Mercurial > repos > kkonganti > cfsan_bettercallsal
diff cfsan_bettercallsal.xml @ 1:365849f031fd
"planemo upload"
| author | kkonganti |
|---|---|
| date | Mon, 05 Jun 2023 18:48:51 -0400 |
| parents | a4b1ee4b68b1 |
| children | 4678c2cd1c9e |
line wrap: on
line diff
--- a/cfsan_bettercallsal.xml Mon Jun 05 16:17:23 2023 -0400 +++ b/cfsan_bettercallsal.xml Mon Jun 05 18:48:51 2023 -0400 @@ -1,7 +1,8 @@ -<tool id="cfsan_centriflaken" name="Centriflaken" version="0.2.0+galaxy0"> - <description>An automated pipeline to generate a MAG of interest (E.coli or Salmonella) and perform serotyping.</description> +<tool id="cfsan_bettercallsal" name="bettercallsal" version="0.2.0+galaxy0"> + <description>An automated workflow to assign Salmonella serotype based on NCBI Pathogen Detection Project for Salmonella.</description> <requirements> - <requirement type="package" version="22.04">nextflow</requirement> + <requirement type="package" version="22.10">nextflow</requirement> + <requirement type="package" version="1.0.0">micromamba</requirement> <requirement type="package">graphviz</requirement> </requirements> <version_command>nextflow -version</version_command> @@ -34,122 +35,72 @@ ln -sf '$pair.reverse' './cpipes-input/$read_R2'; #end for #end if - $__tool_directory__/0.4.0/cpipes + $__tool_directory__/0.5.0/cpipes --pipeline $input_read_type_cond.pipeline_cond.pipeline - #if ($input_read_type_cond.pipeline_cond.pipeline == "centriflaken"): - --fq_single_end true - --flye_genome_size '${genome_size}' - #if ($input_read_type_cond.pipeline_cond.long_read_platform == "nanopore_corr"): - --flye_nano_corr true --flye_nano_raw false - #elif ($input_read_type_cond.pipeline_cond.long_read_platform == "nanopore_hq"): - --flye_nano_hq true --flye_nano_raw false - #elif ($input_read_type_cond.pipeline_cond.long_read_platform == "pacbio_raw"): - --flye_pacbio_raw true --flye_nano_raw false - #elif ($input_read_type_cond.pipeline_cond.long_read_platform == "pacbio_corr"): - --flye_pacbio_corr true --flye_nano_raw false - #elif ($input_read_type_cond.pipeline_cond.long_read_platform == "pacbio_hifi"): - --flye_pacbio_hifi true --flye_nano_raw false - #end if - #elif ($input_read_type_cond.pipeline_cond.pipeline == "centriflaken_hy"): - #if (str($input_read_type_cond.input_read_type) == "single_long"): - --fq_single_end true - #elif (str($input_read_type_cond.input_read_type) == "paired"): - --fq_single_end false --fq2_suffix '${input_read_type_cond.fq2_suffix}' - #end if - #end if - --input \${pwd_path}/cpipes-input + --input \${pwd_path}/cpipes-input --output \${pwd_path}/cpipes-output --fq_suffix '${input_read_type_cond.fq_suffix}' - #if ($fq_filter_by_len != ""): - --fq_filter_by_len $fq_filter_by_len + #if (str($input_read_type_cond.input_read_type) == "single_long"): + --fq_single_end true + #elif (str($input_read_type_cond.input_read_type) == "paired"): + --fq_single_end false --fq2_suffix '${input_read_type_cond.fq2_suffix}' #end if + --tuspy_n $tuspy_n + if ($sourmash_cond.run == "true"): + --sfhpy_fcv $sourmash_run.sfhpy_fcv + #end if + --bcs_thresholds $bcs_thresholds --fq_filename_delim '${fq_filename_delim}' --fq_filename_delim_idx $fq_filename_delim_idx - --centrifuge_extract_bug '${centrifuge_extract_bug}' - #if (str($input_read_type_cond.pipeline_cond.rm_dup_seqs) == "true"): - --seqkit_rmdup_run true - #end if -profile kondagac; mv './cpipes-output/${input_read_type_cond.pipeline_cond.pipeline}-multiqc/multiqc_report.html' './multiqc_report.html' > /dev/null 2>&1 || exit 1; - mv './cpipes-output/${input_read_type_cond.pipeline_cond.pipeline}-results/kraken2_extract_contigs' kraken2_extract_contigs > /dev/null 2>&1 || exit 1; rm -rf ./cpipes-output > /dev/null 2>&1 || exit 1; rm -rf ./work > /dev/null 2>&1 || exit 1 ]]></command> <inputs> <conditional name="input_read_type_cond"> <param name="input_read_type" type="select" label="Select the read collection type"> - <option value="single_long" selected="true">Unpaired reads (i.e. Single-End short reads or Long reads)</option> - <option value="paired">Paired-End reads</option> + <option value="single_long" selected="true">Single-End short reads</option> + <option value="paired">Paired-End short reads</option> </param> <when value="single_long"> <param name="input" type="data_collection" collection_type="list" format="fastq,fastq.gz" label="Dataset list of unpaired short reads or long reads" /> - <conditional name="pipeline_cond"> - <param name="pipeline" type="select" label="CPIPES Workflow name" - help="centriflaken: for long reads (Nanopore or PacBio). centriflaken_hy: for