annotate macros_cluster.xml @ 3:0fa80752a314 draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/raceid3 commit d94b3b8a4c7cf8c604279eb1eea24d32b3868922

<macros>
    <macro name="cluster_inputs" >
        <param name="intable" type="data" format="tabular" label="Count Matrix" />
        <section name="filt" title="Filtering" expanded="true" >
            <param name="mintotal" type="integer" min="1" value="3000" label="Min Transcripts" help="The minimum total transcripts required. Cells with less than mintotal transcripts are filtered out." />
            <param name="minexpr" type="integer" min="1" value="5" label="Min Expression" help="The minimum required transcript counts of a gene in the minimum number of cells (below)" />
            <param name="minnumber" type="integer" min="1" value="5" label="Min Cells" help="The minumum number of cells for gene expression to be counted"  />
            <expand macro="use_defaults_no" >
                <param name="knn" type="integer" min="0" value="10" label="K-nearest-neighbours" help="Number of nearest neighbors used to infer corresponding cell types in different batches" />
                <param name="CGenes" type="text" optional="true" label="CGenes" help="Filter out genes with correlated expression for cell type inference" >
                    <expand macro="sanitize_string_vector" />
                </param>
                <param name="FGenes" type="text" optional="true" label="FGenes" help="Explicitly filter out genes for cell type inference" >
                    <expand macro="sanitize_string_vector" />
                </param>
                <param name="LBatch_regexes" type="text" optional="true" label="Batch Regex" help="List of regexes to capture experimental batches for batch effect correction" >
                    <expand macro="sanitize_string_vector" />
                </param>
                <param name="ccor" type="float" value="0.4" label="CCor" help="Correlation coefficient used as a threshold for determining correlated genes" />
                <param name="bmode" type="select" label="Batch Mode" help="Method to regress out batch effects" >
                    <option value="RaceID" selected="true" >RaceID</option>
                    <option value="scran">SCRAN</option>
                </param>
                <conditional name="ccc" >
                    <param name="use" type="select" label="Perform Cell-cycle correction?" >
                        <option value="yes" >Yes</option>
                        <option value="no" selected="true" >No</option>
                    </param>
                    <when value="no" />
                    <when value="yes" >
                        <param name="vset" type="text" optional="true" label="List of Gene Sets" >
                            <expand macro="sanitize_string_vector" />
                        </param>
                        <param name="pvalue" type="float" value="0.01" min="0" max="1" label="P-value Cutoff" help="P-value cutoff for determining enriched components" />
                        <param name="quant" type="float" value="0.01" min="0" max="1" label="Quantification Fraction" help="Upper and lower fraction of gene loadings use for determining enriched components"  />
                        <param name="ncomp" type="integer" min="0" optional="true" label="Number of components to use" help="If left blank, the maximum number of components are used" /><!-- 0 = NULL -->
                        <param name="dimr" type="boolean" value="true" label="Derive Components from saturation criterion"  />
                        <param name="mode" type="select" label="Type of Component Analysis" help="If ICA is selected, ensure that the number of components value above is sufficiently high" >
                            <option value="pca" selected="true">PCA</option>
                            <option value="ica">ICA</option>
                        </param>
                        <param name="logscale" type="boolean" value="false" label="Log-transform data prior to PCA or ICA" help="" />
                    </when>
                </conditional>
            </expand>
        </section>
        <section name="clust" title="Clustering" expanded="true" >
            <!-- CompDist -->
            <param name="metric" type="select" label="Distance Metric" >
                <option value="pearson" selected="true" >Pearson</option>
                <option value="spearman">Spearman</option>
                <option value="logpearson">Log Pearson</option>
                <option value="euclidean">Euclidean</option>
            </param>
            <!-- ClustExp -->
            <param name="funcluster" type="select" label="Clustering method" >
                <option value="kmedoids" selected="true" >K-medoids</option>
                <option value="kmeans">K-means</option>
                <option value="hclust">H-Clust</option>
            </param>
            <expand macro="use_defaults_no" >
                <!-- CompDist -->
                <param name="fselect" type="boolean" value="true" label="Perform feature selection" />
                <param name="knn" type="integer" min="0" optional="true" label="KNN" help="Number of nearest neighbours for imputing gene expression" /><!-- 0: NULL -->
                <!-- ClustExp -->
