def find_crossed(dataset, chrlist, fixed, run, borutaruns, perc): """ Searching for crossed SNPs among given data sets, writing them into files. :param dataset: (dict) the keys are name of data sets, values are directories to folders with them :param chrlist: (list) chromosomes for analysis :param fixed: (boolean) if number of run can be overwritten :param run: (int or None) number of run given as a parameter - None if not given :return: number of crossed SNPs for the given data sets """ crossed_snps = 0 runs = {} for setname in dataset.keys(): runs[setname] = funcs.establish_run('crossed', fixed, dataset[setname] + 'crossed/', run) for ch in chrlist: print('Analysis for chromosome %d has started!' % ch) crossed, ref = subset_funcs.first_intersection(dataset, ch, borutaruns, perc) ''' for setname in list(dataset.keys())[2:]: set = open('%smatrices/snps_chr%d.txt' % (dataset[setname], ch), 'r') crossed = subset_funcs.next_intersection(set, crossed, ref, ch) ''' for n, setname in enumerate(dataset.keys()): file = open( '%scrossed/crossed_snps_chr%d_%d.txt' % (dataset[setname], ch, runs[setname]), 'w') for snp in sorted(crossed.keys()): file.write('%d\n' % crossed[snp][n]) file.close() crossed_snps += len(crossed) print('For chr %d found %d crossed SNPs.' % (ch, len(crossed))) print('Run information for every dataset is writing to the file.') for setname in dataset.keys(): funcs.runs_file_add( 'crossed', dataset[setname] + 'crossed/', runs[setname], '%d\t%s\t%s\t%s\t%d\t%s\t%d\n' % (runs[setname], setname, ', '.join([ k for k in dataset.keys() if k != setname ]), funcs.make_chrstr(chrlist), crossed_snps, ','.join( list(map(str, borutaruns.values()))), perc)) return crossed_snps
def update_chrlist(fixed, linechrs, chrlist): chrs = funcs.read_chrstr(linechrs) + chrlist for key, value in Counter(chrs).items(): if value > 1: if not fixed: print( "WARNING: chromosome %d has already been analysed in this run, so it was omitted. " % key + "If you want to analyse it anyway, please add '-fixed' attribute" ) chrlist.remove(key) if not chrlist: raise exceptions.WrongValueError( 'chrlist', chrlist, 'There are no chromosomes to analyze!!!') chrs = list(set(chrs)) chrs.sort() return funcs.make_chrstr(chrs)
def map_locs_to_rows(directory, infile, run, fixed, name, analysistype='frombed'): run = funcs.establish_run(analysistype, fixed, '%s%s/' % (directory, analysistype), run) bedfile = open(infile, 'r') bedline = bedfile.readline().strip().split() ch = int(bedline[0].strip('chr')) pos = int(bedline[2]) chrlist = [ch] numsnps = 0 while bedline: out = open( '%s%s/%s_snps_chr%d_%d.txt' % (directory, analysistype, analysistype, ch, run), 'w') print('Rewriting SNPs for chr %s' % ch) with open('%smatrices/snps_chr%d.txt' % (directory, ch), 'r') as snpfile: for i, snpline in enumerate(snpfile): if snpline.startswith(str(pos)): out.write('%d\n' % i) numsnps += 1 bedline = bedfile.readline().strip().split() if not bedline: break pos = int(bedline[2]) if int(bedline[0].strip('chr')) != ch: ch = int(bedline[0].strip('chr')) chrlist.append(ch) break out.close() bedfile.close() funcs.runs_file_add( analysistype, '%s%s/' % (directory, analysistype), run, '%d\t%s\t%s\t%d\t%s\t' % (run, infile, name, numsnps, funcs.make_chrstr(chrlist))) print('%s SNPs were rewritten to a %s file!' % (numsnps, analysistype)) return 0
if not continuation: if patruns is None: patruns_string = '-' else: patruns_string = '+'.join(list(map(str, patruns.values()))) if snpruns is None: snpruns_string = '-' else: snpruns_string = '+'.join(list(map(str, snpruns.values()))) funcs.runs_file_add( 'boruta', outdir, borutarun, '%d\t%s\t%d\t%s\t%s\t%s\t%s\t%.2f\t%s\t%d\t%s\n' % (borutarun, '+'.join(dataset.keys()), len(trainpat) + len(testpat), patsubset, patruns_string, snpsubset, snpruns_string, testsize, ','.join(list(map(str, perc))), r, funcs.make_chrstr(chrlist))) else: funcs.runs_file_rewrite('boruta', outdir, towrite) if not boruta_only: if classrun is None and run is not None: classrun = run # determination of number of class run classrun = funcs.establish_run('class', fixed, outdir, classrun) scores_file = open('%sclass_scores_%d.txt' % (outdir, classrun), 'w', 1) if frombed and cv: scores_file.write( 'perc\tSNPs\tdataset_train_score\tdataset_test_score\tdataset_AUC\ttestset_score\ttestset_AUC\n' )
runs[name] = funcs.establish_run('boruta', fixed, outdir, runs[name]) testpat, trainpat = read_patlist(dataset, outdir, pat, patsubset, patruns, testsize) else: dataset, outdir, patruns, perc, r, snpsubset, snpruns, testpat, testsize, towrite, trainpat = \ read_boruta_params(chrlist, continuation, dataset, fixed, pat, runs) # running Boruta analysis pooling(chrlist, dataset, outdir, pat, perc, r, borutarun, snpsubset, snpruns, testpat, trainpat) # saving information about done run to boruta_runs file if not continuation: if patruns is None: patruns_string = '-' else: patruns_string = '+'.join(list(map(str, patruns.values()))) if snpruns is None: snpruns_string = '-' else: snpruns_string = '+'.join(list(map(str, snpruns.values()))) funcs.runs_file_add( 'boruta', outdir, borutarun, '%d\t%s\t%d\t%s\t%s\t%s\t%s\t%.2f\t%s\t%d\t%s\n' % (borutarun, '+'.join(dataset.keys()), len(trainpat) + len(testpat), patsubset, patruns_string, snpsubset, snpruns_string, testsize, ','.join(list(map(str, perc))), r, funcs.make_chrstr(chrlist))) else: funcs.runs_file_rewrite('boruta', outdir, towrite)