for gene in gene_list: # First row is ensembl_id, but we ignoreit. output_writer.writerow(['did_not_read_ensembl_id', gene]) writecount += 1 print('%s rows written, no more genes to write.' %writecount) print('File written to %s' %output_fullpath) return None if __name__ == '__main__': if len(sys.argv) < 3: print('List of comma-separated input filenames (partial paths relative to input folder)'\ ' and output filename (relative to output folder) must be specified'\ ' in command line.') sys.exit() comma_separated_input_partialpaths = sys.argv[1] output_partialpath = sys.argv[2] # Parse comma-separated inputs input_partialpaths = comma_separated_input_partialpaths.split(',') input_fullpaths = [] for i in input_partialpaths: input_fullpaths.append(os.path.join(mydirs.inputdir, i)) output_fullpath = os.path.join(mydirs.inputdir, output_partialpath) gene_list = [] for filepath in input_fullpaths: gene_list += extract_gene_names_from_textfile(filepath, genename_colname) write_gene_list_to_file(output_fullpath, gene_list, write_ensembl_id=False)
for i in col_indices: influence_on_cgenes.append(current_row[i]) influence.writenext([current_gene] + influence_on_cgenes) print("%s rows read, %s written." % (influence.readrowcount, influence.writerowcount)) if __name__ == "__main__": if len(sys.argv) < 5: print( "4 files: influence matrix, aberrant, outlier, and outputfile " "must be specified in command line. \nPaths relative to input folder." ) sys.exit() influence_partialpath = sys.argv[1] aberrant_partialpath = sys.argv[2] outlier_partialpath = sys.argv[3] output_partialpath = sys.argv[4] influence_fullpath = os.path.join(mydirs.outputdir, influence_partialpath) aberrant_fullpath = os.path.join(mydirs.inputdir, aberrant_partialpath) outlier_fullpath = os.path.join(mydirs.inputdir, outlier_partialpath) output_fullpath = os.path.join(mydirs.outputdir, output_partialpath) # Get list of aberrant and list of outlier genes. aberrant_genes = extract_gene_names_from_textfile(aberrant_fullpath, genename_colname) outlier_genes = extract_gene_names_from_textfile(outlier_fullpath, genename_colname) # Get influence values between aberrant genes and outlier genes. get_influence(influence_fullpath, aberrant_genes, outlier_genes, output_fullpath)
output_writer.writerow(['did_not_read_ensembl_id', gene]) writecount += 1 print('%s rows written, no more genes to write.' % writecount) print('File written to %s' % output_fullpath) return None if __name__ == '__main__': if len(sys.argv) < 3: print('List of comma-separated input filenames (partial paths relative to input folder)'\ ' and output filename (relative to output folder) must be specified'\ ' in command line.') sys.exit() comma_separated_input_partialpaths = sys.argv[1] output_partialpath = sys.argv[2] # Parse comma-separated inputs input_partialpaths = comma_separated_input_partialpaths.split(',') input_fullpaths = [] for i in input_partialpaths: input_fullpaths.append(os.path.join(mydirs.inputdir, i)) output_fullpath = os.path.join(mydirs.inputdir, output_partialpath) gene_list = [] for filepath in input_fullpaths: gene_list += extract_gene_names_from_textfile(filepath, genename_colname) write_gene_list_to_file(output_fullpath, gene_list, write_ensembl_id=False)
influence.writenext([current_gene] + influence_on_cgenes) print('%s rows read, %s written.' % (influence.readrowcount, influence.writerowcount)) if __name__ == '__main__': if len(sys.argv) < 5: print('4 files: influence matrix, aberrant, outlier, and outputfile '\ 'must be specified in command line. \nPaths relative to input folder.') sys.exit() influence_partialpath = sys.argv[1] aberrant_partialpath = sys.argv[2] outlier_partialpath = sys.argv[3] output_partialpath = sys.argv[4] influence_fullpath = os.path.join(mydirs.outputdir, influence_partialpath) aberrant_fullpath = os.path.join(mydirs.inputdir, aberrant_partialpath) outlier_fullpath = os.path.join(mydirs.inputdir, outlier_partialpath) output_fullpath = os.path.join(mydirs.outputdir, output_partialpath) # Get list of aberrant and list of outlier genes. aberrant_genes = extract_gene_names_from_textfile(aberrant_fullpath, genename_colname) outlier_genes = extract_gene_names_from_textfile(outlier_fullpath, genename_colname) # Get influence values between aberrant genes and outlier genes. get_influence(influence_fullpath, aberrant_genes, outlier_genes, output_fullpath)