def try_int(s):
"Convert to integer if possible."
try: return int(s)
except: return s
def natsort_key(s):
"Used internally to get a tuple by which s is sorted."
import re
return map(try_int, re.findall(r'(\d+|\D+)', s))
if len(sys.argv)==1: sys.exit(__doc__)
usage = "%prog [- <] <input fasta file>"
parser = OptionParser(usage=usage, version="%prog - Version 1")
options, args = parser.parse_args(sys.argv)
if args[1]=='-':
seqs = fasta.FastaFile(sys.stdin).readAll()
else:
seqs = fasta.FastaFile(args[1]).readAll()
seqs.sort(key=lambda x: natsort_key(x[0]))
for h,s in seqs:
print '>%s' % h
print fasta.pretty(s)
print
#!/usr/bin/env python
"""
reverse_comp.py <filename>
Prints the reverse complement of a DNA string (in fasta format).
"""
import sys
from mungo import fasta
from mungo import sequence
if len(sys.argv)!=2 or '-h' in sys.argv or '--help' in sys.argv:
sys.exit(__doc__)
for h,s in fasta.FastaFile(sys.argv[1]):
rc = sequence.reverseComplement(s.upper())
print '>%s' % h
print fasta.pretty(rc)
"""
fastaExtract.py <fasta file> <accession> <start> <end>
Extract sequence between given start & end coordinates from fasta file.
"""
import sys
from mungo.fasta import FastaFile, pretty
if '-h' in sys.argv:
sys.exit(__doc__)
iFilename = sys.argv[1]
accession = sys.argv[2]
try:
start = int(sys.argv[3])
end = int(sys.argv[4])
except:
start = None
end = None
for h,s in FastaFile(iFilename):
tokens = h.split()
if tokens[0]==accession:
print '>%s:%s-%s' % (tokens[0],start,end)
if start:
print pretty(s[start-1:end])
else:
print pretty(s)
break
parser.add_option("-o",
"--output",
dest="oFilename",
help="Output filename",
default=None)
parser.add_option("-w",
"--width",
dest="width",
type="int",
help="Sequence width",
default=60)
options, args = parser.parse_args(sys.argv)
if len(args) != 2: sys.exit(__doc__)
if args[1] != '-':
faFile = FastaFile(args[1])
else:
faFile = FastaFile(sys.stdin)
if options.oFilename:
oFile = open(options.oFilename, 'w')
else:
oFile = sys.stdout
for header, seq in faFile:
protein = sequence.translate(seq)
print >> oFile, '>%s' % header
print >> oFile, pretty(protein, width=options.width)
from mungo.fasta import FastaFile, pretty
from mungo import sequence
usage = "%prog [options] <fasta file>"
parser = OptionParser(usage=usage)
parser.add_option("-o", "--output", dest="oFilename",
help="Output filename", default=None)
parser.add_option("-w", "--width", dest="width", type="int",
help="Sequence width", default=60)
options, args = parser.parse_args(sys.argv)
if len(args)!=2: sys.exit(__doc__)
if args[1]!='-':
faFile = FastaFile(args[1])
else:
faFile = FastaFile(sys.stdin)
if options.oFilename:
oFile = open(options.oFilename, 'w')
else:
oFile = sys.stdout
for header,seq in faFile:
protein = sequence.translate(seq)
print >> oFile, '>%s' % header
print >> oFile, pretty(protein, width=options.width)
"""
fastaExtract.py <fasta file> <accession> <start> <end>
Extract sequence between given start & end coordinates from fasta file.
"""
import sys
from mungo.fasta import FastaFile, pretty
if '-h' in sys.argv:
sys.exit(__doc__)
iFilename = sys.argv[1]
accession = sys.argv[2]
try:
start = int(sys.argv[3])
end = int(sys.argv[4])
except:
start = None
end = None
for h, s in FastaFile(iFilename):
tokens = h.split()
if tokens[0] == accession:
print '>%s:%s-%s' % (tokens[0], start, end)
if start:
print pretty(s[start - 1:end])
else:
print pretty(s)
break
def try_int(s):
"Convert to integer if possible."
try:
return int(s)
except:
return s
def natsort_key(s):
"Used internally to get a tuple by which s is sorted."
import re
return map(try_int, re.findall(r'(\d+|\D+)', s))
if len(sys.argv) == 1: sys.exit(__doc__)
usage = "%prog [- <] <input fasta file>"
parser = OptionParser(usage=usage, version="%prog - Version 1")
options, args = parser.parse_args(sys.argv)
if args[1] == '-':
seqs = fasta.FastaFile(sys.stdin).readAll()
else:
seqs = fasta.FastaFile(args[1]).readAll()
seqs.sort(key=lambda x: natsort_key(x[0]))
for h, s in seqs:
print '>%s' % h
print fasta.pretty(s)
print