def extract_sequences(fastafile, hits, addhitname=False):
"""
Extract the sequences from a fasta file
:param fastafile: The fasta file to get the sequences from
:type fastafile: str
:param hits: The dict of hits using contig, start, end
:type hits: dict
:return: A dict of the sequences with contig_start_end as ID and sequence as value
:rtype: dict
"""
sequences = {}
if not os.path.exists(fastafile):
sys.exit("{} not found\n".format(fastafile))
fa = roblib.read_fasta(fastafile)
for contig in hits:
if contig not in fa:
sys.stderr.write("WARNING: {} was not found in {}\n".format(
contig, fastafile))
for tple in hits[contig]:
seq = fa[contig][tple[0]:tple[1]]
if tple[2]:
seq = roblib.rc(seq)
loc = "_".join(map(str, [contig, tple[0] + 1, tple[1]]))
if addhitname:
loc += " [hit={}]".format(tple[3])
sequences[loc] = seq
return sequences
def read_sequence(conf, verbose=False):
"""
Read the contigs file for this genome and return it
:param conf: the contigs file
:param verbose:
:return: a dict of contig/sequence
"""
if verbose:
sys.stderr.write(f"{bcolors.GREEN}READING {conf}{bcolors.ENDC}\n")
return read_fasta(conf, whole_id=False)
def write_permutations(faf, outputf, verbose=False):
"""
Create and write all the permutations
"""
fa = read_fasta(faf, whole_id=False)
ids = list(fa.keys())
with open(outputf, 'w') as out:
for tple in combinations(ids, 2):
out.write(
f">{tple[0]}\n{fa[tple[0]]}\n>{tple[1]}\n{fa[tple[1]]}\n")
def fasta2ids(faf, verbose=False):
"""
Extract IDs from a fasta file
:param faf: fasta file
:param verbose: more output
:return: a set of IDS
"""
if verbose:
sys.stderr.write(
f"{bcolors.GREEN} Reading IDs from fasta file: {faf}{bcolors.ENDC}"
)
f = read_fasta(faf, whole_id=False)
return set(f.keys())
from roblib import read_fasta
from random import randint
__author__ = 'Rob Edwards'
parser = argparse.ArgumentParser(
description='Convert a fasta file to fastq, faking the qual scores')
parser.add_argument('-f', help='fasta file', required=True)
parser.add_argument('-q', help='fastq output file', required=True)
parser.add_argument('-s',
help='quality score. Default = 40',
default=40,
type=int)
parser.add_argument('-r',
help='random quality scores between 5 and 40',
action='store_true')
args = parser.parse_args()
c = chr(args.s)
fa = read_fasta(args.f)
with open(args.q, 'w') as out:
for i in fa:
l = len(fa[i])
q = l * c
if args.r:
q = ""
for s in range(l):
q = q + chr(randint(33, 125))
out.write("@{}\n{}\n+\n{}\n".format(i, fa[i], q))
sys.exit(1)
if args.f:
files = args.f
else:
files = []
if args.d:
for subdir in args.d:
for f in os.listdir(subdir):
files.append(os.path.join(subdir, f))
overall = {'number': 0, 'total': 0, 'shortest': 1e6, 'longest': 0}
for faf in files:
fa = read_fasta(faf)
if len(fa.keys()) == 1 and list(fa.keys())[0] == '':
sys.stderr.write(f"No sequences found in {faf}\n")
sys.exit(0)
if args.l:
for i in fa:
print("{}\t{}".format(i, len(fa[i])))
print()
lensall = [len(fa[i]) for i in fa]
lens = list(filter(lambda x: x > args.m, lensall))
lens.sort()
length = sum(lens)
import os
import sys
import argparse
from roblib import read_fasta
__author__ = "Rob Edwards"
parser = argparse.ArgumentParser(description="Convert a fasta file to fastq, faking the qual scores")
parser.add_argument("-f", help="fasta file", required=True)
parser.add_argument("-q", help="fastq output file", required=True)
parser.add_argument("-s", help="quality score. Default = 40", default=40, type=int)
args = parser.parse_args()
c = chr(args.s)
fa = read_fasta(args.f)
with open(args.q, "w") as out:
for i in fa:
l = len(fa[i])
out.write("@{}\n{}\n+\n{}\n".format(i, fa[i], l * c))
import numpy
from roblib import read_fasta
__author__ = 'Rob Edwards'
if __name__ == "__main__":
