def __init__(self, annotation, reference):
self.annotation = pd.read_csv(os.path.join(
ANNOTATION, annotation + '.exon.gff.tsv'),
sep='\t',
header=None,
dtype={0: str})
self.matrix5 = load_matrix5()
self.matrix3 = load_matrix3()
self.reference = pyfaidx.Fasta(reference)
def get_sequences(length):
exon_names, exon_seqs = files.read_fasta(exons_file)
exons = collections.defaultdict(lambda: collections.defaultdict(lambda: []))
[exons[name.split('(')[0].split('.')[0]][int(name.split('(')[0].split('.')[1])].append(exon_seqs[i]) for i, name in enumerate(exon_names) if len(exon_seqs[i]) > length]
exons = {id: {exon_id: exons[id][exon_id][0] for exon_id in exons[id]} for id in exons}
intron_names, intron_seqs = files.read_fasta(introns_file)
introns = collections.defaultdict(lambda: collections.defaultdict(lambda: []))
[introns[name.split('(')[0].split('.')[0]][int(name.split('(')[0].split('.')[1].split('-')[0])].append(intron_seqs[i]) for i, name in enumerate(intron_names) if name.split('.')[0] in exons]
introns = {id: {intron_id: introns[id][intron_id][0] for intron_id in introns[id]} for id in introns}
#
with open(output_file, 'w') as outfile:
for id in exons:
for exon_id in exons[id]:
if id in introns:
if exon_id in introns[id]:
outfile.write(">{0}.{1}\n{2}{3}\n".format(id, exon_id, exons[id][exon_id][-length:].lower(), introns[id][exon_id][:length]))
matrix5 = load_matrix5()
entries = files.read_fasta(output_file)
entries = {id: entries.sequences[i] for i, id in enumerate(entries.ids)}
decoys = []
for id in entries:
seq = entries[id]
splice_site = int(len(seq)/2)
splice_site_seq = seq[splice_site-3:splice_site+6]
real_splice_site_max_ent = maxent.score5(splice_site_seq, matrix=matrix5)
kept = False
for i in range(1, len(seq) - splice_site - 5):
if not kept:
query = seq[splice_site + i - 3:splice_site + i + 6]
query = "{0}{1}".format(query[:3].lower(), query[3:])
max_ent_score = maxent.score5(query, matrix=matrix5)
if max_ent_score >= real_splice_site_max_ent:
print(id, real_splice_site_max_ent, i, query, max_ent_score)
decoys.append(id)
kept = True
with open(decoy_file, "w") as outfile:
[outfile.write(">{0}\n{1}\n".format(id, entries[id])) for id in decoys]
def __init__(self, side='5prime'):
"""
"""
if side not in ['5prime', '3prime']:
raise Exception("side should be 5prime or 3prime")
self.side = side
if self.side == '5prime':
self.matrix = load_matrix5()
self.model = score5
else:
self.matrix = load_matrix3()
self.model = score3
def parse_intron(options, chrom, start, end, strand, intron_info):
# fetch fasta
fa = check_fasta(options['--genome'])
intron_fa = dna_to_rna(fa.fetch(chrom, start, end), strand)
# load matrix
matrix5 = load_matrix5()
# parse options
phastcons_f = pyBigWig.open(options['--bigwig'])
min_distance = int(options['--min-distance'])
min_score = float(options['--min-score'])
min_phastcons = float(options['--min-phastcons'])
# start to parse rs sites
rs_list = []
for m in re.finditer('AGGT', intron_fa):
if strand == '+':
pos = start + m.start() + 2
left_dist, right_dist, dist_flag = cal_distance(
pos, start, end, min_distance)
if not dist_flag: # not enough distance
continue
ss5_seq = dna_to_rna(fa.fetch(chrom, pos - 3, pos + 6))
if ss5_seq.find('N') != -1: # ensure there is no N
continue
ss5, score_flag = cal_score(ss5_seq, matrix5, min_score)
if not score_flag: # not high score
continue
else:
pos = end - m.start() - 2
left_dist, right_dist, dist_flag = cal_distance(
pos, start, end, min_distance)
if not dist_flag: # not enough distance
continue
ss5_seq = dna_to_rna(fa.fetch(chrom, pos - 6, pos + 3), strand='-')
if ss5_seq.find('N') != -1: # ensure there is no N
continue
ss5, score_flag = cal_score(ss5_seq, matrix5, min_score)
if not score_flag: # not high score
continue
phastcons = phastcons_f.stats(chrom, pos - 2, pos + 2)[0]
if phastcons is None or phastcons < min_phastcons: # not conserved
continue
rs_feature = '%d|%d|%d|%f|%f' % (pos, left_dist, right_dist, ss5,
phastcons)
rs_list.append(rs_feature)
if rs_list:
return (intron_info, rs_list)
else:
return (None, None)
def findSpliceSites(self):
