def filter_trf_gff(self,
input_gff,
output_gff,
filtered_out_gff,
min_period=None,
max_period=None,
min_copy_number=None,
max_copy_number=None,
pattern=None,
min_percentage_of_matches=None,
max_percentage_of_indels=None,
min_entropy=None,
max_entropy=None):
def filtering_expression(gff_description_dict):
return self.gff_filtering_expression(
gff_description_dict,
min_period=min_period,
max_period=max_period,
min_copy_number=min_copy_number,
max_copy_number=max_copy_number,
pattern=pattern,
min_percentage_of_matches=min_percentage_of_matches,
max_percentage_of_indels=max_percentage_of_indels,
min_entropy=min_entropy,
max_entropy=max_entropy)
AnnotationsRoutines.filter_gff_by_description(input_gff, output_gff,
filtered_out_gff,
filtering_expression)
def filter_trf_gff_by_exact_copy_number(input_gff,
output_gff,
filtered_out_gff,
min_copy_number,
perfect_tandem=False):
if perfect_tandem:
def filtering_expression(gff_description_dict):
if (gff_description_dict["Pattern"] *
min_copy_number) in gff_description_dict["seq"]:
return True
return False
else:
def filtering_expression(gff_description_dict):
if gff_description_dict["seq"].count(
gff_description_dict["Pattern"]) >= min_copy_number:
return True
return False
AnnotationsRoutines.filter_gff_by_description(input_gff, output_gff,
filtered_out_gff,
filtering_expression)
def correct_regions_from_gff(
self,
reference,
variants_vcf,
gff_file,
output_prefix=None,
feature_type_list=["CDS"],
unification_key="Parent",
#raw_seq_per_line=False,
vcf_with_masking=None,
override_vcf_by_mask=None,
use_ambiguous_nuccleotides=None):
feature_dict = AnnotationsRoutines.get_feature_dict(
gff_file,
output_prefix=output_prefix,
feature_type_list=feature_type_list,
unification_key=unification_key)
region_file = "%s.coordinates_only.list" % output_prefix
raw_regions = "%s.raw.seq" % output_prefix
final_regions = "%s.fasta" % output_prefix
regions_with_frameshift_file = "%s.frameshifts.region.ids" % output_prefix
self.correct_reference(
reference,
raw_regions,
variants_vcf,
raw_seq_per_line=True,
vcf_with_masking=vcf_with_masking,
override_vcf_by_mask=override_vcf_by_mask,
use_ambiguous_nuccleotides=use_ambiguous_nuccleotides,
interval_list=region_file)
region_with_frameshift = SynDict()
def new_regions_generator():
with open(raw_regions, "r") as in_fd:
for region_id in feature_dict:
seq = ""
for i in range(0, len(feature_dict[region_id])):
seq_fragment = in_fd.readline().strip()
if ((int(feature_dict[region_id][i][2]) -
int(feature_dict[region_id][i][1]) + 1) -
len(seq_fragment)) % 3 != 0:
if region_id not in region_with_frameshift:
region_with_frameshift[region_id] = [i]
else:
region_with_frameshift[region_id].append(i)
seq += seq_fragment
yield SeqRecord(
seq=Seq(seq) if feature_dict[region_id][0][3] == "+"
else Seq(seq).reverse_complement(),
id=region_id,
description="")
SeqIO.write(new_regions_generator(), final_regions, format="fasta")
region_with_frameshift.write(regions_with_frameshift_file,
splited_values=True)
def get_monomer_len_file_from_trf_gff(trf_gff, len_file):
len_dict = SynDict()
with open(trf_gff, "r") as trf_fd:
for line in trf_fd:
if line[0] == "#":
continue
description_dict = AnnotationsRoutines.get_description_dict_from_gff_string(
line)
len_dict[description_dict["ID"]] = description_dict["Period"]
# print len_dict
len_dict.write(len_file)
#!/usr/bin/env python
__author__ = 'Sergei F. Kliver'
import argparse
from Routines import AnnotationsRoutines
parser = argparse.ArgumentParser()
parser.add_argument("-i",
"--input_gff",
action="store",
dest="input_gff",
help="Gff file with annotations to extract")
parser.add_argument("-o",
"--output_gff",
action="store",
dest="output_gff",
help="Output gff file with extracted transcripts")
parser.add_argument("-d",
"--ids_file",
action="store",
dest="ids_file",
