kkonganti@0: <tool id="cfsan_centriflaken" name="Centriflaken" version="0.2.0+galaxy0">
kkonganti@0:     <description>An automated pipeline to generate a MAG of interest (E.coli or Salmonella) and perform serotyping.</description>
kkonganti@0:     <requirements>
kkonganti@0: 	<requirement type="package" version="22.04">nextflow</requirement>
kkonganti@0: 	<requirement type="package">graphviz</requirement>
kkonganti@0:     </requirements>    
kkonganti@0:     <version_command>nextflow -version</version_command>
kkonganti@0:     <command detect_errors="exit_code"><![CDATA[
kkonganti@50: 	mkdir -p cpipes-input || exit 1;
kkonganti@4: 	#for $key in $input.keys()
kkonganti@4: 	    ln -sf '$input[$key]' './cpipes-input/$key';
kkonganti@0: 	#end for
kkonganti@16: 	pwd_path=\$(pwd);
kkonganti@0: 	$__tool_directory__/0.2.1/cpipes
kkonganti@26:     --pipeline $pipeline
kkonganti@4:     #if ($pipeline == "centriflaken"):
kkonganti@4:         --fq_single_end true
kkonganti@33:         --flye_genome_size '${genome_size}'
kkonganti@33:         #if ($long_read_platform == "nanopore_corr"):
kkonganti@33:             --flye_nano_corr true --flye_nano_raw false
kkonganti@33:         #elif ($long_read_platform == "nanopore_hq"):
kkonganti@33:             --flye_nano_hq true --flye_nano_raw false
kkonganti@33:         #elif ($long_read_platform == "pacbio_raw"):
kkonganti@33:             --flye_pacbio_raw true --flye_nano_raw false
kkonganti@33:         #elif ($long_read_platform == "pacbio_corr"):
kkonganti@33:             --flye_pacbio_corr true --flye_nano_raw false
kkonganti@33:         #elif ($long_read_platform == "pacbio_hifi"):
kkonganti@33:             --flye_pacbio_hifi true --flye_nano_raw false
kkonganti@33:         #end if
kkonganti@16:     #elif ($pipeline == "centriflaken_hy"):
kkonganti@4:         #if ($reads_lib_layout == "single"):
kkonganti@4:             --fq_single_end true
kkonganti@30:         #elif ($reads_lib_layout == "paired"):
kkonganti@32:             --fq_single_end false --fq2_suffix '${fq2_suffix}'
kkonganti@4:         #end if
kkonganti@0:     #end if
kkonganti@0: 	--input \${pwd_path}/cpipes-input
kkonganti@0: 	--output \${pwd_path}/cpipes-output
kkonganti@4:     --fq_suffix '${fq_suffix}'
kkonganti@41:     #if ($fq_filter_by_len != ""):
kkonganti@39:         --fq_filter_by_len $fq_filter_by_len
kkonganti@39:     #end if
kkonganti@0: 	--fq_filename_delim '${fq_filename_delim}'
kkonganti@0: 	--fq_filename_delim_idx $fq_filename_delim_idx
kkonganti@0: 	--centrifuge_extract_bug '${centrifuge_extract_bug}'
kkonganti@47: 	-profile kondagac;
kkonganti@24:     mv './cpipes-output/${pipeline}-multiqc/multiqc_report.html' './multiqc_report.html';
kkonganti@24:     mv './cpipes-output/${pipeline}-results/kraken2_extract_contigs' kraken2_extract_contigs;
kkonganti@46:     rm -rf ./cpipes-output;
kkonganti@46:     rm -rf ./work
kkonganti@0:     ]]></command>
kkonganti@0:     <inputs>
kkonganti@3:         <param name="input" type="data_collection" collection_type="list" format="fastq,fastq.gz,fastqsanger.gz,fastqsanger" label="Input read collection" />
kkonganti@31:         <param name="pipeline" type="select" label="CPIPES Workflow name"
kkonganti@9:             help="centriflaken: for long reads (Nanopore or PacBio). centriflaken_hy: for short reads (paired or unpaired). Default: centriflaken">
kkonganti@31:             <option value="centriflaken" selected="true">centriflaken</option>
kkonganti@4:             <option value="centriflaken_hy">centriflaken_hy</option>
kkonganti@4:         </param>
kkonganti@31:         <param name="reads_lib_layout" type="select" label="Short Read Library Layout"