# chr15:28235701-28235871,chr15:28235789-28235790,G,A,1921,682,1467,315,3223,1142,1276,367,attgggactgtgac...
# first line is schema, every line after that is data
i = 0
for line in self.inputData:
if i == 0:
print(line.strip() + "," + "wt5start" + "," + "wt5sequence" +
","
"wt5score" + ","
"mu5start" + "," + "mu5sequence" + "," + "mu5score" +
"," + "wt3start" + "," + "wt3sequence" + "," +
"wt3score" + "," + "mu3start" + "," + "mu3sequence" +
"," + "mu3score")
else:
splitLine = line.strip().split(',')
sequenceStart = int(splitLine[0].split(":")[1].split("-")[0])
mutationStart = int(splitLine[1].split(":")[1].split("-")[1])
mutationTuple = (splitLine[2], splitLine[3])
matrix5 = maxent.load_matrix5()
self.fivePrimeSites[splitLine[0]] = self.check5Prime(
splitLine[12].strip(), self.fivePrimeSiteLength,
sequenceStart, mutationStart, mutationTuple, matrix5)
matrix3 = maxent.load_matrix3()
self.threePrimeSites[splitLine[0]] = self.check3Prime(
splitLine[12].strip(), self.threePrimeSiteLength,
sequenceStart, mutationStart, mutationTuple, matrix3)
print(line.strip() + "," +
str(self.fivePrimeSites[splitLine[0]][0]) + "," +
str(self.fivePrimeSites[splitLine[0]][1]) + "," +
str(self.fivePrimeSites[splitLine[0]][2]) + "," +
str(self.fivePrimeSites[splitLine[0]][3]) + "," +
str(self.fivePrimeSites[splitLine[0]][4]) + "," +
str(self.fivePrimeSites[splitLine[0]][5]) + "," +
str(self.threePrimeSites[splitLine[0]][0]) + "," +
str(self.threePrimeSites[splitLine[0]][1]) + "," +
str(self.threePrimeSites[splitLine[0]][2]) + "," +
str(self.threePrimeSites[splitLine[0]][3]) + "," +
str(self.threePrimeSites[splitLine[0]][4]) + "," +
str(self.threePrimeSites[splitLine[0]][5]))
i += 1
#!/usr/bin/env python
# -*- coding:utf-8 -*-
# author: Jiguang Peng
# datetime: 2019/6/27 17:54
import itertools
import re
from pyhgvs.models import Transcript
from maxentpy import maxent
from maxentpy.maxent import load_matrix5, load_matrix3
from read_data import transcripts, genome, domain_bed, hotspot_bed, curated_region, pathogenic_dict
from utils import contained_in_bed
matrix5 = load_matrix5()
matrix3 = load_matrix3()
class Splicing:
"""
splice class
"""
donor_threshold = 3
acceptor_threshold = 3
percent_threshold = 0.7
def __init__(self, vcfrecord, transcript):
self.chrom = vcfrecord.chrom
self.offset = int(vcfrecord.pos)
self.ref = vcfrecord.ref
self.alt = vcfrecord.alt
def read_and_score_fasta(outdir,
species,
donor_dinucleotide_start=3,
acceptor_dinucleotide_start=18):
donor_dict = {}
acceptor_dict = {}
acceptor_scorefile = open(outdir + "/" + species + "_acceptor_scores.tsv",
'w')
acceptor_scorefile.write("\t".join([
"splice_site_type", "location", "seq", "score", "dinucleotide",
"dinucleotide_is_standard"
]) + "\n")
donor_scorefile = open(outdir + "/" + species + "_donor_scores.tsv", 'w')
donor_scorefile.write("\t".join([
"splice_site_type", "location", "seq", "score", "dinucleotide",
"dinucleotide_is_standard"
]) + "\n")
with open(outdir + "/" + species + "_donor.fastatab", 'r') as file:
donor_matrix = maxent.load_matrix5()
for line in file:
entry = line.strip().split("\t")
key = entry[0].split("(")[0]
seq = entry[1].upper()
dinucleotide = seq[
donor_dinucleotide_start:donor_dinucleotide_start + 2]
standard_dinucleotide = dinucleotide == "GT"
donor_dict[key] = {
"seq": seq,
"score":
maxent.score5(seq, donor_matrix) if "N" not in seq else "NA",
"dinucleotide": dinucleotide,
"standard_dinucleotide": standard_dinucleotide
}
donor_scorefile.write("\t".join([
"donor", key, seq,
str(donor_dict[key]["score"]), dinucleotide,
str(standard_dinucleotide)
]) + "\n")
with open(outdir + "/" + species + "_acceptor.fastatab", 'r') as file:
acceptor_matrix = maxent.load_matrix3()
for line in file:
entry = line.strip().split("\t")
key = entry[0].split("(")[0]
seq = entry[1].upper()
dinucleotide = seq[
acceptor_dinucleotide_start:acceptor_dinucleotide_start + 2]
standard_dinucleotide = dinucleotide == "AG"
acceptor_dict[key] = {
"seq":
seq,
"score":
maxent.score3(seq, acceptor_matrix)
if "N" not in seq else "NA",
"dinucleotide":
dinucleotide,
"standard_dinucleotide":
standard_dinucleotide
}
acceptor_scorefile.write("\t".join([
"acceptor", key, seq,
str(acceptor_dict[key]["score"]), dinucleotide,
str(standard_dinucleotide)
]) + "\n")
donor_scorefile.close()
acceptor_scorefile.close()
return donor_dict, acceptor_dict