Mercurial > repos > yufei-luo > s_mart

comparison SMART/DiffExpAnal/fastq_groomer_parallel.py @ 18:94ab73e8a190

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author m-zytnicki
date Mon, 29 Apr 2013 03:20:15 -0400
parents
children
comparison
equal deleted inserted replaced
17:b0e8584489e6 18:94ab73e8a190
1 import sys, os, optparse, random
2 from galaxy_utils.sequence.fastq import fastqReader, fastqVerboseErrorReader, fastqAggregator, fastqWriter
3
4 def stop_err(msg):
5 sys.stderr.write("%s\n" % msg)
6 sys.exit()
7
8 def main():
9
10 input_filename = sys.argv[1] #a txt file
11 input_type = sys.argv[2]
12 output_filename = sys.argv[3] #a txt file
13 output_type = sys.argv[4]
14 force_quality_encoding = sys.argv[5]
15 summarize_input = sys.argv[6] == 'summarize_input'
16 pairedEnd_input = sys.argv[7]
17 if pairedEnd_input == 'None':
18 pairedEnd_input = None
19 else:
20 output_pairedEndFileName = sys.argv[8]
21
22 if force_quality_encoding == 'None':
23 force_quality_encoding = None
24
25 #Parse the input txt file and read a list of fastq files
26 file = open(input_filename, "r")
27 lines = file.readlines()
28 inputFileNames = []
29 outGroomerNames = []
30 resDirName = os.path.dirname(output_filename) + "/"
31 #Write output txt file and define all output groomer file names
32 outFile = open(output_filename, "w")
33 for line in lines:
34 tab = line.split()
35 inputFileNames.append(tab[1])
36 outGroomerName = resDirName + tab[0] + '_outGroomer_%s.fastq' % random.randrange(0, 10000)
37 outGroomerNames.append(outGroomerName)
38 outFile.write(tab[0] + '\t' + outGroomerName + '\n')
39 outFile.close()
40 file.close()
41
42 if pairedEnd_input != None:
43 inPairedFile = open(pairedEnd_input, "r")
44 lines = inPairedFile.readlines()
45 inputPairedEndFileNames = []
46 outGroomerPairedEndNames = []
47 outPairedEndFile = open(output_pairedEndFileName, "w")
48 for line in lines:
49 tab = line.split()
50 inputPairedEndFileNames.append(tab[1])
51 outGroomerPairedEndName = resDirName + tab[0] + '_outGroomer_pairedEnd_%s.fastq' % random.randrange(0, 10000)
52 outGroomerPairedEndNames.append(outGroomerPairedEndName)
53 outPairedEndFile.write(tab[0] + '\t' + outGroomerPairedEndName + '\n')
54 outPairedEndFile.close()
55 inPairedFile.close()
56
57 # Write output file
58 aggregator = fastqAggregator()
59 for i in range(len(outGroomerNames)):
60 out = fastqWriter( open( outGroomerNames[i], 'wb' ), format = output_type, force_quality_encoding = force_quality_encoding )
61 read_count = None
62 if summarize_input:
63 reader = fastqVerboseErrorReader
64 else:
65 reader = fastqReader
66 for read_count, fastq_read in enumerate( reader( open( inputFileNames[i] ), format = input_type, apply_galaxy_conventions = True ) ):
67 if summarize_input:
68 aggregator.consume_read( fastq_read )
69 out.write( fastq_read )
70 out.close()
71
72 if read_count is not None:
73 print "Groomed %i %s reads into %s reads." % ( read_count + 1, input_type, output_type )
74 if input_type != output_type and 'solexa' in [ input_type, output_type ]:
75 print "Converted between Solexa and PHRED scores."
76 if summarize_input:
77 print "Based upon quality and sequence, the input data is valid for: %s" % ( ", ".join( aggregator.get_valid_formats() ) or "None" )
78 ascii_range = aggregator.get_ascii_range()
79 decimal_range = aggregator.get_decimal_range()
80 print "Input ASCII range: %s(%i) - %s(%i)" % ( repr( ascii_range[0] ), ord( ascii_range[0] ), repr( ascii_range[1] ), ord( ascii_range[1] ) ) #print using repr, since \x00 (null) causes info truncation in galaxy when printed
81 print "Input decimal range: %i - %i" % ( decimal_range[0], decimal_range[1] )
82 else:
83 print "No valid FASTQ reads were provided."
84
85
86 # Write output pairedEnd file
87 if pairedEnd_input != None:
88 aggregator = fastqAggregator()
89 for i in range(len(outGroomerPairedEndNames)):
90 outPair = fastqWriter(open(outGroomerPairedEndNames[i], 'wb'), format = output_type, force_quality_encoding = force_quality_encoding)
91 read_count = None
92 if summarize_input:
93 reader = fastqVerboseErrorReader
94 else:
95 reader = fastqReader
96 for read_count, fastq_reader in enumerate(reader(open(inputPairedEndFileNames[i]), format=input_type, apply_galaxy_conventions=True)):
97 if summarize_input:
98 aggregator.consume_read(fastq_read)
99 outPair.write(fastq_read)
100 outPair.close()
101
102 if read_count is not None:
103 print "Groomed %i %s reads into %s reads." % ( read_count + 1, input_type, output_type )
104 if input_type != output_type and 'solexa' in [ input_type, output_type ]:
105 print "Converted between Solexa and PHRED scores."
106 if summarize_input:
107 print "Based upon quality and sequence, the input data is valid for: %s" % ( ", ".join( aggregator.get_valid_formats() ) or "None" )
108 ascii_range = aggregator.get_ascii_range()
109 decimal_range = aggregator.get_decimal_range()
110 print "Input ASCII range: %s(%i) - %s(%i)" % ( repr( ascii_range[0] ), ord( ascii_range[0] ), repr( ascii_range[1] ), ord( ascii_range[1] ) ) #print using repr, since \x00 (null) causes info truncation in galaxy when printed
111 print "Input decimal range: %i - %i" % ( decimal_range[0], decimal_range[1] )
112 else:
113 print "No valid paired-end FASTQ reads were provided."
114
115 if __name__ == "__main__": main()