kkonganti@133: <tool id="cfsan_centriflaken" name="Centriflaken" profile="23.0" version="0.4.2+galaxy23">
kkonganti@0:     <description>An automated pipeline to generate a MAG of interest (E.coli or Salmonella) and perform serotyping.</description>
kkonganti@0:     <requirements>
kkonganti@110:         <container type="docker">quay.io/biocontainers/nextflow:24.04.2--hdfd78af_0</container>
kkonganti@0:     </requirements>    
kkonganti@0:     <version_command>nextflow -version</version_command>
kkonganti@0:     <command detect_errors="exit_code"><![CDATA[
kkonganti@130:     input_path=\$(pwd)"/cpipes-input";
kkonganti@123:     mkdir -p "\${input_path}" || exit 1;
kkonganti@86:     #import re
kkonganti@58:     #if (str($input_read_type_cond.input_read_type) == "single_long"):
kkonganti@75: 	    #for _, $unpaired in enumerate($input_read_type_cond.input):
kkonganti@85:             #set read1 = str($unpaired.name)
kkonganti@84:             #if not str($unpaired.name).endswith(('.fastq', '.fastq.gz')):
kkonganti@96:                 #set read1_ext = re.sub('fastqsanger', 'fastq', str($unpaired.ext))
kkonganti@96:                 #set read1 = str($unpaired.name) + str('.') + $read1_ext
kkonganti@75:             #end if
kkonganti@123:             ln -sf '$unpaired' "\${input_path}/$read1";
kkonganti@58: 	    #end for
kkonganti@66:     #elif (str($input_read_type_cond.input_read_type) == "paired"):
kkonganti@75: 	    #for _, $pair in enumerate($input_read_type_cond.input_pair)
kkonganti@94:             #set read_R1 = re.sub('\:forward', '_forward', str($pair.forward.name))
kkonganti@94:             #set read_R2 = re.sub('\:reverse', '_reverse', str($pair.reverse.name))
kkonganti@96:             #set read_R1_ext = re.sub('fastqsanger', 'fastq', str($pair.forward.ext))
kkonganti@96:             #set read_R2_ext = re.sub('fastqsanger', 'fastq', str($pair.reverse.ext))
kkonganti@85:             #if not str($pair.forward.name).endswith(('.fastq', '.fastq.gz')):
kkonganti@96: 	            #set read_R1 = $read_R1 + str('.') + $read_R1_ext
kkonganti@85:             #end if
kkonganti@85:             #if not str($pair.reverse.name).endswith(('.fastq', '.fastq.gz')):
kkonganti@96:                 #set read_R2 = $read_R2 + str('.') + $read_R2_ext
kkonganti@85:             #end if
kkonganti@123: 	        ln -sf '$pair.forward' "\${input_path}/$read_R1";
kkonganti@123: 	        ln -sf '$pair.reverse' "\${input_path}/$read_R2";
kkonganti@58: 	    #end for
kkonganti@60:     #end if
kkonganti@130: 	$__tool_directory__/0.4.2/cpipes
kkonganti@61:     --pipeline $input_read_type_cond.pipeline_cond.pipeline
kkonganti@58:     #if ($input_read_type_cond.pipeline_cond.pipeline == "centriflaken"):
kkonganti@4:         --fq_single_end true
kkonganti@33:         --flye_genome_size '${genome_size}'
kkonganti@58:         #if ($input_read_type_cond.pipeline_cond.long_read_platform == "nanopore_corr"):
kkonganti@33:             --flye_nano_corr true --flye_nano_raw false
kkonganti@58:         #elif ($input_read_type_cond.pipeline_cond.long_read_platform == "nanopore_hq"):
kkonganti@33:             --flye_nano_hq true --flye_nano_raw false
kkonganti@58:         #elif ($input_read_type_cond.pipeline_cond.long_read_platform == "pacbio_raw"):
kkonganti@33:             --flye_pacbio_raw true --flye_nano_raw false
kkonganti@58:         #elif ($input_read_type_cond.pipeline_cond.long_read_platform == "pacbio_corr"):
kkonganti@33:             --flye_pacbio_corr true --flye_nano_raw false
kkonganti@58:         #elif ($input_read_type_cond.pipeline_cond.long_read_platform == "pacbio_hifi"):
kkonganti@33:             --flye_pacbio_hifi true --flye_nano_raw false
kkonganti@33:         #end if
kkonganti@58:     #elif ($input_read_type_cond.pipeline_cond.pipeline == "centriflaken_hy"):
kkonganti@64:         #if (str($input_read_type_cond.input_read_type) == "single_long"):
kkonganti@4:             --fq_single_end true
kkonganti@64:         #elif (str($input_read_type_cond.input_read_type) == "paired"):
kkonganti@64:             --fq_single_end false --fq2_suffix '${input_read_type_cond.fq2_suffix}'
