Mercurial > repos > earlhaminst > lotus2
diff lotus2.xml @ 17:28f284a679ce draft
planemo upload for repository https://github.com/TGAC/earlham-galaxytools/tree/master/tools/lotus2 commit 501bb8e75e2245e0ce1ff93308d12be84198d6fd
| author | earlhaminst |
|---|---|
| date | Fri, 28 Oct 2022 12:22:34 +0000 |
| parents | 12599a8dd22f |
| children | 6c22795e1be0 |
line wrap: on
line diff
--- a/lotus2.xml Tue Mar 22 13:45:18 2022 +0000 +++ b/lotus2.xml Fri Oct 28 12:22:34 2022 +0000 @@ -1,7 +1,7 @@ <tool id="lotus2" name="LotuS2" version="@VERSION@" profile="20.09"> <description>fast OTU processing pipeline</description> <macros> - <token name="@VERSION@">2.19</token> + <token name="@VERSION@">2.21</token> <xml name="refDB_macro" token_ref_fasta_formats="fasta,fasta.gz"> <conditional name="refDB_cond"> <param argument="-refDB" type="select" label="Taxonomy reference database"> @@ -27,9 +27,6 @@ </conditional> <param argument="-useBestBlastHitOnly" type="boolean" truevalue="1" falsevalue="0" checked="false" label="Use the best Blast hit only" help="Do not use LCA (lowest common ancestor) to determine the most likely taxonomic level (not recommended)" /> </xml> - <xml name="id_macro"> - <param argument="-id" type="float" min="0.9" max="1" value="" optional="true" label="Clustering threshold for OTUs (optional)" /> - </xml> <xml name="ITSx_macro"> <param argument="-ITSx" type="boolean" truevalue="1" falsevalue="0" checked="true" label="Use ITSx to only retain OTUs fitting to ITS1/ITS2 hmm models" /> </xml> @@ -75,10 +72,10 @@ #end for #end if -#if $tax_args.aligner_cond.taxAligner not in ('0', '3') and $tax_args.aligner_cond.refDB_cond.refDB == 'history': - #set $ext = $tax_args.aligner_cond.refDB_cond.ref_fasta.ext - #set $ref_fasta_symlink = $symlink_basename($tax_args.aligner_cond.refDB_cond.ref_fasta, strip_ext=True) + '.' + $ext - ln -s '$tax_args.aligner_cond.refDB_cond.ref_fasta' '$ref_fasta_symlink' && +#if $aligner_cond.taxAligner not in ('0', '3') and $aligner_cond.refDB_cond.refDB == 'history': + #set $ext = $aligner_cond.refDB_cond.ref_fasta.ext + #set $ref_fasta_symlink = $symlink_basename($aligner_cond.refDB_cond.ref_fasta, strip_ext=True) + '.' + $ext + ln -s '$aligner_cond.refDB_cond.ref_fasta' '$ref_fasta_symlink' && #end if #if not $map: @@ -92,14 +89,14 @@ -tmpDir tmp_folder -threads "\${GALAXY_SLOTS:-1}" -map '$map' -#if $sdmopt: - -sdmopt '$sdmopt' +#if $other_opts.sdmopt: + -sdmopt '$other_opts.sdmopt' #end if -#if $platform != '': - -platform $platform +#if $other_opts.platform != '': + -platform $other_opts.platform #end if -#if $barcode: - -barcode '$barcode' +#if $other_opts.barcode: + -barcode '$other_opts.barcode' #end if #if $forwardPrimer: -forwardPrimer '$forwardPrimer' @@ -107,19 +104,19 @@ #if $reversePrimer: -reversePrimer '$reversePrimer' #end if -#if $offtarget_cond.offtargetDB != 'no': - -offtargetDB '$offtarget_cond.ref_file' +#if $other_opts.offtarget_cond.offtargetDB != 'no': + -offtargetDB '$other_opts.offtarget_cond.ref_file' #end if --useMini4map $useMini4map +-useMini4map $other_opts.useMini4map --clustering $clu_args.clu_cond.clustering -#if $clu_args.clu_cond.clustering in ('1', '3'): - #if str($clu_args.clu_cond.id): - -id $clu_args.clu_cond.id +-clustering $clu_cond.clustering +#if $clu_cond.clustering in ('1', '3'): + #if str($clu_cond.id): + -id $clu_cond.id #end if -#elif $clu_args.clu_cond.clustering == '2': - #if str($clu_args.clu_cond.swarm_distance): - -swarm_distance $clu_args.clu_cond.swarm_distance +#elif $clu_cond.clustering == '2': + #if str($clu_cond.swarm_distance): + -swarm_distance $clu_cond.swarm_distance #end if #end if #if $clu_args.derepMin: @@ -133,26 +130,26 @@ -chim_skew $clu_args.chim_skew #end if --taxAligner $tax_args.aligner_cond.taxAligner -#if $tax_args.aligner_cond.taxAligner == '0': - #if str($tax_args.aligner_cond.rdp_thr): - -rdp_thr $tax_args.aligner_cond.rdp_thr +-taxAligner $aligner_cond.taxAligner +#if $aligner_cond.taxAligner == '0': + #if str($aligner_cond.rdp_thr): + -rdp_thr $aligner_cond.rdp_thr #end if -#elif $tax_args.aligner_cond.taxAligner == '3': - #if str($tax_args.aligner_cond.utax_thr): - -utax_thr $tax_args.aligner_cond.utax_thr +#elif $aligner_cond.taxAligner == '3': + #if str($aligner_cond.utax_thr): + -utax_thr $aligner_cond.utax_thr #end if #else: - #if $tax_args.aligner_cond.refDB_cond.refDB == 'cached': - #if $tax_args.aligner_cond.refDB_cond.ref_db != '': - -refDB $tax_args.aligner_cond.refDB_cond.ref_db - -greengenesSpecies $tax_args.aligner_cond.refDB_cond.greengenesSpecies + #if $aligner_cond.refDB_cond.refDB == 'cached': + #if $aligner_cond.refDB_cond.ref_db != '': + -refDB $aligner_cond.refDB_cond.ref_db + -greengenesSpecies $aligner_cond.refDB_cond.greengenesSpecies #end if #else: -refDB '$ref_fasta_symlink' - -tax4refDB '$tax_args.aligner_cond.refDB_cond.tax4refDB' + -tax4refDB '$aligner_cond.refDB_cond.tax4refDB' #end if - -useBestBlastHitOnly $tax_args.aligner_cond.useBestBlastHitOnly + -useBestBlastHitOnly $aligner_cond.useBestBlastHitOnly #end if #if $tax_args.amplicon_cond.amplicon_type != '': -amplicon_type $tax_args.amplicon_cond.amplicon_type @@ -221,59 +218,50 @@ </when> </conditional> <param argument="-map" type="data" format="tabular" optional="true" label="Mapping file (optional)" help="Needed to demultiplex the FASTQ files using sdm. If the FASTQ are already demultiplexed, this can be omitted." /> - <param argument="-sdmopt" type="data" format="txt" optional="true" label="SDM option file (optional)" /> - <param argument="-platform" type="select" label="Sequencing platform"> - <option value="" selected="true">(Default)</option> - <option value="miSeq">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="Barcode (MID) sequences (optional)" help="FASTQ file with barcodes (in the processed mi/hiSeq format), if provided by the sequencer" /> <param argument="-forwardPrimer" type="text" value="" label="Forward primer used to amplify DNA region (optional)" help="E.g. 16S primer fwd" /> <param argument="-reversePrimer" type="text" value="" label="Reverse primer used to amplify DNA region (optional)" help="E.g. 16S primer rev" /> - <conditional name="offtarget_cond"> - <param argument="-offtargetDB" type="select" label="Remove likely contaminant OTUs/ASVs based on alignment to host genome" help="Useful for low-bacterial biomass samples to remove possible host genome contaminations"> - <option value="no" selected="true">Disabled</option> - <option value="cached">Use a built-in genome</option> - <option value="history">Use a genome from history</option> + <conditional name="clu_cond"> + <param argument="-clustering" type="select" label="Clustering algorithm"> + <option value="7" selected="true">DADA2</option> + <option value="2">swarm</option> + <option value="3">CD-HIT</option> + <option value="8">VSEARCH</option> </param> - <when value="no" /> - <when value="cached"> - <param name="ref_file" type="select" label="Using reference genome" help="Select genome from the list"> - <options from_data_table="all_fasta"> - <filter type="sort_by" column="2" /> - <validator type="no_options" message="No reference genomes are available" /> - </options> - </param> + <when value="2"> + <param argument="-swarm_distance" type="integer" min="1" value="1" optional="true" label="Clustering threshold for OTUs when using swarm clustering (optional)" /> </when> - <when value="history"> - <param name="ref_file" type="data" format="fasta,fasta.gz" label="FASTA reference genome" /> + <when value="3"> + <param argument="-id" type="float" min="0.9" max="1" value="0.97" optional="true" label="Clustering threshold for OTUs" /> + </when> + <when value="7"> + </when> + <when value="8"> </when> </conditional> - <param argument="-useMini4map" type="boolean" truevalue="1" falsevalue="0" checked="true" label="Use minimap2 instead of VSEARCH to map back reads to OTUs" /> - <section name="clu_args" title="Clustering Options"> - <conditional name="clu_cond"> - <param argument="-clustering" type="select" label="Clustering