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
51
52
53
54
|
#!/usr/bin/env python
import sys
import os
import argparse
import quikr
import numpy as np
def main():
parser = argparse.ArgumentParser(description=
"Quikr returns the estimated frequencies of batcteria present when given a \
input FASTA file. \n \
A default trained matrix will be used if none is supplied \n \
You must supply a kmer and default lambda if using a custom trained \
matrix.")
parser.add_argument("-f", "--fasta", help="the sample's fasta file of NGS READS", required=True)
parser.add_argument("-o", "--output", help="OTU_FRACTION_PRESENT, a vector \
representing the percentage of database sequence's presence in a sequence. (csv output)", required=True)
parser.add_argument("-t", "--trained-matrix", help="the trained matrix", required=True)
parser.add_argument("-l", "--lamb", type=int, help="the lambda size. (default is 10,000")
parser.add_argument("-k", "--kmer", type=int, required=True,
help="specifies the size of the kmer to use (the default is 6)")
args = parser.parse_args()
# our default lambda is 10,000
lamb = 10000
# our default kmer size is 6
kmer = 6
# Make sure our input exist
if not os.path.isfile(args.fasta):
parser.error( "Input fasta file not found")
if not os.path.isfile(args.trained_matrix):
parser.error("Custom trained matrix not found")
# use alternative lambda
if args.lamb is not None:
lamb = args.lamb
# use alternative kmer
if args.kmer is not None:
kmer = args.kmer
trained_matrix = quikr.load_trained_matrix_from_file(args.trained_matrix)
xstar = quikr.calculate_estimated_frequencies(args.fasta, trained_matrix, kmer, lamb)
np.savetxt(args.output, xstar, delimiter=",", fmt="%f")
return 0
if __name__ == "__main__":
sys.exit(main())
|
