Mercurial > repos > qfabrepo > metadegalaxy_pear_stats

comparison pear_stats.py @ 0:ec62f17fcfe6 draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload for repository https://github.com/QFAB-Bioinformatics/metaDEGalaxy/tree/master/pear_stats commit 0db3cb4e9a87400bb2f8402ffc23334e24ad4b4e"
author qfabrepo
date Mon, 14 Sep 2020 04:50:28 +0000
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:ec62f17fcfe6
1 #!/usr/bin/env python
2 import sys
3 import argparse
4
5 parser = argparse.ArgumentParser(
6 description="Parse multiple Pear statistic log to a tabular format\n" +
7 "Example:\n python pear_stats.py -i \"file1.log,file2.log\" -s \"samplename1 samplename2\" -o outputfile")
8 parser.add_argument("-v","--version",action="version",version="%(prog)s 1.0")
9 parser.add_argument("-i","--input",dest="inputfilelist",default=False,help="a list of input file")
10 parser.add_argument("-s","--samplename", dest="samplename",default=False,help="a list of input filename")
11 parser.add_argument("-o","--outfile",dest="outputfile",default=False,help="Pear statistic output")
12
13
14 if(len(sys.argv) == 1):
15 parser.print_help(sys.stderr)
16 sys.exit()
17
18 args = parser.parse_args()
19
20 tags = ['Assembled reads','Discarded reads','Not assembled reads']
21 LINESTART=30
22 LINEEND =LINESTART+2
23
24
25 inputfiles=args.inputfilelist.split(',')
26 inputfilenames=args.samplename.split(',')
27 outputfile=open(args.outputfile,'w')
28
29 allAssembled = 0
30
31 def processfile(instr):
32 result=[]
33 with open(instr,'r') as f:
34 for linenum,line in enumerate(f):
35 if LINESTART <= linenum <= LINEEND:
36 ix = linenum-LINESTART
37 if (line.startswith(tags[ix])):
38 result.append(line.rstrip())
39 if (ix == 0):
40 token = line.strip().split('(')[1]
41 token = token.replace("%)","")
42 global allAssembled
43 allAssembled += float(token)
44 else:
45 print("ARGH!:", line)
46 return(result)
47
48 for element in range(0,len(inputfiles)):
49 output=processfile(inputfiles[element])
50 output.insert(0,inputfilenames[element])
51 outputfile.write("\t".join(output))
52 outputfile.write("\n")
53
54 averageAssembled = allAssembled / len(inputfiles)
55
56 averageAssembledOut=["The above assessment has been performed on 1000 randomly selected reads per sample file.\nAverage % of overlapping paired-end reads =",str(averageAssembled),"\nIf the average percentage is greater than 50%, you can consider using workflow 16S_biodiversity_for_overlap_PE.\nHowever, if the average percentage is less than 50%, use 16S_biodiversity_nonoverlap_PE."]
57
58
59 outputfile.write("\n\n\n")
60 outputfile.write("\t".join(averageAssembledOut))
61 outputfile.close()