Replace vcf.VCFReader by pysam.VariantFile

build_results.py

@@ -15,11 +15,12 @@ and is associated to the corresponding CNVs.
 """
 
 import argparse
-import vcf
 import string
 import os
 import re
 
+from pysam import VariantFile
+
 import sys
 prg_path = os.path.dirname(os.path.realpath(__file__))
 sys.path.insert(0, os.path.join(prg_path, "lib"))
@@ -172,17 +173,19 @@ def get_genotypes(genotypes_file, true_vcf_file):
     gt_quality = {}
 
     # Real data:
-    reader_t = vcf.VCFReader(filename=true_vcf_file)
+    reader_t = VariantFile(true_vcf_file)
     for rec_t in reader_t:
-        genotypes[rec_t.ID] = [x.data.GT for x in rec_t.samples]
+        samples = rec_t.samples
+        genotypes[rec_t.id] = ["/".join(map(str, samples[x]["GT"])) for x in samples]
 
     nb_inds = len(list(genotypes.values())[0])
 
     # Samples:
-    reader = vcf.VCFReader(filename=genotypes_file)
+    reader = VariantFile(genotypes_file)
     for rec in reader:
-        genotypes[rec.ID] = [x.data.GT for x in rec.samples]
-        gt_quality[rec.ID] = [x.data.GQ for x in rec.samples]
+        samples = rec.samples
+        genotypes[rec.id] = ["/".join(map(str, samples[x]["GT"])) for x in samples]
+        gt_quality[rec.id] = [samples[x]["GQ"] for x in samples]
 
     return genotypes, gt_quality, nb_inds