annotate lotus2.xml @ 21:fa84bba02a62 draft

planemo upload for repository https://github.com/TGAC/earlham-galaxytools/tree/master/tools/lotus2 commit 1632994d621dd37cd96792b152f4fe3f8e85b90c

<tool id="lotus2" name="LotuS2" version="@VERSION@+galaxy2" profile="20.09">
    <description>fast OTU processing pipeline</description>
    <macros>
        <token name="@VERSION@">2.23</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">
                    <option value="cached">Use a built-in taxonomy database</option>
                    <option value="history">Use a taxonomy from history</option>
                </param>
                <when value="cached">
                    <param argument="-ref_db" type="select" label="Using reference database" help="Select database from the list">
                        <option value="" selected="true">(Default)</option>
                        <option value="SLV">Silva LSU (23/28S) or SSU (16/18S) (SLV)</option>
                        <option value="GG">Greengenes (GG)</option>
                        <option value="UNITE">ITS focused on fungi (UNITE)</option>
                        <option value="PR2">SSU focused on Protists (PR2)</option>
                        <option value="beetax">Bee gut specific database and tax names (beetax)</option>
                        <option value="HITdb">Human gut microbiota (HITdb)</option>
                    </param>
                    <param argument="-greengenesSpecies" type="boolean" truevalue="1" falsevalue="0" checked="false" label="Create greengenes output labels instead of OTU" />
                </when>
                <when value="history">
                    <param name="ref_fasta" type="data" format="@REF_FASTA_FORMATS@" label="Taxonomy reference sequences" help="In FASTA format" />
                    <param argument="-tax4refDB" type="data" format="tabular" label="Taxonomy reference lineages" help="Tab-separated file with 2 columns mapping each FASTA header of the reference sequences to a GTDB-style taxonomy string" />
                </when>
            </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="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>
    </macros>
    <xrefs>
        <xref type="bio.tools">lotus2</xref>
    </xrefs>
    <requirements>
        <requirement type="package" version="@VERSION@">lotus2</requirement>
    </requirements>
    <version_command>lotus2 --version</version_command>
    <command detect_errors="exit_code"><![CDATA[
#import os.path
#import re
#def symlink_basename($f, strip_ext=False):
    #set $fn = re.sub('[^\w\-_.]', '_', $f.name)
    #if strip_ext:
        #if $fn.endswith('.gz'):
            #set $fn = $fn[:-3]
        #end if
        #if $f.ext.startswith('fasta'):
            #set $exts_to_drop = ('.fa', '.fasta', '.fna')
        #else:
            #set $exts_to_drop = []
        #end if
        #for $ext in $exts_to_drop:
            #if $fn.endswith($ext):
                #set $fn = $fn[:-len($ext)]
                #break
            #end if
        #end for
    #end if
${fn}#slurp
#end def

mkdir input
&&
#if $inputs.paired_or_single == 'single':
    #for $f in $inputs.input:
        ln -s '$f' 'input/${symlink_basename($f)}' &&
    #end for
#else:
    #for $f in $inputs.pair_input:
        ln -s '$f.forward' 'input/${symlink_basename($f.forward.dataset)}' &&
        ln -s '$f.reverse' 'input/${symlink_basename($f.reverse.dataset)}' &&
    #end for
#end if

#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 $map:
    cat '$generated_mapping' &&
    #set map = $generated_mapping
#end if

set +e &&

lotus2
-i input/
-o output
-tmpDir tmp_folder
-threads "\${GALAXY_SLOTS:-1}"
-map '$map'
#if $other_opts.sdmopt:
    -sdmopt '$other_opts.sdmopt'
#end if
#if $other_opts.platform != '':
    -platform $other_opts.platform
#end if
#if $other_opts.barcode:
    -barcode '$other_opts.barcode'
#end if
#if $forwardPrimer:
    -forwardPrimer '$forwardPrimer'
#end if
#if $reversePrimer:
    -reversePrimer '$reversePrimer'
#end if
#if $other_opts.offtarget_cond.offtargetDB != 'no':
    -offtargetDB '$other_opts.offtarget_cond.ref_file'
#end if
-useMini4map $other_opts.useMini4map

-clustering $clu_cond.clustering
#if $clu_cond.clustering in ('1', '3'):
    #if str($clu_cond.id):
        -id $clu_cond.id
    #end if
#elif $clu_cond.clustering == '2':
    #if str($clu_cond.swarm_distance):
        -swarm_distance $clu_cond.swarm_distance
    #end if
#end if
#if $clu_args.derepMin:
    -derepMin '$clu_args.derepMin'
#end if

#if $clu_args.deactivateChimeraCheck != '':
    -deactivateChimeraCheck $clu_args.deactivateChimeraCheck
#end if
#if str($clu_args.chim_skew):
    -chim_skew $clu_args.chim_skew
#end if

-taxAligner $aligner_cond.taxAligner
#if $aligner_cond.taxAligner == '0':
    #if str($aligner_cond.rdp_thr):
        -rdp_thr $aligner_cond.rdp_thr
    #end if
#elif $aligner_cond.taxAligner == '3':
    #if str($aligner_cond.utax_thr):
        -utax_thr $aligner_cond.utax_thr
    #end if
#else:
    #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 '$aligner_cond.refDB_cond.tax4refDB'
    #end if
    -useBestBlastHitOnly $aligner_cond.useBestBlastHitOnly
#end if
#if $tax_args.amplicon_cond.amplicon_type != '':
    -amplicon_type $tax_args.amplicon_cond.amplicon_type
#end if
#if $tax_args.amplicon_cond.amplicon_type in ('ITS', 'ITS1', 'ITS2'):
    -ITSx $tax_args.amplicon_cond.ITSx
#end if