kkonganti@28:             help="Leave this option as Single-End for centriflaken. If the pipeline is centriflaken_hy (i.e for short reads), what is the library layout? Default: Single-End">
kkonganti@31:             <option value="single" selected="true">Single-End</option>
kkonganti@4:             <option value="paired">Paired-End</option>
kkonganti@4:         </param>
kkonganti@31:         <param name="long_read_platform" type="select" label="Mention long read sequencing platform and type"
kkonganti@25:             help="THIS OPTION IS IGNORED IF THE INPUT READS ARE SHORT READS.">
kkonganti@31:             <option value="nanopore_raw" selected="true">Nanopore raw reads, pre-Guppy5 (&lt;20% error)</option>
kkonganti@25:             <option value="nanopore_corr">Nanopore reads that were corrected with other methods (&lt;3% error)</option>
kkonganti@25:             <option value="nanopore_hq">Nanopore high-quality reads, Guppy5+ SUP or Q20 (5% error)</option>
kkonganti@25:             <option value="pacbio_raw">PacBio regular CLR reads (&lt;20% error)</option>
kkonganti@25:             <option value="pacbio_corr">PacBio reads that were corrected with other methods (&lt;3% error)</option>
kkonganti@25:             <option value="pacbio_hifi">PacBio HiFi reads (&lt;1% error)</option>
kkonganti@25:         </param>
kkonganti@4:         <param name="fq_suffix" value=".fastq.gz" type="text" label="Suffix of the R1 FASTQ or Unpaired FASTQ"/>
kkonganti@47:         <param name="fq2_suffix" value="_R2_001.fastq.gz" type="text" label="Suffix of the R2 FASTQ"
kkonganti@47:             help="THIS OPTION IS IGNORED IF THE INPUT READS ARE UNPAIRED/LONG READS."/>
kkonganti@44:         <param name="fq_filter_by_len" optional="true" value="" type="integer" label="Enter minimum read length to retain before starting the analysis"
kkonganti@48:             help="Keep this option empty to use default values. Default for centriflaken (long reads) is 4000 bp and for centriflaken_hy (short reads) is 75 bp."/>
kkonganti@40:         <param name="fq_filename_delim" type="text" value="_" label="File name delimitor by which samples are grouped together (--fq_filename_delim)" 
kkonganti@48:             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_delim_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)."/>
kkonganti@6:         <param name="fq_filename_delim_idx" type="integer" value="1" label="File name delimitor index (--fq_filename_delim_idx)" />
kkonganti@0:         <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"/>
kkonganti@0:         <param name="genome_size" type="text" optional="true" value="5.5m" label="Estimated genome size" help="For example, 5m or 2.6g.">
kkonganti@0:             <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]?$</validator>
kkonganti@0:         </param>
kkonganti@47:         <!-- <param name="runtime_profile" type="select" label="Run time profile">
kkonganti@31:             <option value="kondagac" selected="true">conda</option>
kkonganti@12:             <option value="cingularitygac">singularity</option>
kkonganti@47:         </param> -->
kkonganti@0:     </inputs>
kkonganti@0:     <outputs>
kkonganti@36:         <data name="multiqc_report" format="html" label="${pipeline}: MultiQC Report on ${on_string}" from_work_dir="multiqc_report.html"/>
kkonganti@36:         <collection name="assembled_mags" type="list" label="${pipeline}: Assembled MAGs on ${on_string}">
kkonganti@24:             <discover_datasets pattern="(?P&lt;name&gt;.*)\.assembly_filtered_contigs\.fasta" ext="fasta" directory="kraken2_extract_contigs"/>
kkonganti@18:         </collection>
kkonganti@0:     </outputs>
