0
|
1 #Dan Blankenberg
|
|
2 import sys
|
|
3 from galaxy_utils.sequence.fastq import fastqReader, fastqVerboseErrorReader, fastqAggregator, fastqWriter
|
|
4
|
|
5 def main():
|
|
6 input_filename = sys.argv[1]
|
|
7 input_type = sys.argv[2]
|
|
8 output_filename = sys.argv[3]
|
|
9 output_type = sys.argv[4]
|
|
10 force_quality_encoding = sys.argv[5]
|
|
11 summarize_input = sys.argv[6] == 'summarize_input'
|
|
12 if force_quality_encoding == 'None':
|
|
13 force_quality_encoding = None
|
|
14
|
|
15 aggregator = fastqAggregator()
|
|
16 out = fastqWriter( open( output_filename, 'wb' ), format = output_type, force_quality_encoding = force_quality_encoding )
|
|
17 read_count = None
|
|
18 if summarize_input:
|
|
19 reader = fastqVerboseErrorReader
|
|
20 else:
|
|
21 reader = fastqReader
|
|
22 for read_count, fastq_read in enumerate( reader( open( input_filename ), format = input_type, apply_galaxy_conventions = True ) ):
|
|
23 if summarize_input:
|
|
24 aggregator.consume_read( fastq_read )
|
|
25 out.write( fastq_read )
|
|
26 out.close()
|
|
27
|
|
28 if read_count is not None:
|
|
29 print "Groomed %i %s reads into %s reads." % ( read_count + 1, input_type, output_type )
|
|
30 if input_type != output_type and 'solexa' in [ input_type, output_type ]:
|
|
31 print "Converted between Solexa and PHRED scores."
|
|
32 if summarize_input:
|
|
33 print "Based upon quality and sequence, the input data is valid for: %s" % ( ", ".join( aggregator.get_valid_formats() ) or "None" )
|
|
34 ascii_range = aggregator.get_ascii_range()
|
|
35 decimal_range = aggregator.get_decimal_range()
|
|
36 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
|
|
37 print "Input decimal range: %i - %i" % ( decimal_range[0], decimal_range[1] )
|
|
38 else:
|
|
39 print "No valid FASTQ reads were provided."
|
|
40
|
|
41
|
|
42 if __name__ == "__main__": main()
|