Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Remove all hisatgenotype specific scripts #225

Open
wants to merge 7 commits into
base: master
Choose a base branch
from
Open

Remove all hisatgenotype specific scripts #225

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
512b378
Remove hisatgenotype codes
parkchanhee Feb 6, 2020
15799fa
Merge pull request #224 from DaehwanKimLab/dev-cleangenotype
parkchanhee Feb 6, 2020
d47e96e
Remove all hisatgenotype specific scripts
chbe-helix Feb 14, 2020
3ce220d
Remove genotype in Makefule
chbe-helix Feb 17, 2020
640d080
Support python3
parkchanhee Mar 27, 2020
b7180c3
removed unnecessary codes
parkchanhee Mar 31, 2020
05e73a2
Merge pull request #238 from DaehwanKimLab/dev-python3
chbe-helix Apr 16, 2020
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 0 additions & 2 deletions Makefile
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -237,8 +237,6 @@ HT2LIB_PKG_SRC = \
GENERAL_LIST = $(wildcard scripts/*.sh) \
$(wildcard scripts/*.pl) \
$(wildcard *.py) \
$(wildcard hisatgenotype_modules/*.py) \
$(wildcard hisatgenotype_scripts/*.py) \
$(wildcard example/index/*.ht2) \
$(wildcard example/reads/*.fa) \
example/reference/22_20-21M.fa \
Expand Down
4 changes: 1 addition & 3 deletions hisat2_extract_exons.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
#!/usr/bin/env python
#!/usr/bin/env python3

#
# Copyright 2015, Daehwan Kim <[email protected]>
Expand All @@ -19,8 +19,6 @@
# along with HISAT 2. If not, see <http://www.gnu.org/licenses/>.
#

from __future__ import print_function

from sys import stderr, exit
from collections import defaultdict as dd, Counter
from argparse import ArgumentParser, FileType
Expand Down
48 changes: 25 additions & 23 deletions hisat2_extract_snps_haplotypes_UCSC.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
#!/usr/bin/env python
#!/usr/bin/env python3

#
# Copyright 2015, Daehwan Kim <[email protected]>
Expand All @@ -23,6 +23,7 @@
import sys, subprocess
import re
from argparse import ArgumentParser, FileType
from functools import cmp_to_key


"""
Expand Down Expand Up @@ -80,8 +81,8 @@ def compare_vars(a, b):

# daehwan - for debugging purposes
if a_chr != b_chr:
print a
print b
print(a)
print(b)

assert a_chr == b_chr
if a_pos != b_pos:
Expand Down Expand Up @@ -129,7 +130,7 @@ def generate_haplotypes(snp_file,
assert len(vars) > 0

# Sort variants and remove redundant variants
vars = sorted(vars, cmp=compare_vars)
vars = sorted(vars, key=cmp_to_key(compare_vars))
tmp_vars = []
v = 0
while v < len(vars):
Expand Down Expand Up @@ -223,8 +224,8 @@ def generate_haplotypes(snp_file,
else:
assert type == 'I'
type = "insertion"
print >> snp_file, "%s\t%s\t%s\t%s\t%s" % \
(varID, type, chr, pos, data)
print("%s\t%s\t%s\t%s\t%s" % (varID, type, chr, pos, data),
file=snp_file)

# genotypes_list looks like
# Var0: 0
Expand Down Expand Up @@ -270,7 +271,7 @@ def split_haplotypes(haplotypes):
split_haplotypes.add('#'.join(haplotype[prev_s:s]))
return split_haplotypes

haplotypes2 = split_haplotypes(haplotypes)
haplotypes2 = sorted(list(split_haplotypes(haplotypes)))

def cmp_haplotype(a, b):
a = a.split('#')
Expand All @@ -288,8 +289,8 @@ def cmp_haplotype(a, b):
if a_begin != b_begin:
return a_begin - b_begin
return a_end - b_end
haplotypes = sorted(list(haplotypes2), cmp=cmp_haplotype)

haplotypes = sorted(list(haplotypes2), key=cmp_to_key(cmp_haplotype))

