Mercurial > repos > kkonganti > cfsan_centriflaken

annotate cfsan_centriflaken.xml @ 108:2bda095a1222

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload"
author kkonganti
date Thu, 27 Jun 2024 14:24:42 -0400
parents c02d3cf60fe0
children 6d1ac92520b6
rev   line source
kkonganti@108 1 <tool id="cfsan_centriflaken" name="Centriflaken" version="0.4.2+galaxy1">
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@105 4 <requirement type="package" version="24.04">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@105 11 time_stamp=\$(date +%Y-%m-%d-%s);
kkonganti@105 12 work_dir="\${pwd_path}/centriflaken_work_dir-"\${time_stamp};
kkonganti@105 13 mkdir -p \$work_dir || exit 1;
kkonganti@86 14 #import re
kkonganti@58 15 #if (str($input_read_type_cond.input_read_type) == "single_long"):
kkonganti@75 16 #for _, $unpaired in enumerate($input_read_type_cond.input):
kkonganti@85 17 #set read1 = str($unpaired.name)
kkonganti@84 18 #if not str($unpaired.name).endswith(('.fastq', '.fastq.gz')):
kkonganti@96 19 #set read1_ext = re.sub('fastqsanger', 'fastq', str($unpaired.ext))
kkonganti@96 20 #set read1 = str($unpaired.name) + str('.') + $read1_ext
kkonganti@75 21 #end if
kkonganti@83 22 ln -sf '$unpaired' './cpipes-input/$read1';
kkonganti@58 23 #end for
kkonganti@66 24 #elif (str($input_read_type_cond.input_read_type) == "paired"):
kkonganti@75 25 #for _, $pair in enumerate($input_read_type_cond.input_pair)
kkonganti@94 26 #set read_R1 = re.sub('\:forward', '_forward', str($pair.forward.name))
kkonganti@94 27 #set read_R2 = re.sub('\:reverse', '_reverse', str($pair.reverse.name))
kkonganti@96 28 #set read_R1_ext = re.sub('fastqsanger', 'fastq', str($pair.forward.ext))
kkonganti@96 29 #set read_R2_ext = re.sub('fastqsanger', 'fastq', str($pair.reverse.ext))
kkonganti@85 30 #if not str($pair.forward.name).endswith(('.fastq', '.fastq.gz')):
kkonganti@96 31 #set read_R1 = $read_R1 + str('.') + $read_R1_ext
kkonganti@85 32 #end if
kkonganti@85 33 #if not str($pair.reverse.name).endswith(('.fastq', '.fastq.gz')):
kkonganti@96 34 #set read_R2 = $read_R2 + str('.') + $read_R2_ext
kkonganti@85 35 #end if
kkonganti@75 36 ln -sf '$pair.forward' './cpipes-input/$read_R1';
kkonganti@75 37 ln -sf '$pair.reverse' './cpipes-input/$read_R2';
kkonganti@58 38 #end for
kkonganti@60 39 #end if
kkonganti@105 40 $__tool_directory__/0.4.2/cpipes
kkonganti@61 41 --pipeline $input_read_type_cond.pipeline_cond.pipeline
kkonganti@58 42 #if ($input_read_type_cond.pipeline_cond.pipeline == "centriflaken"):
kkonganti@4 43 --fq_single_end true
kkonganti@33 44 --flye_genome_size '${genome_size}'
kkonganti@58 45 #if ($input_read_type_cond.pipeline_cond.long_read_platform == "nanopore_corr"):
kkonganti@33 46 --flye_nano_corr true --flye_nano_raw false
kkonganti@58 47 #elif ($input_read_type_cond.pipeline_cond.long_read_platform == "nanopore_hq"):
kkonganti@33 48 --flye_nano_hq true --flye_nano_raw false
kkonganti@58 49 #elif ($input_read_type_cond.pipeline_cond.long_read_platform == "pacbio_raw"):
kkonganti@33 50 --flye_pacbio_raw true --flye_nano_raw false
kkonganti@58 51 #elif ($input_read_type_cond.pipeline_cond.long_read_platform == "pacbio_corr"):
kkonganti@33 52 --flye_pacbio_corr true --flye_nano_raw false
kkonganti@58 53 #elif ($input_read_type_cond.pipeline_cond.long_read_platform == "pacbio_hifi"):
kkonganti@33 54 --flye_pacbio_hifi true --flye_nano_raw false
kkonganti@33 55 #end if
kkonganti@58 56 #elif ($input_read_type_cond.pipeline_cond.pipeline == "centriflaken_hy"):
kkonganti@64 57 #if (str($input_read_type_cond.input_read_type) == "single_long"):
kkonganti@4 58 --fq_single_end true
kkonganti@64 59 #elif (str($input_read_type_cond.input_read_type) == "paired"):
kkonganti@64 60 --fq_single_end false --fq2_suffix '${input_read_type_cond.fq2_suffix}'
