Fix some low hanings of #154 after all

genmod/annotate_models/genetic_models.py

@@ -62,10 +62,6 @@
 from __future__ import absolute_import, print_function
 
 import logging
-import os
-import sys
-from datetime import datetime
-from pprint import pprint as pp
 
 from genmod.utils import generate_pairs
 

genmod/annotate_models/models/compound_model.py

@@ -13,9 +13,6 @@
 from __future__ import print_function
 
 import logging
-import os
-import sys
-
 
 def check_compounds(variant_1, variant_2, family, intervals, phased):
     """

genmod/annotate_models/models/recessive_model.py

@@ -11,10 +11,6 @@
 
 from __future__ import print_function
 
-import os
-import sys
-
-
 def check_recessive(variant, family, strict):
     """
     Check if the variant follows the autosomal recessive homozygote (AR_hom)

genmod/annotate_models/variant_annotator.py

@@ -18,7 +18,7 @@
 
 from genmod.vcf_tools import get_genotypes
 
-from . import check_genetic_models, get_haploblocks, get_model_score, make_print_version
+from . import check_genetic_models, get_haploblocks, make_print_version
 
 
 class VariantAnnotator(Process):

genmod/annotate_regions/parse_annotations.py

@@ -19,11 +19,6 @@
 
 import logging
 
-try:
-    import cPickle as pickle
-except:
-    import pickle
-
 from intervaltree import Interval, IntervalTree
 
 logger = logging.getLogger(__name__)

genmod/annotate_variants/read_tabix_files.py

@@ -64,7 +64,6 @@ def get_frequencies(tabix_reader, chrom, start, alt):
     Returns:
         frequencies (dict): A dictionary with relevant frequencies
     """
-    freq = None
     records = get_tabix_records(tabix_reader, chrom, start)
 
     frequencies = {}

genmod/commands/analyze.py

@@ -16,11 +16,6 @@
 
 import click
 
-try:
-    import cPickle as pickle
-except:
-    import pickle
-
 from codecs import open
 from datetime import datetime
 
@@ -398,11 +393,6 @@ def get_interesting_variants(
     help="""Specify genotype quality treshold for variants 
                             to be considered. Default 20.""",
 )
-# @click.option('-p', '--patterns',
-#                     type=click.Choice(['AR', 'AD', 'X']),
-#                     multiple=True,
-#                     help='Specify the inheritance patterns. Default is all patterns'
-# )
 @click.option(
     "-o",
     "--outdir",
@@ -465,20 +455,9 @@ def analyze(
 
     start_time_analysis = datetime.now()
 
-    # configs = ConfigObj(config_file)
-    # prefered_models = make_models([])
-
-    inheritance_keyword = "GeneticModels"
     families = check_families(variant_file)
     file_name = os.path.splitext(os.path.split(variant_file)[-1])[0]
 
-    # if config_file:
-    #     frequency_treshold = float(configs.get('frequency', {}).get('rare', frequency_treshold))
-    #     freq_keyword = configs.get('frequency', {}).get('keyword', freq_keyword)
-    #     inheritance_patterns = [pattern for pattern in configs.get('inheritance', {}).get('patterns',[])]
-    #     inheritance_keyword = configs.get('inheritance', {}).get('keyword',inheritance_keyword)
-    #     prefered_models = make_models(inheritance_patterns)
-
     if variant_file == "-":
         variant_parser = VCFParser(fsock=sys.stdin)
     else:

genmod/commands/annotate_models.py

@@ -192,14 +192,14 @@ def models(
         sys.exit(0)
 
     if vep:
-        if not "CSQ" in head.info_dict:
+        if "CSQ" not in head.info_dict:
             logger.warning("vep flag is used but there is no CSQ field specified in header")
             logger.info("Please check VCF file")
             context.abort()
         else:
             logger.info("Using VEP annotation")
     else:
-        if not keyword in head.info_dict:
+        if keyword not in head.info_dict:
             logger.warning("Annotation key {0} could not be found in VCF header".format(keyword))
             logger.info("Please check VCF file")
             context.abort()
@@ -337,11 +337,9 @@ def models(
         logger.info("Starting the variant printer process")
         variant_printer.start()
 
-        start_time_variant_parsing = datetime.now()
-
         # This process parses the original vcf and create batches to put in the variant queue:
         logger.info("Start parsing the variants")
-        chromosome_list = get_batches(
+        get_batches(
             variants=variant_file,
             batch_queue=variant_queue,
             header=head,

genmod/commands/score_compounds.py

@@ -148,10 +148,10 @@ def compound(
         logger.info("Starting the variant printer process")
         variant_printer.start()
 