algorithm"> - <option value="2">swarm</option> - <option value="3">cd-hit</option> - <option value="6">unoise3</option> - <option value="7" selected="true">dada2</option> - <option value="8">vsearch</option> - </param> - <when value="2"> - <param argument="-swarm_distance" type="integer" min="1" value="1" optional="true" label="Clustering threshold for OTUs when using swarm clustering (optional)" /> - </when> - <when value="3"> - <expand macro="id_macro" /> - </when> - <when value="6"> - </when> - <when value="7"> - </when> - <when value="8"> - </when> - </conditional> + <conditional name="aligner_cond"> + <param argument="-taxAligner" type="select" label="Taxonomy aligner for taxonomic profiling of OTUs"> + <option value="0" selected="true">RDPclassifier (max likelihood)</option> + <!-- <option value="1">Blast LCA against custom reference database</option> --> + <option value="2">LAMBDA, LCA against custom reference database</option> + <!-- <option value="4">VSEARCH LCA against custom reference database</option> --> + </param> + <when value="0"> + <param argument="-rdp_thr" type="float" min="0" max="1" value="0.8" optional="true" label="Confidence threshold for RDP (optional)"/> + </when> + <!-- <when value="1"> + <expand macro="refDB_macro" ref_fasta_formats="fasta" /> + </when> --> + <when value="2"> + <expand macro="refDB_macro" /> + </when> + <!-- <when value="3"> + <param argument="-utax_thr" type="float" min="0" max="1" value="0.8" optional="true" label="Confidence threshold for UTAX (optional)"/> + </when> + <when value="4"> + <expand macro="refDB_macro" /> + </when> --> + </conditional> + <section name="clu_args" title="Other Clustering Options"> <param argument="-derepMin" type="text" value="" label="Minimum size of dereplicated raw reads (optional)" help="E.g. 4:1,4:2,3:3 . See http://lotus2.earlham.ac.uk/images/Derep_options.pdf for how to specify this parameter. If not specified, LotuS2 will select an appropriate default for the chosen clustering algorithm." /> <param argument="-deactivateChimeraCheck" type="select" label="Chimera check"> <option value="" selected="true">(Default)</option> @@ -284,30 +272,7 @@ </param> <param argument="-chim_skew" type="integer" min="0" value="" optional="true" label="Skew in chimeric fragment abundance" /> </section> - <section name="tax_args" title="Taxonomy Options"> - <conditional name="aligner_cond"> - <param argument="-taxAligner" type="select" label="Taxonomy aligner for taxonomic profiling of OTUs"> - <option value="0" selected="true">RDPclassifier (max likelihood)</option> - <!-- <option value="1">Blast LCA against custom reference database</option> --> - <option value="2">LAMBDA LCA against custom reference database</option> - <!-- <option value="4">VSEARCH LCA against custom reference database</option> --> - </param> - <when value="0"> - <param argument="-rdp_thr" type="float" min="0" max="1" value="0.8" optional="true" label="Confidence threshold for RDP (optional)"/> - </when> - <!-- <when value="1"> - <expand macro="refDB_macro" ref_fasta_formats="fasta" /> - </when> --> - <when value="2"> - <expand macro="refDB_macro" /> - </when> - <!-- <when value="3"> - <param argument="-utax_thr" type="float" min="0" max="1" value="0.8" optional="true" label="Confidence threshold for UTAX (optional)"/> - </when> - <when value="4"> - <expand macro="refDB_macro" /> - </when> --> - </conditional> + <section name="tax_args" title="Other Taxonomy Options"> <conditional name="amplicon_cond"> <param argument="-amplicon_type" type="select" label="Amplicon type"> <option value="" selected="true">(Default)</option> @@ -338,7 +303,7 @@ <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="-LCA_cover" type="float" min="0" max="1" value="" optional="true" label="Minimum horizontal coverage of an OTU sequence against ref DB (optional)"/> <param argument="-LCA_frac" type="float" min="0" max="1" value="" optional="true" label="Minimum fraction of reads with identical taxonomy (optional)"/> - <param