--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/adjust_bracken_kreport_for_unclassified_reads.py	Thu Oct 27 19:13:25 2022 +0000
@@ -0,0 +1,73 @@
+#!/usr/bin/env python
+
+import argparse
+import csv
+import json
+import sys
+
+
+def parse_kraken_report(kraken_report_path):
+    kraken_report = []
+    with open(kraken_report_path, 'r') as f:
+        for line in f:
+            kraken_line = {}
+            [percentage, seqs_total, seqs_this_level, taxonomic_level, ncbi_taxid, taxon_name] = line.strip().split('\t')
+            kraken_line['percentage'] = float(percentage)
+            kraken_line['seqs_total'] = int(seqs_total)
+            kraken_line['seqs_this_level'] = int(seqs_this_level)
+            kraken_line['taxonomic_level'] = taxonomic_level
+            kraken_line['ncbi_taxid'] = ncbi_taxid
+            kraken_line['taxon_name'] = taxon_name
+            kraken_report.append(kraken_line)
+
+    return kraken_report
+
+
+def main(args):
+    kraken_report = parse_kraken_report(args.kraken_report)
+    kraken_style_bracken_report = parse_kraken_report(args.kraken_style_bracken_report)
+
+    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']
+    kraken_style_bracken_report_classified_seqs = list(filter(lambda x: x['taxon_name'] == 'root', kraken_style_bracken_report))[0]['seqs_total']
+
+    total_seqs = kraken_style_bracken_report_classified_seqs + kraken_report_unclassified_seqs
+    fraction_unclassified = float(kraken_report_unclassified_seqs) / float(total_seqs)
+
+    output_fieldnames = [
+        'percentage',
+        'seqs_total',
+        'seqs_this_level',
+        'taxonomic_level',
+        'ncbi_taxid',
+        'taxon_name',
+    ]
+    
+    writer = csv.DictWriter(sys.stdout, fieldnames=output_fieldnames, dialect='excel-tab')
+
+    bracken_unclassified_entry = {
+        'percentage': '{:.2f}'.format(kraken_report_unclassified_seqs / total_seqs * 100),
+        'seqs_total': kraken_report_unclassified_seqs,
+        'seqs_this_level': kraken_report_unclassified_seqs,
+        'taxonomic_level': 'U',
+        'ncbi_taxid': 0,
+        'taxon_name': 'unclassified',
+    }
+
+    for row in kraken_style_bracken_report:
+        row['percentage'] = '{:.2f}'.format(row['seqs_total'] / total_seqs * 100)
+
+    kraken_style_bracken_report_with_unclassified = [bracken_unclassified_entry] + kraken_style_bracken_report
+    for row in kraken_style_bracken_report_with_unclassified:
+        writer.writerow(row)
+
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser()
+    parser.add_argument('-k', '--kraken-report')
+    parser.add_argument('-b', '--kraken-style-bracken-report')
+    args = parser.parse_args()
+    main(args)