def fetch(args):
fasta = Fasta(args.fasta)
regions = args.regions
if args.list:
with args.list as listfile:
for region in listfile:
regions.append(region.rstrip())
for region in regions:
region = region.split()[0]
try:
rname, interval = region.split(':')
except ValueError:
rname = region
interval = None
try:
start, end = interval.split('-')
sequence = fasta[rname][int(start) - 1:int(end)]
except (AttributeError, ValueError):
sequence = fasta[rname][:]
if args.complement:
sequence = sequence.complement
if args.reverse:
sequence = sequence.reverse
line_len = fasta[rname]._fa.faidx.index[rname]['lenc']
if args.name:
sys.stdout.write('>' + sequence.name + '\n')
for line in wrap_sequence(line_len, sequence.seq):
sys.stdout.write(line)
else:
for line in wrap_sequence(line_len, sequence.seq):
sys.stdout.write(line)
fasta.close()
def fetch_sequence(args, fasta, name, start=None, end=None):
try:
line_len = fasta.faidx.index[name].lenc
if args.auto_strand and start > end and start is not None and end is not None:
# flip (0, 1] coordinates
sequence = fasta[name][end - 1:start + 1]
sequence = sequence.reverse.complement
else:
sequence = fasta[name][start:end]
except KeyError:
sys.stderr.write(
"warning: {name} not found in file\n".format(**locals()))
return
if args.complement:
sequence = sequence.complement
if args.reverse:
sequence = sequence.reverse
if args.no_output:
return
if args.no_names:
pass
else:
if (start or end) and not args.no_coords:
yield ''.join(['>', sequence.fancy_name, '\n'])
else:
yield ''.join(['>', sequence.name, '\n'])
for line in wrap_sequence(line_len, sequence.seq):
yield line
def splitGenome(self):
fa = Fasta(self.fastaFileName)
for seq in fa:
with open('{}{}.fa'.format(STANDARD_GENOME_PATH, seq.name),
'w') as out:
out.write('>{}\n'.format(seq.name))
for line in wrap_sequence(70, str(seq)):
out.write(line)
print("<<<<<<<Splitted>>>>>>")
def make_long_fasta(filename, nrecs=250, seqlen=SEQLEN):
headers = []
with open(filename, 'w') as f:
s = "ACTGACTGAC"
for i in range(nrecs):
h = "header%i" % i
headers.append(h)
f.write('>' + h + '\n')
for line in pyfaidx.wrap_sequence(80, s * (seqlen//10)):
f.write(line)
return headers
def Split_chromosome():
print("Enter the FASTA file :")
fasta = input()
fasta = '{}.{}'.format(fasta, 'fa')
fa = Fasta(fasta)
print("Splitting chromosomes..........")
for seq in fa:
with open('{}.fa'.format(seq.name), 'w') as out:
out.write('>{}\n'.format(seq.name))
for line in wrap_sequence(70, str(seq)):
out.write(line)
print("<<<<<<<Splitted>>>>>>")
def fetch_sequence(args, fasta, name, start=None, end=None):
line_len = fasta.faidx.index[name].lenc
sequence = fasta[name][start:end]
if args.complement:
sequence = sequence.complement
if args.reverse:
sequence = sequence.reverse
if not args.no_names:
if start or end:
yield ''.join(['>', sequence.longname, '\n'])
else:
yield ''.join(['>', sequence.name, '\n'])
for line in wrap_sequence(line_len, sequence.seq):
yield line
def bed_to_introns(bed_in, fasta_in, fasta_out):
logging.info("Opening FASTA: {0}".format(fasta_in))
logging.info("Note: will take a while the first time it is opened.")