#if $tax_args.tax_group != '':
    -tax_group $tax_args.tax_group
#end if
-keepUnclassified $tax_args.keepUnclassified
#if str($tax_args.LCA_cover):
    -LCA_cover $tax_args.LCA_cover
#end if
#if str($tax_args.LCA_frac):
    -LCA_frac $tax_args.LCA_frac
#end if
-lulu $tax_args.lulu
-buildPhylo $tax_args.buildPhylo
#if $tax_args.taxExcludeGrep:
    -taxExcludeGrep '$tax_args.taxExcludeGrep'
#end if
; EXIT_VALUE=\$? ;

zip -8 -r -v output.zip output/
&&
exit \$EXIT_VALUE
    ]]></command>
    <configfiles>
        <configfile name="generated_mapping"><![CDATA[#slurp
#import re
#def symlink_basename($f):
    #set $fn = re.sub('[^\w\-_.]', '_', $f.name)
${fn}#slurp
#end def
#SampleID	fastqFile	SequencingRun
#if $inputs.paired_or_single == 'single':
    #for $i, $f in enumerate($inputs.input):
SMPL${i}	${symlink_basename($f)}	a
    #end for
#else:
    #for $i, $f in enumerate($inputs.pair_input):
SMPL${i}	${symlink_basename($f.forward.dataset)},${symlink_basename($f.reverse.dataset)}	a
    #end for
#end if
]]></configfile>
    </configfiles>
    <inputs>
        <conditional name="inputs">
            <param name="paired_or_single" type="select" label="Single- or Paired-end data?">
                <option value="single" selected="true">Single-end</option>
                <option value="paired_collection">Paired-end list</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="-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="-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="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="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">
                <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>
        <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 https://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>
                <option value="0">OTU chimera checks</option>
                <option value="1">No chimera check at all</option>
                <option value="2">Disable deNovo chimera check</option>
                <option value="3">Disable ref based chimera check</option>
            </param>
            <param argument="-chim_skew" type="integer" min="0" value="" optional="true" label="Skew in chimeric fragment abundance" />
        </section>
        <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>
                    <option value="LSU">LSU Large subunit (23S/28S)</option>
                    <option value="SSU">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>
                <when value="" />
                <when value="LSU" />
                <when value="SSU" />
                <when value="ITS">
                    <expand macro="ITSx_macro" />
                </when>
                <when value="ITS1">
                    <expand macro="ITSx_macro" />
                </when>
                <when value="ITS2">
                    <expand macro="ITSx_macro" />
                </when>
            </conditional>
            <param argument="-tax_group" type="select" label="Tax group">
                <option value="" selected="true">(Default)</option>
                <option value="bacteria">bacterial 16S rDNA annnotation</option>
                <option value="fungi">fungal 18S/23S/ITS annotation</option>
            </param>
            <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="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>
                <option value="2">Use iqtree2</option>
            </param>
            <param argument="-taxExcludeGrep" type="text" value="" label="Taxonomic groups to exclude, as a regular expression" help="OTUs matching this regular expression will be assigned as unknown, and by default removed">
                <sanitizer>
                    <valid initial="default">
                        <add value="|" />
                        <add value="$" />
                    </valid>
                </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>
        <data name="outputs" format="zip" label="${tool.name} on ${on_string}: Complete LotuS2 output" from_work_dir="output.zip" />
        <data name="otu" format="tabular" label="${tool.name} on ${on_string}: OTU abundance matrix" from_work_dir="output/OTU.txt" />
        <data name="otu_fna" format="fasta" label="${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 ${on_string}: Newick-formatted phylogenetic tree between sequences" from_work_dir="output/OTUphylo.nwk" />
        <data name="mapping" format="tabular" label="${tool.name} on ${on_string}: mapping file" from_work_dir="output/primary/in.map" />
        <data name="runlog" format="txt" label="${tool.name} on ${on_string}: main log file" from_work_dir="output/LotuSLogS/LotuS_run.log" />
    </outputs>

    <tests>
        <test>
            <conditional name="inputs">
                <param name="paired_or_single" value="single"/>
                <param name="input" value="Anh_sample1.fastq.gz,Anh_sample2.fastq.gz" ftype="fastqsanger.gz"/>
            </conditional>
            <conditional name="clu_cond">
                <param name="clustering" value="3" />
            </conditional>
            <section name="clu_args">
                <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" />
        </test>
        <test>
            <conditional name="inputs">
                <param name="paired_or_single" value="paired_collection"/>
                <param name="pair_input">
                    <collection type="list:paired">
                        <element name="Anh_sample">
                            <collection type="paired">
                                <element name="forward" value="Arabidopsis_R1.fastqsanger.gz" ftype="fastqsanger.gz" />
                                <element name="reverse" value="Arabidopsis_R2.fastqsanger.gz" ftype="fastqsanger.gz" />
                            </collection>
                        </element>
                    </collection>
                </param>
            </conditional>
            <param name="map" value="mapping_paired.txt" ftype="tabular" />
            <section name="tax_args">
                <param name="lulu" value="true" />
            </section>
            <output name="otu" file="OTU_paired.txt" compare="sim_size" />
            <output name="otu_fna" file="OTU_paired.fna" 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.

.. class:: infomark

The full LotuS2 **documentation** can be found at `<https://lotus2.earlham.ac.uk/>`_.
    ]]></help>
    <citations>
        <citation type="doi">10.1186/s40168-022-01365-1</citation>
        <citation type="doi">10.1186/s40168-021-01012-1</citation>
    </citations>
</tool>