Mercurial > repos > earlhaminst > lotus2
diff lotus2.xml @ 0:478e767a0e7a draft
"planemo upload for repository https://github.com/TGAC/earlham-galaxytools/tree/master/tools/lotus2 commit d05728af3d4d2ffd49548a320e8e8b4c6cc2f5e7"
author | earlhaminst |
---|---|
date | Thu, 13 May 2021 17:38:45 +0000 |
parents | |
children | 85da3173a488 |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/lotus2.xml Thu May 13 17:38:45 2021 +0000 @@ -0,0 +1,202 @@ +<tool id="lotus2" name="LotuS2" version="@VERSION@" profile="20.01"> + <description>fast OTU processing pipeline</description> + <macros> + <token name="@VERSION@">2.04</token> + </macros> + <requirements> + <requirement type="package" version="@VERSION@">lotus2</requirement> + </requirements> + <version_command>lotus2 --version</version_command> + <command detect_errors="exit_code"><![CDATA[ +mkdir input +&& +#if $inputs.paired_or_single == 'single': + #for i, f in enumerate($inputs.input): + #set ext = $f.ext.replace('sanger', '') + ln -s '$f' 'input/input${i}.${ext}' && + #end for +#elif $inputs.paired_or_single == 'paired': + #for i, f in enumerate($inputs.left_input): + #set ext = $f.ext.replace('sanger', '') + ln -s '$f' 'input/input${i}.1.${ext}' && + #end for + #for i, f in enumerate($inputs.right_input): + #set ext = $f.ext.replace('sanger', '') + ln -s '$f' 'input/input${i}.2.${ext}' && + #end for +#else: + #for i, f in enumerate($inputs.pair_input): + #set ext = $f.forward.ext.replace('sanger', '') + ln -s '$f.forward' 'input/input${i}.1.${ext}' && + #set ext = $f.reverse.ext.replace('sanger', '') + ln -s '$f.reverse' 'input/input${i}.2.${ext}' && + #end for +#end if + +lotus2 -create_map mapping.txt -i input/ && +cat mapping.txt && + +lotus2 +-i input/ +-o output +-tmpDir tmp_folder +-threads "\${GALAXY_SLOTS:-1}" +-map mapping.txt +-platform $platform +#if $barcode: + -barcode '$barcode' +#end if +#if $forwardPrimer: + -forwardPrimer '$forwardPrimer' +#end if +#if $reversePrimer: + -reversePrimer '$reversePrimer' +#end if + +-clustering $clu_args.clustering +-id $clu_args.id +-derepMin $clu_args.derepMin +-chim_skew $clu_args.chim_skew +-deactivateChimeraCheck $clu_args.deactivateChimeraCheck +-readOverlap $clu_args.readOverlap + +-refDB $tax_args.refDB +-amplicon_type $tax_args.amplicon_type +-tax_group $tax_args.tax_group +-rdp_thr $tax_args.rdp_thr +-utax_thr $tax_args.utax_thr +-keepUnclassified $tax_args.keepUnclassified +-taxAligner $tax_args.taxAligner +-useBestBlastHitOnly $tax_args.useBestBlastHitOnly +-LCA_cover $tax_args.LCA_cover +-LCA_frac $tax_args.LCA_frac +-greengenesSpecies $tax_args.greengenesSpecies +-pseudoRefOTUcalling $tax_args.pseudoRefOTUcalling + +&& + +cd output/ && +tar -cvzf higherLvl.tar.gz higherLvl/ && +tar -cvzf ExtraFiles.tar.gz ExtraFiles/ && +tar -cvzf LotuSLogS.tar.gz LotuSLogS/ && +tar -cvzf primary.tar.gz primary/ + ]]></command> + + <inputs> + <conditional name="inputs"> + <param name="paired_or_single" type="select" label="Paired or Single-end data?"> + <option value="single" selected="true">Single-end</option> + <option value="paired">Paired-end</option> + <option value="paired_collection">Paired-end collection</option> + </param> + <when value="single"> + <param name="input" type="data" format="fastqsanger,fastqsanger.gz" multiple="true" label="Single-end reads" /> + </when> + <when value="paired"> + <param name="left_input" type="data" format="fastqsanger,fastqsanger.gz" multiple="true" label="Left/Forward strand reads" /> + <param name="right_input" type="data" format="fastqsanger,fastqsanger.gz" multiple="true" label="Right/Reverse strand reads" /> + </when> + <when