--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/cfsan_centriflaken.xml	Mon Jun 27 15:55:37 2022 -0400
@@ -0,0 +1,131 @@
+<tool id="cfsan_centriflaken" name="Centriflaken" version="0.2.0+galaxy0">
+    <description>An automated pipeline to generate a MAG of interest (E.coli or Salmonella) and perform serotyping.</description>
+    <requirements>
+	<requirement type="package" version="22.04">nextflow</requirement>
+	<requirement type="package">graphviz</requirement>
+    </requirements>    
+    <version_command>nextflow -version</version_command>
+    <command detect_errors="exit_code"><![CDATA[
+	mkdir -p cpipes-input
+	#for $input in $LIST
+	    ln -sf '$input' './cpipes-input/${input.element_identifier}';
+	#end for
+	pwd_path=\$(pwd)
+	$__tool_directory__/0.2.1/cpipes
+    #if (reads.type == "long"):
+        --pipeline $pipeline
+    #else:
+        --pipeline $pipeline
+    #end if
+	--input \${pwd_path}/cpipes-input
+	--output \${pwd_path}/cpipes-output
+	#if ($reads_lib.paired_end == "true"):
+	    --fq_single_end false
+        --fq_suffix '${fq_suffix}'
+	    --fq2_suffix '${fq2_suffix}'
+    #else:
+        --fq_single_end true
+        --fq_suffix '${fq_suffix}'
+	#end if
+	--fq_filename_delim '${fq_filename_delim}'
+	--fq_filename_delim_idx $fq_filename_delim_idx
+	--centrifuge_extract_bug '${centrifuge_extract_bug}'
+	--flye_genome_size '${genome_size}'
+	-profile $profile
+    ]]></command>
+    <inputs>
+        <param name="input" type="data" format="fastq,fastq.gz,fastqsanger.gz,fastqsanger" label="Input reads" />
+        <conditional name="reads">
+            <param name="type" type="select" label="Sequencing Read Library Type" value="long">
+                <option value="long">Long reads</option>
+                <option value="short">Short reads</option>
+            </param>
+            <when value="short">
+                <conditional name="reads_lib">
+                    <param name="paired_end" type="select" label="Sequencing Read Library Layout" value="false">
+                        <option value="false">Short read Single-End or Long reads</option>
+                        <option value="true">Short read Paired-End</option>
+                    </param>
+                    <when value="true">
+                        <param name="fq_suffix" value="_R1_001.fastq.gz" type="text" label="Suffix of the FASTQ R1 file of Paired-End reads."/>
+                        <param name="fq2_suffix" value="_R2_001.fastq.gz" type="text" label="Suffix of the FASTQ R2 file of Paired-End reads."/>
+                    </when>
+                    <when value="false">
+                        <param name="fq_suffix" value="_R1_001.fastq.gz" type="text" label="Suffix of the FASTQ R1 file of Paired-End reads."/>
+                    </when>
+                </conditional>
+            </when>
+            <when value="long">
+                <param name="fq_suffix" value=".fastq.gz" type="text" label="Suffix of the FASTQ file of Long reads."/>
+            </when>
+        </conditional>
+        <param name="fq_filename_delim" type="text" value="_" label="File name delimitor by which samples are grouped together (--fq_filename_delim)" 
+            help="This is the delimitor by which samples are grouped together to display in the final MultiQC report. For example, if your input data sets are mango_replicate1.fastq.gz, mango_replicate2.fastq.gz, orange_replicate1_maryland.fastq.gz, orange_replicate2_maryland.fastq.gz, then to create 2 samples mango and orange, the value for --fq_filename_delim would be _ (underscore) and the value for --fq_filename_idx would be 1, since you want to group by the first word (i.e. mango or orange) after splitting the filename based on _ (underscore)"/>
+        <param name="fq_filename_delim_idx" type="integer" value="1" label="File name delimitor index (--fq_filename_delimitor_idx)" />
+        <param name="centrifuge_extract_bug" type="text" value="Escherichia coli" label="Reads belonging to this taxa are extracted and a MAG is generated to allow for serotyping"/>
+        <param name="genome_size" type="text" optional="true" value="5.5m" label="Estimated genome size" help="For example, 5m or 2.6g.">
+            <validator type="regex" message="Genome size must be a float  or integer, optionally followed by the a unit prefix (kmg)">^([0-9]*[.])?[0-9]+[kmg]?$</validator>
+        </param>
+        <param name="runtime_profile" type="select" label="Run time profile" value="kondagac">
+            <option value="kondagac">conda</option>
+            <option value="cingularitygac">singularity</option>
+        </param>
+    </inputs>
+    <outputs>
+        <data name="multiqc_report" format="html" label="MultiQC Report on ${on_string}">
+            <discover_datasets pattern="multiqc_report.html" assign_primary_output="true" directory="cpipes-output"/>
+        </data>
+        <data name="assembled_mags" format="fasta" label="CENTRIFLAKEN: Assembled MAGs">
+            <discover_datasets pattern=".*\.assembly_filtered_contigs.fasta" visible="true" directory="cpipes-output"/>
+        </data>
+    </outputs>
+    <help><![CDATA[
+
+.. class:: infomark
+
+**Purpose**
+
+Centriflaken suite of automated data analysis pipelines based on Nextflow DSL2 developed at CFSAN, FDA. Thess piepelines allow rapid 
+and effective construction of metagenomic assembled genomes (MAGs) to enable bacterial source-tracking. It is based on methods described in our 
+previous publication (https://doi.org/10.1371/journal.pone.0245172).
+----
+
+.. class:: infomark
+
+**Testing and Validation**
+
+The pipeline has been wrapped to make it work in Galaxy. It takes in either paired or unpaired short reads or long reads, generates MAGs and performs 
+in silico-based analysis (i.e., virulence gene finding). Additionally, AMR gene finding analysis is also included in Centriflaken and performed on MAGs 
+of interest. The final summary plots and tables can be downloaded from the provided MultiQC HTML report generated as part of the pipeline. 
+The Centriflaken pipeline was validated with data from our previously published method (Maguire et al, 2021) and was able to replicate the detection 
+and classification of STECs for each sample. We tested the pipeline with nanopore data obtained from 21 additional enriched samples from 
+irrigation water and was able to perform the entire precision metagenomics analysis in less than 5 hours for all of them. All the original testing and validation was 
+done on the command line on the CFSAN Raven2 HPC Cluster.
+
+
+----
+
+.. class:: infomark
+
+**Outputs**
+
+The main output files are:
+
+    ::
+
+        - MultiQC Report: Contains a brief summary report including any serotyping and AMR result tables.
+        - Final assembly: contains contigs and possibly scaffolds (see below).
+
+  ]]></help>
+    <citations>
+        <citation type="bibtex">
+            @misc{gitlabCPIPES,
+            author = {Konganti, Kranti},
+            year = {2022},
+            title = {CPIPES - Centriflaken},
+            publisher = {GitLab},
+            journal = {GitLab repository},
+            url = {https://cfsan-git.fda.gov/Kranti.Konganti/cpipes}}
+        </citation>
+    </citations>
+</tool>