view findSpanin.xml @ 3:fd70980a516b draft

planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
author cpt
date Mon, 05 Jun 2023 02:42:01 +0000
parents
children 673d1776d3b9
line wrap: on
line source

<tool id="edu.tamu.cpt2.spanin.findSpanin" name="Find Spanin" version="1.0">
    <description>With the outputs from the ISP and OSP candidate tools, cull the list down to candidate pairs</description>
    <macros>
        <import>macros.xml</import>
        <import>cpt-macros.xml</import>
    </macros>
    <expand macro="requirements">
    </expand>
    <command detect_errors="aggressive"><![CDATA[
python '$__tool_directory__/findSpanin.py'
'$putative_isp_fasta_file'
'$putative_osp_fasta_file'
--max_isp_osp_distance '$max_isp_osp_distance'
--embedded_txt '$embedded_txt'
--overlap_txt '$overlap_txt'
--separate_txt '$separate_txt'
--summary_txt '$summary_txt'
]]></command>
    <inputs>
        <param label="(putative) i-spanin FASTA file" name="putative_isp_fasta_file" type="data" format="fasta"/>
        <param label="(putative) o-spanin FASTA file" name="putative_osp_fasta_file" type="data" format="fasta"/>
        <param label="max distance from end of i-spanin to beginning of o-spanin (measured in AAs)" name="max_isp_osp_distance" type="integer" value="10"/>
    </inputs>
    <outputs>
        <data format="txt" name="summary_txt" label="FindSpanin_summary.txt"/>
        <data format="tabular" name="embedded_txt" label="embedded_results.txt"/>
        <data format="tabular" name="overlap_txt" label="overlap_results.txt"/>
        <data format="tabular" name="separate_txt" label="separate_results.txt"/>
    </outputs>
    <help><![CDATA[
**What it does**
Compares the protein FASTA files with candidate i-spanins and o-spanins from a genome and matches them into candidate pairs based on position in a strand-aware fashion.

**INPUT** --> Putative i-spanin and o-spanin protein multiFASTAs (generated from the ISP/OSP Candidate Tools). 

**METHODOLOGY** 
Does a pairwise comparison between candidate i-spanins and o-spanins based on their genomic location, and classifies them into the known bimolecular spanin genetic architectures. Classes are: embedded, overlapping, separated, or NOT a potential pair.

**OUTPUT** --> File with candidate pairs for each bimolecular spanin class and a basic summary statistics file. 

]]></help>
    <expand macro="citations-2020"/>
</tool>