value="paired_collection"> + <param name="pair_input" type="data_collection" collection_type="list:paired" format="fastqsanger,fastqsanger.gz" label="List of paired reads" /> + </when> + </conditional> + <param argument="-platform" type="select" label="Sequencing platform"> + <option value="miSeq" selected="true">miSeq</option> + <option value="hiSeq">hiSeq</option> + <option value="454">454</option> + <option value="PacBio">PacBio</option> + </param> + <param argument="-barcode" type="data" format="fastqsanger" optional="true" label="Barcodes (MIDs)" help="FASTQ file with barcodes (in the processed mi/hiSeq format)" /> + <param argument="-forwardPrimer" type="text" value="" label="Forward primer used to amplify DNA region" help="E.g. 16S primer fwd" /> + <param argument="-reversePrimer" type="text" value="" label="Reverse primer used to amplify DNA region" help="E.g. 16S primer rev" /> + <section name="clu_args" title="Clustering Options"> + <param argument="-clustering" type="select" label="Clustering algorithm"> + <option value="1">UPARSE</option> + <option value="2">swarm</option> + <option value="3" selected="true">cd-hit</option> + <option value="6">unoise3</option> + <option value="7">dada2</option> + </param> + <param argument="-id" type="float" min="0" max="1" value="0.97" label="Clustering threshold for OTUs" /> + <param argument="-derepMin" type="integer" min="0" value="1" label="Minimum size of dereplicated clustered" /> + <param argument="-chim_skew" type="integer" min="0" value="2" label="Skew in chimeric fragment abundance" /> + <param argument="-deactivateChimeraCheck" type="select" label="Chimera check"> + <option value="0" selected="true">OTU chimera checks</option> + <option value="1">No chimera check at all</option> + <option value="2">Deactivate deNovo chimera check</option> + <option value="3">Deactivate ref based chimera check</option> + </param> + <param argument="-readOverlap" type="integer" min="0" value="300" label="Maximum number of basepairs that two reads are overlapping" /> + </section> + <section name="tax_args" title="Taxonomy Options"> + <param argument="-refDB" type="select" label="Reference Database"> + <option value="SLV" selected="true">Silva LSU (23/28S) or SSU (16/18S)</option> + <option value="GG">Greengenes</option> + <option value="UNITE">ITS focused on fungi</option> + <option value="PR2">SSU focused on Protists</option> + <option value="beetax">Bee gut specific database and tax names</option> + <option value="HITdb">Human gut microbiota</option> + </param> + <param argument="-amplicon_type" type="select" label="Amplicon type"> + <option value="LSU">LSU Large subunit (23S/28S)</option> + <option value="SSU" selected="true">SSU small subunit (16S/18S)</option> + <option value="ITS">ITS internal transcribed spacer</option> + <option value="ITS1">ITS1</option> + <option value="ITS2">ITS2</option> + </param> + <param argument="-tax_group" type="select" label="Tax group"> + <option value="bacteria" selected="true">bacterial 16S rDNA annnotation</option> + <option value="fungi">fungal 18S/23S/ITS annotation</option> + </param> + <param argument="-rdp_thr" type="float" min="0" max="1" value="0.8" label="Confidence threshold for RDP"/> + <param argument="-utax_thr" type="float" min="0" max="1" value="0.8" label="Confidence threshold for UTAX"/> + <param argument="-keepUnclassified" type="boolean" truevalue="1" falsevalue="0" checked="true" label="Keep unclassified OTUs" help="Includes unclassified OTUs (i.e. no match in RDP/Blast database) in OTU and taxa abundance matrix calculations" /> + <param