parser = argparse.ArgumentParser(description=' ')
parser.add_argument('-d', help='directory of fasta files', required=True, action='append')
parser.add_argument('-p', help='figure file name for the graph', required=True)
parser.add_argument('-m', help='minimum length to be included (default = all reads)', default=0, type=int)
args = parser.parse_args()
lengths = {}
maxd = 0
for d in args.d:
lengths[d] = []
for f in os.listdir(d):
fa = read_fasta(os.path.join(d, f))
lengths[d].extend([len(fa[x]) for x in fa])
maxd = max(lengths[d]) if max(lengths[d]) > maxd else maxd
bins = numpy.linspace(args.m, maxd, 100)
alpha = 1.0 / len(args.d)
#pyplot.ylim(ymin=args.m)
for d in args.d:
data = list(filter(lambda x: x > args.m, lengths[d]))
pyplot.hist(data, bins, alpha=alpha, label=d)
pyplot.legend(loc='upper right')
pyplot.savefig(args.p)
counter = args.n - 1
if not args.f and not args.d:
sys.stderr.write(
f"{bcolors.RED}FATAL: Please supply either -d or -f options{bcolors.ENDC}\n"
)
sys.exit(-1)
idmap = open(args.i, 'w')
out = open(args.o, 'w')
if args.f:
for f in args.f:
if args.v:
sys.stderr.write(f"{bcolors.GREEN}Reading {f}{bcolors.ENDC}\n")
fa = read_fasta(f)
for id in fa:
counter += 1
out.write(">{}\n{}\n".format(counter, fa[id]))
idmap.write("{}\t{}\t{}\n".format(f, id, counter))
if args.x and (counter - (args.n - 2)) > args.x:
break
if args.d:
for d in args.d:
if args.v:
sys.stderr.write(f"{bcolors.GREEN}Reading {d}{bcolors.ENDC}\n")
for f in os.listdir(d):
if args.v:
sys.stderr.write(
f"{bcolors.BLUE}\tReading {f}{bcolors.ENDC}\n")
parser.add_argument('-v', help='verbose output', action='store_true')
args = parser.parse_args()
endings = {'.fna', '.fasta', '.fa'}
for f in os.listdir(args.d):
longest = [0, None, None]
isfasta = False
for e in endings:
if f.endswith(e):
isfasta = True
break
if not isfasta:
if args.v:
sys.stderr.write(
f"{bcolors.PINK}Don't think {f} is a fasta file. Skipped\n{bcolors.ENDC}"
)
continue
if args.v:
sys.stderr.write(f"{bcolors.GREEN}{f}{bcolors.ENDC}\n")
fa = read_fasta(os.path.join(args.d, f))
for x in fa:
if len(fa[x]) > longest[0]:
longest = [len(fa[x]), x, fa[x]]
if 0 == longest[0]:
continue
print("{}\t{}".format(f, longest[0]))
if args.f:
with open(args.f, 'a') as out:
out.write(f">{longest[1]} [from {f}]\n{longest[2]}\n")
"""
Print the length of the longest contig for each file in a directory of fasta files.
"""
import os
import sys
import argparse
from roblib import read_fasta
__author__ = 'Rob Edwards'
if __name__ == "__main__":
parser = argparse.ArgumentParser(description='Print the length of the longest contig for each file in a directory of fasta files')
parser.add_argument('-d', help='Directory of fasta files', required=True)
args = parser.parse_args()
for f in os.listdir(args.d):
fa = read_fasta(os.path.join(args.d, f))
lengths = [len(fa[x]) for x in fa]
lengths.sort()
print("{}\t{}".format(f, lengths[-1]))
import os
import sys
import argparse
from roblib import read_fasta, write_fastq, message
__author__ = 'Rob Edwards'
__copyright__ = 'Copyright 2020, Rob Edwards'
__credits__ = ['Rob Edwards']
__license__ = 'MIT'
__maintainer__ = 'Rob Edwards'
__email__ = '*****@*****.**'
if __name__ == '__main__':
parser = argparse.ArgumentParser(description=" ")
parser.add_argument('-f', help='fasta file', required=True)
parser.add_argument('-q', help='quality file', required=True)
parser.add_argument('-o', help='output fastq file', required=True)
parser.add_argument('-v', help='verbose output', action='store_true')
args = parser.parse_args()
if not os.path.exists(args.f) and not os.path.exists(args.q):
message("FATAL: either {args.f} or {args.q} not found", "RED")
sys.exit(-1)
fa = read_fasta(args.f, True, False)
qu = read_fasta(args.q, True, True)
write_fastq(fa, qu, args.o, args.v)