSize+" -n "+treatedSample+"_"+controlSample+"_bampe_q_value_filtered_dedup_00001_pval -outdir "+out_dir) if __name__ == '__main__': parser = argparse.ArgumentParser(description = 'Peaking calling with MACS2') 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='Path to folder containing fastq files. Default=trimmedReads/', default='trimmedReads/') parser.add_argument('--out_dir', help='Path to out put folder. Default=alignedReads/', default='alignedReads/') args=parser.parse_args() params_file=args.analysis_info_file path=functions.read_parameters_file(params_file)['Working directory'] #refGenome=functions.read_parameters_file(params_file)['Reference Genome'] os.chdir(path) # Read sample names text file sampleNames = functions.read_sample_names() # Set input and output directories if not '/' in_dir=args.in_dir out_dir=args.out_dir readLength=args.read_length fragSize = args.fragSize readFormat = args.readFormat qCutOff = args.qCutoff broad = args.broad broadCutOff = args.broadCutOff
parser.add_argument( '--in_dir', help='Path to folder containing fastq files. Default=alignedReads/', default='alignedReads/') parser.add_argument( '--out_dir', help='Path to out put folder. Default=alignedReads/QC/', default='alignedReads/QC/') parser.add_argument( '--out_dir_plots', help='Path to out put folder to copy plots. Default=Report/figure/', default='Report/figure/') args = parser.parse_args() params_file = args.analysis_info_file path = functions.read_parameters_file(params_file)['Working directory'] refGenome = functions.read_parameters_file(params_file)['Reference Genome'] bedFile_10k = functions.read_parameters_file(params_file)['BedFile10K'] bedFile = functions.read_parameters_file(params_file)['BedFile'] refFlat = functions.read_parameters_file(params_file)['refFlat'] rRNA_interval_list = functions.read_parameters_file( params_file)['rRNA_interval_list'] strand = functions.read_parameters_file(params_file)['strand'] strand_piccard, strand_htseq = functions.get_strand(strand) #if strand == 'reverse': # strand = 'SECOND_READ_TRANSCRIPTION_STRAND' #os.chdir(path) # Read sample names text file sampleNames = functions.read_sample_names()