Mercurial > repos > kkonganti > cfsan_bettercallsal

annotate cfsan_bettercallsal.xml @ 21:4ce0e079377d tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload
author kkonganti
date Mon, 15 Jul 2024 12:01:00 -0400
parents 4b304d77bbfb
children
rev   line source
kkonganti@17 1 <tool id="cfsan_bettercallsal" name="bettercallsal" version="0.7.0+galaxy23.1">
kkonganti@1 2 <description>An automated workflow to assign Salmonella serotype based on NCBI Pathogen Detection Project for Salmonella.</description>
kkonganti@0 3 <requirements>
kkonganti@21 4 <container type="docker">quay.io/biocontainers/nextflow:24.04.3--hdfd78af_0</container>
kkonganti@17 5 </requirements>
kkonganti@0 6 <version_command>nextflow -version</version_command>
kkonganti@0 7 <command detect_errors="exit_code"><![CDATA[
kkonganti@17 8 input_path=\$(pwd)"/cpipes-input";
kkonganti@17 9 mkdir -p "\${input_path}" || exit 1;
kkonganti@0 10 #import re
kkonganti@0 11 #if (str($input_read_type_cond.input_read_type) == "single_long"):
kkonganti@0 12 #for _, $unpaired in enumerate($input_read_type_cond.input):
kkonganti@0 13 #set read1 = str($unpaired.name)
kkonganti@0 14 #if not str($unpaired.name).endswith(('.fastq', '.fastq.gz')):
kkonganti@0 15 #set read1_ext = re.sub('fastqsanger', 'fastq', str($unpaired.ext))
kkonganti@0 16 #set read1 = str($unpaired.name) + str('.') + $read1_ext
kkonganti@0 17 #end if
kkonganti@17 18 ln -sf '$unpaired' "\${input_path}/$read1";
kkonganti@0 19 #end for
kkonganti@0 20 #elif (str($input_read_type_cond.input_read_type) == "paired"):
kkonganti@0 21 #for _, $pair in enumerate($input_read_type_cond.input_pair)
kkonganti@0 22 #set read_R1 = re.sub('\:forward', '_forward', str($pair.forward.name))
kkonganti@0 23 #set read_R2 = re.sub('\:reverse', '_reverse', str($pair.reverse.name))
kkonganti@0 24 #set read_R1_ext = re.sub('fastqsanger', 'fastq', str($pair.forward.ext))
kkonganti@0 25 #set read_R2_ext = re.sub('fastqsanger', 'fastq', str($pair.reverse.ext))
kkonganti@0 26 #if not str($pair.forward.name).endswith(('.fastq', '.fastq.gz')):
kkonganti@0 27 #set read_R1 = $read_R1 + str('.') + $read_R1_ext
kkonganti@0 28 #end if
kkonganti@0 29 #if not str($pair.reverse.name).endswith(('.fastq', '.fastq.gz')):
kkonganti@0 30 #set read_R2 = $read_R2 + str('.') + $read_R2_ext
kkonganti@0 31 #end if
kkonganti@17 32 ln -sf '$pair.forward' "\${input_path}/$read_R1";
kkonganti@17 33 ln -sf '$pair.reverse' "\${input_path}/$read_R2";
kkonganti@0 34 #end for
kkonganti@0 35 #end if
kkonganti@17 36 $__tool_directory__/0.7.0/cpipes
kkonganti@2 37 --pipeline bettercallsal
kkonganti@17 38 --input \${input_path}
kkonganti@19 39 --output cpipes-output
kkonganti@0 40 --fq_suffix '${input_read_type_cond.fq_suffix}'
kkonganti@1 41 #if (str($input_read_type_cond.input_read_type) == "single_long"):
kkonganti@1 42 --fq_single_end true
kkonganti@1 43 #elif (str($input_read_type_cond.input_read_type) == "paired"):
kkonganti@1 44 --fq_single_end false --fq2_suffix '${input_read_type_cond.fq2_suffix}'
kkonganti@0 45 #end if
kkonganti@1 46 --tuspy_n $tuspy_n
kkonganti@3 47 #if ($sourmash_cond.run == "true"):
kkonganti@4 48 --sfhpy_fcv $sourmash_cond.sfhpy_fcv
kkonganti@1 49 #end if
kkonganti@17 50 #if ($bcs_thresholds != 'relax'):
kkonganti@17 51 --kmaalign_ID $kma_id
kkonganti@17 52 #end if
kkonganti@17 53 #if ($sourmash_cond.run == "true"):
kkonganti@17 54 --sfhpy_fcv $sourmash_cond.sfhpy_fcv
kkonganti@17 55 #end if
kkonganti@11 56 --bcs_db_mode $bcs_db_mode
kkonganti@1 57 --bcs_thresholds $bcs_thresholds
kkonganti@0 58 --fq_filename_delim '${fq_filename_delim}'
kkonganti@0 59 --fq_filename_delim_idx $fq_filename_delim_idx
kkonganti@17 60 -profile gxkubernetes;
kkonganti@17 61 mv './cpipes-output/bettercallsal-multiqc/multiqc_report.html' './multiqc_report.html' || exit 1;
kkonganti@19 62 rm -rf ./cpipes-output || exit 1;
kkonganti@19 63 rm -rf ./work || exit 1;
kkonganti@0 64 ]]></command>
kkonganti@0 65 <inputs>
kkonganti@0 66 <conditional name="input_read_type_cond">
kkonganti@0 67 <param name="input_read_type" type="select" label="Select the read collection type">
kkonganti@1 68 <option value="single_long" selected="true">Single-End short reads</option>
kkonganti@1 69 <option value="paired">Paired-End short reads</option>
kkonganti@0 70 </param>
