Created
February 7, 2015 18:39
-
-
Save daler/c637e96d640c1bbe5d8b to your computer and use it in GitHub Desktop.
fasta from BED-like file with dashes
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import pybedtools | |
# This demo uses files that ship with pybedtools | |
a = pybedtools.example_bedtool('a.bed') | |
fasta = pybedtools.example_filename('test.fa') | |
# Use a properly-formatted BED file, and then post-process the resulting fasta. | |
x = a.sequence(fi=fasta, s=True) | |
for i, line in enumerate(open(x.seqfn)): | |
if line.startswith('>') and i >0: | |
print '>\n------------' | |
print line, | |
# Alternative method: use a text file with dashes, without stripping the dashes first. | |
# First make a version of `a.bed` that has dashes every other line | |
with open('a-with-dashes.txt', 'w') as fout: | |
for i in a: | |
fout.write(str(i)) | |
fout.write('------------\n') | |
for line in open('a-with-dashes.txt'): | |
if line.startswith('------'): | |
print('>\n--------') | |
else: | |
print open( | |
pybedtools.BedTool(line, from_string=True)\ | |
.sequence(fi=fasta, s=True).seqfn | |
).read(), |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment