Merge pull request #2 from simpsonlab/add_mixture_qc_flag

Add mixture qc flag

bin/collect_qc_summary.py

@@ -21,6 +21,7 @@
 args = parser.parse_args()
 
 summary_data = collect_qc_summary_data(path=args.path)
+summary_data.sort()
 
 write_qc_summary_header()
 for summary_line in summary_data:

bin/get_qc.py

@@ -7,6 +7,7 @@
 import sys
 import ncov.parser.qc as qc
 import ncov.parser
+import csv
 
 parser = argparse.ArgumentParser(description="Tool for summarizing QC data")
 parser.add_argument('-c', '--consensus', help='<sample>.consensus.fasta file to process')
@@ -22,6 +23,8 @@
                     help='full path to the alleles.tsv file')
 parser.add_argument('-s', '--sample',
                     help='name of sample being processed')
+parser.add_argument('-x', '--mixture', default=None,
+                    help='full path to the mixture report')
 parser.add_argument('-p', '--platform', default='illumina',
                     help='sequencing platform used')
 parser.add_argument('-r', '--run_name',
@@ -80,6 +83,18 @@
 if qc_line['num_consensus_iupac'] > 5:
     qc_flags.append("EXCESS_AMBIGUITY")
 
+# the mixture report is currently generated for illuina runs, ont is
+# not supported at this time
+if args.mixture:
+    if args.platform == 'illumina':
+        mixture = set()
+        with open(args.mixture, 'r') as mfh:
+            reader = csv.DictReader(mfh, delimiter='\t')
+            for record in reader:
+                mixture.add(record['sample_a'])
+        if args.sample in mixture:
+            qc_flags.append("POSSIBLE_MIXTURE")
+
 # Calculate number of variants per week, while accounting for incompleteness
 if qc_line['num_weeks'] != 'NA':
 

setup.py

@@ -8,14 +8,15 @@
 
 setuptools.setup(
     name="ncov_parser",
-    version="0.6.0",
+    version="0.6.1",
     author="Richard J. de Borja",
     author_email="[email protected]",
     description="A nCoV package for parsing analysis files",
     long_description=long_description,
     long_description_content_type="text/markdown",
     url="https://github.com/rdeborja/ncov_parser",
     packages=setuptools.find_packages(),
+    license="MIT",
     classifiers=[
         "Programming Language :: Python :: 3",
         "License :: OSI Approved :: MIT License",