                <param name="sat" type="boolean" checked="true" label="Saturation-based clustering?" help="Determine number of clusters on saturation point of the mean within-cluster dispersion as a function of the cluster number." />
                <param name="clustnr" type="integer" min="0" value="30" label="Max number of clusters using Saturation-by-mean" help="Max number of clusters for the derivation of the cluster number by the saturation of mean within-cluster-dispersion." />
                <param name="samp" type="integer" min="0" optional="true" label="Sample random number of cells" help="Number of random sample of cells used for the inference of cluster number and Jaccard similarity" /><!-- 0:NULL -->
                <param name="cln" type="integer" min="0" optional="true" label="Number of clusters" /><!-- 0:Null -->
                <param name="bootnr" type="integer" min="0" value="50" label="Number of booststrapping runs" />
                <param name="rseed" type="integer" value="17000" label="Random seed" />
            </expand>
        </section>
        <section name="outlier" title="Outliers" expanded="true" >
            <!-- Find Outliers -->
            <param name="outminc" type="integer" min="0" value="5" label="Minimum Transcripts" help="minimal transcript count of a gene in a clusters to be tested for being an outlier gene" />
            <param name="outlg" type="integer" min="1" value="2" label="Minimum Genes" help="Minimum number of outlier genes required for being an outlier cell" />
            <!-- RFCorrect -->
            <param name="final" type="boolean" value="true" label="Plot Final Clusters?" help="Reclassification of cell types using out-of-bag analysis is performed based on the final clusters after outlier identification. If 'FALSE', then the cluster partition prior to outlier identification is used for reclassification." />
            <expand macro="use_defaults_no" >
                <!-- Find Outliers -->
                <param name="probthr" type="float" min="0" value="0.001" label="Outlier Probability Threshold" help="Probability threshold for the above specified minimum number of genes to be an outlier cell. This probability is computed from a negative binomial background model of expression in a cluster" />
                <param name="outdistquant" type="float" min="0" max="1" value="0.95" label="Outlier Distance Quantile" help="Outlier cells are merged to outlier clusters if their distance smaller than the outdistquant-quantile of the distance distribution of pairs of cells in the orginal clusters after outlier removal" />
                <!-- RFCorrect -->
                <param name="nbtree" type="integer" optional="true" label="Number of trees to be built" /><!-- 0:Null -->
                <param name="nbfactor" type="integer" min="0" value="5" label="Tree Factor" help="Number of trees based on the number of cells multiplied by this factor. Effective only if the number of trees parameter is set to 0" />
                <param name="rfseed" type="integer" value="12345" label="Random Seed" />
            </expand>
        </section>
        <section name="tsne" title="tSNE and FR" expanded="true" >
            <!-- CompTSNE -->
            <param name="perplexity" type="integer" min="0" value="30" label="Perplexity" help="Perplexity of the t-SNE map" />
            <!-- CompFR -->
            <param name="knn" type="integer" min="0" value="10" label="KNN" help="Number of nearest neighbours used for the inference of the Fruchterman-Rheingold layout" />
            <expand macro="use_defaults_no" >
                <!-- CompTSNE -->
                <param name="initial_cmd" type="boolean" checked="true" label="tSNE map initialised by classical multidimensional scaling" />
                <param name="rseed_tsne" type="integer" value="15555" label="Random Seed (tSNE)" />
                <!-- CompFR -->
                <param name="rseed_fr" type="integer" min="0" value="15555" label="Random Seed (FR)" />
            </expand>
        </section>
        <section name="extra" title="Extra Parameters" expanded="false" >
            <param name="tablelim" type="integer" min="1" value="25" label="Table Limit" help="Top N genes to print per cluster" />
            <param name="plotlim" type="integer" min="1" value="10" label="Plot Limit" help="Top N genes to plot. Must be less than or equal to the Table Limit" />
            <param name="foldchange" type="float" min="0" value="1" label="Fold change" />
            <param name="pvalue" type="float" min="0" max="1" value="0.01" label="P-value Cutoff" help="P-value cutoff for the inference of differential gene expression" />
        </section>
    </macro>
    <macro name="cluster_tests" >
        <test>
            <!-- default test -->
            <conditional name="tool" >
                <param name="mode" value="cluster" />
                <!-- This is a file with a single word 'test', which prompts the scripts to use the test intestinalData in the library -->
                <param name="intable" value="use.intestinal" />
            </conditional>
            <output name="outgenelist" value="intestinal.genelist" />
            <output name="outpdf" value="intestinal.pdf" compare="sim_size" delta="50" />
        </test>
        <test>
            <!-- defaults, feeding in a matrix with reduced filtering -->
            <conditional name="tool" >
