def pkg_requirements():
reqs = subprocess.check_output([sys.executable, '-m', 'pip', 'freeze'])
installed_packages = [r.decode().split('==')[0] for r in reqs.split()]
required = ['biopython', 'matplotlib']
if not set(required).issubset(installed_packages):
bomb(
f"install package(s) {required} with: pip install {' '.join(list(required))}\n"
)
def check_path():
if not isdir(my_parser().filePath):
return bomb(f'No files found at path = {my_parser().filePath}\n')
elif isdir(my_parser().filePath) and \
not [item for item in flatten(file_list) if item.endswith(('vcf', 'vcf.gz', 'ped', 'map'))]:
return bomb(
f'No vcf or plink files found at path = {abspath(my_parser().filePath)}\n'
)
def check_dups():
err = open('Error.txt', 'w')
# SNPs occurring more than once in same file
dict0 = {
k: {x
for x in v if v.count(x) > 1}
for k, v in within_file_snps_dups.items() if len(v) > len(set(v))
}
if dict0:
err.write(''.join('SNPs occurring more than once in same file'))
err.write(''.join('\n------------------------------------------\n'))
for k, v in dict0.items():
err.write('{:<3} {:<5} {:<8}\n'.format(k, '>>', ' '.join(v)))
bomb(
'> duplicate SNP found. SNP should be unique in each file\n'
' > check `less -S Error.txt` for optional additional information\n'
)
# sample occurring more than once in same file
if within_file_sample_dups:
err.write(''.join('\n--------------------------------------------\n'))
err.write(''.join('sample occurring more than once in same file'))
err.write(''.join('\n--------------------------------------------\n'))
for k, v in within_file_sample_dups.items():
err.write('{:<3} {:<5} {:<8}\n'.format(k, '>>', ' '.join(v)))
bomb(
'> duplicate sample(s) found. Sample(s) should be unique in each file\n'
' > check `less -S Error.txt` for optional additional information\n'
)
# sample occurring more than once two or more files
if len(file_list) > 1:
if between_file_sample_dups:
err.write(''.join(
'\n----------------------------------------------------\n'))
err.write(''.join(
'sample occurring more than once in two or more files'))
err.write(''.join(
'\n----------------------------------------------------\n'))
err.write(' '.join(find_common(between_file_sample_dups)))
sets0 = set_counter(between_file_sample_dups.values())
sets1 = [len(i) for i in [*between_file_sample_dups.values()]]
if sets0 != sets1:
bomb(
'> sample(s) found in more than one file. Sample(s) should be unique to each file\n'
' > check `less -S Error.txt` for optional additional information\n'
)
result_chrom = set_counter(between_file_chroms.values())
if sum(result_chrom) > 0:
bomb(
'> files have differing number of chromosomes or chromosome ids\n'
' > check `less -S Error.txt` for optional additional information\n'
)
import timeit
import re
from datetime import datetime
from Bio import bgzf
from funtools import flatten, bomb
from parse_args import my_parser
from recode_dict import fimpute_2_vcf
start = timeit.default_timer()
try:
samples = open(my_parser().samples, "r")
except FileNotFoundError:
bomb(f"Missing argument or '{my_parser().samples}' may be empty\n")
try:
snp_info = open(my_parser().snps, "r")
except FileNotFoundError:
bomb(f"Missing argument or '{my_parser().snps}' may be empty\n")
try:
geno_info = open(my_parser().geno, "r")
except FileNotFoundError:
bomb(f"Missing argument or '{my_parser().geno}' may be empty\n")
try:
allele_info = open(my_parser().allele, "r")
except FileNotFoundError:
bomb(f"Missing argument or '{my_parser().allele}' may be empty\n")
toto = my_parser().type_
if not my_parser().out:
bomb('Missing argument, "-o PREFIX", "--out PREFIX"\n'
from os.path import abspath, isdir
from funtools import file_by_size, to_mat, line_count, find_common, bomb, std_capture, flatten, set_counter
from parse_args import my_parser
# get a list of input files
if not isdir(my_parser().filePath):
bomb(f'No files found at path = {abspath(my_parser().filePath)}\n')
vcf_list = [
file_ for file_ in file_by_size(my_parser().filePath, ['vcf'])
if file_.endswith(('vcf', 'vcf.gz'))
]
plink_list = to_mat(sorted(file_by_size(my_parser().filePath, ["ped", "map"])),
2)
files = vcf_list + plink_list
file_list = []
# first check
if len(files) > 10:
bomb('FImpute does not support imputing more than 10 chips simultaneously')
elif len(files) < 1:
bomb(f'No files found at path = {abspath(my_parser().filePath)}\n')
# sort file from largest smallest
'''
for file in vcf_list + plink_list:
if str(file).endswith(("vcf", "vcf.gz")):
unsorted_file_list.append([line_count(file), file])
else:
unsorted_file_list.append([line_count(file[0]), file])