kkonganti@4:         #end if
kkonganti@0:     #end if
kkonganti@123: 	--input \${input_path}
kkonganti@130: 	--output cpipes-output
kkonganti@64:     --fq_suffix '${input_read_type_cond.fq_suffix}'
kkonganti@41:     #if ($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@102:     #if (str($input_read_type_cond.pipeline_cond.rm_dup_seqs) == "true"):
kkonganti@101:         --seqkit_rmdup_run true
kkonganti@101:     #end if
kkonganti@106: 	-profile gxkubernetes;
kkonganti@131:     mv "./cpipes-output/${input_read_type_cond.pipeline_cond.pipeline}-multiqc/multiqc_report.html" "./multiqc_report.html" || exit 1;
kkonganti@131:     mv "./cpipes-output/${input_read_type_cond.pipeline_cond.pipeline}-results/kraken2_extract_contigs" "kraken2_extract_contigs" || exit 1;
kkonganti@0:     ]]></command>
kkonganti@0:     <inputs>
kkonganti@58:         <conditional name="input_read_type_cond">
kkonganti@58:             <param name="input_read_type" type="select" label="Select the read collection type">
kkonganti@61:                 <option value="single_long" selected="true">Unpaired reads (i.e. Single-End short reads or Long reads)</option>
kkonganti@58:                 <option value="paired">Paired-End reads</option>
kkonganti@58:             </param>
kkonganti@58:             <when value="single_long">
kkonganti@75:                 <param name="input" type="data_collection" collection_type="list" format="fastq,fastq.gz"
kkonganti@61:                     label="Dataset list of unpaired short reads or long reads" />
kkonganti@58:                 <conditional name="pipeline_cond">
kkonganti@58:                     <param name="pipeline" type="select" label="CPIPES Workflow name"
kkonganti@90:                         help="centriflaken: for long reads (Nanopore or PacBio). centriflaken_hy: for unpaired short reads. Default: centriflaken">
kkonganti@58:                         <option value="centriflaken" selected="true">centriflaken</option>
kkonganti@58:                         <option value="centriflaken_hy">centriflaken_hy</option>
kkonganti@58:                     </param>
kkonganti@58:                     <when value="centriflaken">
kkonganti@58:                         <param name="long_read_platform" type="select" label="Mention long read sequencing platform and type">
kkonganti@58:                             <option value="nanopore_raw" selected="true">Nanopore raw reads, pre-Guppy5 (&lt;20% error)</option>
kkonganti@58:                             <option value="nanopore_corr">Nanopore reads that were corrected with other methods (&lt;3% error)</option>
kkonganti@58:                             <option value="nanopore_hq">Nanopore high-quality reads, Guppy5+ SUP or Q20 (5% error)</option>
kkonganti@58:                             <option value="pacbio_raw">PacBio regular CLR reads (&lt;20% error)</option>
kkonganti@58:                             <option value="pacbio_corr">PacBio reads that were corrected with other methods (&lt;3% error)</option>
kkonganti@58:                             <option value="pacbio_hifi">PacBio HiFi reads (&lt;1% error)</option>
kkonganti@58:                         </param>
kkonganti@103:                         <param name="rm_dup_seqs" type="select" label="Remove duplicate sequences"
kkonganti@103:                             help="THIS OPTION IS IGNORED IF THE INPUT READS ARE LONG READS.">
kkonganti@103:                             <option value="NA" selected="true">N/A</option>
kkonganti@103:                         </param>
kkonganti@58:                     </when>
kkonganti@58:                     <when value="centriflaken_hy">
kkonganti@89:                         <param name="long_read_platform" type="select" label="Mention long read sequencing platform and type"
kkonganti@89:                             help="THIS OPTION IS IGNORED IF THE INPUT READS ARE SHORT READS.">
kkonganti@89:                                 <option value="NA" selected="true">N/A</option>
kkonganti@89:                         </param>
kkonganti@101:                         <param name="rm_dup_seqs" type="select" label="Remove duplicate sequences"
kkonganti@101:                             help="Selecting yes will compare sequence content and remove identical sequences i.e. only the first occured sequence record will be saved.">
kkonganti@101:                             <option value="true">yes</option>
kkonganti@101:                             <option value="false" selected="true">no</option>
kkonganti@101:                         </param>
kkonganti@58:                     </when>
kkonganti@58:                 </conditional>
kkonganti@74:                 <param name="fq_suffix" value=".fastq.gz" type="text" label="Suffix of the Unpaired FASTQ"/>
kkonganti@58:             </when>
kkonganti@58:             <when value="paired">
kkonganti@85:                 <param name="input_pair" type="data_collection" collection_type="list:paired" format="fastq,fastq.gz" label="List of Dataset pairs" />
kkonganti@66:                 <conditional name="pipeline_cond">
kkonganti@66:                     <param name="pipeline" type="select" label="CPIPES Workflow name"
kkonganti@90:                         help="Auto selected centriflaken_hy workflow for paired-end short reads.">
kkonganti@66:                         <option value="centriflaken_hy" selected="true">centriflaken_hy</option>
kkonganti@66:                     </param>
kkonganti@66:                     <when value="centriflaken_hy">
kkonganti@91:                         <param name="long_read_platform" type="select" label="Mention long read sequencing platform and type"
kkonganti@91:                             help="THIS OPTION IS IGNORED IF THE INPUT READS ARE SHORT READS.">
kkonganti@91:                                 <option value="NA" selected="true">N/A</option>
kkonganti@91:                         </param>
kkonganti@101:                         <param name="rm_dup_seqs" type="select" label="Remove duplicate sequences"
kkonganti@101:                             help="Selecting yes will compare sequence content and remove identical sequences i.e. only the first occured sequence record will be saved.">
kkonganti@101:                             <option value="true">yes</option>
kkonganti@101:                             <option value="false" selected="true">no</option>
kkonganti@101:                         </param>
kkonganti@66:                     </when>
kkonganti@66:                 </conditional>
kkonganti@74:                 <param name="fq_suffix" value="_R1_001.fastq.gz" type="text" label="Suffix of the R1 FASTQ"/>
kkonganti@58:                 <param name="fq2_suffix" value="_R2_001.fastq.gz" type="text" label="Suffix of the R2 FASTQ"/>
kkonganti@58:             </when>
kkonganti@58:         </conditional>
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@59:         <data name="multiqc_report" format="html" label="${input_read_type_cond.pipeline_cond.pipeline}: MultiQC Report on ${on_string}" from_work_dir="multiqc_report.html"/>
kkonganti@59:         <collection name="assembled_mags" type="list" label="${input_read_type_cond.pipeline_cond.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@53: previous publication (Maguire *et al*, 2021. doi: https://doi.org/10.1371/journal.pone.0245172).
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@53: The Centriflaken pipeline was validated with data from our previously published method (Maguire *et al*, 2021. doi: https://doi.org/10.1371/journal.pone.0245172) 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@55:         - MultiQC Report: Contains a brief summary report including any serotyping and AMR result tables.
kkonganti@56:                           Please note that due to MultiQC customizations, the preview (eye icon) will not
kkonganti@56:                           work within Galaxy for the MultiQC report. Please download the file by clicking
kkonganti@57:                           on the floppy icon and view it in your browser on your local desktop/workstation.
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>