0
|
1 #Dan Blankenberg
|
|
2 import sys, os, shutil
|
|
3 from galaxy_utils.sequence.fastq import fastqWriter, fastqSequencingRead, fastqCombiner, fastqFakeFastaScoreReader
|
|
4 from galaxy_utils.sequence.fasta import fastaReader, fastaNamedReader
|
|
5
|
|
6 def main():
|
|
7 #Read command line arguments
|
|
8 fasta_filename = sys.argv[1]
|
|
9 fasta_type = sys.argv[2] or 'fasta' #should always be fasta or csfasta? what if txt?
|
|
10 qual_filename = sys.argv[3]
|
|
11 qual_type = sys.argv[4] or 'qualsanger' #qual454 qualsolid
|
|
12 output_filename = sys.argv[5]
|
|
13 force_quality_encoding = sys.argv[6]
|
|
14 if force_quality_encoding == 'None':
|
|
15 force_quality_encoding = None
|
|
16
|
|
17 format = 'sanger'
|
|
18 if fasta_type == 'csfasta' or qual_type == 'qualsolid':
|
|
19 format = 'cssanger'
|
|
20 elif qual_type == 'qualsolexa':
|
|
21 format = 'solexa'
|
|
22 elif qual_type == 'qualillumina':
|
|
23 format = 'illumina'
|
|
24
|
|
25 out = fastqWriter( open( output_filename, 'wb' ), format = format, force_quality_encoding = force_quality_encoding )
|
|
26 if qual_filename == 'None':
|
|
27 qual_input = fastqFakeFastaScoreReader( format, quality_encoding = force_quality_encoding )
|
|
28 else:
|
|
29 qual_input = fastaNamedReader( open( qual_filename, 'rb' ) )
|
|
30
|
|
31 fastq_combiner = fastqCombiner( format )
|
|
32 i = None
|
|
33 skip_count = 0
|
|
34 for i, sequence in enumerate( fastaReader( open( fasta_filename, 'rb' ) ) ):
|
|
35 quality = qual_input.get( sequence )
|
|
36 if quality:
|
|
37 fastq_read = fastq_combiner.combine( sequence, quality )
|
|
38 out.write( fastq_read )
|
|
39 else:
|
|
40 skip_count += 1
|
|
41 out.close()
|
|
42 if i is None:
|
|
43 print "Your file contains no valid FASTA sequences."
|
|
44 else:
|
|
45 print qual_input.has_data()
|
|
46 print 'Combined %s of %s sequences with quality scores (%.2f%%).' % ( i - skip_count + 1, i + 1, float( i - skip_count + 1 ) / float( i + 1 ) * 100.0 )
|
|
47
|
|
48 if __name__ == "__main__":
|
|
49 main()
|