Mercurial > repos > crusoe > khmer
changeset 59:08a599cf71d0
Bjoern's suggestions
| author | Michael R. Crusoe <mcrusoe@msu.edu> |
|---|---|
| date | Mon, 18 Aug 2014 07:02:05 -0400 |
| parents | be2f355d6841 |
| children | fe697e0cb24a |
| files | abundance-dist-single.xml abundance-dist.xml count-median.xml do-partition.xml extract-partitions.xml filter-abund.xml filter-below-abund.xml macros.xml normalize-by-median.xml |
| diffstat | 9 files changed, 60 insertions(+), 80 deletions(-) [+] |
line wrap: on
line diff
--- a/abundance-dist-single.xml Wed Aug 06 18:32:24 2014 -0400 +++ b/abundance-dist-single.xml Mon Aug 18 07:02:05 2014 -0400 @@ -1,4 +1,4 @@ -<tool id="gedlab-khmer-abudance-dist-single" +<tool id="gedlab-khmer-abundance-dist-single" name="Abundance Distribution (all-in-one)" version="1.1-1" force_history_refresh="true"> @@ -35,14 +35,14 @@ <param name="save_countingtable" type="boolean" label="Save the k-mer counting table(s) in a file" - help="" /> + help="(--savetable)" /> <expand macro="input_zero" /> <param name="bigcount" type="boolean" truevalue="" falsevalue="--no-bigcount" checked="true" - help="Count k-mers past 255" /> + help="Count k-mers past 255 (--no-bigcount)" /> <expand macro="tableinputs" /> </inputs> <outputs> @@ -53,12 +53,7 @@ </data> <expand macro="abundance-histogram-output" /> </outputs> - <stdio> - <!-- [HELP] If no exit code rule is defined, the tool will stop if anything is written to STDERR --> - <exit_code range="1:" - level="fatal" /> - </stdio> - + <expand macro="stdio" /> <tests> <test> <param name="input_sequence_filename" value="test-abund-read-2.fa" />
--- a/abundance-dist.xml Wed Aug 06 18:32:24 2014 -0400 +++ b/abundance-dist.xml Mon Aug 18 07:02:05 2014 -0400 @@ -31,12 +31,7 @@ <outputs> <expand macro="abundance-histogram-output" /> </outputs> - <stdio> - <!-- [HELP] If no exit code rule is defined, the tool will stop if anything is written to STDERR --> - <exit_code range="1:" - level="fatal" /> - </stdio> - + <expand macro="stdio" /> <tests> <test> <param name="input_sequence_filename" value="test-abund-read-2.fa" />
--- a/count-median.xml Wed Aug 06 18:32:24 2014 -0400 +++ b/count-median.xml Mon Aug 18 07:02:05 2014 -0400 @@ -4,9 +4,10 @@ force_history_refresh="true"> <description> - Count the median/avg k-mer abundance for each sequence in the input file, - based on the k-mer counts in the given k-mer counting table. Can be used to - estimate expression levels (mRNAseq) or coverage (genomic/metagenomic). + Count the median/avg k-mer abundance for each sequence in the + input file, based on the k-mer counts in the given k-mer + counting table. Can be used to estimate expression levels + (mRNAseq) or coverage (genomic/metagenomic). </description> <macros> <token name="@BINARY@">count-median.py</token> @@ -14,13 +15,10 @@ </macros> <expand macro="requirements" /> <command> -## The command is a Cheetah template which allows some Python based syntax. -## Lines starting hash hash are comments. Galaxy will turn newlines into spaces -mkdir output; cd output; @BINARY@ - $input_counting_table_filename - $input_sequence_filename - $output_summary_filename +$input_counting_table_filename +$input_sequence_filename +$output_summary_filename </command> <inputs> @@ -28,22 +26,22 @@ <expand macro="input_counting_table_filename" /> </inputs> <outputs> - <data name="output_summary_filename" format="text" label="${input_sequence_filename} sequence id, median, average, stddev, and seq length" /> + <data name="output_summary_filename" format="text" + label="${input_sequence_filename} sequence id, median, average, stddev, and seq length" /> </outputs> - <stdio> - <!-- [HELP] If no exit code rule is defined, the tool will stop if anything is written to STDERR --> - <exit_code range="1:" - level="fatal" /> - </stdio> - + <expand macro="stdio" /> <tests> <test interactor="api"> - <param name="input_sequence_filename" value="test-abund-read-2.fa" /> - <param name="input_counting_table_filename" value="test-abund-read-2.ct" ftype="ct" /> + <param name="input_sequence_filename" + value="test-abund-read-2.fa" /> + <param name="input_counting_table_filename" + value="test-abund-read-2.ct" ftype="ct" /> <output name="output_summary_filename"> <assert_contents> - <has_line_matching expression="seq 1001 1001.0 0.0 18" /> - <has_line_matching expression="895:1:37:17593:9954/1 1 103.803741455 303.702941895 114" /> + <has_line_matching + expression="seq 1001 1001.0 0.0 18" /> + <has_line_matching + expression="895:1:37:17593:9954/1 1 103.803741455 303.702941895 114" /> </assert_contents> </output> </test>
--- a/do-partition.xml Wed Aug 06 18:32:24 2014 -0400 +++ b/do-partition.xml Mon Aug 18 07:02:05 2014 -0400 @@ -30,17 +30,17 @@ type="integer" value="20" label="ksize" - help="k-mer size to use" /> + help="k-mer size to use (--ksize/-k)" /> <param name="n_tables" type="integer" min="1" value="4" label="n_tables" - help="number of tables to use" /> + help="number of tables to use (--n_tables/-N)" /> <param name="tablesize_specific" type="text" label="tablesize" - help="lower bound on the tablesize to use" /> + help="lower bound on the tablesize to use (--min-tablesize/-x)" /> </inputs> <outputs> <data name="information" @@ -48,12 +48,7 @@ label="${tool.name} summary for #echo ','.join(map(str, $inputs ))#" /> <expand macro="output_sequences" /> </outputs> - <stdio> - <!-- [HELP] If no exit code rule is defined, the tool will stop if anything is written to STDERR --> - <exit_code range="1:" - level="fatal" /> - </stdio> - + <expand macro="stdio" /> <!-- <tests> <test interactor="api"> <conditional name="parameters">
--- a/extract-partitions.xml Wed Aug 06 18:32:24 2014 -0400 +++ b/extract-partitions.xml Mon Aug 18 07:02:05 2014 -0400 @@ -4,7 +4,8 @@ force_history_refresh="true"> <description> - Separate sequences that are annotated with partitions into grouped files. + Separate sequences that are annotated with partitions into + grouped files. </description> <macros> <token name="@BINARY@">extract-partitions.py</token> @@ -30,19 +31,19 @@ <param name="max_size" type="integer" label="Max group size" - help="No more than this many number of sequences will be stored in each output" + help="No more than this many number of sequences will be stored in each output (--max-size/-X)" value="1000000" /> <param name="min_partition_size" type="integer" label="Min partition size" - help="The minimum partition size worth keeping" + help="The minimum partition size worth keeping (--min-partition-size/-m)" value="5" /> <param name="output_unassigned" type="boolean" checked="false" truevalue="--output-unassigned" falsevalue="" - label="Output unassigned sequences" /> + label="Output unassigned sequences (--output-unassigned/-U)" /> </inputs> <outputs> <data name="distribution" @@ -50,18 +51,15 @@ label="Partition size distribution from ${tool.name}" /> <expand macro="output_sequences" /> </outputs> - <stdio> - <!-- [HELP] If no exit code rule is defined, the tool will stop if anything is written to STDERR --> - <exit_code range="1:" - level="fatal" /> - </stdio> + <expand macro="stdio" /> <tests> <test interactor="api"> <param name="inputs" value="random-20-a.fa.part"/> <output name="distribution"> <assert_contents> - <has_line_matching expression="'99 1 1 99" /> + <has_line_matching + expression="99 1 1 99" /> </assert_contents> </output> </test>
--- a/filter-abund.xml Wed Aug 06 18:32:24 2014 -0400 +++ b/filter-abund.xml Mon Aug 18 07:02:05 2014 -0400 @@ -35,27 +35,24 @@ truevalue="--variable-coverage" falsevalue="" label="Variable coverage" - help="Only trim when a sequence has high enough coverage (median abundance > 20)" /> + help="Only trim when a sequence has high enough coverage; median abundance > 20 (--variable_coverage)" /> <param name="cutoff" type="integer" value="2" label="cutoff" - help="Trim at k-mers below this abundance." /> + help="Trim at k-mers below this abundance. (--cutoff)" /> <expand macro="input_counting_table_filename" /> </inputs> <outputs> <!-- <expand macro="output_sequences" /> --> <expand macro="output_sequences_single" /> </outputs> - <stdio> - <!-- [HELP] If no exit code rule is defined, the tool will stop if anything is written to STDERR --> - <exit_code range="1:" - level="fatal" /> - </stdio> - <tests> + <expand macro="stdio" /> + <tests> <test interactor="api"> <param name="inputs" value="test-abund-read-2.fa" /> - <param name="input_counting_table_filename" value="test-abund-read-2.ct" ftype="ct" /> + <param name="input_counting_table_filename" + value="test-abund-read-2.ct" ftype="ct" /> <output name="output"> <!-- <discover_dataset name="test-abund-read-2.fa.abundfilt"> --> <assert_contents> @@ -65,8 +62,10 @@ </output> </test> <test interactor="api"> - <param name="input_sequence_filename" value="test-abund-read-2.fa" /> - <param name="input_counting_table_filename" value="test-abund-read-2.ct" ftype="ct" /> + <param name="input_sequence_filename" + value="test-abund-read-2.fa" /> + <param name="input_counting_table_filename" + value="test-abund-read-2.ct" ftype="ct" /> <param name="cutoff" value="1" /> <output name="output"> <!-- <discover_dataset name="test-abund-read-2.fa.abundfilt"> -->
--- a/filter-below-abund.xml Wed Aug 06 18:32:24 2014 -0400 +++ b/filter-below-abund.xml Mon Aug 18 07:02:05 2014 -0400 @@ -2,7 +2,8 @@ name="Filter below abundance cutoff of 50" version="1.1-1" force_history_refresh="true"> - + +<!-- Work in progress, gating on filter-below-abund.py being upgraded --> <description> Trims fastq/fasta sequences at k-mers with abundance below 50 based on a provided k-mer counting table. @@ -29,11 +30,7 @@ <!-- <expand macro="output_sequences" /> --> <expand macro="output_sequences_single" /> </outputs> - <stdio> - <!-- [HELP] If no exit code rule is defined, the tool will stop if anything is written to STDERR --> - <exit_code range="1:" - level="fatal" /> - </stdio> + <expand macro="stdio" /> <!-- <tests> <test interactor="api"> <param name="inputs" value="test-abund-read-2.fa" />
--- a/macros.xml Wed Aug 06 18:32:24 2014 -0400 +++ b/macros.xml Mon Aug 18 07:02:05 2014 -0400 @@ -15,7 +15,7 @@ --n_tables=$parameters.n_tables --min-tablesize=$parameters.tablesize_specific #end if</token> - <token name="@THREADS@">--threads \$GALAXY_SLOTS</token> + <token name="@THREADS@">--threads \${GALAXY_SLOTS:-4}</token> <xml name="tableinputs"> <conditional name="parameters"> <param name="type" @@ -43,7 +43,8 @@ Animal Transcriptome </option> <option value="4e9"> - Small Animal Genome or Low-Diversity Metagenome + Small Animal Genome or + Low-Diversity Metagenome </option> <option value="16e9"> Large Animal Genome @@ -117,7 +118,7 @@ truevalue="" falsevalue="--no-zero" checked="true" - help="Output zero count bins" /> + help="Output zero count bins (--no-zero)" /> </xml> <xml name="software-citation"> <citation type="bibtex">@article{khmer2014, @@ -149,5 +150,11 @@ <xml name="counting-citation"> <citation type="doi">10.1371/journal.pone.0101271</citation> </xml> - + <xml name="stdio"> + <stdio> + <!-- [HELP] If no exit code rule is defined, the tool will stop if anything is written to STDERR --> + <exit_code range="1:" + level="fatal" /> + </stdio> + </xml> </macros>
--- a/normalize-by-median.xml Wed Aug 06 18:32:24 2014 -0400 +++ b/normalize-by-median.xml Mon Aug 18 07:02:05 2014 -0400 @@ -73,11 +73,7 @@ <!-- <expand macro="output_sequences" /> --> <expand macro="output_sequences_single" /> </outputs> - <stdio> - <!-- [HELP] If no exit code rule is defined, the tool will stop if anything is written to STDERR --> - <exit_code range="1:" - level="fatal" /> - </stdio> + <expand macro="stdio" /> <tests> <test interactor="api">