Mercurial > repos > public-health-bioinformatics > fastp_json_to_tabular
diff fastp_json_to_tabular.py @ 3:e342bf27e717 draft
"planemo upload for repository https://github.com/public-health-bioinformatics/galaxy_tools/tree/master/tools/fastp_json_to_tabular commit fb12c97e94741abedc71332572bdcb33338504a7"
| author | public-health-bioinformatics |
|---|---|
| date | Thu, 10 Mar 2022 19:03:59 +0000 |
| parents | dc655c5e77d6 |
| children | b86961fa4ac4 |
line wrap: on
line diff
--- a/fastp_json_to_tabular.py Thu Mar 10 00:13:02 2022 +0000 +++ b/fastp_json_to_tabular.py Thu Mar 10 19:03:59 2022 +0000 @@ -7,31 +7,54 @@ with open(args.fastp_json, 'r') as f: fastp_report = json.load(f) + reads_single_paired = fastp_report['summary']['sequencing'].split(' ')[0] + + if reads_single_paired == 'paired': + total_read_pairs_before_filtering = str(int(fastp_report['summary']['before_filtering']['total_reads']) / 2) + total_read_pairs_after_filtering = str(int(fastp_report['summary']['after_filtering']['total_reads']) / 2) + read2_mean_length_before_filtering = fastp_report['summary']['before_filtering']['read2_mean_length'] + read2_mean_length_after_filtering = fastp_report['summary']['after_filtering']['read2_mean_length'] + else: + total_read_pairs_before_filtering = 'NA' + total_read_pairs_after_filtering = 'NA' + read2_mean_length_before_filtering = 'NA' + read2_mean_length_after_filtering = 'NA' + total_reads_before_filtering = fastp_report['summary']['before_filtering']['total_reads'] total_reads_after_filtering = fastp_report['summary']['after_filtering']['total_reads'] + total_bases_before_filtering = fastp_report['summary']['before_filtering']['total_bases'] total_bases_after_filtering = fastp_report['summary']['after_filtering']['total_bases'] + read1_mean_length_before_filtering = fastp_report['summary']['before_filtering']['read1_mean_length'] - read2_mean_length_before_filtering = fastp_report['summary']['before_filtering']['read2_mean_length'] read1_mean_length_after_filtering = fastp_report['summary']['after_filtering']['read1_mean_length'] - read2_mean_length_after_filtering = fastp_report['summary']['after_filtering']['read2_mean_length'] + q20_bases_before_filtering = fastp_report['summary']['before_filtering']['q20_bases'] q20_bases_after_filtering = fastp_report['summary']['after_filtering']['q20_bases'] + q20_rate_before_filtering = fastp_report['summary']['before_filtering']['q20_rate'] q20_rate_after_filtering = fastp_report['summary']['after_filtering']['q20_rate'] + q30_bases_before_filtering = fastp_report['summary']['before_filtering']['q30_bases'] q30_bases_after_filtering = fastp_report['summary']['after_filtering']['q30_bases'] + q30_rate_before_filtering = fastp_report['summary']['before_filtering']['q30_rate'] q30_rate_after_filtering = fastp_report['summary']['after_filtering']['q30_rate'] + gc_content_before_filtering = fastp_report['summary']['before_filtering']['gc_content'] gc_content_after_filtering = fastp_report['summary']['after_filtering']['gc_content'] - adapter_trimmed_reads = fastp_report['adapter_cutting']['adapter_trimmed_reads'] - adapter_trimmed_bases = fastp_report['adapter_cutting']['adapter_trimmed_bases'] - + if 'adapter_cutting' in fastp_report: + adapter_trimmed_reads = fastp_report['adapter_cutting']['adapter_trimmed_reads'] + adapter_trimmed_bases = fastp_report['adapter_cutting']['adapter_trimmed_bases'] + else: + adapter_trimmed_reads = 0 + adapter_trimmed_bases = 0 output_fields = [ 'total_reads_before_filtering', + 'total_read_pairs_before_filtering', 'total_reads_after_filtering', + 'total_read_pairs_after_filtering', 'total_bases_before_filtering', 'total_bases_after_filtering', 'read1_mean_length_before_filtering', @@ -58,10 +81,12 @@ output_data = [args.sample_id] print(args.delimiter.join(output_fields)) - + output_data = output_data + [ total_reads_before_filtering, + total_read_pairs_before_filtering, total_reads_after_filtering, + total_read_pairs_after_filtering, total_bases_before_filtering, total_bases_after_filtering, read1_mean_length_before_filtering,