fasta = Fasta(fasta_in,
key_function=lambda key: key.split()[0],
strict_bounds=True)
bed_h = open(bed_in, 'r')
all_keys = {}
output_seq = []
count = 0
for line in bed_h:
if count % 10000 == 0 and count > 0:
logging.info("On intron: {0}".format(count))
ref, start, stop, genename = line.split()
seq = fasta[ref][int(start):int(stop)]
key = ref + ':' + start + '-' + stop
if key in all_keys:
logging.warning("ERROR: {0} appears once already".format(key))
continue
all_keys[key] = True
if int(start) > int(stop):
logging.warning(
"Intron coords greater than reference: {0}:{1}-{2}".format(
ref, start, stop))
logging.warning("Reference length: {0}".format(len(fasta[ref])))
continue
if len(seq) == 0:
logging.warning("Intron length is 0? {0}:{1}-{2}".format(
ref, start, stop))
continue
output_seq.append(seq)
count += 1
bed_h.close()
with open(fasta_out, 'w') as outf:
logging.info("Writing intron sequences out to {0}".format(fasta_out))
for rec in output_seq:
print('>{rname}:{start}-{end}'.format(rname=rec.name,
start=str(rec.start - 1),
end=str(rec.end)),
file=outf)
for line in wrap_sequence(60, rec.seq):
outf.write(line)
def fetch_sequence(args, fasta, name, start=None, end=None):
try:
line_len = fasta.faidx.index[name].lenc
sequence = fasta[name][start:end]
except KeyError:
sys.stderr.write("warning: {name} not found in file\n".format(**locals()))
return
if args.complement:
sequence = sequence.complement
if args.reverse:
sequence = sequence.reverse
if args.no_names:
pass
elif args.full_names:
yield ''.join(['>', fasta[name].long_name, '\n'])
else:
if start or end:
yield ''.join(['>', sequence.longname, '\n'])
else:
yield ''.join(['>', sequence.name, '\n'])
for line in wrap_sequence(line_len, sequence.seq):
yield line
def fetch_sequence(args, fasta, name, start=None, end=None):
try:
line_len = fasta.faidx.index[name].lenc
sequence = fasta[name][start:end]
except KeyError:
sys.stderr.write("warning: {name} not found in file\n".format(**locals()))
return
if args.complement:
sequence = sequence.complement
if args.reverse:
sequence = sequence.reverse
if args.no_names:
pass
elif args.full_names:
yield ''.join(['>', fasta[name].long_name, '\n'])
else:
if start or end:
yield ''.join(['>', sequence.longname, '\n'])
else:
yield ''.join(['>', sequence.name, '\n'])
for line in wrap_sequence(line_len, sequence.seq):
yield line
with open(pos) as P, open(outfa, 'w') as OUT, open(outdisstat, 'w') as DIS:
tmp = {}
basedis = {}
DIS.write('\t'.join(['location', 'A', 'C', 'G', 'T']) + '\n')
for i in P.readlines():
if i.startswith('PA'): continue
#this is use the python spice method, so must substract one
id, st, ed, strand = makecord(i.strip())
seqname = id + ':' + str(st) + '-' + str(ed) + ':' + strand
sequence = fasta[id][st:ed]
line_len = fasta.faidx.index[id].lenc
if strand == '-':
sequence = sequence.complement
sequence = sequence.reverse
OUT.write('>' + seqname + '\n')
for line in wrap_sequence(line_len, sequence.seq):
OUT.write(line)
else:
OUT.write('>' + seqname + '\n')
for line in wrap_sequence(line_len, sequence.seq):
OUT.write(line)
for index, base in enumerate(list(sequence.seq)):
if index not in basedis:
basedis[index] = [base]
else:
basedis[index].append(base)
for index, base in basedis.items():
c = Counter(base)
total = sum(c.values())
percent = {key: value / total for key, value in c.items()}
def main(progname=None):
parse = argparse.ArgumentParser(
description=
'Build normal genome by integrating germline SNPs from a VCF file.',
prog=progname if progname else sys.argv[0])
parse.add_argument('-v',
'--vcf',
type=check_vcf,
required=True,
metavar='FILE',
help='a VCF file containing germline SNPs')
parse.add_argument('-r',
'--reference',
type=str,
required=True,
metavar='FILE',
help='a fasta file of reference genome')
default = 'normal_fa'
parse.add_argument('-o',
'--output',
type=check_output_folder,
default=default,
metavar='DIR',
help='output directory [{}]'.format(default))
parse.add_argument(
'-a',
'--autosomes',
type=check_autosomes,
required=True,
metavar='STR',
help='autosomes of the genome (e.g. 1,2,3,4,5 or 1..4,5)')
default = None
parse.add_argument(
'-s',
'--sex_chr',
type=check_sex,
default=default,
metavar='STR',
help='sex chromosomes of the genome (separated by comma) [{}]'.format(
default))
args = parse.parse_args()
if args.sex_chr == None:
args.sex_chr = []
else:
args.sex_chr = args.sex_chr.split(',')
autosomes = parse_autosomes(args.autosomes)
#build the data structure: genome_profile
reference = pyfaidx.Fasta(args.reference)
genome_profile = fai_info(fai=args.reference + '.fai',
autosomes=autosomes,
sex_chr=args.sex_chr)
#fill in the list hap_vars in genome_profile
add_vcf_vars(profile=genome_profile, vcf=args.vcf)
os.mkdir(args.output, mode=0o755)
for i in range(2):
with open('{}/normal.parental_{}.fa'.format(args.output, i),
'w') as output:
for chroms in genome_profile['order']:
if i < len(genome_profile[chroms]['hap_vars']):
start = 0
segments = []
for snp in genome_profile[chroms]['hap_vars'][i]:
try:
segments.append(reference[chroms][start:(snp[0] -
1)].seq)
except ValueError:
if snp[0] - start == 1:
#This snp and the previous one is adjacent snps. e.g. chr1 45 (previous) and chr1 46 (current)
#If you retrive by reference['chr1'][45:(46-1)].seq, the return is not '', an error will pop actually.
pass
else:
raise
segments.append(snp[1])
start = snp[0]
if start < genome_profile[chroms]['length']:
segments.append(reference[chroms][start:].seq)
output.write('>{}\n'.format(chroms))
for outputline in pyfaidx.wrap_sequence(
genome_profile[chroms]['linebases'],
''.join(segments)):
output.write(outputline)
def build_fasta(output=None, chain=None, normal_fa=None, width=None):
refs = []
for fa in normal_fa.split(','):
refs.append(pyfaidx.Fasta(fa))
parentalre = re.compile('^parental:[01]$')
node = os.path.basename(chain)
node = node.split('.')[0]
outputf = []
for parental in 0, 1:
outputf.append(
open('{}/{}.parental_{}.fa'.format(output, node, parental), 'w'))
reference = None
with open(chain) as inputf:
seq_name = None
parental = None
seq = []
for line in inputf:
line = line.rstrip()
if line.startswith('>'):
if seq:
outputf[parental].write('>{}\n'.format(seq_name))
for outputline in pyfaidx.wrap_sequence(
width, ''.join(seq)):
outputf[parental].write(outputline)
seq_name, parental = line[1:].split()
if parentalre.match(parental):
parental = int(parental.split(':')[1])
try:
reference = refs[parental]
except IndexError:
raise FastaMissingError(
'There is no parental {} avalible,\n'.format(
parental) +
'which is required in the record ({}):\n{}\n'.
format(chain, line))
else:
raise ChainFileError(
'The format of this line below from the chain file ' +
'({}) is not correct:\n{}\n'.format(chain, line))
seq = []
else:
column = line.split()
chroms = column[0]
start = int(column[1])
end = int(column[2])
seq_type = column[3]
segment = ''
if seq_type == 'REF':
segment = reference[chroms][start:end].seq
elif seq_type == 'SNV':
ref = reference[chroms][start:end].seq
m = Mutation(ref=ref, form=column[4])
segment = m.alternative
elif seq_type == 'DEL':
pass
else:
raise ChainFileError(
'Can not recognize the sequence type ({}) '.format(
seq_type) +
'of the record below from the chain file ({}):\n{}\n'.
format(chain, line))
seq.append(segment)
if seq:
outputf[parental].write('>{}\n'.format(seq_name))
for outputline in pyfaidx.wrap_sequence(width, ''.join(seq)):
outputf[parental].write(outputline)
for parental in 0, 1:
outputf[parental].close()
# Import packages
import os
import sys
# Import packages
from Bio import SeqIO
from Bio.SeqRecord import SeqRecord
from Bio.SeqFeature import FeatureLocation, CompoundLocation
from Bio import pairwise2
from Bio.Seq import Seq
from pyfaidx import Fasta, wrap_sequence
file = sys.argv[1]
output_file = file
with open(output_file + ".nosynthetic", 'a') as out:
fasta_sequences = SeqIO.parse(open(file), 'fasta')
for fasta in fasta_sequences:
name = fasta.name
desc = fasta.description
if '>' in desc:
desc_s = desc.split('>')[0]
else:
desc_s = desc
if 'synthetic' not in desc_s \
and 'artificial' not in desc_s \
and 'fragment' not in desc_s \
and 'low quality' not in desc_s \
and 'partial' not in desc_s:
out.write('>{}\n'.format(desc_s))
for line in wrap_sequence(70, str(fasta.seq)):
out.write(line)
from os import listdir
from pyfaidx import Fasta, wrap_sequence
fileList = listdir('.')
fileList.remove('BhybridumS_002_v1.0.softmasked.fa')
fileList.remove('q.PAC4GC.hybridum.S.chr.list')
fileList = [fasta for fasta in fileList if fasta.endswith('.fasta')]
with open('q.PAC4GC.hybridum.S.chr.list','r') as f:
chrList = f.read().split('\n')
print chrList
chrList.remove('')
for file in fileList:
newfilename = file[:file.find('.')]+'S.fasta'
print newfilename
fasta = Fasta(file)
open(newfilename,'w').close()
with open(newfilename,'w') as fOut:
print chrList
print file,newfilename
for chromName in chrList:
print '>'+chromName
fOut.write('>' + chromName +'\n%s\n'%(''.join(line for line in wrap_sequence(60, str(fasta[chromName])))))
