Mercurial > repos > kkonganti > cfsan_centriflaken

annotate cfsan_centriflaken.xml @ 3:3154e7efa1c4

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload"
author kkonganti
date Mon, 27 Jun 2022 18:19:22 -0400
parents 29a590703d3e
children 34d3ef477de3
rev   line source
kkonganti@0 1 <tool id="cfsan_centriflaken" name="Centriflaken" version="0.2.0+galaxy0">
kkonganti@0 2 <description>An automated pipeline to generate a MAG of interest (E.coli or Salmonella) and perform serotyping.</description>
kkonganti@0 3 <requirements>
kkonganti@0 4 <requirement type="package" version="22.04">nextflow</requirement>
kkonganti@0 5 <requirement type="package">graphviz</requirement>
kkonganti@0 6 </requirements>
kkonganti@0 7 <version_command>nextflow -version</version_command>
kkonganti@0 8 <command detect_errors="exit_code"><![CDATA[
kkonganti@2 9 mkdir -p cpipes-input &&
kkonganti@3 10 #for $input_dataset in $input
kkonganti@3 11 ln -sf '$input_dataset' './cpipes-input/${input.element_identifier}';
kkonganti@0 12 #end for
kkonganti@2 13 pwd_path=\$(pwd) &&
kkonganti@0 14 $__tool_directory__/0.2.1/cpipes
kkonganti@0 15 #if (reads.type == "long"):
kkonganti@1 16 --pipeline centriflaken
kkonganti@0 17 #else:
kkonganti@1 18 --pipeline centriflaken_hy
kkonganti@0 19 #end if
kkonganti@0 20 --input \${pwd_path}/cpipes-input
kkonganti@0 21 --output \${pwd_path}/cpipes-output
kkonganti@3 22 #if ($reads.reads_lib.paired_end == "true"):
kkonganti@0 23 --fq_single_end false
kkonganti@3 24 --fq_suffix '${reads.reads_lib.fq_suffix}'
kkonganti@3 25 --fq2_suffix '${reads.reads_lib.fq2_suffix}'
kkonganti@0 26 #else:
kkonganti@0 27 --fq_single_end true
kkonganti@3 28 --fq_suffix '${reads.fq_suffix}'
kkonganti@0 29 #end if
kkonganti@0 30 --fq_filename_delim '${fq_filename_delim}'
kkonganti@0 31 --fq_filename_delim_idx $fq_filename_delim_idx
kkonganti@0 32 --centrifuge_extract_bug '${centrifuge_extract_bug}'
kkonganti@0 33 --flye_genome_size '${genome_size}'
kkonganti@0 34 -profile $profile
kkonganti@0 35 ]]></command>
kkonganti@0 36 <inputs>
kkonganti@3 37 <param name="input" type="data_collection" collection_type="list" format="fastq,fastq.gz,fastqsanger.gz,fastqsanger" label="Input read collection" />
kkonganti@0 38 <conditional name="reads">
kkonganti@0 39 <param name="type" type="select" label="Sequencing Read Library Type" value="long">
kkonganti@0 40 <option value="long">Long reads</option>
kkonganti@0 41 <option value="short">Short reads</option>
kkonganti@0 42 </param>
kkonganti@0 43 <when value="short">
kkonganti@0 44 <conditional name="reads_lib">
kkonganti@0 45 <param name="paired_end" type="select" label="Sequencing Read Library Layout" value="false">
kkonganti@0 46 <option value="false">Short read Single-End or Long reads</option>
kkonganti@0 47 <option value="true">Short read Paired-End</option>
kkonganti@0 48 </param>
kkonganti@0 49 <when value="true">
kkonganti@0 50 <param name="fq_suffix" value="_R1_001.fastq.gz" type="text" label="Suffix of the FASTQ R1 file of Paired-End reads."/>
kkonganti@0 51 <param name="fq2_suffix" value="_R2_001.fastq.gz" type="text" label="Suffix of the FASTQ R2 file of Paired-End reads."/>
kkonganti@0 52 </when>
kkonganti@0 53 <when value="false">
kkonganti@0 54 <param name="fq_suffix" value="_R1_001.fastq.gz" type="text" label="Suffix of the FASTQ R1 file of Paired-End reads."/>
kkonganti@0 55 </when>
kkonganti@0 56 </conditional>
kkonganti@0 57 </when>
kkonganti@0 58 <when value="long">
kkonganti@0 59 <param name="fq_suffix" value=".fastq.gz" type="text" label="Suffix of the FASTQ file of Long reads."/>
kkonganti@0 60 </when>
kkonganti@0 61 </conditional>
kkonganti@0 62 <param name="fq_filename_delim" type="text" value="_" label="File name delimitor by which samples are grouped together (--fq_filename_delim)"
kkonganti@0 63 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)"/>
kkonganti@0 64 <param name="fq_filename_delim_idx" type="integer" value="1" label="File name delimitor index (--fq_filename_delimitor_idx)" />
kkonganti@0 65 <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 66 <param name="genome_size" type="text" optional="true" value="5.5m" label="Estimated genome size" help="For example, 5m or 2.6g.">
kkonganti@0 67 <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 68 </param>
kkonganti@0 69 <param name="runtime_profile" type="select" label="Run time profile" value="kondagac">
kkonganti@0 70 <option value="kondagac">conda</option>
kkonganti@0 71 <option value="cingularitygac">singularity</option>
kkonganti@0 72 </param>
kkonganti@0 73 </inputs>
kkonganti@0 74 <outputs>
kkonganti@0 75 <data name="multiqc_report" format="html" label="MultiQC Report on ${on_string}">
kkonganti@0 76 <discover_datasets pattern="multiqc_report.html" assign_primary_output="true" directory="cpipes-output"/>
kkonganti@0 77 </data>
kkonganti@0 78 <data name="assembled_mags" format="fasta" label="CENTRIFLAKEN: Assembled MAGs">
kkonganti@0 79 <discover_datasets pattern=".*\.assembly_filtered_contigs.fasta" visible="true" directory="cpipes-output"/>
kkonganti@0 80 </data>
kkonganti@0 81 </outputs>
kkonganti@3 82 <tests>
kkonganti@3 83 <!--Test 01: long reads-->
kkonganti@3 84 <test expect_num_outputs="2">
kkonganti@3 85 <param name="input" value="FAL11127.fastq.gz" >
kkonganti@3 86 <collection type="list">
kkonganti@3 87 <element name="file1" value="FAL11127.fastq.gz" />
kkonganti@3 88 <element name="file2" value="FAL11341.fastq.gz" />
kkonganti@3 89 <element name="file3" value="FAL11342.fastq.gz" />
kkonganti@3 90 </collection>
kkonganti@3 91 </param>
kkonganti@3 92 <param name="fq_suffix" value=".fastq.gz"/>
kkonganti@3 93 <output name="multiqc_report" file="multiqc_report.html" ftype="html" compare="sim_size"/>
kkonganti@3 94 <output name="assembled_mags" file="FAL11127.assembly_filtered.contigs.fasta" ftype="fasta" compare="sim_size"/>
kkonganti@3 95 </test>
kkonganti@3 96 </tests>
kkonganti@0 97 <help><![CDATA[
kkonganti@0 98
kkonganti@0 99 .. class:: infomark
kkonganti@0 100
kkonganti@0 101 **Purpose**
kkonganti@0 102
kkonganti@0 103 Centriflaken suite of automated data analysis pipelines based on Nextflow DSL2 developed at CFSAN, FDA. Thess piepelines allow rapid
kkonganti@0 104 and effective construction of metagenomic assembled genomes (MAGs) to enable bacterial source-tracking. It is based on methods described in our
kkonganti@0 105 previous publication (https://doi.org/10.1371/journal.pone.0245172).
kkonganti@0 106 ----
kkonganti@0 107
kkonganti@0 108 .. class:: infomark
kkonganti@0 109
kkonganti@0 110 **Testing and Validation**
kkonganti@0 111
kkonganti@0 112 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
kkonganti@0 113 in silico-based analysis (i.e., virulence gene finding). Additionally, AMR gene finding analysis is also included in Centriflaken and performed on MAGs
kkonganti@0 114 of interest. The final summary plots and tables can be downloaded from the provided MultiQC HTML report generated as part of the pipeline.
kkonganti@0 115 The Centriflaken pipeline was validated with data from our previously published method (Maguire et al, 2021) and was able to replicate the detection
kkonganti@0 116 and classification of STECs for each sample. We tested the pipeline with nanopore data obtained from 21 additional enriched samples from
kkonganti@0 117 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@0 118 done on the command line on the CFSAN Raven2 HPC Cluster.
kkonganti@0 119
kkonganti@0 120
kkonganti@0 121 ----
kkonganti@0 122
kkonganti@0 123 .. class:: infomark
kkonganti@0 124
kkonganti@0 125 **Outputs**
kkonganti@0 126
kkonganti@0 127 The main output files are:
kkonganti@0 128
kkonganti@0 129 ::
kkonganti@0 130
kkonganti@0 131 - MultiQC Report: Contains a brief summary report including any serotyping and AMR result tables.
kkonganti@0 132 - Final assembly: contains contigs and possibly scaffolds (see below).
kkonganti@0 133
kkonganti@0 134 ]]></help>
kkonganti@0 135 <citations>
kkonganti@0 136 <citation type="bibtex">
kkonganti@0 137 @misc{gitlabCPIPES,
kkonganti@0 138 author = {Konganti, Kranti},
kkonganti@0 139 year = {2022},
kkonganti@0 140 title = {CPIPES - Centriflaken},
kkonganti@0 141 publisher = {GitLab},
kkonganti@0 142 journal = {GitLab repository},
kkonganti@0 143 url = {https://cfsan-git.fda.gov/Kranti.Konganti/cpipes}}
kkonganti@0 144 </citation>
kkonganti@0 145 </citations>
kkonganti@0 146 </tool>