kkonganti@0 71 <when value="single_long">
kkonganti@0 72 <param name="input" type="data_collection" collection_type="list" format="fastq,fastq.gz"
kkonganti@0 73 label="Dataset list of unpaired short reads or long reads" />
kkonganti@1 74 <param name="fq_suffix" value=".fastq.gz" type="text" label="Suffix of the Single-End FASTQ"/>
kkonganti@0 75 </when>
kkonganti@0 76 <when value="paired">
kkonganti@0 77 <param name="input_pair" type="data_collection" collection_type="list:paired" format="fastq,fastq.gz" label="List of Dataset pairs" />
kkonganti@5 78 <param name="fq_suffix" value="_R1_001.fastq.gz" type="text" label="Suffix of the R1 FASTQ"
kkonganti@5 79 help="For any data sets downloaded from NCBI into Galaxy, change this to _forward.fastq.gz suffix."/>
kkonganti@5 80 <param name="fq2_suffix" value="_R2_001.fastq.gz" type="text" label="Suffix of the R2 FASTQ"
kkonganti@6 81 help="For any data sets downloaded from NCBI into Galaxy, change this to _reverse.fastq.gz suffix."/>
kkonganti@0 82 </when>
kkonganti@0 83 </conditional>
kkonganti@11 84 <param name="bcs_db_mode" type="select" label="Select the database mode with bettercallsal"
kkonganti@11 85 help="Refer to `Database generation` section in our manuscript: https://doi.org/10.3389/fmicb.2023.1200983">
kkonganti@11 86 <option value="snp" selected="true">per_snp_cluster</option>
kkonganti@11 87 <option value="comp">per_computed_type</option>
kkonganti@11 88 </param>
kkonganti@2 89 <param name="tuspy_n" optional="true" value="10" type="integer" label="Enter the number of top unique serotypes to retain after initial MASH screen step"
kkonganti@1 90 help="The default value of 10 is suitable for almost all scenarios."/>
kkonganti@2 91 <param name="bcs_thresholds" type="select" label="Enter the type of base quality thresholds to be set with bettercallsal"
kkonganti@1 92 help="The default value sets strictest thresholds that tends to filter out most of the false positive hits.">
kkonganti@1 93 <option value="strict" selected="true">strict</option>
kkonganti@1 94 <option value="relax">relax</option>
kkonganti@1 95 </param>
kkonganti@17 96 <param name="kma_id" optional="true" value="10.0" type="text" label="Enter the %ID threshold for KMA alignments of samples against genomes"
kkonganti@17 97 help="The default value of 10% works well for enrichment samples tested within FDA. The 'relax' preset for base quality thresholds automatically sets this value to 5%."/>
kkonganti@1 98 <conditional name="sourmash_cond">
kkonganti@1 99 <param name="run" type="select" label="Run sourmash"
kkonganti@2 100 help="Should sourmash be used for additional genome fraction filtering">
kkonganti@1 101 <option value="true" selected="true">yes</option>
kkonganti@1 102 <option value="false">no</option>
kkonganti@1 103 </param>
kkonganti@1 104 <when value="true">
kkonganti@2 105 <param name="sfhpy_fcv" type="text" value="0.1" label="Enter the minimum coverage match with sourmash before a serotype hit is considered for further processing"
kkonganti@1 106 help="The default value is set at 10% coverage threshold."/>
kkonganti@1 107 </when>
kkonganti@1 108 <when value="false">
kkonganti@2 109 <param name="sfhpy_fcv" type="select" label="Enter the minimum coverage match with sourmash before a serotype hit is considered for further processing"
kkonganti@8 110 help="THIS OPTION IS IGNORED IF SOURMASH TOOL IS NOT RUN.">
kkonganti@1 111 <option value="NA" selected="true">N/A</option>
kkonganti@1 112 </param>
kkonganti@1 113 </when>
kkonganti@1 114 </conditional>
kkonganti@0 115 <param name="fq_filename_delim" type="text" value="_" label="File name delimitor by which samples are grouped together (--fq_filename_delim)"
kkonganti@0 116 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@0 117 <param name="fq_filename_delim_idx" type="integer" value="1" label="File name delimitor index (--fq_filename_delim_idx)" />
kkonganti@0 118 <!-- <param name="runtime_profile" type="select" label="Run time profile">
kkonganti@0 119 <option value="kondagac" selected="true">conda</option>
kkonganti@0 120 <option value="cingularitygac">singularity</option>
kkonganti@0 121 </param> -->
kkonganti@0 122 </inputs>
kkonganti@0 123 <outputs>
kkonganti@2 124 <data name="multiqc_report" format="html" label="bettercallsal: MultiQC Report on ${on_string}" from_work_dir="multiqc_report.html"/>
