Mercurial > repos > fangly > grinder
changeset 6:68576b1d2d8b
Uploaded
| author | fangly |
|---|---|
| date | Tue, 18 Oct 2011 01:48:14 -0400 |
| parents | 5ba7c9ac056a |
| children | bac7e652a9aa |
| files | grinder.xml grinder_multiple_outputs.py |
| diffstat | 2 files changed, 163 insertions(+), 129 deletions(-) [+] |
line wrap: on
line diff
--- a/grinder.xml Tue Oct 04 02:01:58 2011 -0400 +++ b/grinder.xml Tue Oct 18 01:48:14 2011 -0400 @@ -1,13 +1,4 @@ -<tool id="grinder" name="Grinder" version="0.3.8" force_history_refresh="True"> - - <!-- - Author: florent.angly@gmail.com - TODO: - • See bfast tool (tools/sr_mapping/bfast_wrapper.xml) for how to use datatables easily - • Basic tests - • Link to full manual - • Better sync with Grinder parameters, defaults and help - --> +<tool id="grinder" name="Grinder" version="0.3.9"> <description>genomic, metagenomic and amplicon read simulator</description> @@ -17,12 +8,8 @@ <version_string>grinder --version</version_string> - <command> - #set $tool_dir = os.path.join( os.path.abspath($__root_dir__), 'tools', 'ngs_simulation' ) - #set $script1 = os.path.join( $tool_dir, 'stderr_wrapper.py' ) - #set $script2 = os.path.join( $tool_dir, 'grinder_multiple_outputs.py' ) - - $script1 + <command interpreter="python"> + stderr_wrapper.py grinder #if $reference_file.specify == "builtin": -reference_file ${ filter( lambda x: str( x[0] ) == str( $reference_file.value ), $__app__.tool_data_tables[ 'all_fasta' ].get_fields() )[0][-1] } @@ -101,7 +88,7 @@ #if str($qual_levels): -qual_levels $qual_levels #end if - #if str($fastq_output): + #if str($fastq_output) == '1': -fastq_output $fastq_output #end if #if str($profile_file) != "None": @@ -110,16 +97,6 @@ <!-- When Galaxy bug #661 is resolved, then we can use the same method to check for all optional argument --> <!-- i.e. either if str($param) != "None": or if str($param): --> <!-- URL: https://bitbucket.org/galaxy/galaxy-central/issue/661/optional-arguments-problems#comment-655611 --> - - #set $output_dir = $__new_file_path__ - -output_dir $output_dir - - #set $base_name = $output.id - -base_name $base_name - ; - - $script2 $output_dir $base_name - </command> <inputs> @@ -199,7 +176,7 @@ 1/ uniform distribution: uniform, 2/ powerlaw distribution with parameter 0.1: powerlaw 0.1." /> - <param name="num_libraries" type="text" value="1" optional="true" label="Number of libraries" help="Number of independent libraries to create. Specify how diverse and similar they should be using the options diversity, shared percent; and permuted percent. Assign them different MID tags with the multiplex mids option." /> + <param name="num_libraries" type="text" value="1" optional="true" label="Number of libraries" help="Number of independent libraries to create. Specify how diverse and similar they should be using the options diversity, shared percent; and permuted percent. Assign them different MID tags with the multiplex mids option. Note that in Galaxy, the maximum number of libraries is 10." /> <param name="multiplex_ids" type="data" format="fasta" optional="true" label="Specify MID tags file" help="Specify an optional FASTA file that contains sequence identifiers (a.k.a MIDs or barcodes) to add to the sequences (one per library)."/> @@ -248,7 +225,164 @@ --> <outputs> - <data format="text" name="output" /> + + <!-- single library output --> + <data format="tabular" name="ranks" from_work_dir="grinder-ranks.txt" label="${tool.name} ranks from ${on_string}"> + <filter>int(str(num_libraries)) == 1</filter> + </data> + <data format="fasta" name="fasta" from_work_dir="grinder-reads.fa" label="${tool.name} reads from ${on_string}"> + <filter>int(str(num_libraries)) == 1 and fastq_output == 0</filter> + </data> + <data format="qual" name="qual" from_work_dir="grinder-reads.qual" label="${tool.name} quals from ${on_string}"> + <filter>int(str(num_libraries)) == 1 and str(qual_levels) and fastq_output == 0</filter> + </data> + <data format="fastq" name="fastq" from_work_dir="grinder-reads.fastq" label="${tool.name} reads from ${on_string}"> + <filter>int(str(num_libraries)) == 1 and fastq_output == 1</filter> + </data> + + <!