From cc29fe602519a340cb937c1dbf9a5117def559b7 Mon Sep 17 00:00:00 2001
From: Thomas Faraut <Thomas.Faraut@inra.fr>
Date: Tue, 28 Jan 2020 14:36:59 +0100
Subject: [PATCH] more pep8 compliance
---
svreader/annotation.py | 20 +++++++++++---------
1 file changed, 11 insertions(+), 9 deletions(-)
diff --git a/svreader/annotation.py b/svreader/annotation.py
index 51ac2d1..c1aa1cf 100644
--- a/svreader/annotation.py
+++ b/svreader/annotation.py
@@ -178,7 +178,7 @@ class AnnotateRecord(VCFRecord):
filters = [f for f in record.filter]
# We make the assumption when a "." is present no other filter
# are present
- if len(filters) == 0 or "." in filters:
+ if not filters or "." in filters:
record.filter.clear()
record.filter.add("PASS")
@@ -416,7 +416,9 @@ def add_redundancy_infos_header(reader):
def redundancy_annotator(SVSet, reader,
- duplicatescore_threshold=-2, genotyper="svtyper"):
+ overlap_cutoff,
+ duplicatescore_threshold=-2,
+ genotyper="svtyper"):
""" Annotating duplicate candidates based on the genotype likelihoods
- genotype likelihoods can be provided by svtyper or genomestrip
"""
@@ -430,7 +432,7 @@ def redundancy_annotator(SVSet, reader,
pybed_variants = vcf_to_pybed(SVSet)
self_overlap = pybed_variants.intersect(pybed_variants,
- f=0.5, r=True, wo=True)
+ f=overlap_cutoff, r=True, wo=True)
seen = defaultdict(tuple)
duplicates = defaultdict(list)
@@ -519,7 +521,7 @@ def add_filter_infos_header(reader):
reader.addFilter("ABFREQ", "AB frequency <0.3 for >50% heterosamples")
-def variant_filtration(variants, reader, filter_monomorph=False,
+def variant_filtration(variant_set, reader, filter_monomorph=False,
filter_callrate=False):
""" Filtering the candidate CNVs according to the following criteria
- non duplicate sites
@@ -534,7 +536,7 @@ def variant_filtration(variants, reader, filter_monomorph=False,
add_callrate_infos_header(reader)
add_filter_infos_header(reader)
- for sv in variants:
+ for sv in variant_set:
info = sv.record.info
sv.record.info['CALLRATE'] = sv.call_rate(13)
sv.record.info['VARIANTCALLRATE'] = sv.variant_call_rate(13)
@@ -563,14 +565,14 @@ def AB_filtering(variant_set):
sv.filter.add("ABFREQ")
-def get_connected_duplicates(SVSet):
+def get_connected_duplicates(variant_set):
"""
Construct connected components of duplicates and rename the variants
"""
undirected = Graph()
variant_dict = defaultdict()
representatives = defaultdict()
- for s in SVSet:
+ for s in variant_set:
variant_dict[s.id] = s
if "DUPLICATE" in s.filter:
for dupli_repr in s.record.info["DUPLICATEOF"]:
@@ -604,8 +606,8 @@ def get_tool_name(sv_ident):
return sv_ident.split("_")[0]
-def set_supporting_tools(SVSet):
- for sv in SVSet:
+def set_supporting_tools(variant_set):
+ for sv in variant_set:
tools = {get_tool_name(sv.id)}
if "DUPLICATES" in sv.record.info:
duplicates = sv.record.info['DUPLICATES']
--
GitLab