blob: 2076f5a02b8a384eeb1fb290ab7cb23ecfa2a5cf (
plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
|
#from scipy.sparse import *
import numpy as np
import sys
from subprocess import *
import platform
# You can call this script independently, and will save the
# trained matrix as a numpy file.
# example: python quikr-train.py input.fasta 6 trained_matrix.npy
def main(argv):
input_file_location = argv[1]
kmer = argv[2]
output_file_location = argv[3]
# call the quikr train function, save the output with np.save
matrix = quikr_train(argv[1], argv[2])
np.save(output_file_location, matrix)
return 0
def quikr_train(input_file_location, kmer):
print "input fasta training file: " + input_file_location
print "kmer: " + kmer
kmer_file_name = kmer + "mers.txt"
print kmer_file_name
uname = platform.uname()[0]
if uname == "Linux":
print "Detected Linux"
input_file = Popen(["./probabilities-by-read-linux", kmer, input_file_location, kmer_file_name], stdout=PIPE)
elif uname == "Darwin":
print "Detected Mac OS X"
input_file = Popen(["./probabilities-by-read-osx", kmer, input_file_location, kmer_file_name])
# load and normalize the matrix by dividing each element by the sum of it's column.
matrix = np.loadtxt(input_file.stdout)
normalized = matrix / matrix.sum(0)
return normalized
if __name__ == "__main__":
sys.exit(main(sys.argv))
|
