def main(countsfile, outpath, countsfile2, strand_symmetry, force_overwrite, dry_run, verbose): args = locals() table = LoadTable(countsfile, sep='\t') if not dry_run: log_file_path = os.path.join(util.abspath(outpath), 'spectra_analysis.log') LOGGER.log_file_path = log_file_path LOGGER.log_message(str(args), label='vars') LOGGER.input_file(countsfile) # if there's a strand symmetry argument then we don't need a second file if strand_symmetry: group_label = 'strand' counts_table = util.spectra_table(table, group_label) if not strand_symmetry: group_label = 'group' # be sure there's two files counts_table2 = LoadTable(countsfile2, sep='\t') LOGGER.input_file(countsfile2) counts_table2 = counts_table2.with_new_column('group', lambda x: '2', columns=counts_table2.header[0]) counts_table1 = table.with_new_column('group', lambda x: '1', columns=table.header[0]) counts_table1 = util.spectra_table(counts_table1, group_label) counts_table2 = util.spectra_table(counts_table2, group_label) # now combine header = ['group'] + counts_table2.header[:-1] raw1 = counts_table1.tolist(header) raw2 = counts_table2.tolist(header) counts_table = LoadTable(header=header, rows=raw1 + raw2) if verbose: print(counts_table) # spectra table has [count, start, end, group] order # we reduce comparisons to a start base results = [] saveable = {} for start_base in counts_table.distinct_values('start'): subtable = counts_table.filtered('start == "%s"' % start_base) columns = [c for c in counts_table.header if c != 'start'] subtable = subtable.get_columns(columns) total_re, dev, df, collated, formula = log_lin.spectra_difference( subtable, group_label) r = [list(x) for x in collated.to_records(index=False)] if not strand_symmetry: grp_labels = {'1': countsfile, '2': countsfile2} grp_index = list(collated.columns).index('group') for row in r: row[grp_index] = grp_labels[row[grp_index]] p = chisqprob(dev, df) if p < 1e-6: prob = "%.2e" % p else: prob = "%.6f" % p for row in r: row.insert(0, start_base) row.append(prob) results += r significance = ["RE=%.6f" % total_re, "Dev=%.2f" % dev, "df=%d" % df, "p=%s" % p] stats = " : ".join(significance) print("Start base=%s %s" % (start_base, stats)) saveable[start_base] = dict(rel_entropy=total_re, deviance=dev, df=df, prob=p, formula=formula, stats=collated.to_json()) table = LoadTable(header=['start_base'] + list(collated.columns) + ['prob'], rows=results, digits=5).sorted(columns='ret') json_path = None outpath = util.abspath(outpath) if not dry_run: util.makedirs(outpath) json_path = os.path.join(outpath, 'spectra_analysis.json') dump_json(saveable, json_path) LOGGER.output_file(json_path) table_path = os.path.join(outpath, 'spectra_summary.txt') table.write(table_path, sep='\t') LOGGER.output_file(table_path) LOGGER.log_message(str(significance), label="significance")
def main(counts_pattern, output_path, strand_symmetric, split_dir, dry_run, force_overwrite): """export tab delimited combined counts table by appending the 12 mutation direction tables, adding a new column ``direction``.""" args = locals() output_path = abspath(output_path) if strand_symmetric and split_dir: split_dir = abspath(split_dir) else: split_dir = None # check we the glob pattern produces the correct number of files counts_files = glob.glob(counts_pattern) check_found_filenames(counts_files) counts_filename = os.path.join(output_path, 'combined_counts.txt') runlog_path = os.path.join(output_path, "combined_counts.log") if not dry_run: if not force_overwrite and (os.path.exists(counts_filename) or os.path.exists(runlog_path)): msg = "Either %s or %s already exist. Force overwrite of "\ "existing files with -F." raise ValueError(msg % (counts_filename, runlog_path)) makedirs(output_path) if split_dir: makedirs(split_dir) LOGGER.log_file_path = runlog_path LOGGER.log_message(str(args), label='vars') for fn in counts_files: LOGGER.input_file(fn, label="count_file") start_time = time.time() # run the program all_counts = [] header = None num_rows = 0 basenames = [] for fn in counts_files: basenames.append(os.path.basename(fn)) mutation = direction.findall(fn)[0] table = LoadTable(fn, sep='\t') if header is None: header = list(table.header) header.append('direction') num_rows = table.shape[0] data = table.tolist() new = [] for row in data: row.append(mutation) new.append(row) all_counts += new table = LoadTable(header=header, rows=all_counts) if strand_symmetric: table = make_strand_symmetric_table(table) if split_dir: group_subtables = get_subtables(table, group_label='direction') if not dry_run: table.write(counts_filename, sep='\t') LOGGER.output_file(counts_filename) if split_dir: for group, subtable in group_subtables: # we first assume that group is part of the filenames! fn = [bn for bn in basenames if group in bn] if len(fn) == 1: fn = fn[0] else: fn = "%s.txt" % group counts_filename = os.path.join(split_dir, fn) subtable.write(counts_filename, sep='\t') LOGGER.output_file(counts_filename) # determine runtime duration = time.time() - start_time if not dry_run: LOGGER.log_message("%.2f" % (duration / 60.), label="run duration (minutes)") print("Done!")