-- When Galaxy bug #670 is resolved, then we won't have to harcode the number of output datasets --> + <!-- URL: https://bitbucket.org/galaxy/galaxy-central/issue/670/better-support-for-multiple-outputs --> + + <!-- multiple libraries: library 1 --> + <data format="tabular" name="ranks1" from_work_dir="grinder-1-ranks.txt" label="${tool.name} lib 1 ranks from ${on_string}"> + <filter>int(str(num_libraries)) >= 2</filter> + </data> + <data format="fasta" name="fasta1" from_work_dir="grinder-1-reads.fa" label="${tool.name} lib 1 reads from ${on_string}"> + <filter>int(str(num_libraries)) >= 2 and fastq_output == 0</filter> + </data> + <data format="qual" name="qual1" from_work_dir="grinder-1-reads.qual" label="${tool.name} lib 1 quals from ${on_string}"> + <filter>int(str(num_libraries)) >= 2 and str(qual_levels) and fastq_output == 0</filter> + </data> + <data format="fastq" name="fastq1" from_work_dir="grinder-1-reads.fastq" label="${tool.name} lib 1 reads from ${on_string}"> + <filter>int(str(num_libraries)) >= 2 and fastq_output == 1</filter> + </data> + + <!-- multiple libraries: library 2 --> + <data format="tabular" name="ranks2" from_work_dir="grinder-2-ranks.txt" label="${tool.name} lib 2 ranks from ${on_string}"> + <filter>int(str(num_libraries)) >= 2</filter> + </data> + <data format="fasta" name="fasta2" from_work_dir="grinder-2-reads.fa" label="${tool.name} lib 2 reads from ${on_string}"> + <filter>int(str(num_libraries)) >= 2 and fastq_output == 0</filter> + </data> + <data format="qual" name="qual2" from_work_dir="grinder-2-reads.qual" label="${tool.name} lib 2 quals from ${on_string}"> + <filter>int(str(num_libraries)) >= 2 and str(qual_levels) and fastq_output == 0</filter> + </data> + <data format="fastq" name="fastq2" from_work_dir="grinder-2-reads.fastq" label="${tool.name} lib 2 reads from ${on_string}"> + <filter>int(str(num_libraries)) >= 2 and fastq_output == 1</filter> + </data> + + <!-- multiple libraries: library 3 --> + <data format="tabular" name="ranks3" from_work_dir="grinder-3-ranks.txt" label="${tool.name} lib 3 ranks from ${on_string}"> + <filter>int(str(num_libraries)) >= 3</filter> + </data> + <data format="fasta" name="fasta3" from_work_dir="grinder-3-reads.fa" label="${tool.name} lib 3 reads from ${on_string}"> + <filter>int(str(num_libraries)) >= 3 and fastq_output == 0</filter> + </data> + <data format="qual" name="qual3" from_work_dir="grinder-3-reads.qual" label="${tool.name} lib 3 quals from ${on_string}"> + <filter>int(str(num_libraries)) >= 3 and str(qual_levels) and fastq_output == 0</filter> + </data> + <data format="fastq" name="fastq3" from_work_dir="grinder-3-reads.fastq" label="${tool.name} lib 3 reads from ${on_string}"> + <filter>int(str(num_libraries)) >= 3 and fastq_output == 1</filter> + </data> + + <!-- multiple libraries: library 4 --> + <data format="tabular" name="ranks4" from_work_dir="grinder-4-ranks.txt" label="${tool.name} lib 4 ranks from ${on_string}"> + <filter>int(str(num_libraries)) >= 4</filter> + </data> + <data format="fasta" name="fasta4" from_work_dir="grinder-4-reads.fa" label="${tool.name} lib 4 reads from ${on_string}"> + <filter>int(str(num_libraries)) >= 4 and fastq_output == 0</filter> + </data> + <data format="qual" name="qual4" from_work_dir="grinder-4-reads.qual" label="${tool.name} lib 4 quals from ${on_string}"> + <filter>int(str(num_libraries)) >= 4 and str(qual_levels) and fastq_output == 0</filter> + </data> + <data format="fastq" name="fastq4" from_work_dir="grinder-4-reads.fastq" label="${tool.name} lib 4 reads from ${on_string}"> + <filter>int(str(num_libraries)) >= 4 and fastq_output == 1</filter> + </data> + + <!