-        start_time_variant_parsing = datetime.now()
+        datetime.now()
 
         # This process parses the original vcf and create batches to put in the variant queue:
-        chromosome_list = get_batches(
+        get_batches(
             variants=variant_file,
             batch_queue=variant_queue,
             header=head,

genmod/commands/score_variants.py

@@ -13,9 +13,7 @@
 
 import itertools
 import logging
-import os
 import sys
-from codecs import open
 from datetime import datetime
 
 import click

genmod/commands/summarize_variants.py

@@ -169,10 +169,6 @@ def summarize(
 
     head = HeaderParser()
 
-    nr_of_variants = 0
-
-    header = ["sample_id", "nr_of_variants"]
-
     samples = {}
 
     logger.debug("Setting up a variant parser")

genmod/errors/warning.py

@@ -11,7 +11,6 @@
 
 from __future__ import print_function, unicode_literals
 
-import os
 import sys
 
 

genmod/log.py

@@ -1,6 +1,4 @@
 import logging
-import os
-import sys
 
 LEVELS = {
     0: "WARNING",

genmod/score_variants/compound_scorer.py

@@ -14,8 +14,6 @@
 from __future__ import division, print_function
 
 import logging
-import os
-import sys
 from multiprocessing import Process
 from typing import Dict, List, Tuple, Union
 

genmod/score_variants/config_parser.py

@@ -287,7 +287,7 @@ def check_plugin(self, plugin):
 
         try:
             vcf_field = vcf_section["field"]
-            if not vcf_field in self.vcf_columns:
+            if vcf_field not in self.vcf_columns:
                 raise ValidateError(
                     "field has to be in {0}\n" "Wrong field name in plugin: {1}".format(
                         self.vcf_columns, plugin
@@ -299,10 +299,10 @@ def check_plugin(self, plugin):
 
                     if info_key == "CSQ":
                         try:
-                            csq_key = vcf_section["csq_key"]
+                            vcf_section["csq_key"]
                         except KeyError:
                             try:
-                                csq_key = vcf_section["vep_key"]
+                                vcf_section["vep_key"]
                             except KeyError:
                                 raise ValidateError(
                                     "CSQ entrys has to refer to an csq field.\n"
@@ -324,7 +324,7 @@ def check_plugin(self, plugin):
 
         try:
             data_type = vcf_section["data_type"]
-            if not data_type in self.data_types:
+            if data_type not in self.data_types:
                 raise ValidateError(
                     "data_type has to be in {0}\n" "Wrong data_type in plugin: {1}".format(
                         self.data_types, plugin
@@ -352,7 +352,7 @@ def check_plugin(self, plugin):
         record_rule = vcf_section.get("record_rule", None)
 
         if record_rule:
-            if not record_rule in ["min", "max"]:
+            if record_rule not in ["min", "max"]:
                 raise ValidateError(
                     "Record rules have to be in {0}\n" "Wrong record_rule in plugin: {1}".format(
                         ["min", "max"], plugin

genmod/score_variants/score_function.py

@@ -158,7 +158,7 @@ def get_score(self, value):
         ## TODO fix this ugly solution
         try:
             score = int(score)
-        except error as e:
+        except ValueError:
             score = int(float(score))
 