unpaired short reads. Default: centriflaken"> - <option value="centriflaken" selected="true">centriflaken</option> - <option value="centriflaken_hy">centriflaken_hy</option> - </param> - <when value="centriflaken"> - <param name="long_read_platform" type="select" label="Mention long read sequencing platform and type"> - <option value="nanopore_raw" selected="true">Nanopore raw reads, pre-Guppy5 (<20% error)</option> - <option value="nanopore_corr">Nanopore reads that were corrected with other methods (<3% error)</option> - <option value="nanopore_hq">Nanopore high-quality reads, Guppy5+ SUP or Q20 (5% error)</option> - <option value="pacbio_raw">PacBio regular CLR reads (<20% error)</option> - <option value="pacbio_corr">PacBio reads that were corrected with other methods (<3% error)</option> - <option value="pacbio_hifi">PacBio HiFi reads (<1% error)</option> - </param> - <param name="rm_dup_seqs" type="select" label="Remove duplicate sequences" - help="THIS OPTION IS IGNORED IF THE INPUT READS ARE LONG READS."> - <option value="NA" selected="true">N/A</option> - </param> - </when> - <when value="centriflaken_hy"> - <param name="long_read_platform" type="select" label="Mention long read sequencing platform and type" - help="THIS OPTION IS IGNORED IF THE INPUT READS ARE SHORT READS."> - <option value="NA" selected="true">N/A</option> - </param> - <param name="rm_dup_seqs" type="select" label="Remove duplicate sequences" - help="Selecting yes will compare sequence content and remove identical sequences i.e. only the first occured sequence record will be saved."> - <option value="true">yes</option> - <option value="false" selected="true">no</option> - </param> - </when> - </conditional> - <param name="fq_suffix" value=".fastq.gz" type="text" label="Suffix of the Unpaired FASTQ"/> + <param name="fq_suffix" value=".fastq.gz" type="text" label="Suffix of the Single-End FASTQ"/> </when> <when value="paired"> <param name="input_pair" type="data_collection" collection_type="list:paired" format="fastq,fastq.gz" label="List of Dataset pairs" /> - <conditional name="pipeline_cond"> - <param name="pipeline" type="select" label="CPIPES Workflow name" - help="Auto selected centriflaken_hy workflow for paired-end short reads."> - <option value="centriflaken_hy" selected="true">centriflaken_hy</option> - </param> - <when value="centriflaken_hy"> - <param name="long_read_platform" type="select" label="Mention long read sequencing platform and type" - help="THIS OPTION IS IGNORED IF THE INPUT READS ARE SHORT READS."> - <option value="NA" selected="true">N/A</option> - </param> - <param name="rm_dup_seqs" type="select" label="Remove duplicate sequences" - help="Selecting yes will compare sequence content and remove identical sequences i.e. only the first occured sequence record will be saved."> - <option value="true">yes</option> - <option value="false" selected="true">no</option> - </param> - </when> - </conditional> <param name="fq_suffix" value="_R1_001.fastq.gz" type="text" label="Suffix of the R1 FASTQ"/> <param name="fq2_suffix" value="_R2_001.fastq.gz" type="text" label="Suffix of the R2 FASTQ"/> </when> </conditional> - <param name="fq_filter_by_len" optional="true" value="" type="integer" label="Enter minimum read length to retain before starting the analysis" - 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."/> + <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." + help="The default value of 10 is suitable for almost all scenarios."/> + <param name="bcs_thresholds" type="select" label="Enter the type of base quality thresholds to be set with bettercallsal." + help="The default value sets strictest thresholds that tends to filter out most of the false positive hits."> + <option value="strict" selected="true">strict</option> + <option value="relax">relax</option> + </param> + <conditional name="sourmash_cond"> + <param name="run" type="select" label="Run sourmash" + help="Should sourmash be used for additional genome fraction filtering."> + <option value="true" selected="true">yes</option> + <option value="false">no</option> + </param> + <when value="true"> + <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." + help="The default value is set at 10% coverage threshold."/> + </when> + <when value="false"> + <param name="sfhpy_fcv" type="select" label="Enter the minimum coverage match with sourmash before a serotype hit is considered for further processing." + help="THIS OPTION IS IGNORED IF SOURMASH TOOL IgreS DISABLED."