-- multiple libraries: library 5 --> + <data format="tabular" name="ranks5" from_work_dir="grinder-5-ranks.txt" label="${tool.name} lib 5 ranks from ${on_string}"> + <filter>int(str(num_libraries)) >= 5</filter> + </data> + <data format="fasta" name="fasta5" from_work_dir="grinder-5-reads.fa" label="${tool.name} lib 5 reads from ${on_string}"> + <filter>int(str(num_libraries)) >= 5 and fastq_output == 0</filter> + </data> + <data format="qual" name="qual5" from_work_dir="grinder-5-reads.qual" label="${tool.name} lib 5 quals from ${on_string}"> + <filter>int(str(num_libraries)) >= 5 and str(qual_levels) and fastq_output == 0</filter> + </data> + <data format="fastq" name="fastq5" from_work_dir="grinder-5-reads.fastq" label="${tool.name} lib 5 reads from ${on_string}"> + <filter>int(str(num_libraries)) >= 5 and fastq_output == 1</filter> + </data> + + <!-- multiple libraries: library 6 --> + <data format="tabular" name="ranks6" from_work_dir="grinder-6-ranks.txt" label="${tool.name} lib 6 ranks from ${on_string}"> + <filter>int(str(num_libraries)) >= 6</filter> + </data> + <data format="fasta" name="fasta6" from_work_dir="grinder-6-reads.fa" label="${tool.name} lib 6 reads from ${on_string}"> + <filter>int(str(num_libraries)) >= 6 and fastq_output == 0</filter> + </data> + <data format="qual" name="qual6" from_work_dir="grinder-6-reads.qual" label="${tool.name} lib 6 quals from ${on_string}"> + <filter>int(str(num_libraries)) >= 6 and str(qual_levels) and fastq_output == 0</filter> + </data> + <data format="fastq" name="fastq6" from_work_dir="grinder-6-reads.fastq" label="${tool.name} lib 6 reads from ${on_string}"> + <filter>int(str(num_libraries)) >= 6 and fastq_output == 1</filter> + </data> + + <!-- multiple libraries: library 7 --> + <data format="tabular" name="ranks7" from_work_dir="grinder-7-ranks.txt" label="${tool.name} lib 7 ranks from ${on_string}"> + <filter>int(str(num_libraries)) >= 7</filter> + </data> + <data format="fasta" name="fasta7" from_work_dir="grinder-7-reads.fa" label="${tool.name} lib 7 reads from ${on_string}"> + <filter>int(str(num_libraries)) >= 7 and fastq_output == 0</filter> + </data> + <data format="qual" name="qual7" from_work_dir="grinder-7-reads.qual" label="${tool.name} lib 7 quals from ${on_string}"> + <filter>int(str(num_libraries)) >= 7 and str(qual_levels) and fastq_output == 0</filter> + </data> + <data format="fastq" name="fastq7" from_work_dir="grinder-7-reads.fastq" label="${tool.name} lib 7 reads from ${on_string}"> + <filter>int(str(num_libraries)) >= 7 and fastq_output == 1</filter> + </data> + + <!-- multiple libraries: library 8 --> + <data format="tabular" name="ranks8" from_work_dir="grinder-8-ranks.txt" label="${tool.name} lib 8 ranks from ${on_string}"> + <filter>int(str(num_libraries)) >= 8</filter> + </data> + <data format="fasta" name="fasta8" from_work_dir="grinder-8-reads.fa" label="${tool.name} lib 8 reads from ${on_string}"> + <filter>int(str(num_libraries)) >= 8 and fastq_output == 0</filter> + </data> + <data format="qual" name="qual8" from_work_dir="grinder-8-reads.qual" label="${tool.name} lib 8 quals from ${on_string}"> + <filter>int(str(num_libraries)) >= 8 and str(qual_levels) and fastq_output == 0</filter> + </data> + <data format="fastq" name="fastq8" from_work_dir="grinder-8-reads.fastq" label="${tool.name} lib 8 reads from ${on_string}"> + <filter>int(str(num_libraries)) >= 8 and fastq_output == 1</filter> + </data> + + <!-- multiple libraries: library 9 --> + <data format="tabular" name="ranks9" from_work_dir="grinder-9-ranks.txt" label="${tool.name} lib 9 ranks from ${on_string}"> + <filter>int(str(num_libraries)) >= 9</filter> + </data> + <data format="fasta" name="fasta9" from_work_dir="grinder-9-reads.fa" label="${tool.name} lib 9 reads from ${on_string}"> + <filter>int(str(num_libraries)) >= 9 and fastq_output == 0</filter> + </data> + <data format="qual" name="qual9" from_work_dir="grinder-9-reads.qual" label="${tool.name} lib 9 quals from ${on_string}"> + <filter>int(str(num_libraries)) >= 9 and str(qual_levels) and fastq_output == 0</filter> + </data> + <data format="fastq" name="fastq9" from_work_dir="grinder-9-reads.fastq" label="${tool.name} lib 9 reads from ${on_string}"> + <filter>int(str(num_libraries)) >= 9 and fastq_output == 1</filter> + </data> + + <!