         return score

genmod/utils/__init__.py

@@ -1,67 +1,25 @@
 # -*- coding: utf-8 -*-
 
-INTERESTING_SO_TERMS = set(
-    [
-        "transcript_ablation",
-        "splice_donor_variant",
-        "splice_acceptor_variant",
-        "stop_gained",
-        "start_lost",
-        "frameshift_variant",
-        "stop_lost",
-        "initiator_codon_variant",
-        "transcript_amplification",
-        "inframe_insertion",
-        "inframe_deletion",
-        "protein_altering_variant",
-        "missense_variant",
-        "splice_region_variant",
-        "incomplete_terminal_codon_variant",
-        "stop_retained_variant",
-        "synonymous_variant",
-        "coding_sequence_variant",
-        "mature_miRNA_variant",
-        "5_prime_UTR_variant",
-        "3_prime_UTR_variant",
-        "non_coding_exon_variant",
-        "non_coding_transcript_exon_variant",
-        "non_coding_transcript_variant",
-        "nc_transcript_variant",
-        "intron_variant",
-        "NMD_transcript_variant",
-        "non_coding_transcript_variant",
-        "upstream_gene_variant",
-        "downstream_gene_variant",
-    ]
-)
-
-EXONIC_SO_TERMS = set(
-    [
-        "transcript_ablation",
-        "splice_donor_variant",
-        "splice_acceptor_variant",
-        "stop_gained",
-        "frameshift_variant",
-        "stop_lost",
-        "start_lost",
-        "initiator_codon_variant",
-        "transcript_amplification",
-        "inframe_insertion",
-        "inframe_deletion",
-        "missense_variant",
-        "protein_altering_variant",
-        "splice_region_variant",
-        "incomplete_terminal_codon_variant",
-        "stop_retained_variant",
-        "synonymous_variant",
-        "coding_sequence_variant",
-    ]
-)
-
 from .check_individuals import check_individuals
 from .get_batches import get_batches
 from .get_features import check_vep_annotation, get_annotation
 from .get_priority import get_chromosome_priority, get_rank_score
 from .is_number import is_number
 from .pair_generator import generate_pairs
 from .variant_printer import VariantPrinter
+
+INTERESTING_SO_TERMS = {"transcript_ablation", "splice_donor_variant", "splice_acceptor_variant", "stop_gained",
+                        "start_lost", "frameshift_variant", "stop_lost", "initiator_codon_variant",
+                        "transcript_amplification", "inframe_insertion", "inframe_deletion", "protein_altering_variant",
+                        "missense_variant", "splice_region_variant", "incomplete_terminal_codon_variant",
+                        "stop_retained_variant", "synonymous_variant", "coding_sequence_variant",
+                        "mature_miRNA_variant", "5_prime_UTR_variant", "3_prime_UTR_variant", "non_coding_exon_variant",
+                        "non_coding_transcript_exon_variant", "non_coding_transcript_variant", "nc_transcript_variant",
+                        "intron_variant", "NMD_transcript_variant", "non_coding_transcript_variant",
+                        "upstream_gene_variant", "downstream_gene_variant"}
+
+EXONIC_SO_TERMS = {"transcript_ablation", "splice_donor_variant", "splice_acceptor_variant", "stop_gained",
+                   "frameshift_variant", "stop_lost", "start_lost", "initiator_codon_variant",
+                   "transcript_amplification", "inframe_insertion", "inframe_deletion", "missense_variant",
+                   "protein_altering_variant", "splice_region_variant", "incomplete_terminal_codon_variant",
+                   "stop_retained_variant", "synonymous_variant", "coding_sequence_variant"}

genmod/vcf_tools/genotype.py

@@ -39,9 +39,6 @@
 Copyright (c) 2013 __MyCompanyName__. All rights reserved.
 """
 
-import os
-import sys
-
 
 class Genotype(object):
     """Holds information about a genotype"""

genmod/vcf_tools/header_parser.py

@@ -325,20 +325,6 @@ def add_contig(self, contig_id, length):
         self.parse_meta_data(contig_line)
         return
 
-    def add_contig(self, contig_id, length):
-        """
-        Add a contig line to the header.
-
-        Arguments:
-            contig_id (str): The id of the alternative line
-            length (str): A description of the info line
-
-        """
-        contig_line = "##contig=<ID={0},length={1}>".format(contig_id, length)
-        self.logger.info("Adding contig line to vcf: {0}".format(contig_line))
-        self.parse_meta_data(contig_line)
-        return
-
     def add_version_tracking(self, info_id, version, date, command_line=""):
         """
         Add a line with information about which software that was run and when

genmod/vcf_tools/parse_variant.py

@@ -1,7 +1,6 @@
 """Parse a variant line in different ways"""
 
 import logging
-import string
 
 logging = logging.getLogger(__name__)
 

genmod/vcf_tools/print_variants.py

@@ -17,12 +17,6 @@
 
 from __future__ import print_function
 
-import codecs
-import locale
-import sys
-
-# sys.stdout = codecs.getwriter(locale.getpreferredencoding())(sys.stdout)
-
 
 def print_variant_dict(variant, header_line, outfile=None, silent=False):
     """Print a variant dictionary

genmod/vcf_tools/sort_variants.py

@@ -12,8 +12,6 @@
 from __future__ import print_function
 
 import logging
-import os
-import sys
 from datetime import datetime
 from subprocess import call
 

tests/conftest.py

@@ -1,6 +1,3 @@
-import os
-from tempfile import NamedTemporaryFile
-
 import pytest
 import tabix
 from genmod.annotations import ensembl_path_37 as ensembl_path