kkonganti@0 125 </outputs>
kkonganti@0 126 <tests>
kkonganti@0 127 <!--Test 01: long reads-->
kkonganti@0 128 <test expect_num_outputs="2">
kkonganti@0 129 <param name="input">
kkonganti@0 130 <collection type="list">
kkonganti@0 131 <element name="FAL11127.fastq.gz" value="FAL11127.fastq.gz" />
kkonganti@0 132 <element name="FAL11341.fastq.gz" value="FAL11341.fastq.gz" />
kkonganti@0 133 <element name="FAL11342.fastq.gz" value="FAL11342.fastq.gz" />
kkonganti@0 134 </collection>
kkonganti@0 135 </param>
kkonganti@0 136 <param name="fq_suffix" value=".fastq.gz"/>
kkonganti@0 137 <output name="multiqc_report" file="multiqc_report.html" ftype="html" compare="sim_size"/>
kkonganti@0 138 <!-- <output name="assembled_mags" file="FAL11127.assembly_filtered.contigs.fasta" ftype="fasta" compare="sim_size"/> -->
kkonganti@0 139 </test>
kkonganti@0 140 </tests>
kkonganti@0 141 <help><![CDATA[
kkonganti@0 142
kkonganti@0 143 .. class:: infomark
kkonganti@0 144
kkonganti@0 145 **Purpose**
kkonganti@0 146
kkonganti@1 147 bettercallsal is an automated workflow to assign Salmonella serotype based on NCBI Pathogen Detection Project for Salmonella.
kkonganti@1 148 It uses MASH to reduce the search space followed by additional genome filtering with sourmash. It then performs genome based
kkonganti@1 149 alignment with kma followed by count generation using salmon. This workflow can be used to analyze shotgun metagenomics
kkonganti@1 150 datasets, quasi-metagenomic datasets (enriched for Salmonella) and target enriched datasets (enriched with molecular baits specific for Salmonella)
kkonganti@1 151 and is especially useful in a case where a sample is of multi-serovar mixture.
kkonganti@1 152
kkonganti@1 153 It is written in Nextflow and is part of the modular data analysis pipelines (CFSAN PIPELINES or CPIPES for short) at CFSAN.
kkonganti@1 154
kkonganti@0 155
kkonganti@0 156 ----
kkonganti@0 157
kkonganti@0 158 .. class:: infomark
kkonganti@0 159
kkonganti@0 160 **Testing and Validation**
kkonganti@0 161
kkonganti@1 162 The CPIPES - bettercallsal Nextflow pipeline has been wrapped to make it work in Galaxy. It takes in either paired or unpaired short reads list as an input
kkonganti@17 163 and generates a MultiQC report in the final step. The pipeline has been tested on 2x300 bp MiSeq and 2x150 bp NextSeq simulated reads and has been shown to call multiple
kkonganti@17 164 Salmonella serotypes with up to ~95% accuracy. The pipeline has also been tested on metagenomics data sets from Peach and Papaya outbreaks as discussed in
kkonganti@17 165 our publication (https://www.frontiersin.org/articles/10.3389/fmicb.2023.1200983/full). All the original testing and validation was
kkonganti@17 166 done on the command line on the CFSAN Raven2 HPC Cluster.
kkonganti@0 167
kkonganti@0 168
kkonganti@0 169 ----
kkonganti@0 170
kkonganti@0 171 .. class:: infomark
kkonganti@0 172
kkonganti@0 173 **Outputs**
kkonganti@0 174
kkonganti@7 175 The main output file is a:
kkonganti@0 176
kkonganti@0 177 ::
kkonganti@0 178
kkonganti@0 179 - MultiQC Report: Contains a brief summary report including any serotyping and AMR result tables.
kkonganti@0 180 Please note that due to MultiQC customizations, the preview (eye icon) will not
kkonganti@0 181 work within Galaxy for the MultiQC report. Please download the file by clicking
kkonganti@0 182 on the floppy icon and view it in your browser on your local desktop/workstation.
kkonganti@1 183 You can export the tables and plots from the downloaded MultiQC report.
kkonganti@0 184
kkonganti@0 185 ]]></help>
kkonganti@0 186 <citations>
kkonganti@0 187 <citation type="bibtex">
kkonganti@11 188 @article{bettercallsal,
kkonganti@0 189 author = {Konganti, Kranti},
kkonganti@1 190 year = {2023},
kkonganti@11 191 month = {August},
kkonganti@1 192 title = {bettercallsal: better calling of Salmonella serotypes from enrichment cultures using shotgun metagenomic profiling and its application in an outbreak setting},
kkonganti@11 193 journal = {Frontiers in Microbiology},
kkonganti@11 194 doi = {10.3389/fmicb.2023.1200983},
kkonganti@11 195 url = {https://www.frontiersin.org/articles/10.3389/fmicb.2023.1200983/full}}
kkonganti@0 196 </citation>
kkonganti@0 197 </citations>
kkonganti@0 198 </tool>