diff generate-putative-osp.xml @ 1:05b97a4dce94 draft

planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
author cpt
date Mon, 05 Jun 2023 02:51:44 +0000
parents
children 05244a021b80
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/generate-putative-osp.xml	Mon Jun 05 02:51:44 2023 +0000
@@ -0,0 +1,74 @@
+<tool id="edu.tamu.cpt2.spanin.generate-putative-osp" name="OSP candidates" version="1.0">
+    <description>constructs a putative list of potential o-spanin from an input genomic FASTA</description>
+    <macros>
+        <import>macros.xml</import>
+        <import>cpt-macros.xml</import>
+    </macros>
+    <expand macro="requirements">
+    </expand>
+    <command detect_errors="aggressive"><![CDATA[
+'$__tool_directory__/generate-putative-osp.py'
+'$fasta_file'
+--strand '$strand'
+--switch '$switch'
+--osp_on '$osp_on'
+--osp_op '$osp_op'
+--osp_ob '$osp_ob'
+--osp_og '$osp_og'
+--osp_min_len '$osp_min_len'
+--putative_osp '$putative_osp'
+--summary_osp_txt '$summary_osp'
+--putative_osp_gff '$putative_osp_gff'
+--min_lipo_after '$lipo_min'
+--max_lipo_after '$lipo_max'
+--osp_max '$osp_max'
+]]></command>
+    <inputs>
+        <param type="select" label="Strand Choice" name="strand">
+            <option value="both">both</option>
+            <option value="forward">+</option>
+            <option value="reverse">-</option>
+        </param>
+        <param label="Single Genome FASTA" name="fasta_file" type="data" format="fasta"/>
+        <param label="o-spanin minimal length" name="osp_min_len" type="integer" value="45"/>
+        <param label="o-spanin maximum length" name="osp_max" type="integer" value="200"/>
+        <param label="Range Selection; default is all; for a specific range to check for a spanin input integers separated by a colon (eg. 1234:4321)" type="text" name="switch" value="all"/>
+        <param label="Lipobox minimal distance from start codon" name="osp_min_dist" type="integer" value="10"/>
+        <param label="Lipobox maximum distance from start codon" name="osp_max_dist" type="integer" value="60" help="Searches for a Lipobox between Lipoboxmin and Lipoboxmax ie [Lipoboxmin,Lipoboxmax]"/>
+        <param label="Minimum amount of residues after lipobox is found" name="lipo_min" type="integer" value="25"/>
+        <param label="Maximum amount of residues after lipobox is found" name="lipo_max" type="integer" value="170"/>
+    </inputs>
+    <outputs>
+        <data format="fasta" name="osp_on" label="NucSequences.fa" hidden="true"/>
+        <data format="fasta" name="osp_op" label="ProtSequences.fa" hidden="true"/>
+        <data format="bed" name="osp_ob" label="BED_Output.bed" hidden="true"/>
+        <data format="gff3" name="osp_og" label="GFF_Output.gff" hidden="true"/>
+        <data format="fasta" name="putative_osp" label="putative_osp.fa"/>
+        <data format="txt" name="summary_osp" label="summary_osp.txt"/>
+        <data format="gff3" name="putative_osp_gff" label="putative_osp.gff3"/>
+    </outputs>
+    <help><![CDATA[
+
+**What it does**
+Searches a genome for candidate o-spanins (OSPs), a phage protein involved in outer membrane disruption during Gram-negative bacterial host cell lysis.
+
+
+**METHODOLOGY**
+
+Locates ALL potential start sequences, based on TTG / ATG / GTG (M / L / V). This list is pared down to those within the user-set min/max lengths. That filtered list generates a set of files with the ORFs in FASTA (nt and aa), BED, and GFF3 file formats.
+
+For each sequence in the protein FASTA, the tool then checks within the user-specified range (min/max distance from start codon) for a regular expression (RegEx) to identify a potential lipobox. The following residues are allowed for the potential lipobox: 
+
+    * [ILMFTV][^REKD][GAS]C
+    * AW[AGS]C
+
+Finally, the protein list is filtered for size with user-set periplasmic length parameters, calculated as the number of residues after the putative lipobox.
+
+**INPUT** --> Genomic FASTA
+*NOTE: This tool only takes a SINGLE genomic fasta. It does not work with multiFASTAs.*
+
+**OUTPUT** --> putative_osp.fa (FASTA) file, putative_osp.gff3, and basic summary statistics file as sumamry_osp.txt
+Protein sequences which passed the above filters are returned as the candidate OSPs.
+]]></help>
+    <expand macro="citations-crr"/>
+</tool>