> + <option value="NA" selected="true">N/A</option> + </param> + </when> + </conditional> <param name="fq_filename_delim" type="text" value="_" label="File name delimitor by which samples are grouped together (--fq_filename_delim)" 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)."/> <param name="fq_filename_delim_idx" type="integer" value="1" label="File name delimitor index (--fq_filename_delim_idx)" /> - <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"/> - <param name="genome_size" type="text" optional="true" value="5.5m" label="Estimated genome size" help="For example, 5m or 2.6g."> - <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> - </param> <!-- <param name="runtime_profile" type="select" label="Run time profile"> <option value="kondagac" selected="true">conda</option> <option value="cingularitygac">singularity</option> @@ -157,9 +108,6 @@ </inputs> <outputs> <data name="multiqc_report" format="html" label="${input_read_type_cond.pipeline_cond.pipeline}: MultiQC Report on ${on_string}" from_work_dir="multiqc_report.html"/> - <collection name="assembled_mags" type="list" label="${input_read_type_cond.pipeline_cond.pipeline}: Assembled MAGs on ${on_string}"> - <discover_datasets pattern="(?P<name>.*)\.assembly_filtered_contigs\.fasta" ext="fasta" directory="kraken2_extract_contigs"/> - </collection> </outputs> <tests> <!--Test 01: long reads--> @@ -182,9 +130,14 @@ **Purpose** -Centriflaken suite of automated data analysis pipelines are based on Nextflow DSL2 developed at CFSAN, FDA. These pipelines allow rapid -and effective construction of metagenomic assembled genomes (MAGs) to enable bacterial source-tracking. It is based on methods described in our -previous publication (Maguire *et al*, 2021. doi: https://doi.org/10.1371/journal.pone.0245172). +bettercallsal is an automated workflow to assign Salmonella serotype based on NCBI Pathogen Detection Project for Salmonella. +It uses MASH to reduce the search space followed by additional genome filtering with sourmash. It then performs genome based +alignment with kma followed by count generation using salmon. This workflow can be used to analyze shotgun metagenomics +datasets, quasi-metagenomic datasets (enriched for Salmonella) and target enriched datasets (enriched with molecular baits specific for Salmonella) +and is especially useful in a case where a sample is of multi-serovar mixture. + +It is written in Nextflow and is part of the modular data analysis pipelines (CFSAN PIPELINES or CPIPES for short) at CFSAN. + ---- @@ -192,12 +145,10 @@ **Testing and Validation** -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 -in silico-based analysis (i.e., virulence gene finding). Additionally, AMR gene finding analysis is also included in Centriflaken and performed on MAGs -of interest. The final summary plots and tables can be downloaded from the provided MultiQC HTML report generated as part of the pipeline. -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 -and classification of STECs for each sample. We tested the pipeline with Nanopore data obtained from 21 additional enriched samples from -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 +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 +and generates a MultiQC report in the final step. The pipeline has been tested on 2x300 bp MiSeq and 2x150 bp NextSeq reads and has shown to call multiple +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 +our preprint (https://www.biorxiv.org/content/10.1101/2023.04.06.535929v1.full). All the original testing and validation was done on the command line on the CFSAN Raven2 HPC Cluster. @@ -215,18 +166,18 @@ Please note that due to MultiQC customizations, the preview (eye icon) will not work within Galaxy for the MultiQC report. Please download the file by clicking on the floppy icon and view it in your browser on your local desktop/workstation. - - Final assembly: contains contigs and possibly scaffolds. + You can export the tables and plots from the downloaded MultiQC report. ]]></help> <citations> <citation type="bibtex"> - @misc{gitlabCPIPES, + @misc{bettercallsal, author = {Konganti, Kranti}, - year = {2022}, - title = {CPIPES - Centriflaken}, - publisher = {GitLab}, - journal = {GitLab repository}, - url = {https://cfsan-git.fda.gov/Kranti.Konganti/cpipes}} + year = {2023}, + title = {bettercallsal: better calling of Salmonella serotypes from enrichment cultures using shotgun metagenomic profiling and its application in an outbreak setting}, + publisher = {Cold Spring Harbor Laboratory}, + journal = {bioRxiv}, + url = {https://www.biorxiv.org/content/10.1101/2023.04.06.535929v1.full}} </citation> </citations> </tool>