argument="-taxAligner" type="select" label="Taxonomy aligner"> + <option value="0" selected="true">Deactivated (just use RDP)</option> + <option value="1">Blast</option> + <option value="2">Use LAMBDA to search against a 16S reference database for taxonomic profiling of OTUs</option> + <option value="3">Use UTAX with custom databases</option> + <option value="4">Use VSEARCH to align OTUs to custom databases</option> + <option value="5">Use USEARCH to align OTUs to custom databases</option> + </param> + <param argument="-useBestBlastHitOnly" type="boolean" truevalue="1" falsevalue="0" checked="false" label="Use best blast hit only" help="If selected, do not use LCA (lowest common ancestor) to determine most likely taxonomic level (not recommended)" /> + <param argument="-LCA_cover" type="float" min="0" max="1" value="0.9" label="Minimum horizontal coverage of an OTU sequence against ref DB"/> + <param argument="-LCA_frac" type="float" min="0" max="1" value="0.9" label="Minimum fraction of reads with identical taxonomy"/> + <param argument="-greengenesSpecies" type="boolean" truevalue="1" falsevalue="0" checked="false" label="Create greengenes output labels instead of OTU" /> + <param argument="-pseudoRefOTUcalling" type="boolean" truevalue="1" falsevalue="0" checked="false" label="Create Reference based (open) OTUs" /> + </section> + </inputs> + + <outputs> + <data name="otu" format="tabular" label="${tool.name} on ${on_string}: OTU abundance matrix" from_work_dir="output/OTU.txt" /> + <data name="otu_biom" format="biom" label="${tool.name} on ${on_string}: biom-formatted OTU abundance matrix" from_work_dir="output/OTU.biom" /> + <data name="otu_fna" format="fasta" label="${tool.name} on ${on_string}: FASTA-formatted extended OTU seed sequences" from_work_dir="output/OTU.fna" /> + <data name="OTUphylo_nwk" format="newick" label="${tool.name} on ${on_string}: Newick-formatted phylogenetic tree between sequences" from_work_dir="output/OTUphylo.nwk" /> + <data name="hiera_blast" format="tabular" label="${tool.name} on ${on_string}: OTU taxonomy assignments based on Blastn" from_work_dir="output/hiera_BLAST.txt" /> + <data name="hiera_rdp" format="tabular" label="${tool.name} on ${on_string}: OTU taxonomy assignments based on RDP classifier" from_work_dir="output/hiera_RDP.txt" /> + <data name="primary" format="tar" label="${tool.name} on ${on_string}: Copies of sdm options and mapping file" from_work_dir="output/primary.tar.gz" /> + <data name="higherlvl" format="tar" label="${tool.name} on ${on_string}: Abundance matrices" from_work_dir="output/higherLvl.tar.gz" /> + <data name="lotuslogs" format="tar" label="${tool.name} on ${on_string}: Log files" from_work_dir="output/LotuSLogS.tar.gz" /> + <data name="extrafiles" format="tar" label="${tool.name} on ${on_string}: Extra files" from_work_dir="output/ExtraFiles.tar.gz" /> + </outputs> + + <tests> + <test> + <param name="paired_or_single" value="single"/> + <param name="input" value="Anh_sample1.fastq.gz,Anh_sample2.fastq.gz" ftype="fastqsanger.gz"/> + <param name="platform" value="454" /> + <output name="otu" file="OTU.txt" compare="sim_size" /> + <output name="otu_fna" file="OTU.fna" compare="sim_size" /> + <output name="hiera_rdp" file="hiera_RDP.txt" compare="sim_size" /> + </test> + </tests> + + <help><![CDATA[ +If you have separate FASTA and quality files, these can be combined in a FASTQ file using the "Combine FASTA and QUAL into FASTQ" tool. + +Documentation can be found at `<http://lotus2.earlham.ac.uk/>`_. + ]]></help> + <citations> + <citation type="doi">10.1186/2049-2618-2-30</citation> + </citations> +</tool>