kkonganti@4 61 #end if
kkonganti@0 62 #end if
kkonganti@0 63 --input \${pwd_path}/cpipes-input
kkonganti@0 64 --output \${pwd_path}/cpipes-output
kkonganti@64 65 --fq_suffix '${input_read_type_cond.fq_suffix}'
kkonganti@41 66 #if ($fq_filter_by_len != ""):
kkonganti@39 67 --fq_filter_by_len $fq_filter_by_len
kkonganti@39 68 #end if
kkonganti@0 69 --fq_filename_delim '${fq_filename_delim}'
kkonganti@0 70 --fq_filename_delim_idx $fq_filename_delim_idx
kkonganti@0 71 --centrifuge_extract_bug '${centrifuge_extract_bug}'
kkonganti@102 72 #if (str($input_read_type_cond.pipeline_cond.rm_dup_seqs) == "true"):
kkonganti@101 73 --seqkit_rmdup_run true
kkonganti@101 74 #end if
kkonganti@106 75 -profile gxkubernetes;
kkonganti@87 76 mv './cpipes-output/${input_read_type_cond.pipeline_cond.pipeline}-multiqc/multiqc_report.html' './multiqc_report.html' > /dev/null 2>&1 || exit 1;
kkonganti@87 77 mv './cpipes-output/${input_read_type_cond.pipeline_cond.pipeline}-results/kraken2_extract_contigs' kraken2_extract_contigs > /dev/null 2>&1 || exit 1;
kkonganti@87 78 rm -rf ./cpipes-output > /dev/null 2>&1 || exit 1;
kkonganti@87 79 rm -rf ./work > /dev/null 2>&1 || exit 1
kkonganti@0 80 ]]></command>
kkonganti@0 81 <inputs>
kkonganti@58 82 <conditional name="input_read_type_cond">
kkonganti@58 83 <param name="input_read_type" type="select" label="Select the read collection type">
kkonganti@61 84 <option value="single_long" selected="true">Unpaired reads (i.e. Single-End short reads or Long reads)</option>
kkonganti@58 85 <option value="paired">Paired-End reads</option>
kkonganti@58 86 </param>
kkonganti@58 87 <when value="single_long">
kkonganti@75 88 <param name="input" type="data_collection" collection_type="list" format="fastq,fastq.gz"
kkonganti@61 89 label="Dataset list of unpaired short reads or long reads" />
kkonganti@58 90 <conditional name="pipeline_cond">
kkonganti@58 91 <param name="pipeline" type="select" label="CPIPES Workflow name"
kkonganti@90 92 help="centriflaken: for long reads (Nanopore or PacBio). centriflaken_hy: for unpaired short reads. Default: centriflaken">
kkonganti@58 93 <option value="centriflaken" selected="true">centriflaken</option>
kkonganti@58 94 <option value="centriflaken_hy">centriflaken_hy</option>
kkonganti@58 95 </param>
kkonganti@58 96 <when value="centriflaken">
kkonganti@58 97 <param name="long_read_platform" type="select" label="Mention long read sequencing platform and type">
kkonganti@58 98 <option value="nanopore_raw" selected="true">Nanopore raw reads, pre-Guppy5 (&lt;20% error)</option>
kkonganti@58 99 <option value="nanopore_corr">Nanopore reads that were corrected with other methods (&lt;3% error)</option>
kkonganti@58 100 <option value="nanopore_hq">Nanopore high-quality reads, Guppy5+ SUP or Q20 (5% error)</option>
kkonganti@58 101 <option value="pacbio_raw">PacBio regular CLR reads (&lt;20% error)</option>
kkonganti@58 102 <option value="pacbio_corr">PacBio reads that were corrected with other methods (&lt;3% error)</option>
kkonganti@58 103 <option value="pacbio_hifi">PacBio HiFi reads (&lt;1% error)</option>
kkonganti@58 104 </param>
kkonganti@103 105 <param name="rm_dup_seqs" type="select" label="Remove duplicate sequences"
kkonganti@103 106 help="THIS OPTION IS IGNORED IF THE INPUT READS ARE LONG READS.">
kkonganti@103 107 <option value="NA" selected="true">N/A</option>
kkonganti@103 108 </param>
kkonganti@58 109 </when>
kkonganti@58 110 <when value="centriflaken_hy">
kkonganti@89 111 <param name="long_read_platform" type="select" label="Mention long read sequencing platform and type"
kkonganti@89 112 help="THIS OPTION IS IGNORED IF THE INPUT READS ARE SHORT READS.">
kkonganti@89 113 <option value="NA" selected="true">N/A</option>
