test v0.2.4

pirl-unc · Jul 11, 2024 · 038def0 · 038def0
1 parent cb661c5
commit 038def0
Show file tree

Hide file tree

Showing 5 changed files with 15 additions and 30 deletions.
diff --git a/pyproject.toml b/pyproject.toml
@@ -21,7 +21,7 @@ build-backend = "maturin"
 
 [project]
 name = "vstol"
-version = "0.2.3"
+version = "0.2.4"
 requires-python = ">=3.10"
 keywords = [
     "somatic variants",

diff --git a/python/vstolib/vcf/cutesv.py b/python/vstolib/vcf/cutesv.py
@@ -17,6 +17,7 @@
 
 
 import pandas as pd
+import re
 from collections import OrderedDict
 from typing import Dict
 from ..constants import NucleicAcidTypes, VariantCallingMethods, VariantTypes
@@ -134,20 +135,12 @@ def parse_cutesv_callset(
             if 'AF' in attributes.keys():
                 alternate_allele_fraction = get_typed_value(value=attributes['AF'], default_value=-1.0, type=float)
 
-            # Update chromosome_2 for 'BND' or 'TRA'
+            # Update chromosome_2 and position_2 for 'BND' or 'TRA'
             if variant_type in [VariantTypes.BREAKPOINT, VariantTypes.TRANSLOCATION]:
-                chromosome_2 = alternate_allele.split(":")[0]
-                chromosome_2 = chromosome_2.replace("[", "")
-                chromosome_2 = chromosome_2.replace("]", "")
-                chromosome_2 = chromosome_2.replace("N", "")
-
-            # Update position_2 for 'BND' or 'TRA'
-            if variant_type in [VariantTypes.BREAKPOINT, VariantTypes.TRANSLOCATION]:
-                position_2 = alternate_allele.split(":")[1]
-                position_2 = position_2.replace("[", "")
-                position_2 = position_2.replace("]", "")
-                position_2 = position_2.replace("N", "")
-                position_2 = int(position_2)
+                pattern = re.compile(r'(chr\S+):(\d+)')
+                matches = pattern.findall(str(row['ALT']))
+                chromosome_2 = str(matches[0][0])
+                position_2 = int(matches[0][1])
 
             # Update variant_size for 'BND' or 'TRA'
             if (variant_type in [VariantTypes.BREAKPOINT, VariantTypes.TRANSLOCATION]) and \

diff --git a/python/vstolib/vcf/savana.py b/python/vstolib/vcf/savana.py
@@ -149,7 +149,7 @@ def parse_savana_callset(
 
             # Update chromosome_2 and position_2 for 'BND'
             if variant_type == VariantTypes.BREAKPOINT or variant_type == VariantTypes.TRANSLOCATION:
-                pattern = re.compile(r'(chr(?:\d+|X|Y|MT|M)):(\d+)')
+                pattern = re.compile(r'(chr\S+):(\d+)')
                 matches = pattern.findall(str(row['ALT']))
                 chromosome_2 = str(matches[0][0])
                 position_2 = int(matches[0][1])

diff --git a/python/vstolib/vcf/sniffles2.py b/python/vstolib/vcf/sniffles2.py
@@ -134,7 +134,7 @@ def parse_sniffles2_callset(
 
             # Update position_2 for 'BND'
             if variant_type == VariantTypes.BREAKPOINT or variant_type == VariantTypes.TRANSLOCATION:
-                pattern = re.compile(r'(chr(?:\d+|X|Y|MT|M)):(\d+)')
+                pattern = re.compile(r'(chr\S+):(\d+)')
                 matches = pattern.findall(str(row['ALT']))
                 position_2 = int(matches[0][1])
 

diff --git a/python/vstolib/vcf/svim.py b/python/vstolib/vcf/svim.py
@@ -17,6 +17,7 @@
 
 
 import pandas as pd
+import re
 from collections import OrderedDict
 from typing import Dict
 from ..constants import NucleicAcidTypes, VariantCallingMethods, VariantTypes
@@ -136,21 +137,12 @@ def parse_svim_callset(
             if 'READS' in attributes.keys():
                 alternate_allele_read_ids = attributes['READS'].split(',')
 
-            # Update chromosome_2 for 'BND'
+            # Update chromosome_2 and position_2 for 'BND' or 'TRA'
             if variant_type in [VariantTypes.BREAKPOINT, VariantTypes.TRANSLOCATION]:
-                alt_val = alternate_allele.split(":")[0]
-                alt_val = alt_val.replace("[", "")
-                alt_val = alt_val.replace("]", "")
-                alt_val = alt_val.replace("N", "")
-                chromosome_2 = str(alt_val)
-
-            # Update position_2 for 'BND'
-            if variant_type in [VariantTypes.BREAKPOINT, VariantTypes.TRANSLOCATION]:
-                alt_val = alternate_allele.split(":")[1]
-                alt_val = alt_val.replace("[", "")
-                alt_val = alt_val.replace("]", "")
-                alt_val = alt_val.replace("N", "")
-                position_2 = int(alt_val)
+                pattern = re.compile(r'(chr\S+):(\d+)')
+                matches = pattern.findall(str(row['ALT']))
+                chromosome_2 = str(matches[0][0])
+                position_2 = int(matches[0][1])
 
             # Update variant_size 'BND'
             if (variant_type in [VariantTypes.BREAKPOINT, VariantTypes.TRANSLOCATION]) and \