argument="-lulu" type="boolean" truevalue="1" falsevalue="0" checked="false" label="Use LULU to merge OTUs based on their occurrence" /> + <param argument="-lulu" type="boolean" truevalue="1" falsevalue="0" checked="true" label="Use LULU to merge OTUs based on their occurrence" /> <param argument="-buildPhylo" type="select" label="Build OTU phylogeny"> <option value="0">Disable</option> <option value="1" selected="true">Use fasttree2</option> @@ -353,6 +318,37 @@ </sanitizer> </param> </section> + <section name="other_opts" title="Other options"> + <param argument="-sdmopt" type="data" format="txt" optional="true" label="SDM option file (optional)" /> + <param argument="-platform" type="select" label="Sequencing platform"> + <option value="" selected="true">(Default)</option> + <option value="miSeq">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="Barcode (MID) sequences (optional)" help="FASTQ file with barcodes (in the processed mi/hiSeq format), if provided by the sequencer" /> + <conditional name="offtarget_cond"> + <param argument="-offtargetDB" type="select" label="Remove likely contaminant OTUs/ASVs based on alignment to host genome" help="Useful for low-bacterial biomass samples to remove possible host genome contaminations"> + <option value="no" selected="true">Disabled</option> + <option value="cached">Use a built-in genome</option> + <option value="history">Use a genome from history</option> + </param> + <when value="no" /> + <when value="cached"> + <param name="ref_file" type="select" label="Using reference genome" help="Select genome from the list"> + <options from_data_table="all_fasta"> + <filter type="sort_by" column="2" /> + <validator type="no_options" message="No reference genomes are available" /> + </options> + </param> + </when> + <when value="history"> + <param name="ref_file" type="data" format="fasta,fasta.gz" label="FASTA reference genome" /> + </when> + </conditional> + <param argument="-useMini4map" type="boolean" truevalue="1" falsevalue="0" checked="true" label="Use minimap2 instead of VSEARCH to map back reads to OTUs" /> + </section> </inputs> <outputs> @@ -370,13 +366,18 @@ <param name="paired_or_single" value="single"/> <param name="input" value="Anh_sample1.fastq.gz,Anh_sample2.fastq.gz" ftype="fastqsanger.gz"/> </conditional> - <param name="platform" value="454" /> + <conditional name="clu_cond"> + <param name="clustering" value="3" /> + </conditional> <section name="clu_args"> - <conditional name="clu_cond"> - <param name="clustering" value="3" /> - </conditional> <param name="derepMin" value="1" /> </section> + <section name="tax_args"> + <param name="lulu" value="false" /> + </section> + <section name="other_opts"> + <param name="platform" value="454" /> + </section> <output name="otu" file="OTU.txt" compare="sim_size" /> <output name="otu_fna" file="OTU.fna" compare="sim_size" /> <output name="mapping" file="mapping.txt" /> @@ -396,13 +397,18 @@ </param> </conditional> <param name="map" value="mapping_paired.txt" /> - <param name="platform" value="454" /> + <conditional name="clu_cond"> + <param name="clustering" value="3" /> + </conditional> <section name="clu_args"> - <conditional name="clu_cond"> - <param name="clustering" value="3" /> - </conditional> <param name="derepMin" value="1" /> </section> + <section name="tax_args"> + <param name="lulu" value="false" /> + </section> + <section name="other_opts"> + <param name="platform" value="454" /> + </section> <output name="otu" file="OTU_paired.txt" compare="sim_size" /> <output name="otu_fna" file="OTU_paired.fna" compare="sim_size" /> </test> @@ -411,9 +417,12 @@ <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/>`_. +.. class:: infomark + +The full LotuS2 **documentation** can be found at `<http://lotus2.earlham.ac.uk/>`_. ]]></help> <citations> - <citation type="doi">10.1101/2021.12.24.474111</citation> + <citation type="doi">10.1186/s40168-022-01365-1</citation> + <citation type="doi">10.1186/s40168-021-01012-1</citation> </citations> </tool>