Mercurial > repos > devteam > tabular_to_fastq
changeset 3:643018aa1435 draft
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tool_collections/galaxy_sequence_utils/tabular_to_fastq commit f2582539542b33240234e8ea6093e25d0aee9b6a
| author | devteam |
|---|---|
| date | Sat, 30 Sep 2017 13:54:43 -0400 |
| parents | 6e9c13e70d45 |
| children | 1f75d46e55f5 |
| files | tabular_to_fastq.py tabular_to_fastq.xml tool_dependencies.xml |
| diffstat | 3 files changed, 59 insertions(+), 65 deletions(-) [+] |
line wrap: on
line diff
--- a/tabular_to_fastq.py Fri Dec 18 19:31:46 2015 -0500 +++ b/tabular_to_fastq.py Sat Sep 30 13:54:43 2017 -0400 @@ -1,29 +1,33 @@ -#Dan Blankenberg +# Dan Blankenberg +from __future__ import print_function + import sys + def main(): input_filename = sys.argv[1] output_filename = sys.argv[2] - identifier_col = int( sys.argv[3] ) - 1 - sequence_col = int( sys.argv[4] ) - 1 - quality_col = int( sys.argv[5] ) - 1 - - max_col = max( identifier_col, sequence_col, quality_col ) + identifier_col = int(sys.argv[3]) - 1 + sequence_col = int(sys.argv[4]) - 1 + quality_col = int(sys.argv[5]) - 1 + + max_col = max(identifier_col, sequence_col, quality_col) num_reads = None - fastq_read = None skipped_lines = 0 - out = open( output_filename, 'wb' ) - for num_reads, line in enumerate( open( input_filename ) ): - fields = line.rstrip( '\n\r' ).split( '\t' ) - if len( fields ) > max_col: - out.write( "@%s\n%s\n+\n%s\n" % ( fields[identifier_col], fields[sequence_col], fields[quality_col] ) ) + out = open(output_filename, 'w') + for num_reads, line in enumerate(open(input_filename)): + fields = line.rstrip('\n\r').split('\t') + if len(fields) > max_col: + out.write("@%s\n%s\n+\n%s\n" % (fields[identifier_col], fields[sequence_col], fields[quality_col])) else: skipped_lines += 1 - + out.close() if num_reads is None: - print "Input was empty." + print("Input was empty.") else: - print "%i tabular lines were written as FASTQ reads. Be sure to use the FASTQ Groomer tool on this output before further analysis." % ( num_reads + 1 - skipped_lines ) - -if __name__ == "__main__": main() + print("%i tabular lines were written as FASTQ reads. Be sure to use the FASTQ Groomer tool on this output before further analysis." % (num_reads + 1 - skipped_lines)) + + +if __name__ == "__main__": + main()
--- a/tabular_to_fastq.xml Fri Dec 18 19:31:46 2015 -0500 +++ b/tabular_to_fastq.xml Sat Sep 30 13:54:43 2017 -0400 @@ -1,45 +1,41 @@ -<tool id="tabular_to_fastq" name="Tabular to FASTQ" version="1.0.0"> - <description>converter</description> - <requirements> - <requirement type="package" version="1.0.0">galaxy_sequence_utils</requirement> - </requirements> - <command interpreter="python">tabular_to_fastq.py '$input_file' '$output_file' '$identifier' '$sequence' '$quality'</command> - <inputs> - <param name="input_file" type="data" format="tabular" label="Tabular file to convert" /> - <param name="identifier" label="Identifier column" type="data_column" data_ref="input_file" /> - <param name="sequence" label="Sequence column" type="data_column" data_ref="input_file" /> - <param name="quality" label="Quality column" type="data_column" data_ref="input_file" /> - </inputs> - <outputs> - <data name="output_file" format="fastq" /> - </outputs> - <tests> - <!-- basic test --> - <test> - <param name="input_file" value="fastq_to_tabular_out_1.tabular" ftype="tabular" /> - <param name="identifier" value="1" /> - <param name="sequence" value="2" /> - <param name="quality" value="3" /> - <output name="output_file" file="sanger_full_range_original_sanger.fastqsanger" /> - </test> - <!-- color space test --> - <test> - <param name="input_file" value="fastq_to_tabular_out_2.tabular" ftype="tabular" /> - <param name="identifier" value="1" /> - <param name="sequence" value="2" /> - <param name="quality" value="3" /> - <output name="output_file" file="sanger_full_range_as_cssanger.fastqcssanger" /> - </test> - </tests> - <help> +<tool id="tabular_to_fastq" name="Tabular to FASTQ" version="1.1.1"> + <description>converter</description> + <command><![CDATA[ +python '$__tool_directory__/tabular_to_fastq.py' '$input_file' '$output_file' '$identifier' '$sequence' '$quality' + ]]></command> + <inputs> + <param name="input_file" type="data" format="tabular" label="Tabular file to convert" /> + <param name="identifier" type="data_column" data_ref="input_file" label="Identifier column" /> + <param name="sequence" type="data_column" data_ref="input_file" label="Sequence column" /> + <param name="quality" type="data_column" data_ref="input_file" label="Quality column" /> + </inputs> + <outputs> + <data name="output_file" format="fastq" /> + </outputs> + <tests> + <!-- basic test --> + <test> + <param name="input_file" value="fastq_to_tabular_out_1.tabular" ftype="tabular" /> + <param name="identifier" value="1" /> + <param name="sequence" value="2" /> + <param name="quality" value="3" /> + <output name="output_file" file="sanger_full_range_original_sanger.fastqsanger" /> + </test> + <!-- color space test --> + <test> + <param name="input_file" value="fastq_to_tabular_out_2.tabular" ftype="tabular" /> + <param name="identifier" value="1" /> + <param name="sequence" value="2" /> + <param name="quality" value="3" /> + <output name="output_file" file="sanger_full_range_as_cssanger.fastqcssanger" /> + </test> + </tests> + <help><![CDATA[ **What it does** -This tool attempts to convert a tabular file containing sequencing read data to a FASTQ formatted file. The FASTQ Groomer tool should always be used on the output of this tool. - - </help> - - <citations> - <citation type="doi">10.1093/bioinformatics/btq281</citation> - </citations> - +This tool attempts to convert a tabular file containing sequencing read data to a FASTQ formatted file. The FASTQ Groomer tool should always be used on the output of this tool. + ]]></help> + <citations> + <citation type="doi">10.1093/bioinformatics/btq281</citation> + </citations> </tool>
--- a/tool_dependencies.xml Fri Dec 18 19:31:46 2015 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,6 +0,0 @@ -<?xml version="1.0"?> -<tool_dependency> - <package name="galaxy_sequence_utils" version="1.0.0"> - <repository changeset_revision="6334612a010e" name="package_galaxy_utils_1_0" owner="devteam" toolshed="https://testtoolshed.g2.bx.psu.edu" /> - </package> -</tool_dependency>