help="File with ids of transcripts to extract")
args = parser.parse_args()
AnnotationsRoutines.extract_transcripts_by_ids(args.input_gff, args.ids_file,
args.output_gff)
SequenceRoutines.extract_sequence_by_ids(
output_pep, "%s.ids" %
output_swissprot_pfam_or_hints_supported_transcripts_longest_pep_evidence,
output_swissprot_pfam_or_hints_supported_transcripts_longest_pep)
SequenceRoutines.extract_sequence_by_ids(
output_pep, "%s.ids" %
output_swissprot_pfam_and_hints_supported_transcripts_longest_pep_evidence,
output_swissprot_pfam_and_hints_supported_transcripts_longest_pep)
for id_file in output_swissprot_pfam_or_hints_supported_transcripts_ids, \
output_swissprot_pfam_and_hints_supported_transcripts_ids, \
"%s.ids" % output_swissprot_pfam_or_hints_supported_transcripts_longest_pep_evidence, \
"%s.ids" % output_swissprot_pfam_and_hints_supported_transcripts_longest_pep_evidence:
out_pref = id_file[:-4]
out_gff = "%s.gff" % out_pref
AnnotationsRoutines.extract_transcripts_by_ids(output_gff, id_file,
out_gff)
for suffix in ".trimmed.cds", ".transcript":
SequenceRoutines.extract_sequence_by_ids(
"%s%s" % (args.output, suffix), id_file,
"%s%s" % (out_pref, suffix))
HMMER3.intersect_ids_from_files(
output_swissprot_pfam_or_hints_supported_transcripts_ids,
cds_with_inframe_stop_codons_ids,
output_swissprot_pfam_or_hints_supported_transcripts_inframe_stop_ids,
mode="common")
HMMER3.intersect_ids_from_files(
output_swissprot_pfam_and_hints_supported_transcripts_ids,
cds_with_inframe_stop_codons_ids,
output_swissprot_pfam_and_hints_supported_transcripts_inframe_stop_ids,
#!/usr/bin/env python
__author__ = 'Sergei F. Kliver'
import argparse
from Routines import AnnotationsRoutines
parser = argparse.ArgumentParser()
parser.add_argument("-i",
"--input_gff",
action="store",
dest="input_gff",
required=True,
help="input gff file")
parser.add_argument("-o",
"--output_gff",
action="store",
dest="output_gff",
required=True,
help="Output fixed gff file")
args = parser.parse_args()
AnnotationsRoutines.fix_gff_coordinates_order(args.input_gff, args.output_gff)
#!/usr/bin/env python
__author__ = 'Sergei F. Kliver'
import os
import argparse
from Bio import SeqIO
from Routines import AnnotationsRoutines
parser = argparse.ArgumentParser()
parser.add_argument("-g",
"--gtf_file",
action="store",
dest="input",
required=True,
help="Input gtf file")
parser.add_argument("-o",
"--output",
action="store",
dest="output",
required=True,
help="Output accordance file")
args = parser.parse_args()
AnnotationsRoutines.get_transcript_to_pep_accordance_from_gtf(
args.input, args.output, comment_symbol="#")
__author__ = 'Sergei F. Kliver'
import argparse
from Routines import AnnotationsRoutines
parser = argparse.ArgumentParser()
parser.add_argument("-i",
"--input_gff",
action="store",
dest="input_gff",
required=True,
help="Input .gff file")
parser.add_argument("-o",
"--output_gff",
action="store",
dest="output_gff",
required=True,
help="Output .gff file")
parser.add_argument("-s",
"--syn_file_file",
action="store",
dest="syn_file",
required=True,
help="File with synonyms of region names")
args = parser.parse_args()
AnnotationsRoutines.replace_region_names_in_gff(args.input_gff, args.syn_file,
args.output_gff)
__author__ = 'Sergei F. Kliver'
import argparse
from Routines import AnnotationsRoutines
parser = argparse.ArgumentParser()
parser.add_argument("-i",
"--input_gff",
action="store",
dest="input_gff",
required=True,
help="input gff file")
parser.add_argument("-o",
"--output_gff",
action="store",
dest="output_gff",
required=True,
help="Output fixed gff file")
parser.add_argument("-f",
"--feature_type",
action="store",
dest="feature_type",
required=True,
help="Feature type to use")
args = parser.parse_args()
AnnotationsRoutines.fix_absent_feature_type_field(args.input_gff,
args.output_gff,
args.feature_type)