kkonganti@3:     <tests>
kkonganti@3:         <!--Test 01: long reads-->
kkonganti@3:         <test expect_num_outputs="2">
kkonganti@4:             <param name="input">
kkonganti@3:                 <collection type="list">
kkonganti@4:                     <element name="FAL11127.fastq.gz" value="FAL11127.fastq.gz" />
kkonganti@4:                     <element name="FAL11341.fastq.gz" value="FAL11341.fastq.gz" />
kkonganti@4:                     <element name="FAL11342.fastq.gz" value="FAL11342.fastq.gz" />
kkonganti@3:                 </collection>
kkonganti@3:             </param>
kkonganti@3:             <param name="fq_suffix" value=".fastq.gz"/>
kkonganti@3:             <output name="multiqc_report" file="multiqc_report.html" ftype="html" compare="sim_size"/>
kkonganti@18:             <!-- <output name="assembled_mags" file="FAL11127.assembly_filtered.contigs.fasta" ftype="fasta" compare="sim_size"/> -->
kkonganti@3:         </test>
kkonganti@3:     </tests>
kkonganti@0:     <help><![CDATA[
kkonganti@0: 
kkonganti@0: .. class:: infomark
kkonganti@0: 
kkonganti@0: **Purpose**
kkonganti@0: 
kkonganti@50: Centriflaken suite of automated data analysis pipelines are based on Nextflow DSL2 developed at CFSAN, FDA. These pipelines allow rapid 
kkonganti@0: and effective construction of metagenomic assembled genomes (MAGs) to enable bacterial source-tracking. It is based on methods described in our 
kkonganti@51: previous publication (<a href="https://doi.org/10.1371/journal.pone.0245172" target="_blank">Maguire *et al*, 2021</a>).
kkonganti@14: 
kkonganti@0: ----
kkonganti@0: 
kkonganti@0: .. class:: infomark
kkonganti@0: 
kkonganti@0: **Testing and Validation**
kkonganti@0: 
kkonganti@47: The CPIPES - Centriflaken Nextflow 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 
kkonganti@0: in silico-based analysis (i.e., virulence gene finding). Additionally, AMR gene finding analysis is also included in Centriflaken and performed on MAGs 
kkonganti@0: of interest. The final summary plots and tables can be downloaded from the provided MultiQC HTML report generated as part of the pipeline. 
kkonganti@51: The Centriflaken pipeline was validated with data from our previously published method (<a href="https://doi.org/10.1371/journal.pone.0245172" target="_blank">Maguire *et al*, 2021</a>) and was able to replicate the detection 
kkonganti@47: and classification of STECs for each sample. We tested the pipeline with Nanopore data obtained from 21 additional enriched samples from 
kkonganti@0: 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 
kkonganti@0: done on the command line on the CFSAN Raven2 HPC Cluster.
kkonganti@0: 
kkonganti@0: 
kkonganti@0: ----
kkonganti@0: 
kkonganti@0: .. class:: infomark
kkonganti@0: 
kkonganti@0: **Outputs**
kkonganti@0: 
kkonganti@0: The main output files are:
kkonganti@0: 
kkonganti@0:     ::
kkonganti@0: 
kkonganti@0:         - MultiQC Report: Contains a brief summary report including any serotyping and AMR result tables.
kkonganti@27:         - Final assembly: contains contigs and possibly scaffolds.
kkonganti@0: 
kkonganti@0:   ]]></help>
kkonganti@0:     <citations>
kkonganti@0:         <citation type="bibtex">
kkonganti@0:             @misc{gitlabCPIPES,
kkonganti@0:             author = {Konganti, Kranti},
kkonganti@0:             year = {2022},
kkonganti@0:             title = {CPIPES - Centriflaken},
kkonganti@0:             publisher = {GitLab},
kkonganti@0:             journal = {GitLab repository},
kkonganti@0:             url = {https://cfsan-git.fda.gov/Kranti.Konganti/cpipes}}
kkonganti@0:         </citation>
kkonganti@0:     </citations>
kkonganti@0: </tool>