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
|
#!/usr/bin/python3
__doc__="""
pliu 20160309
run pRSEM to prepare reference genome and select training set isoforms
"""
import os
import sys
import Util
import Prsem
def main():
import Gene
import Param
import Transcript
argdict = getCommandLineArguments()
prm = Param.initFromCommandLineArguments(argdict)
prepBowtieRef(prm)
prm.transcripts = Transcript.quicklyReadRSEMTI(prm.fti)
prm.genes = Gene.constructGenesFromTranscripts(prm.transcripts)
Prsem.buildTrainingSet(prm)
def getCommandLineArguments():
import argparse
parser = argparse.ArgumentParser()
parser.add_argument('--num-threads', type=int)
parser.add_argument('--bowtie-path')
parser.add_argument('--mappability-bigwig-file')
parser.add_argument('--quiet', action='store_true')
## need to be in the same order as fed in argument
parser.add_argument('ref_fasta')
parser.add_argument('ref_name')
argdict = vars(parser.parse_args())
return argdict
def prepBowtieRef(prm):
bowtie_build = prm.bowtie_path + '/bowtie-build'
#bowtie_inspect = prm.bowtie_path + '/bowtie-inspect'
prsem_ref = prm.ref_name + '_prsem'
## run bowtie-build for index whole genome for ChIP-seq
## use --offrate=3, which is 2 less than the default value 5
## will trade ~1.5 time memory for 1/4 alignment time for human genome
if prm.quiet:
Util.runCommand(bowtie_build, '-o', 3, '--quiet', prm.ref_fasta,
prsem_ref, quiet=prm.quiet)
else:
Util.runCommand(bowtie_build, '-o', 3, prm.ref_fasta,
prsem_ref, quiet=prm.quiet)
#Util.runCommandnAndGetOutput(bowtie_inspect, '-s', prsem_ref, quiet=False)
if __name__=='__main__':
main()
|
