Created
May 20, 2014 19:13
-
-
Save ethanagb/1eaa8273d51133a1caf4 to your computer and use it in GitHub Desktop.
This file contains 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
#from pprint import pprint | |
FN ='Trinity.fasta' | |
def get_data(fn): | |
with open(fn, mode='r') as fh: | |
header, fasta = "","" | |
for line in fh: | |
if line[0]=='>' and header: | |
yield header, fasta | |
header = line.strip() | |
fasta = '' | |
elif line[0]=='>': | |
header = line.strip() | |
else: | |
fasta += line.strip() | |
if header: | |
yield header, fasta | |
seqs = {} | |
for h,f in get_data(FN): | |
if h not in seqs or len(f)>len(seqs[h]): | |
seqs[h]=f | |
#pprint(seqs) | |
def new_fasta(x): | |
new_file = open(raw_input('Enter new file name: '), 'a') | |
y = x.replace(': ', '\n') | |
z = y.strip() | |
w = z.replace("', '",'\n') | |
q = w.replace("'",'') | |
new_file.write(q.strip()) | |
x=str(seqs) | |
new_fasta(x) | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment