def bins_contig_gc(self, inputs, out_path, bin_id_pattern=r"bin\..+\.\d+"):
array = []
for bp in glob.glob(inputs):
bin_id = re.search(bin_id_pattern, os.path.basename(bp)).group()
for header, seq in iter_fa(bp, trim_line_break=True):
contig_id = header.split()[0].lstrip(">")
seq.upper()
gc = (seq.count('G') + seq.count('C')) / len(seq)
array.append([contig_id, bin_id, gc])
df = pd.DataFrame(array, columns=["ContigID", "BinID", "GC"])
df.to_csv(out_path, sep="\t", index=False)
def parse_bin_fa(self):
seqs_dict = {}
kar_ids = []
lens = []
for header, seq in iter_fa(bp, trim_line_break=True):
kar_id = header.split()[0].lstrip(">")
seqs_dict[kar_id] = seq
kar_ids.append(kar_id)
lens.append(len(seq))
df = pd.DataFrame({"Length": lens}, index=kar_ids)
help="input fasta files.",
default=False,
metavar='<path>')
p.add_argument('--minlen',
'-l',
help="min contigs length to keep in output",
default=False,
metavar='<path>')
p.add_argument('--replaceinput',
action='store_true',
help="replace input files")
options = p.parse_args()
i = 1
for ipt in options.inputs:
with open(ipt + '.renamed', 'w') as fout:
for header, seq in iter_fa(ipt):
if options.minlen:
if len(seq) <= options.minlen:
continue
header = re.sub(r'^\S+', ">contig_" + str(i), header)
fout.write(header + seq)
i += 1
if options.replaceinput:
for ipt in options.inputs:
os.remove(ipt)
os.rename(ipt + '.renamed', ipt)
description="extract sequences from an fasta file with sequence headers")
p.add_argument('-s',
'--headers',
required=True,
help='file containing sequence headers.')
p.add_argument('-f',
'--fasta',
required=True,
help='fasta file containing sequences.')
p.add_argument('-o',
'--out_file',
required=True,
help='file to save the extracted sequences. fasta format.')
options = p.parse_args()
headers_dict = {}
with open(options.headers) as file_handler:
for line in file_handler:
headers_dict[line.split()[0].split('_')[1]] = True
sequences_dict = {}
with open(options.out_file, 'w') as fh:
for header, seq in iter_fa(options.fasta, trim_line_break=True):
if sequences_dict.get(seq):
continue
if headers_dict.get(header.split()[0].split('_')[1]):
fh.write("{}\n{}\n".format(header, seq))
sequences_dict[seq] = True
#!/usr/bin/env python3.8
from MetaGenome.pyutils.read import iter_fa
import argparse
p = argparse.ArgumentParser(
description="find subset contigs in union contigs.")
p.add_argument('-s',
'--subset',
required=True,
help='fasta file containing subset contigs')
p.add_argument('-u',
'--union',
required=True,
help='fasta file containing union contigs')
p.add_argument('-o',
'--out_file',
required=True,
help='file to save the found match contig names')
options = p.parse_args()
subset_dict = {}
for header, seq in iter_fa(options.subset, trim_line_break=True):
subset_dict[seq] = True
with open(options.out_file, 'w') as file_handler:
for header, seq in iter_fa(options.union, trim_line_break=True):
if subset_dict.get(seq):
file_handler.write("{}\n".format(header))