kkonganti@89 114 </param>
kkonganti@101 115 <param name="rm_dup_seqs" type="select" label="Remove duplicate sequences"
kkonganti@101 116 help="Selecting yes will compare sequence content and remove identical sequences i.e. only the first occured sequence record will be saved.">
kkonganti@101 117 <option value="true">yes</option>
kkonganti@101 118 <option value="false" selected="true">no</option>
kkonganti@101 119 </param>
kkonganti@58 120 </when>
kkonganti@58 121 </conditional>
kkonganti@74 122 <param name="fq_suffix" value=".fastq.gz" type="text" label="Suffix of the Unpaired FASTQ"/>
kkonganti@58 123 </when>
kkonganti@58 124 <when value="paired">
kkonganti@85 125 <param name="input_pair" type="data_collection" collection_type="list:paired" format="fastq,fastq.gz" label="List of Dataset pairs" />
kkonganti@66 126 <conditional name="pipeline_cond">
kkonganti@66 127 <param name="pipeline" type="select" label="CPIPES Workflow name"
kkonganti@90 128 help="Auto selected centriflaken_hy workflow for paired-end short reads.">
kkonganti@66 129 <option value="centriflaken_hy" selected="true">centriflaken_hy</option>
kkonganti@66 130 </param>
kkonganti@66 131 <when value="centriflaken_hy">
kkonganti@91 132 <param name="long_read_platform" type="select" label="Mention long read sequencing platform and type"
kkonganti@91 133 help="THIS OPTION IS IGNORED IF THE INPUT READS ARE SHORT READS.">
kkonganti@91 134 <option value="NA" selected="true">N/A</option>
kkonganti@91 135 </param>
kkonganti@101 136 <param name="rm_dup_seqs" type="select" label="Remove duplicate sequences"
kkonganti@101 137 help="Selecting yes will compare sequence content and remove identical sequences i.e. only the first occured sequence record will be saved.">
kkonganti@101 138 <option value="true">yes</option>
kkonganti@101 139 <option value="false" selected="true">no</option>
kkonganti@101 140 </param>
kkonganti@66 141 </when>
kkonganti@66 142 </conditional>
kkonganti@74 143 <param name="fq_suffix" value="_R1_001.fastq.gz" type="text" label="Suffix of the R1 FASTQ"/>
kkonganti@58 144 <param name="fq2_suffix" value="_R2_001.fastq.gz" type="text" label="Suffix of the R2 FASTQ"/>
kkonganti@58 145 </when>
kkonganti@58 146 </conditional>
kkonganti@44 147 <param name="fq_filter_by_len" optional="true" value="" type="integer" label="Enter minimum read length to retain before starting the analysis"
kkonganti@48 148 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@40 149 <param name="fq_filename_delim" type="text" value="_" label="File name delimitor by which samples are grouped together (--fq_filename_delim)"
kkonganti@48 150 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@6 151 <param name="fq_filename_delim_idx" type="integer" value="1" label="File name delimitor index (--fq_filename_delim_idx)" />
kkonganti@0 152 <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@0 153 <param name="genome_size" type="text" optional="true" value="5.5m" label="Estimated genome size" help="For example, 5m or 2.6g.">
kkonganti@0 154 <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@0 155 </param>
kkonganti@47 156 <!-- <param name="runtime_profile" type="select" label="Run time profile">
kkonganti@31 157 <option value="kondagac" selected="true">conda</option>
kkonganti@12 158 <option value="cingularitygac">singularity</option>
kkonganti@47 159 </param> -->
kkonganti@0 160 </inputs>
kkonganti@0 161 <outputs>
kkonganti@59 162 <data name="multiqc_report" format="html" label="${input_read_type_cond.pipeline_cond.pipeline}: MultiQC Report on ${on_string}" from_work_dir="multiqc_report.html"/>
kkonganti@59 163 <collection name="assembled_mags" type="list" label="${input_read_type_cond.pipeline_cond.pipeline}: Assembled MAGs on ${on_string}">