# Write haplotypes
for h_i in range(len(haplotypes)):
Expand Down Expand Up @@ -317,8 +318,8 @@ def cmp_haplotype(a, b):
for id in h:
var_dic = vars[int(id)][4]
h_add.append(var_dic["id2"])
print >> haplotype_file, "ht%d\t%s\t%d\t%d\t%s" % \
(num_haplotypes, chr, h_new_begin, h_end, ','.join(h_add))
print("ht%d\t%s\t%d\t%d\t%s" % (num_haplotypes, chr, h_new_begin, h_end, ','.join(h_add)),
file=haplotype_file)
num_haplotypes += 1

return num_haplotypes
Expand Down Expand Up @@ -352,6 +353,7 @@ def main(genome_file,
else:
snp_cmd = ["cat", snp_fname]
snp_proc = subprocess.Popen(snp_cmd,
text=True,
stdout=subprocess.PIPE,
stderr=open("/dev/null", 'w'))
ids_seen = set()
Expand Down Expand Up @@ -447,10 +449,10 @@ def main(genome_file,
if testset:
ref_seq = chr_seq[start-50:start+50]
alt_seq = chr_seq[start-50:start] + allele + chr_seq[start+1:start+50]
print >> ref_testset_file, ">%s_single_%d" % (rs_id, start - 50)
print >> ref_testset_file, ref_seq
print >> alt_testset_file, ">%s_single_%d_%s" % (rs_id, start - 50, ref_seq)
print >> alt_testset_file, alt_seq
print(">%s_single_%d" % (rs_id, start - 50), file=ref_testset_file)
print(ref_seq, file=ref_testset_file)
print(">%s_single_%d_%s" % (rs_id, start - 50, ref_seq), file=alt_testset_file)
print(alt_seq, file=alt_testset_file)

elif classType == "deletion":
if start > 0:
Expand All @@ -475,10 +477,10 @@ def main(genome_file,
if testset and delLen > 0 and delLen <= 10:
ref_seq = chr_seq[start-50:start+50]
alt_seq = chr_seq[start-50:start] + chr_seq[start+delLen:start+50+delLen]
print >> ref_testset_file, ">%s_deletion_%d" % (rs_id, start - 50)
print >> ref_testset_file, ref_seq
print >> alt_testset_file, ">%s_deletion_%d_%s" % (rs_id, start - 50, ref_seq)
print >> alt_testset_file, alt_seq
print(">%s_deletion_%d" % (rs_id, start - 50), file=ref_testset_file)
print(ref_seq, file=ref_testset_file)
print(">%s_deletion_%d_%s" % (rs_id, start - 50, ref_seq), file=alt_testset_file)
print(alt_seq, file=alt_testset_file)
else:
assert classType == "insertion"
if start > 0:
Expand All @@ -497,10 +499,10 @@ def main(genome_file,
if testset and insLen > 0 and insLen <= 10:
ref_seq = chr_seq[start-50:start+50]
alt_seq = chr_seq[start-50:start] + allele + chr_seq[start:start+50-insLen]
print >> ref_testset_file, ">%s_insertion_%d" % (rs_id, start - 50)
print >> ref_testset_file, ref_seq
print >> alt_testset_file, ">%s_insertion_%d_%s" % (rs_id, start - 50, ref_seq)
print >> alt_testset_file, alt_seq
print(">%s_insertion_%d" % (rs_id, start - 50), file=ref_testset_file)
print(ref_seq, file=ref_testset_file)
print(">%s_insertion_%d_%s" % (rs_id, start - 50, ref_seq), file=alt_testset_file)
print(alt_seq, file=alt_testset_file)

if curr_right < end:
curr_right = end
Expand Down
44 changes: 24 additions & 20 deletions hisat2_extract_snps_haplotypes_VCF.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
#!/usr/bin/env python
#!/usr/bin/env python3
#
# Copyright 2016, Daehwan Kim <[email protected]>
#
Expand All @@ -21,6 +21,7 @@

import sys, os, subprocess
from argparse import ArgumentParser, FileType
from functools import cmp_to_key

digit2str = [str(i) for i in range(10)]

