|
10
|
1 #!/usr/bin/env python
|
|
|
2 """
|
|
|
3 Yufei LUO
|
|
|
4 """
|
|
|
5
|
|
|
6
|
|
|
7 import sys, os, optparse, random
|
|
|
8 from galaxy_utils.sequence.fastq import fastqReader, fastqVerboseErrorReader, fastqAggregator, fastqWriter
|
|
|
9
|
|
|
10 def stop_err(msg):
|
|
|
11 sys.stderr.write("%s\n" % msg)
|
|
|
12 sys.exit()
|
|
|
13
|
|
|
14 def main():
|
|
|
15
|
|
|
16 input_filename = sys.argv[1] #a txt file
|
|
|
17 input_type = sys.argv[2]
|
|
|
18 output_filename = sys.argv[3] #a txt file
|
|
|
19 output_type = sys.argv[4]
|
|
|
20 force_quality_encoding = sys.argv[5]
|
|
|
21 summarize_input = sys.argv[6] == 'summarize_input'
|
|
|
22 pairedEnd_input = sys.argv[7]
|
|
|
23 if pairedEnd_input == 'None':
|
|
|
24 pairedEnd_input = None
|
|
|
25 else:
|
|
|
26 output_pairedEndFileName = sys.argv[8]
|
|
|
27
|
|
|
28 if force_quality_encoding == 'None':
|
|
|
29 force_quality_encoding = None
|
|
|
30
|
|
|
31 #Parse the input txt file and read a list of fastq files
|
|
|
32 file = open(input_filename, "r")
|
|
|
33 lines = file.readlines()
|
|
|
34 inputFileNames = []
|
|
|
35 outGroomerNames = []
|
|
|
36 resDirName = os.path.dirname(output_filename) + "/"
|
|
|
37 #Write output txt file and define all output groomer file names
|
|
|
38 outFile = open(output_filename, "w")
|
|
|
39 for line in lines:
|
|
|
40 tab = line.split()
|
|
|
41 inputFileNames.append(tab[1])
|
|
|
42 outGroomerName = resDirName + tab[0] + '_outGroomer_%s.fastq' % random.randrange(0, 10000)
|
|
|
43 outGroomerNames.append(outGroomerName)
|
|
|
44 outFile.write(tab[0] + '\t' + outGroomerName + '\n')
|
|
|
45 outFile.close()
|
|
|
46 file.close()
|
|
|
47
|
|
|
48 if pairedEnd_input != None:
|
|
|
49 inPairedFile = open(pairedEnd_input, "r")
|
|
|
50 lines = inPairedFile.readlines()
|
|
|
51 inputPairedEndFileNames = []
|
|
|
52 outGroomerPairedEndNames = []
|
|
|
53 outPairedEndFile = open(output_pairedEndFileName, "w")
|
|
|
54 for line in lines:
|
|
|
55 tab = line.split()
|
|
|
56 inputPairedEndFileNames.append(tab[1])
|
|
|
57 outGroomerPairedEndName = resDirName + tab[0] + '_outGroomer_pairedEnd_%s.fastq' % random.randrange(0, 10000)
|
|
|
58 outGroomerPairedEndNames.append(outGroomerPairedEndName)
|
|
|
59 outPairedEndFile.write(tab[0] + '\t' + outGroomerPairedEndName + '\n')
|
|
|
60 outPairedEndFile.close()
|
|
|
61 inPairedFile.close()
|
|
|
62
|
|
|
63 # Write output file
|
|
|
64 aggregator = fastqAggregator()
|
|
|
65 for i in range(len(outGroomerNames)):
|
|
|
66 out = fastqWriter( open( outGroomerNames[i], 'wb' ), format = output_type, force_quality_encoding = force_quality_encoding )
|
|
|
67 read_count = None
|
|
|
68 if summarize_input:
|
|
|
69 reader = fastqVerboseErrorReader
|
|
|
70 else:
|
|
|
71 reader = fastqReader
|
|
|
72 for read_count, fastq_read in enumerate( reader( open( inputFileNames[i] ), format = input_type, apply_galaxy_conventions = True ) ):
|
|
|
73 if summarize_input:
|
|
|
74 aggregator.consume_read( fastq_read )
|
|
|
75 out.write( fastq_read )
|
|
|
76 out.close()
|
|
|
77
|
|
|
78 if read_count is not None:
|
|
|
79 print "Groomed %i %s reads into %s reads." % ( read_count + 1, input_type, output_type )
|
|
|
80 if input_type != output_type and 'solexa' in [ input_type, output_type ]:
|
|
|
81 print "Converted between Solexa and PHRED scores."
|
|
|
82 if summarize_input:
|
|
|
83 print "Based upon quality and sequence, the input data is valid for: %s" % ( ", ".join( aggregator.get_valid_formats() ) or "None" )
|
|
|
84 ascii_range = aggregator.get_ascii_range()
|
|
|
85 decimal_range = aggregator.get_decimal_range()
|
|
|
86 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
|
|
|
87 print "Input decimal range: %i - %i" % ( decimal_range[0], decimal_range[1] )
|
|
|
88 else:
|
|
|
89 print "No valid FASTQ reads were provided."
|
|
|
90
|
|
|
91
|
|
|
92 # Write output pairedEnd file
|
|
|
93 if pairedEnd_input != None:
|
|
|
94 aggregator = fastqAggregator()
|
|
|
95 for i in range(len(outGroomerPairedEndNames)):
|
|
|
96 outPair = fastqWriter(open(outGroomerPairedEndNames[i], 'wb'), format = output_type, force_quality_encoding = force_quality_encoding)
|
|
|
97 read_count = None
|
|
|
98 if summarize_input:
|
|
|
99 reader = fastqVerboseErrorReader
|
|
|
100 else:
|
|
|
101 reader = fastqReader
|
|
|
102 for read_count, fastq_reader in enumerate(reader(open(inputPairedEndFileNames[i]), format=input_type, apply_galaxy_conventions=True)):
|
|
|
103 if summarize_input:
|
|
|
104 aggregator.consume_read(fastq_read)
|
|
|
105 outPair.write(fastq_read)
|
|
|
106 outPair.close()
|
|
|
107
|
|
|
108 if read_count is not None:
|
|
|
109 print "Groomed %i %s reads into %s reads." % ( read_count + 1, input_type, output_type )
|
|
|
110 if input_type != output_type and 'solexa' in [ input_type, output_type ]:
|
|
|
111 print "Converted between Solexa and PHRED scores."
|
|
|
112 if summarize_input:
|
|
|
113 print "Based upon quality and sequence, the input data is valid for: %s" % ( ", ".join( aggregator.get_valid_formats() ) or "None" )
|
|
|
114 ascii_range = aggregator.get_ascii_range()
|
|
|
115 decimal_range = aggregator.get_decimal_range()
|
|
|
116 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
|
|
|
117 print "Input decimal range: %i - %i" % ( decimal_range[0], decimal_range[1] )
|
|
|
118 else:
|
|
|
119 print "No valid paired-end FASTQ reads were provided."
|
|
|
120
|
|
|
121 if __name__ == "__main__": main()
|
