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
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
|
#!/usr/bin/python
from multiprocessing import Pool
import multiprocessing
import os
import quikr_train as qt
import quikr as q
import sys
import numpy as np
import argparse
import platform
# our defaults
kmer = 6
lamb = 10000
output_directory = ""
input_directory = ""
def main():
global kmer
global input_directory
global output_directory
global lamb
global trained_matrix
#do: write up the description
parser = argparse.ArgumentParser(description="MultifastaOTU")
parser.add_argument("-i", "--input-directory", help="directory containing fasta files", required=True)
parser.add_argument("-o", "--otu-table", help="otu_table", required=True)
parser.add_argument("-t", "--trained-matrix", help="otu_table", required=True)
parser.add_argument("-d", "--output-directory", help="quikr output directory", required=True)
parser.add_argument("-l", "--lamb", type=int, help="the default lambda value is 10,000")
parser.add_argument("-k", "--kmer", type=int, help="specifies which kmer to use, default=6")
parser.add_argument("-j", "--jobs", type=int, help="specifies how many jobs to run at once, default=number of CPUs")
args = parser.parse_args()
# our defaults
jobs=multiprocessing.cpu_count()
trained_matrix = args.trained_matrix
input_directory = args.input_directory
output_directory = args.output_directory
# Make sure our input exist
if not os.path.isdir(args.input_directory):
parser.error( "Input directory not found")
if not os.path.isdir(args.output_directory):
parser.error( "Input directory not found")
if not os.path.isdir(args.output_directory):
os.path.mkdir(args,output_directory)
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
if args.jobs is not None:
jobs = args.jobs
if args.kmer is not None:
kmer = args.kmer
# Load trained matrix
trained_matrix = np.load(args.trained_matrix);
fasta_list = os.listdir(args.input_directory)
pool = Pool(processes=jobs)
results = pool.map(quikr_call, fasta_list)
return 0
def quikr_call(fasta_file):
inp = input_directory + fasta_file
output = output_directory + os.path.basename(fasta_file)
xstar = q.quikr(inp, trained_matrix, kmer, lamb)
np.savetxt(output, xstar, delimiter=",", fmt="%f")
return xstar
if __name__ == "__main__":
sys.exit(main())
|