Expand Down Expand Up @@ -100,11 +101,11 @@ def extract_vars(chr_dic, chr, pos, ref_allele, alt_alleles, varID):
ref_allele2, pos2 = ref_allele, pos

if chr_seq[pos:pos+len(ref_allele)] != ref_allele:
print >> sys.stderr, "Error: the reference genome you provided seems to be incompatible with the VCF file at %d of chromosome %s where %s is in the reference genome while %s is in the VCF file" % (pos, chr, chr_seq[pos:pos+len(ref_allele)], ref_allele)
print("Error: the reference genome you provided seems to be incompatible with the VCF file at %d of chromosome %s where %s is in the reference genome while %s is in the VCF file" % (pos, chr, chr_seq[pos:pos+len(ref_allele)], ref_allele), file=sys.stderr)

def warning_msg():
print >> sys.stderr, "Warning) ref allele (%s) and alt allele (%s in %s) at chr%s:%d are excluded." % \
(ref_allele, alt_allele, ','.join(alt_alleles), chr, pos + 1)
print("Warning) ref allele (%s) and alt allele (%s in %s) at chr%s:%d are excluded." % \
(ref_allele, alt_allele, ','.join(alt_alleles), chr, pos + 1), file=sys.stderr)

min_len = min(len(ref_allele2), len(alt_allele2))
if min_len >= 2:
Expand Down Expand Up @@ -170,7 +171,7 @@ def generate_haplotypes(snp_file,
assert len(vars) > 0

# Sort variants and remove redundant variants
vars = sorted(vars, cmp=compare_vars)
vars = sorted(vars, key=cmp_to_key(compare_vars))
tmp_vars = []
v = 0
while v < len(vars):
Expand Down Expand Up @@ -203,8 +204,8 @@ def generate_haplotypes(snp_file,
else:
assert type == 'I'
type = "insertion"
print >> snp_file, "%s\t%s\t%s\t%s\t%s" % \
(varID, type, chr, pos, data)
print("%s\t%s\t%s\t%s\t%s" % \
(varID, type, chr, pos, data), file=snp_file)

# variant compatibility
vars_cmpt = [-1 for i in range(len(vars))]
Expand Down Expand Up @@ -363,7 +364,7 @@ def split_haplotypes(haplotypes):
split_haplotypes.add('#'.join(haplotype[prev_s:s]))
return split_haplotypes

haplotypes2 = split_haplotypes(haplotypes)
haplotypes2 = sorted(list(split_haplotypes(haplotypes)))

def cmp_haplotype(a, b):
a = a.split('#')
Expand All @@ -382,7 +383,7 @@ def cmp_haplotype(a, b):
return a_begin - b_begin
return a_end - b_end

haplotypes = sorted(list(haplotypes2), cmp=cmp_haplotype)
haplotypes = sorted(list(haplotypes2), key=cmp_to_key(cmp_haplotype))

# daehwan - for debugging purposes
"""
Expand Down Expand Up @@ -424,8 +425,8 @@ def cmp_haplotype(a, b):
for id in h:
var_dic = vars[int(id)][4]
h_add.append(var_dic["id2"])
print >> haplotype_file, "ht%d\t%s\t%d\t%d\t%s" % \
(num_haplotypes, chr, h_new_begin, h_end, ','.join(h_add))
print("ht%d\t%s\t%d\t%d\t%s" % \
(num_haplotypes, chr, h_new_begin, h_end, ','.join(h_add)), file=haplotype_file)
num_haplotypes += 1

return num_haplotypes
Expand Down Expand Up @@ -464,6 +465,7 @@ def main(genome_file,
else:
vcf_cmd = ["cat", genotype_vcf]
vcf_proc = subprocess.Popen(vcf_cmd,
text=True,
stdout=subprocess.PIPE,
stderr=open("/dev/null", 'w'))
for line in vcf_proc.stdout:
Expand Down Expand Up @@ -525,17 +527,17 @@ def main(genome_file,

var_set.add(var_str)

print >> sys.stderr, "Number of variants in %s is:" % (genotype_vcf)
print("Number of variants in %s is:" % (genotype_vcf), file=sys.stderr)
for chr, vars in genotype_var_list.items():
vars = sorted(vars, cmp=compare_vars)
print >> sys.stderr, "\tChromosome %s: %d variants" % (chr, len(vars))
print("\tChromosome %s: %d variants" % (chr, len(vars)), file=sys.stderr)

for chr, gene_ranges in genotype_ranges.items():
for gene, value in gene_ranges.items():
gene_ranges[gene] = [value[0] - 100, value[1] + 100]
value = genotype_ranges[chr][gene]
if verbose:
print >> sys.stderr, "%s\t%s\t%d-%d" % (chr, gene, value[0], value[1])
print("%s\t%s\t%d-%d" % (chr, gene, value[0], value[1]), file=sys.stderr)

if extra_files or True:
clnsig_file = open("%s.clnsig" % base_fname, 'w')
Expand All @@ -544,7 +546,7 @@ def main(genome_file,
varID = var[4]["id2"]
CLNSIG = var[4]["CLNSIG"]
gene = var[4]["gene"]
print >> clnsig_file, "%s\t%s\t%s" % (varID, gene, CLNSIG)
print("%s\t%s\t%s" % (varID, gene, CLNSIG), file=clnsig_file)
clnsig_file.close()

