/lib/galaxy/datatypes/converters/fastqsolexa_to_fasta_converter.py
https://bitbucket.org/cistrome/cistrome-harvard/ · Python · 55 lines · 31 code · 7 blank · 17 comment · 9 complexity · 100c3ff13a4d750bb8d91cf40544c158 MD5 · raw file
- #!/usr/bin/env python
- """
- convert fastqsolexa file to separated sequence and quality files.
- assume each sequence and quality score are contained in one line
- the order should be:
- 1st line: @title_of_seq
- 2nd line: nucleotides
- 3rd line: +title_of_qualityscore (might be skipped)
- 4th line: quality scores
- (in three forms: a. digits, b. ASCII codes, the first char as the coding base, c. ASCII codes without the first char.)
- Usage:
- %python fastqsolexa_to_fasta_converter.py <your_fastqsolexa_filename> <output_seq_filename> <output_score_filename>
- """
- import sys, os
- from math import *
- assert sys.version_info[:2] >= ( 2, 4 )
- def stop_err( msg ):
- sys.stderr.write( "%s" % msg )
- sys.exit()
- def __main__():
- infile_name = sys.argv[1]
- outfile = open( sys.argv[2], 'w' )
- fastq_block_lines = 0
- seq_title_startswith = ''
- for i, line in enumerate( file( infile_name ) ):
- line = line.rstrip() # eliminate trailing space and new line characters
- if not line or line.startswith( '#' ):
- continue
- fastq_block_lines = ( fastq_block_lines + 1 ) % 4
- line_startswith = line[0:1]
- if fastq_block_lines == 1:
- # line 1 is sequence title
- if not seq_title_startswith:
- seq_title_startswith = line_startswith
- if seq_title_startswith != line_startswith:
- stop_err( 'Invalid fastqsolexa format at line %d: %s.' %( i + 1, line ) )
- read_title = line[ 1: ]
- outfile.write( '>%s\n' % line[1:] )
- elif fastq_block_lines == 2:
- # line 2 is nucleotides
- read_length = len( line )
- outfile.write( '%s\n' % line )
- else:
- pass
- outfile.close()
- if __name__ == "__main__": __main__()