kkonganti@24 164 <discover_datasets pattern="(?P&lt;name&gt;.*)\.assembly_filtered_contigs\.fasta" ext="fasta" directory="kraken2_extract_contigs"/>
kkonganti@18 165 </collection>
kkonganti@0 166 </outputs>
kkonganti@3 167 <tests>
kkonganti@3 168 <!--Test 01: long reads-->
kkonganti@3 169 <test expect_num_outputs="2">
kkonganti@4 170 <param name="input">
kkonganti@3 171 <collection type="list">
kkonganti@4 172 <element name="FAL11127.fastq.gz" value="FAL11127.fastq.gz" />
kkonganti@4 173 <element name="FAL11341.fastq.gz" value="FAL11341.fastq.gz" />
kkonganti@4 174 <element name="FAL11342.fastq.gz" value="FAL11342.fastq.gz" />
kkonganti@3 175 </collection>
kkonganti@3 176 </param>
kkonganti@3 177 <param name="fq_suffix" value=".fastq.gz"/>
kkonganti@3 178 <output name="multiqc_report" file="multiqc_report.html" ftype="html" compare="sim_size"/>
kkonganti@18 179 <!-- <output name="assembled_mags" file="FAL11127.assembly_filtered.contigs.fasta" ftype="fasta" compare="sim_size"/> -->
kkonganti@3 180 </test>
kkonganti@3 181 </tests>
kkonganti@0 182 <help><![CDATA[
kkonganti@0 183
kkonganti@0 184 .. class:: infomark
kkonganti@0 185
kkonganti@0 186 **Purpose**
kkonganti@0 187
kkonganti@50 188 Centriflaken suite of automated data analysis pipelines are based on Nextflow DSL2 developed at CFSAN, FDA. These pipelines allow rapid
kkonganti@0 189 and effective construction of metagenomic assembled genomes (MAGs) to enable bacterial source-tracking. It is based on methods described in our
kkonganti@53 190 previous publication (Maguire *et al*, 2021. doi: https://doi.org/10.1371/journal.pone.0245172).
kkonganti@14 191
kkonganti@0 192 ----
kkonganti@0 193
kkonganti@0 194 .. class:: infomark
kkonganti@0 195
kkonganti@0 196 **Testing and Validation**
kkonganti@0 197
kkonganti@47 198 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@0 199 in silico-based analysis (i.e., virulence gene finding). Additionally, AMR gene finding analysis is also included in Centriflaken and performed on MAGs
kkonganti@0 200 of interest. The final summary plots and tables can be downloaded from the provided MultiQC HTML report generated as part of the pipeline.
kkonganti@53 201 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@47 202 and classification of STECs for each sample. We tested the pipeline with Nanopore data obtained from 21 additional enriched samples from
kkonganti@0 203 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@0 204 done on the command line on the CFSAN Raven2 HPC Cluster.
kkonganti@0 205
kkonganti@0 206
kkonganti@0 207 ----
kkonganti@0 208
kkonganti@0 209 .. class:: infomark
kkonganti@0 210
kkonganti@0 211 **Outputs**
kkonganti@0 212
kkonganti@0 213 The main output files are:
kkonganti@0 214
kkonganti@0 215 ::
kkonganti@0 216
kkonganti@55 217 - MultiQC Report: Contains a brief summary report including any serotyping and AMR result tables.
kkonganti@56 218 Please note that due to MultiQC customizations, the preview (eye icon) will not
kkonganti@56 219 work within Galaxy for the MultiQC report. Please download the file by clicking
kkonganti@57 220 on the floppy icon and view it in your browser on your local desktop/workstation.
kkonganti@27 221 - Final assembly: contains contigs and possibly scaffolds.
kkonganti@0 222
kkonganti@0 223 ]]></help>
kkonganti@0 224 <citations>
kkonganti@0 225 <citation type="bibtex">
kkonganti@0 226 @misc{gitlabCPIPES,
kkonganti@0 227 author = {Konganti, Kranti},
kkonganti@0 228 year = {2022},
kkonganti@0 229 title = {CPIPES - Centriflaken},
kkonganti@0 230 publisher = {GitLab},
kkonganti@0 231 journal = {GitLab repository},
kkonganti@0 232 url = {https://cfsan-git.fda.gov/Kranti.Konganti/cpipes}}
kkonganti@0 233 </citation>
kkonganti@0 234 </citations>
kkonganti@0 235 </tool>