-- multiple libraries: library 10 --> + <data format="tabular" name="ranks10" from_work_dir="grinder-10-ranks.txt" label="${tool.name} lib 10 ranks from ${on_string}"> + <filter>int(str(num_libraries)) >= 10</filter> + </data> + <data format="fasta" name="fasta10" from_work_dir="grinder-10-reads.fa" label="${tool.name} lib 10 reads from ${on_string}"> + <filter>int(str(num_libraries)) >= 10 and fastq_output == 0</filter> + </data> + <data format="qual" name="qual10" from_work_dir="grinder-10-reads.qual" label="${tool.name} lib 10 quals from ${on_string}"> + <filter>int(str(num_libraries)) >= 10 and str(qual_levels) and fastq_output == 0</filter> + </data> + <data format="fastq" name="fastq10" from_work_dir="grinder-10-reads.fastq" label="${tool.name} lib 10 reads from ${on_string}"> + <filter>int(str(num_libraries)) >= 10 and fastq_output == 1</filter> + </data> + </outputs> <tests> @@ -270,7 +404,6 @@ <output name="qual" file="" /> </test> --> - </tests> <help>
--- a/grinder_multiple_outputs.py Tue Oct 04 02:01:58 2011 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,99 +0,0 @@ -#!/usr/bin/env python - -""" -Move files create by Grinder to a location where it is going to be recognized by -Galaxy as multiple output files with the right format. See -http://wiki.g2.bx.psu.edu/Admin/Tools/Multiple Output Files -Example: python grinder_move_outputs output_dir output_id -Author: Florent Angly -""" - -import sys, os, re - -assert sys.version_info[:2] >= ( 2, 4 ) - -def stop_err( msg ): - sys.stderr.write( "%s\n" % msg ) - sys.exit() - -def __main__(): - # Get output dir and ID - args = sys.argv - output_dir = args[1] - output_id = args[2] - - # Move Grinder files to the proper output - # Grinder filenames look like this - # grinder-ranks.txt - # grinder-reads.fa - # grinder-reads.qual - # grinder-1-ranks.txt - # grinder-1-reads.fa - # grinder-1-reads.qual - # grinder-2-ranks.txt - # grinder-2-reads.fa - # grinder-2-reads.qual - - p = re.compile(output_id) - q = re.compile('-(\d+)-') - r = re.compile('-(\w+)$') - - - for fname in os.listdir(output_dir): - - # Skip files that do not start with the output_id - source = os.path.join( output_dir, fname ) - basename, extension = os.path.splitext(fname) - if not p.match(fname): - continue - - # Assign the dataset format - if extension == '.txt': - format = 'text' - elif extension == '.fq': - format = 'fastqsanger' - elif extension == '.fastq': - format = 'fastqsanger' - elif extension == '.fa': - format = 'fasta' - elif extension == '.fna': - format = 'fasta' - elif extension == '.faa': - format = 'fasta' - elif extension == '.fasta': - format = 'fasta' - elif extension == '.qual': - format = 'qual' - else: - stop_err( 'Error: File %s had the unknown extension %s' % ( fname, extension ) ) - - # Assign the dataset name - name = '' - match = q.search(basename) - if match != None: - lib_num = match.group(1) - name = 'lib%s-' % lib_num - - match = r.search(basename) - if match == None: - stop_err( 'Error: File with basename %s did not have a recognized name' % (basename) ) - - lib_type = match.group(1) - if format == 'qual': - lib_type = 'qual' - - name = name + lib_type - - # Move the dataset to the proper place - #db_ref = '' - #destination = os.path.join( output_dir, 'primary_%s_%s_visible_%s_%s' % (output_id, name, format, db_ref) ) - destination = os.path.join( output_dir, 'primary_%s_%s_visible_%s' % (output_id, name, format) ) - - print "moving %s to %s" % (source, destination) - - try: - os.rename(source, destination) - except Exception, e: - stop_err( 'Error: ' + str( e ) ) - -if __name__ == "__main__": __main__()