# HG changeset patch
# User estrain
# Date 1734569624 0
# Node ID 05178d77c066d9226ba8f4c6de74db8907b07673

Uploaded

diff -r 000000000000 -r 05178d77c066 qsnp2/qsnp2.xml
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/qsnp2/qsnp2.xml	Thu Dec 19 00:53:44 2024 +0000
@@ -0,0 +1,72 @@
+<tool id="qsp2" name="CSP2 (SNP Pipeline Mode)" version="0.9.7_Dev21">
+  <description>Run SNP Pipeline analysis on isolates using one or more references.</description>
+  <requirements>
+	  <container type="docker">quay.io/redhatfda/csp2:latest</container>
+  </requirements>
+  <command detect_errors="exit_code"><![CDATA[
+    mkdir -p queries references;
+
+    #for query in $query_fasta:
+      ln -sf ${query} queries/${query.element_identifier};
+    #end for
+
+    #for ref in $ref_fasta:
+      ln -sf ${ref} references/${ref.element_identifier}; 
+    #end for
+    ls -al /app;
+	  which nextflow;
+	  df;
+	  pwd;
+
+]]>
+        </command>
+        <inputs>
+          <param name="query_fasta" type="data" format="fasta" value="" label="Query assemblies" multiple="true" optional="true" />
+	  <param name="ref_fasta" type="data" format="fasta" value="" label="Reference assemblies" multiple="true" optional="true" />
+          <conditional name="options">
+            <param name="select" type="select" label="Options Type">
+              <option value="basic">Basic</option>
+              <option value="advanced">Advanced</option>
+            </param>
+	    <when value="advanced">
+              <param name="min_cov" type="float" value="85" label="Minimum reference genome coverage to proceed with distance estimation" optional="true" />
+              <param name="min_iden" type="float" value="99" label="Minimum alignment percent identity to detect SNPs" optional="true" />
+              <param name="min_len" type="integer" value="500" label="Minimum alignment length to detect SNPs" optional="true" />
+              <param name="ref_edge" type="integer" value="150" label="Prune SNPs within this many bases of reference contig edge" optional="true" />
+              <param name="query_edge" type="integer" value="150" label="Prune SNPs within this many bases of query contig edge" optional="true" />
+              <param name="dwin" type="text" value="1000,125,15" label="Comma-separated set of window sizes for SNP density filtration (Set to 0 to disable density filtration)" optional="true" />
+              <param name="wsnps" type="text" value="3,2,1" label="Comma-separated list of maximum SNP counts per density window" optional="true" />
+              <param name="readext" type="text" value="fastq.gz" label="Read extension format (e.g., fastq.gz)" optional="true" />
+              <param name="forward" type="text" value="_1.fastq.gz" label="Forward read suffix (e.g. _1.fastq.gz)" optional="true" />
+              <param name="reverse" type="text" value="_2.fastq.gz" label="Forward read suffix (e.g. _2.fastq.gz)" optional="true" />
+              <param name="trim_name" type="text" value="" label="Text to remove from all file names (e.g., _contigs_skesa)" optional="true" />
+              <param name="rescue" type="boolean" value="false" label="Enable SNP edge rescue mode" optional="true" />
+              <param name="max_missing" type="float" value="50" label="Maximum percent of isolates allowed to have missing data to retain a SNP" optional="true" />
+            </when>
+            <when value="basic"/>
+          </conditional> 
+        </inputs>
+        <outputs>
+          <data name="nextflow_log" format="txt" label="Nextflow Log" from_work_dir="Nextflow_Log.txt" />
+          <data name="isolate_data" format="tabular" label="Isolate Data" from_work_dir="CSP2_SNP_Output/Isolate_Data.tsv" />
+          <data name="raw_mummer" format="tabular" label="Raw MUMmer Output" from_work_dir="CSP2_SNP_Output/Raw_MUMmer_Summary.tsv" />
+          <collection name="reference_results" type="list:list">
+            <discover_datasets pattern="(?P&lt;name&gt;.+)/CSP2_SNP_Pipeline\.log" format="txt" visible="true" directory="CSP2_SNP_Output/SNP_Analysis" />
+            <discover_datasets pattern="(?P&lt;name&gt;.+)/Reference_Screening\.tsv" format="tabular" visible="true" directory="CSP2_SNP_Output/SNP_Analysis" />
+            <discover_datasets pattern="(?P&lt;name&gt;.+)/snp_distance_matrix_preserved\.tsv" format="tabular" visible="true" directory="CSP2_SNP_Output/SNP_Analysis" />
+            <discover_datasets pattern="(?P&lt;name&gt;.+)/snp_distance_pairwise_preserved\.tsv" format="tabular" visible="true" directory="CSP2_SNP_Output/SNP_Analysis" />
+            <discover_datasets pattern="(?P&lt;name&gt;.+)/snpma_preserved\.fasta" format="fasta" visible="true" directory="CSP2_SNP_Output/SNP_Analysis" />
+          </collection>
+        </outputs>
+        <tests>
+        </tests>
+        <help>
+        This tool takes query assemblies and reference assemblies and calculates the pairwise distance between each query/reference combination. If no reference is provided, all queries are compared to all other queries.
+        </help>
+        <citations>
+                <citation type="doi">10.XXXX/placeholder.doi</citation>
+                <citation type="bibtex">@article{example2024,title={CFSAN SNP Pipeline 2 (CSP2): a pipeline for fast and accurate SNP distance estimation from bacterial genome assemblies.},author={Doe, John and Smith, Jane},journal={Submitted},year={2024}}
+                </citation>
+        </citations>
+</tool>
+