<tool id="edu.tamu.cpt2.gbk.adjacent_features" name="Find adjacent Genbank features" version="RC4">
  <description>Searches a Genbank file for a given FASTA sequence, then outputs a file with adjacent upstream features, and another with adjacent downstream features.</description>
  <macros>
    <import>macros.xml</import>
    <import>cpt-macros.xml</import>
  </macros>
  <expand macro="requirements"/>
  <command detect_errors="aggressive"><![CDATA[
python '$__tool_directory__/adjacent_features.py'
#set repeat_var_1 = '" "'.join([ str('$var') for '$var' in '$gbkIn' ])
#set repeat_var_2 = '" "'.join([ str('$var') for '$var' in '$fastaIn' ])
-genbankFiles "$repeat_var_1"
-fastaFiles "$repeat_var_2"
-tTable '$tTable'
-fTable '$fTable'
-upOut '$upstreamOut'
-downOut '$downstreamOut'
'$translate'
'$forceID'
'$mode'
--forward '$ahead'
--behind '$back'
]]></command>
  <inputs>
    <param label="Genbank file" name="gbkIn" type="data" format="genbank" multiple="True"/>
    <param label="Fasta file" name="fastaIn" type="data" format="fasta" multiple="True"/>
    <param label="Translation table to use on Fasta input:" name="fTable" type="select">
      <option value="0" selected="true">[0] Do not translate/ Fasta already translated</option>
      <option value="1">[1] The Standard Code</option>
      <option value="2">[2] The Vertebrate Mitochondrial Code</option>
      <option value="3">[3] The Yeast Mitochondrial Code</option>
      <option value="4">[4] The Mold, Protozoan, and Coelenterate Mitochondrial Code and the Mycoplasma/Spiroplasma Code</option>
      <option value="5">[5] The Invertebrate Mitochondrial Code </option>
      <option value="6">[6] The Ciliate, Dasycladacean and Hexamita Nuclear Code</option>
      <option value="9">[9] The Echinoderm and Flatworm Mitochondrial Code</option>
      <option value="10">[10] The Euplotid Nuclear Code</option>
      <option value="11">[11] The Bacterial, Archaeal and Plant Plastid Code</option>
      <option value="12">[12] The Alternative Yeast Nuclear Code</option>
      <option value="13">[13] The Ascidian Mitochondrial Code</option>
      <option value="14">[14] The Alternative Flatworm Mitochondrial Code</option>
      <option value="15">[15] Blepharisma Nuclear Code</option>
      <option value="16">[16] Chlorophycean Mitochondrial Code</option>
      <option value="21">[21] Trematode Mitochondrial Code</option>
      <option value="22">[22] Scenedesmus Obliquus Mitochondrial Code</option>
      <option value="23">[23] Thraustochytrium Mitochondrial Code</option>
      <option value="24">[24] Pterobranchia Mitochondrial Code</option>
      <option value="25">[25] Candidate Division SR1 and Gracilibacteria Code</option>
    </param>
    <param label="Translation table to use on Genbank features:" name="tTable" type="select">
      <option value="0">[0] Do not translate (Use nucleotide sequence of features)</option>
      <option value="1">[1] The Standard Code</option>
      <option value="2">[2] The Vertebrate Mitochondrial Code</option>
      <option value="3">[3] The Yeast Mitochondrial Code</option>
      <option value="4">[4] The Mold, Protozoan, and Coelenterate Mitochondrial Code and the Mycoplasma/Spiroplasma Code</option>
      <option value="5">[5] The Invertebrate Mitochondrial Code </option>
      <option value="6">[6] The Ciliate, Dasycladacean and Hexamita Nuclear Code</option>
      <option value="9">[9] The Echinoderm and Flatworm Mitochondrial Code</option>
      <option value="10">[10] The Euplotid Nuclear Code</option>
      <option value="11" selected="true">[11] The Bacterial, Archaeal and Plant Plastid Code</option>
      <option value="12">[12] The Alternative Yeast Nuclear Code</option>
      <option value="13">[13] The Ascidian Mitochondrial Code</option>
      <option value="14">[14] The Alternative Flatworm Mitochondrial Code</option>
      <option value="15">[15] Blepharisma Nuclear Code</option>
      <option value="16">[16] Chlorophycean Mitochondrial Code</option>
      <option value="21">[21] Trematode Mitochondrial Code</option>
      <option value="22">[22] Scenedesmus Obliquus Mitochondrial Code</option>
      <option value="23">[23] Thraustochytrium Mitochondrial Code</option>
      <option value="24">[24] Pterobranchia Mitochondrial Code</option>
      <option value="25">[25] Candidate Division SR1 and Gracilibacteria Code</option>
    </param>
    <param label="Number of features upstream to return" name="ahead" type="integer" value="1"/>
    <param label="Number of features downstream to return" name="back" type="integer" value="1"/>
    <param label="Translate output to protein sequence" name="translate" type="boolean" truevalue="--outProt" falsevalue=""/>
    <param label="Genbank Protein's ID must also match Fasta Sequence's ID " name="forceID" type="boolean" truevalue="--forceSeqID" falsevalue="" checked="true"/>
    <param name="mode" type="select" label="Mode">
      <option value="--genesOnly">Search only Gene-type features</option>
      <option value="--cdsOnly">Search only CDS-type features</option>
      <option value="">Search all features (Will most likely cause duplicate results, as this will include sub-features)</option>
    </param>
  </inputs>
  <outputs>
    <data name="upstreamOut" format="fasta" label="upOut"/>
    <data name="downstreamOut" format="fasta" label="downOut"/>
  </outputs>
  <help><![CDATA[
Currently Experimental: Uploaded for review purposes

**What it does**

For a given Fasta file, this tool searches through the features of a Genbank file for one that matches the sequence in the Fasta. If found, it will then output a specified number of features upstream from the hit and a specified number of features downstream as a multifasta file.

The drop down menus provide a selection of translation tables for the Fasta and Genbank inputs. If "translate output to protein sequence"
is selected, the output will be translated using the table selected for the Genbank translation.

It is currently recommended to select either the Gene only or CDS only options for mode, as searching all features will include sub-features of neighbors (ie, selecting 2 for upstream will give you the neighboring gene and then its CDS sub feature, rather than 2 proper neighbors) as well as the sub-features of the search hit itself.


]]></help>
  <citations>
    <citation type="doi">10.1371/journal.pcbi.1008214</citation>
    <citation type="bibtex">
			@unpublished{galaxyTools,
				author = {A. Criscione},
				title = {CPT Galaxy Tools},
				year = {2019-2021},
				note = {https://github.com/tamu-cpt/galaxy-tools/}
			}
			</citation>
  </citations>
</tool>