Mercurial > repos > public-health-bioinformatics > adjust_bracken_for_unclassified_reads
diff adjust_bracken_for_unclassified_reads.py @ 2:87459bd1615a draft
planemo upload for repository https://github.com/public-health-bioinformatics/galaxy_tools/blob/master/tools/adjust_bracken_for_unclassified_reads commit 4ebe8216c423e2d66be92247f273df21cb5852f1
| author | public-health-bioinformatics |
|---|---|
| date | Thu, 27 Oct 2022 00:37:27 +0000 |
| parents | 3ab9d37e547e |
| children |
line wrap: on
line diff
--- a/adjust_bracken_for_unclassified_reads.py Thu Mar 10 21:39:43 2022 +0000 +++ b/adjust_bracken_for_unclassified_reads.py Thu Oct 27 00:37:27 2022 +0000 @@ -43,23 +43,14 @@ kraken_report = parse_kraken_report(args.kraken_report) bracken_abundances = parse_bracken_abundances(args.bracken_abundances) - kraken_report_unclassified_seqs = list(filter(lambda x: x['taxon_name'] == 'unclassified', kraken_report))[0]['seqs_this_level'] + try: + kraken_report_unclassified_seqs = list(filter(lambda x: x['taxon_name'] == 'unclassified', kraken_report))[0]['seqs_this_level'] + except IndexError as e: + kraken_report_unclassified_seqs = 0 kraken_report_classified_seqs = list(filter(lambda x: x['taxon_name'] == 'root', kraken_report))[0]['seqs_total'] total_seqs = kraken_report_classified_seqs + kraken_report_unclassified_seqs - percent_unclassified = float(kraken_report_unclassified_seqs) / float(total_seqs) - - bracken_unclassified_entry = { - 'name': 'unclassified', - 'taxonomy_id': 0, - 'taxonomy_lvl': 'U', - 'kraken_assigned_seqs': kraken_report_unclassified_seqs, - 'bracken_assigned_seqs': kraken_report_unclassified_seqs, - 'kraken_fraction_total_seqs': percent_unclassified, - 'bracken_fraction_total_seqs': 0.0, - } - - bracken_abundances = [bracken_unclassified_entry] + bracken_abundances + fraction_unclassified = float(kraken_report_unclassified_seqs) / float(total_seqs) output_fieldnames = [ 'name', @@ -82,7 +73,20 @@ bracken_adjusted_fraction_total_seqs = float(b['bracken_assigned_seqs']) / float(total_seqs) b['bracken_fraction_total_seqs'] = '{:.6f}'.format(bracken_adjusted_fraction_total_seqs) - for b in sorted(bracken_abundances, key=lambda x: x['bracken_fraction_total_seqs'], reverse=True): + bracken_unclassified_entry = { + 'name': 'unclassified', + 'taxonomy_id': 0, + 'taxonomy_lvl': 'U', + 'kraken_assigned_seqs': kraken_report_unclassified_seqs, + 'bracken_assigned_seqs': kraken_report_unclassified_seqs, + 'total_seqs': total_seqs, + 'kraken_fraction_total_seqs': '{:.6f}'.format(fraction_unclassified), + 'bracken_fraction_total_seqs': '{:.6f}'.format(fraction_unclassified), + } + + bracken_abundances = sorted(bracken_abundances, key=lambda x: x['bracken_fraction_total_seqs'], reverse=True) + bracken_abundances = [bracken_unclassified_entry] + bracken_abundances + for b in bracken_abundances: writer.writerow(b)