Restore output of unresolved variants during svtk vcf2bed

svtk/annotation/annotate.py

@@ -145,7 +145,8 @@ def annotate_vcf(vcf, gencode, noncoding, annotated_vcf):
         fname = vcf.filename.decode()
     else:
         fname = vcf.filename
-    sv = svu.vcf2bedtool(fname, split_bnd=True, split_cpx=True, simple_sinks=True)
+    sv = svu.vcf2bedtool(fname, split_bnd=True, split_cpx=True, 
+                         simple_sinks=True, include_unresolved=False)
 
     effects = annotate(sv, gencode, noncoding)
     effects = effects.to_dict(orient='index')

svtk/cli/utils.py

@@ -42,6 +42,10 @@ def vcf2bed(argv):
     parser.add_argument('--no-sort-coords', dest='no_sort_coords', action='store_true',
                         default=False, help='Do not sort start/end coordinates '
                         'per record before writing to bed.')
+    parser.add_argument('--no-unresolved', dest='no_unresolved', action='store_true',
+                        default=False, help='Do not output unresolved variants.')
+    parser.add_argument('--simple-sinks', dest='simple_sinks', action='store_true',
+                        default=False, help='Report all INS sinks as 1bp intervals.')
 
     # Print help if no arguments specified
     if len(argv) == 0:
@@ -64,6 +68,8 @@ def vcf2bed(argv):
             header = header + args.info
     header = '\t'.join(header)
 
+    include_unresolved = not args.no_unresolved
+
     bt = svu.vcf2bedtool(vcf,
                          split_bnd=args.split_bnd,
                          include_samples=args.include_samples,
@@ -72,7 +78,9 @@ def vcf2bed(argv):
                          include_infos=args.info,
                          annotate_ins=False,
                          report_alt=True,
-                         no_sort_coords=args.no_sort_coords)
+                         no_sort_coords=args.no_sort_coords,
+                         simple_sinks=args.simple_sinks,
+                         include_unresolved=include_unresolved)
 
     if args.bed in 'stdout -'.split():
         if args.header:

svtk/utils/utils.py

@@ -111,7 +111,8 @@ def get_called_samples(record, include_null=False):
 def vcf2bedtool(vcf, split_bnd=True, include_samples=False,
                 include_strands=True, split_cpx=False, include_infos=None,
                 annotate_ins=True, report_alt=False, svtypes=None, 
-                no_sort_coords=False, simple_sinks=False):
+                no_sort_coords=False, simple_sinks=False, 
+                include_unresolved=True):
     """
     Wrap VCF as a bedtool. Necessary as pybedtools does not support SV in VCF.
 
@@ -137,6 +138,8 @@ def vcf2bedtool(vcf, split_bnd=True, include_samples=False,
         Do not sort start & end coordinates
     simple_sinks : bool, optional
         Treat all insertion sinks as single-bp windows
+    include_unresolved : bool, optional
+        Output unresolved variants
 
     Returns
     -------
@@ -172,10 +175,11 @@ def _converter():
         for record in vcf:
             if svtypes is not None and record.info['SVTYPE'] not in svtypes:
                 continue
-            if 'UNRESOLVED' in record.info.keys() \
-            or 'UNRESOLVED_TYPE' in record.info.keys() \
-            or 'UNRESOLVED' in record.filter:
-                continue
+            if not include_unresolved:
+                if 'UNRESOLVED' in record.info.keys() \
+                or 'UNRESOLVED_TYPE' in record.info.keys() \
+                or 'UNRESOLVED' in record.filter:
+                    continue
 
             chrom = record.chrom
             name = record.id