SNP_file = open("%s.snp" % base_fname, 'w')
Expand All @@ -558,7 +560,7 @@ def main(genome_file,
left, right = value
if reference_type == "gene":
left, right = 0, right - left
print >> ref_file, "%s\t%s\t%d\t%d" % (gene, chr, left, right)
print("%s\t%s\t%d\t%d" % (gene, chr, left, right), file=ref_file)
ref_file.close()

if reference_type == "gene":
Expand All @@ -567,10 +569,10 @@ def main(genome_file,
for gene, value in gene_ranges.items():
left, right = value
left, right = 0, right - left
print >> backbone_file, ">%s" % (gene)
print(">%s" % (gene), file=backbone_file)
backbone_seq = chr_dic[chr][value[0]:value[1]+1]
for s in range(0, len(backbone_seq), 60):
print >> backbone_file, backbone_seq[s:s+60]
print(backbone_seq[s:s+60], file=backbone_file)
backbone_file.close()
elif reference_type == "chromosome":
first = True
Expand Down Expand Up @@ -604,6 +606,7 @@ def main(genome_file,
else:
vcf_cmd = ["cat", VCF_fname]
vcf_proc = subprocess.Popen(vcf_cmd,
text=True,
stdout=subprocess.PIPE,
stderr=open("/dev/null", 'w'))

Expand Down Expand Up @@ -665,7 +668,7 @@ def main(genome_file,
offset = 0
gene = None
if num_lines % 10000 == 1:
print >> sys.stderr, "\t%s:%d\r" % (chr, pos),
print("\t%s:%d\r" % (chr, pos), file=sys.stderr)

if chr_genotype_ranges:
skip = True
Expand Down Expand Up @@ -883,6 +886,7 @@ def add_vars(pos,
else:
vcf_cmd = ["cat", args.genotype_vcf]
vcf_proc = subprocess.Popen(vcf_cmd,
text=True,
stdout=subprocess.PIPE,
stderr=open("/dev/null", 'w'))
for line in vcf_proc.stdout:
Expand All @@ -900,7 +904,7 @@ def add_vars(pos,
args.genotype_gene_list = args.genotype_gene_list.split(',')

if len(args.genotype_gene_list) == 0:
print >> sys.stderr, "Error: please specify --genotype-gene-list."
print("Error: please specify --genotype-gene-list.", file=sys.stderr)
sys.exit(1)

else:
Expand Down
12 changes: 5 additions & 7 deletions hisat2_extract_splice_sites.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
#!/usr/bin/env python
#!/usr/bin/env python3

#
# Copyright 2015, Daehwan Kim <[email protected]>
Expand All @@ -19,8 +19,6 @@
# along with HISAT 2. If not, see <http://www.gnu.org/licenses/>.
#

from __future__ import print_function

from sys import stderr, exit
from collections import defaultdict as dd, Counter
from argparse import ArgumentParser, FileType
Expand Down Expand Up @@ -105,18 +103,18 @@ def extract_splice_sites(gtf_file, verbose=False):
len(genes), sum(len(v) > 1 for v in genes.values())),
file=stderr)
print('transcripts: {}, transcript avg. length: {:.0f}'.format(
len(trans), sum(trans_lengths.elements())/len(trans)),
len(trans), sum(trans_lengths.elements())//len(trans)),
file=stderr)
print('exons: {}, exon avg. length: {:.0f}'.format(
sum(exon_lengths.values()),
sum(exon_lengths.elements())/sum(exon_lengths.values())),
sum(exon_lengths.elements())//sum(exon_lengths.values())),
file=stderr)
print('introns: {}, intron avg. length: {:.0f}'.format(
sum(intron_lengths.values()),
sum(intron_lengths.elements())/sum(intron_lengths.values())),
sum(intron_lengths.elements())//sum(intron_lengths.values())),
file=stderr)
print('average number of exons per transcript: {:.0f}'.format(
sum(exon_lengths.values())/len(trans)),
sum(exon_lengths.values())//len(trans)),
file=stderr)


Expand Down
Loading