for item in sorted(unsorted_file_list, key=lambda x: (int(x[0])), reverse=True):
pos] = [bta, snp, cm, pos, ref, alt]
elif snps_list[bta + ":" + pos] == [alt + '_' + ref]:
print(
f'Warning: Allele flipped for SNP {snp} in PLINK file(s)'
)
elif snps_list[bta + ":" + pos][4] != ref:
print(
f'Warning: Possible erroneous allele for SNP {snp} in PLINK file(s)'
f'normalize with `bcftools norm`')
except IndexError:
print(
f'Warning: SNP {snp} in PLINK file(s) not indexed as `chrom_pos_ref_alt`'
)
# raise SystemExit
else:
bomb(f'Recheck files at {file_list}')
raise SystemExit
# Create a comprehensive snps file
mark = [row for row in [list(flatten(i)) for i in list(mark_tot.values())]]
# Sort the snps by chrom then pos and write index
mark = sorted(mark, key=lambda x: (int(x[1]), int(x[2])))
for row in mark:
mark_out.write(' '.join(str(e) for e in row) + '\n')
# Write a marker list with ref/alt information
for row in [list(flatten(i)) for i in list(snps_list.values())]:
allele_out.write('\t'.join(row) + '\n')
if len(mark) - len(snps_list) > 0:
def main():
args1 = [('-D', '--DIR'), ('-O', '--OUT')]
args2 = [('-g', '--geno'), ('-s', '--snps'), ('-o', '--out'),
('-n', '--samples'), ('-t', '--type'), ('-a', '--alleles')]
if len(sys.argv) == 1:
from parse_args import msg
print(msg())
del msg
raise SystemExit
elif sys.argv[1] == '-h' or sys.argv[1] == '--help':
import geno2fi
geno2fi
del geno2fi
raise SystemExit
elif any(x in sys.argv[1:] for x in list(itertools.chain(*args1))):
x = set([item for item in args1 for a in sys.argv[1:] if a in item])
y = set(
[item for item in args1 for a in sys.argv[1:] if a not in item])
z = list(x.symmetric_difference(y))
if z:
bomb(f'Missing argument when trying to convert to fimpute:\n'
f' required args: {z}\n'
f' try `./snprecode -h` for complete arguments list\n')
from check_path import check_path
if not check_path():
print("File path OK...")
else:
print(check_path())
del check_path
from garbage import check_dups, file_list
if not check_dups():
print("File check complete...\nFiles to be processed...\n")
print('\n'.join(map(str, file_list)))
del check_dups
import geno2fi
geno2fi
del geno2fi
raise SystemExit
elif any(x in sys.argv[1:] for x in list(itertools.chain(*args2))):
x = set([item for item in args2 for a in sys.argv[1:] if a in item])
y = set(
[item for item in args2 for a in sys.argv[1:] if a not in item])
z = list(x.symmetric_difference(y))
if z:
bomb(f"Missing argument when trying to convert from fimpute\n"
f" required args: {z}\n"
f" try: `./snprecode -h` for complete arguments list\n")
import fi2geno
fi2geno
del fi2geno
raise SystemExit
elif [item for item in sys.argv[1:] if item.endswith(('bim', 'map'))]:
import snpinfo
snpinfo
del snpinfo
raise SystemExit
elif [item for item in sys.argv[1:] if item.endswith(('vcf', 'vcf.gz'))]:
import geno_corr
geno_corr
del geno_corr
raise SystemExit
else:
bomb('Unknown argument(s)\n try ./snprecode -h')
def py_version():
if float(python_version()[0:3]) < 3.6:
# float(python_version()[0:3]) >= 3.6
return bomb(
"Python version not satisfied, install Python V3.6 or later\n")
#!/usr/bin/env python
# -*- coding: utf-8 -*-
from parse_args import my_parser
from os.path import abspath, isdir
from funtools import bomb, file_by_size, to_mat, flatten
try:
vcf_list = [
file_ for file_ in file_by_size(my_parser().filePath, ['vcf'])
if file_.endswith(('vcf', 'vcf.gz'))
]
plink_list = to_mat(
sorted(file_by_size(my_parser().filePath, ["ped", "map"])), 2)
file_list = vcf_list + plink_list
except FileNotFoundError:
bomb(f'No files found at path = {abspath(my_parser().filePath)}\n')
# get a list of input files
def check_path():
if not isdir(my_parser().filePath):
return bomb(f'No files found at path = {my_parser().filePath}\n')
elif isdir(my_parser().filePath) and \
not [item for item in flatten(file_list) if item.endswith(('vcf', 'vcf.gz', 'ped', 'map'))]:
return bomb(
f'No vcf or plink files found at path = {abspath(my_parser().filePath)}\n'
)
from funtools import allelic_r2, open_by_suffix, bomb
from parse_args import my_parser
from recode_dict import recode
start = timeit.default_timer()
# inputs
in_files = [
item.name for item in my_parser().file
if item.name.endswith(('vcf', 'vcf.gz'))
]
if len(in_files) != 2:
bomb(
'''two vcf files required to calculate genotype correlation\n\ttry: `snprecode --file vcf1 vcf2`'''
)
'''
file1 = my_parser().file[0].name
file2 = my_parser().file[1].name
'''
file1 = in_files[0]
file2 = in_files[1]
mat1 = open_by_suffix(file1)
mat2 = open_by_suffix(file2)
# outputs
file_txt = 'genotype_R2.txt'
file_plot = "genotype_R2.pdf"
with open(file_txt, 'w') as outfile: