Mercurial > repos > iuc > tn93_cluster
diff tn93_cluster.xml @ 0:af03f3398f03 draft
"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/tn93/ commit eec640a7c26b728f8175885926fe368b0756d9e5"
author | iuc |
---|---|
date | Fri, 23 Apr 2021 03:04:15 +0000 |
parents | |
children | 112d80c9ccca |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tn93_cluster.xml Fri Apr 23 03:04:15 2021 +0000 @@ -0,0 +1,71 @@ +<tool id="tn93_cluster" name="TN93 Cluster" version="@VERSION@"> + <description>sequences that lie within a specific distance of each other</description> + <macros> + <import>macros.xml</import> + </macros> + <requirements> + <requirement type="package" version="@VERSION@">tn93</requirement> + <requirement type="package" version="3.9">python</requirement> + </requirements> + <version_command><![CDATA[tn93 --version]]></version_command> + <command detect_errors="exit_code"><![CDATA[ + python '$__tool_directory__/tn93_cluster.py' --input '$input_fasta' --reference '$reference' --output '$tn93_clusters' + --threshold $threshold + --ambigs $ambigs + --cluster-type $cluster_type + --overlap $overlap + --fraction $fraction + --cluster-count $cluster_count + #if $compress: + --compressed '$tn93_compressed_clusters' + #end if + ]]></command> + <inputs> + <param name="input_fasta" type="data" format="fasta" label="Input in FASTA format" /> + <param name="reference" type="data" format="fasta" label="Reference in FASTA format" /> + <param argument="--compress" type="boolean" truevalue="--compress" falsevalue="" label="Output additional fasta dataset with compressed clusters" /> + <param argument="--cluster-count" type="integer" value="200" label="Only retain this many clusters" /> + <param argument="--threshold" type="float" min="0" value="0.0005" label="Distance threshold" help="Sequences which lie within this distance will be clustered" /> + <param argument="--ambigs" type="select" label="Strategy for ambiguous nucleotides"> + <option value="resolve" selected="true">resolve</option> + <option value="average">average</option> + <option value="skip">skip</option> + <option value="gapmm">gapmm</option> + </param> + <param argument="--cluster_type" type="select" label="Clustering rules" help=""All": Each sequence within the cluster must be within the specified distance of every other sequence in the cluster. "Any": Each sequence within the cluster must be within the specified distance of at least one other sequence."> + <option value="all">All</option> + <option value="any">Any</option> + </param> + <param name="overlap" argument="-l" type="integer" value="100" + label="Only process pairs that overlap by at least N bases" /> + <param name="fraction" argument="-g" type="float" value="1.0" + label="Maximum tolerated fraction of ambiguous characters" /> + </inputs> + <outputs> + <data format="json" name="tn93_clusters" /> + <data format="fasta" name="tn93_compressed_clusters"> + <filter>compress</filter> + </data> + </outputs> + <tests> + <test expect_num_outputs="2"> + <param name="input_fasta" value="cluster-in1-1.fa" /> + <param name="reference" value="cluster-in1-2.fa" /> + <param name="threshold" value="0.35" /> + <param name="compress" value="true" /> + <output file="cluster-out1.json" ftype="json" name="tn93_clusters" /> + <output file="cluster-out1.fa" ftype="fasta" name="tn93_compressed_clusters" /> + </test> + </tests> + <help><![CDATA[ +TN93-Cluster +============ + +Clusters sequences within a minimum distance of each other using the 1993 +Tamura-Nei distance calculation. + +]]></help> + <expand macro="citations"> + <citation type="doi">10.1093/oxfordjournals.molbev.a040023</citation> + </expand> +</tool>