--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/SAR_finder.xml	Mon Jun 05 02:52:57 2023 +0000
@@ -0,0 +1,73 @@
+<tool id="edu.tamu.cpt.sar.sar_finder" name="SAR Finder" version="1.0">
+    <description>SAR Domain Finder</description>
+    <macros>
+        <import>macros.xml</import>
+    </macros>
+    <expand macro="requirements">
+    </expand>
+    <command detect_errors="aggressive"><![CDATA[
+python '$__tool_directory__/SAR_finder.py'
+'$fa'
+--sar_min '$sar_min'
+--sar_max '$sar_max'
+--out_fa '$out_fa'
+--out_gff3 '$out_gff3'
+--out_stat '$out_stat'
+    ]]></command>
+    <inputs>
+        <param label="Multi FASTA File" name="fa" type="data" format="fasta"/>
+        <param label="SAR domain minimal size" name="sar_min" type="integer" value="15"/>
+        <param label="SAR domain maximum size" name="sar_max" type="integer" value="20"/>
+    </inputs>
+    <outputs>
+        <data format="tabular" name="out_stat" label="candidate_SAR_stats.tsv"/>
+        <data format="fasta" name="out_fa" label="candidate_SAR.fa"/>
+        <data format="gff3" name="out_gff3" label="candidate_SAR.gff3"/>
+    </outputs>
+    <tests>
+        <test>
+            <param name="fa" value="simple-proteins.fa"/>
+            <param name="sar_min" value="15"/>
+            <param name="sar_max" value="20"/>
+            <output name="out_stat" file="candidate_SAR_stats.tsv"/>
+            <output name="out_fa" file="candidate_SAR.fa"/>
+            <output name="out_gff3" file="candidate_SAR.gff3"/>
+        </test>
+    </tests>
+    <help><![CDATA[
+
+**What it does**
+A tool that analyzes the sequence within the first 50 residues of a protein for a weakly hydrophobic domain called Signal-Anchor-Release (aka SAR). 
+The tool finds proteins that contain a stretch (default 15-20 residues) of hydrophobic residues (Ile, Leu, Val, Phe, Tyr, Trp, Met, Gly, Ala, Ser) and 
+calculates the % Gly/Ala/Ser/Thr residues in the hydrophobic stretch. The net charge on the N-terminus is also displayed to aid in determining the 
+SAR orientation in the membrane.[2]
+
+Definition: A Signal-Anchor-Release (SAR) domain is an N-terminal, weakly hydrophobic transmembrane region rich in Gly/Ala and/or Ser (and sometimes Thr) residues. 
+The SAR domain is sometimes found in phage lysis proteins, including endolysins and holins. The SAR domain can be released from the membrane in a proton 
+motive force-dependent manner. Known SAR domains in phage endolysins often have >50-60% Gly/Ala/Ser/Thr content. SAR endolysins are expected to have a net positive
+charge on the N-terminus by the positive-inside rule.
+
+**INPUT** --> Protein Multi FASTA
+
+**OUTPUT** --> 
+
+* Multi FASTA with candidate proteins that pass the SAR domain criteria
+
+* Tabular summary file that lists every subdomain fitting the criteria for each potential SAR domain-containing protein with the following: protein name/sequence/length, SAR length/start/sequence/end, individual and total GAST% content in SAR, and N-terminal sequence/net charge
+
+* Multi GFF3 for unique candidate SAR domain-containing proteins
+
+    ]]></help>
+    <citations>
+        <citation type="doi">10.1371/journal.pcbi.1008214</citation>
+        <citation type="doi">https://dx.doi.org/10.1016/bs.aivir.2018.09.003</citation>
+        <citation type="bibtex">
+            @unpublished{galaxyTools,
+            author = {C. Ross},
+            title = {CPT Galaxy Tools},
+            year = {2020-},
+            note = {https://github.com/tamu-cpt/galaxy-tools/}
+            }
+        </citation>
+    </citations>
+</tool>