Last active
January 25, 2020 01:07
-
-
Save dkoslicki/f9abdb3875aae3eed593afeea2f66034 to your computer and use it in GitHub Desktop.
Dump the kmers in a CMash database
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
import sys, os | |
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__)))+"/CMash/CMash") | |
from CMash import MinHash as MH | |
import itertools | |
training_database = sys.argv[1] # first input is the training file name | |
dump_file = sys.argv[2] # second input is the desired output dump file | |
CEs = MH.import_multiple_from_single_hdf5(training_database) | |
fid = open(dump_file, 'w') | |
i = 0 | |
for CE in CEs: | |
for kmer in CE._kmers: | |
fid.write('>seq%d\n' % i) | |
fid.write('%s\n' % kmer) | |
i += 1 | |
fid.close() | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment