Mercurial > repos > kkonganti > cfsan_centriflaken

annotate cfsan_centriflaken.xml @ 63:d1efe888e1ed

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload"
author kkonganti
date Wed, 13 Jul 2022 13:05:18 -0400
parents 770ce74dfc47
children ef8d8b8f41cc
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@50 9 mkdir -p cpipes-input || exit 1;
kkonganti@58 10 pwd_path=\$(pwd);
kkonganti@58 11 #import os
kkonganti@58 12 #if (str($input_read_type_cond.input_read_type) == "single_long"):
kkonganti@58 13 #for $key in $input_read_type_cond.input.keys()
kkonganti@58 14 ln -sf '$input_read_type_cond.input[$key]' './cpipes-input/$key';
kkonganti@58 15 #end for
kkonganti@63 16 #elif (str($input_read_type_cond.input_read_type) == "paired"):
kkonganti@58 17 #for $key in $input_read_type_cond.input_pair.keys()
kkonganti@58 18 #set $read_R1 = os.path.basename($input_read_type_cond.input_pair[$key]['forward'])
kkonganti@58 19 #set $read_R2 = os.path.basename($input_read_type_cond.input_pair[$key]['reverse'])
kkonganti@58 20 ln -sf '$input_read_type_cond.input_pair[$key]['forward']' './cpipes-input/$read_R1';
kkonganti@58 21 ln -sf '$input_read_type_cond.input_pair[$key]['reverse']' './cpipes-input/$read_R2';
kkonganti@58 22 #end for
kkonganti@60 23 #end if
kkonganti@0 24 $__tool_directory__/0.2.1/cpipes
kkonganti@61 25 --pipeline $input_read_type_cond.pipeline_cond.pipeline
kkonganti@58 26 #if ($input_read_type_cond.pipeline_cond.pipeline == "centriflaken"):
kkonganti@4 27 --fq_single_end true
kkonganti@33 28 --flye_genome_size '${genome_size}'
kkonganti@58 29 #if ($input_read_type_cond.pipeline_cond.long_read_platform == "nanopore_corr"):
kkonganti@33 30 --flye_nano_corr true --flye_nano_raw false
kkonganti@58 31 #elif ($input_read_type_cond.pipeline_cond.long_read_platform == "nanopore_hq"):
kkonganti@33 32 --flye_nano_hq true --flye_nano_raw false
kkonganti@58 33 #elif ($input_read_type_cond.pipeline_cond.long_read_platform == "pacbio_raw"):
kkonganti@33 34 --flye_pacbio_raw true --flye_nano_raw false
kkonganti@58 35 #elif ($input_read_type_cond.pipeline_cond.long_read_platform == "pacbio_corr"):
kkonganti@33 36 --flye_pacbio_corr true --flye_nano_raw false
kkonganti@58 37 #elif ($input_read_type_cond.pipeline_cond.long_read_platform == "pacbio_hifi"):
kkonganti@33 38 --flye_pacbio_hifi true --flye_nano_raw false
kkonganti@33 39 #end if
kkonganti@58 40 #elif ($input_read_type_cond.pipeline_cond.pipeline == "centriflaken_hy"):
kkonganti@58 41 #if (str($input_read_cond.input_read_type) == "single_long"):
kkonganti@4 42 --fq_single_end true
kkonganti@58 43 #elif (str($input_read_cond.input_read_type) == "paired"):
kkonganti@58 44 --fq_single_end false --fq2_suffix '${input_read_cond.fq2_suffix}'
kkonganti@4 45 #end if
kkonganti@0 46 #end if
kkonganti@0 47 --input \${pwd_path}/cpipes-input
kkonganti@0 48 --output \${pwd_path}/cpipes-output
kkonganti@58 49 --fq_suffix '${input_read_cond.fq_suffix}'
kkonganti@41 50 #if ($fq_filter_by_len != ""):
kkonganti@39 51 --fq_filter_by_len $fq_filter_by_len
kkonganti@39 52 #end if
kkonganti@0 53 --fq_filename_delim '${fq_filename_delim}'
kkonganti@0 54 --fq_filename_delim_idx $fq_filename_delim_idx
kkonganti@0 55 --centrifuge_extract_bug '${centrifuge_extract_bug}'
kkonganti@47 56 -profile kondagac;
kkonganti@62 57 mv './cpipes-output/${input_read_type_cond.pipeline_cond.pipeline}-multiqc/multiqc_report.html' './multiqc_report.html' || exit 1;
kkonganti@62 58 mv './cpipes-output/${input_read_type_cond.pipeline_cond.pipeline}-results/kraken2_extract_contigs' kraken2_extract_contigs || exit 1;
kkonganti@58 59 rm -rf ./cpipes-output || exit 1;
kkonganti@58 60 rm -rf ./work || exit 1
kkonganti@0 61 ]]></command>
kkonganti@0 62 <inputs>
kkonganti@58 63 <conditional name="input_read_type_cond">
kkonganti@58 64 <param name="input_read_type" type="select" label="Select the read collection type">
kkonganti@61 65 <option value="single_long" selected="true">Unpaired reads (i.e. Single-End short reads or Long reads)</option>
kkonganti@58 66 <option value="paired">Paired-End reads</option>
kkonganti@58 67 </param>
kkonganti@58 68 <when value="single_long">
kkonganti@58 69 <param name="input" type="data_collection" collection_type="list" format="fastq,fastq.gz,fastqsanger.gz,fastqsanger"
kkonganti@61 70 label="Dataset list of unpaired short reads or long reads" />
kkonganti@58 71 <conditional name="pipeline_cond">
kkonganti@58 72 <param name="pipeline" type="select" label="CPIPES Workflow name"
kkonganti@58 73 help="centriflaken: for long reads (Nanopore or PacBio). centriflaken_hy: for short reads (paired or unpaired). Default: centriflaken">
kkonganti@58 74 <option value="centriflaken" selected="true">centriflaken</option>
kkonganti@58 75 <option value="centriflaken_hy">centriflaken_hy</option>
kkonganti@58 76 </param>
kkonganti@58 77 <when value="centriflaken">
kkonganti@58 78 <param name="long_read_platform" type="select" label="Mention long read sequencing platform and type">
kkonganti@58 79 <option value="nanopore_raw" selected="true">Nanopore raw reads, pre-Guppy5 (&lt;20% error)</option>
kkonganti@58 80 <option value="nanopore_corr">Nanopore reads that were corrected with other methods (&lt;3% error)</option>
kkonganti@58 81 <option value="nanopore_hq">Nanopore high-quality reads, Guppy5+ SUP or Q20 (5% error)</option>
kkonganti@58 82 <option value="pacbio_raw">PacBio regular CLR reads (&lt;20% error)</option>
kkonganti@58 83 <option value="pacbio_corr">PacBio reads that were corrected with other methods (&lt;3% error)</option>
kkonganti@58 84 <option value="pacbio_hifi">PacBio HiFi reads (&lt;1% error)</option>
kkonganti@58 85 </param>
kkonganti@58 86 </when>
kkonganti@58 87 <when value="centriflaken_hy">
kkonganti@58 88 <param name="long_read_platform" value="N/A" type="text" optional="true" label="Mention long read sequencing platform and type"
kkonganti@58 89 help="THIS OPTION IS IGNORED IF THE INPUT READS ARE SHORT READS."/>
kkonganti@58 90 </when>
kkonganti@58 91 </conditional>
kkonganti@58 92 <param name="fq_suffix" value=".fastq.gz" type="text" label="Suffix of the R1 FASTQ or Unpaired FASTQ"/>
kkonganti@58 93 </when>
kkonganti@58 94 <when value="paired">
kkonganti@58 95 <param name="input_pair" type="data_collection" collection_type="list:paired" format="fastq,fastq.gz,fastqsanger.gz,fastqsanger"
kkonganti@58 96 label="List of Dataset pairs" />
kkonganti@58 97 <param name="fq_suffix" value=".fastq.gz" type="text" label="Suffix of the R1 FASTQ or Unpaired FASTQ"/>
kkonganti@58 98 <param name="fq2_suffix" value="_R2_001.fastq.gz" type="text" label="Suffix of the R2 FASTQ"/>
kkonganti@58 99 </when>
kkonganti@58 100 </conditional>
kkonganti@44 101 <param name="fq_filter_by_len" optional="true" value="" type="integer" label="Enter minimum read length to retain before starting the analysis"
kkonganti@48 102 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@40 103 <param name="fq_filename_delim" type="text" value="_" label="File name delimitor by which samples are grouped together (--fq_filename_delim)"
kkonganti@48 104 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@6 105 <param name="fq_filename_delim_idx" type="integer" value="1" label="File name delimitor index (--fq_filename_delim_idx)" />
kkonganti@0 106 <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@0 107 <param name="genome_size" type="text" optional="true" value="5.5m" label="Estimated genome size" help="For example, 5m or 2.6g.">
kkonganti@0 108 <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]?$</validator>
kkonganti@0 109 </param>
kkonganti@47 110 <!-- <param name="runtime_profile" type="select" label="Run time profile">
kkonganti@31 111 <option value="kondagac" selected="true">conda</option>
kkonganti@12 112 <option value="cingularitygac">singularity</option>
kkonganti@47 113 </param> -->
kkonganti@0 114 </inputs>
kkonganti@0 115 <outputs>
kkonganti@59 116 <data name="multiqc_report" format="html" label="${input_read_type_cond.pipeline_cond.pipeline}: MultiQC Report on ${on_string}" from_work_dir="multiqc_report.html"/>
kkonganti@59 117 <collection name="assembled_mags" type="list" label="${input_read_type_cond.pipeline_cond.pipeline}: Assembled MAGs on ${on_string}">
kkonganti@24 118 <discover_datasets pattern="(?P&lt;name&gt;.*)\.assembly_filtered_contigs\.fasta" ext="fasta" directory="kraken2_extract_contigs"/>
kkonganti@18 119 </collection>
kkonganti@0 120 </outputs>
kkonganti@3 121 <tests>
kkonganti@3 122 <!--Test 01: long reads-->
kkonganti@3 123 <test expect_num_outputs="2">
kkonganti@4 124 <param name="input">
kkonganti@3 125 <collection type="list">
kkonganti@4 126 <element name="FAL11127.fastq.gz" value="FAL11127.fastq.gz" />
kkonganti@4 127 <element name="FAL11341.fastq.gz" value="FAL11341.fastq.gz" />
kkonganti@4 128 <element name="FAL11342.fastq.gz" value="FAL11342.fastq.gz" />
kkonganti@3 129 </collection>
kkonganti@3 130 </param>
kkonganti@3 131 <param name="fq_suffix" value=".fastq.gz"/>
kkonganti@3 132 <output name="multiqc_report" file="multiqc_report.html" ftype="html" compare="sim_size"/>
kkonganti@18 133 <!-- <output name="assembled_mags" file="FAL11127.assembly_filtered.contigs.fasta" ftype="fasta" compare="sim_size"/> -->
kkonganti@3 134 </test>
kkonganti@3 135 </tests>
kkonganti@0 136 <help><![CDATA[
kkonganti@0 137
kkonganti@0 138 .. class:: infomark
kkonganti@0 139
kkonganti@0 140 **Purpose**
kkonganti@0 141
kkonganti@50 142 Centriflaken suite of automated data analysis pipelines are based on Nextflow DSL2 developed at CFSAN, FDA. These pipelines allow rapid
kkonganti@0 143 and effective construction of metagenomic assembled genomes (MAGs) to enable bacterial source-tracking. It is based on methods described in our
kkonganti@53 144 previous publication (Maguire *et al*, 2021. doi: https://doi.org/10.1371/journal.pone.0245172).
kkonganti@14 145
kkonganti@0 146 ----
kkonganti@0 147
kkonganti@0 148 .. class:: infomark
kkonganti@0 149
kkonganti@0 150 **Testing and Validation**
kkonganti@0 151
kkonganti@47 152 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@0 153 in silico-based analysis (i.e., virulence gene finding). Additionally, AMR gene finding analysis is also included in Centriflaken and performed on MAGs
kkonganti@0 154 of interest. The final summary plots and tables can be downloaded from the provided MultiQC HTML report generated as part of the pipeline.
kkonganti@53 155 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@47 156 and classification of STECs for each sample. We tested the pipeline with Nanopore data obtained from 21 additional enriched samples from
kkonganti@0 157 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@0 158 done on the command line on the CFSAN Raven2 HPC Cluster.
kkonganti@0 159
kkonganti@0 160
kkonganti@0 161 ----
kkonganti@0 162
kkonganti@0 163 .. class:: infomark
kkonganti@0 164
kkonganti@0 165 **Outputs**
kkonganti@0 166
kkonganti@0 167 The main output files are:
kkonganti@0 168
kkonganti@0 169 ::
kkonganti@0 170
kkonganti@55 171 - MultiQC Report: Contains a brief summary report including any serotyping and AMR result tables.
kkonganti@56 172 Please note that due to MultiQC customizations, the preview (eye icon) will not
kkonganti@56 173 work within Galaxy for the MultiQC report. Please download the file by clicking
kkonganti@57 174 on the floppy icon and view it in your browser on your local desktop/workstation.
kkonganti@27 175 - Final assembly: contains contigs and possibly scaffolds.
kkonganti@0 176
kkonganti@0 177 ]]></help>
kkonganti@0 178 <citations>
kkonganti@0 179 <citation type="bibtex">
kkonganti@0 180 @misc{gitlabCPIPES,
kkonganti@0 181 author = {Konganti, Kranti},
kkonganti@0 182 year = {2022},
kkonganti@0 183 title = {CPIPES - Centriflaken},
kkonganti@0 184 publisher = {GitLab},
kkonganti@0 185 journal = {GitLab repository},
kkonganti@0 186 url = {https://cfsan-git.fda.gov/Kranti.Konganti/cpipes}}
kkonganti@0 187 </citation>
kkonganti@0 188 </citations>
kkonganti@0 189 </tool>