                <param name="mode" value="cluster" />
                <param name="intable" value="matrix.tabular" />
                <section name="filt" >
                    <param name="mintotal" value="1000" />
                    <param name="minexpr" value="1" />
                    <param name="minnumber" value="3" />
                </section>
                <param name="use_log" value="true" />
                <output name="outgenelist" value="matrix.genelist" />
                <output name="outrdat" value="matrix.rdat" compare="sim_size" delta="15" />
                <output name="outpdf" value="matrix.pdf" compare="sim_size" delta="10" />
                <output name="outlog" value="matrix.log" />
            </conditional>
        </test>
        <test>
            <!-- defaults, but manually specified. No opts, no CC. Generates identical to above -->
            <conditional name="tool" >
                <param name="mode" value="cluster" />
                <param name="intable" value="use.intestinal" />
                <section name="filt" >
                    <param name="mintotal" value="3000" />
                    <param name="minexpr" value="5" />
                    <param name="minnumber" value="5" />
                    <expand macro="test_nondef" >
                        <param name="knn" value="10" />
                        <param name="ccor" value="0.4" />
                        <param name="bmode" value="RaceID" />
                    </expand>
                </section>
                <section name="clust" >
                    <param name="metric" value="pearson" />
                    <param name="funcluster" value="kmedoids" />
                    <expand macro="test_nondef" >
                        <param name="fselect" value="true" />
                        <param name="sat" value="true" />
                        <param name="clustnr" value="30" />
                        <param name="bootnr" value="50" />
                        <param name="rseed" value="17000" />
                    </expand>
                </section>
                <section name="outlier" >
                    <param name="outminc" value="5" />
                    <param name="outlg" value="2" />
                    <param name="final" value="false" />
                    <expand macro="test_nondef" section_name="outlier" >
                        <param name="probthr" value="0.001" />
                        <param name="outdistquant" value="0.95" />
                        <param name="rfseed" value="12345" />
                        <param name="nbfactor" value="5" />
                    </expand>
                </section>
                <section name="tsne" >
                    <param name="perplexity" value="30" />
                    <param name="knn" value="10" />
                    <expand macro="test_nondef" section_name="tsne" >
                        <param name="initial_cmd" value="true" />
                        <param name="rseed_tsne" value="15555" />
                        <param name="rfseed_fr" value="15555" />
                    </expand>
                </section>
            </conditional>
            <output name="outgenelist" value="intestinal.genelist" />
            <output name="outpdf" value="intestinal.pdf" compare="sim_size" delta="50" />
        </test>
        <test>
            <!-- Advanced. Opts, CC used  -->
            <conditional name="tool" >
                <param name="mode" value="cluster" />
                <param name="intable" value="use.intestinal" />
                <section name="filt" >
                    <param name="mintotal" value="2000" />
                    <param name="minexpr" value="3" />
                    <param name="minnumber" value="2" />
                    <expand macro="test_nondef" >
                        <param name="knn" value="5" />
                        <param name="ccor" value="0.5" />
                        <param name="CGenes" value="Gga3,Ggact,Ggct" />
                        <param name="FGenes" value="Zxdc,Zyg11a,Zyg11b,Zyx" />
                        <param name="LBatch_regexes" value="^I5,^II5,^III5,^IV5d,^V5d" />
                        <param name="bmode" value="scran" />
                        <conditional name="ccc" >
                            <param name="use" value="yes" />
                            <param name="pvalue" value="0.05" />
                            <param name="quant" value="0.05" />
                            <param name="ncomp" value="3" />
                            <param name="dimr" value="true" />
                            <param name="mode" value="pca" />
                            <param name="logscale" value="true" />
                        </conditional>
                    </expand>
                </section>
                <section name="clust" >
                    <param name="metric" value="euclidean" />
                    <param name="funcluster" value="hclust" />
                    <expand macro="test_nondef" >
                        <param name="fselect" value="false" />
                        <param name="knn" value="5" />
                        <param name="sat" value="false" />
                        <param name="samp" value="10" />
                        <param name="cln" value="10" />
                        <param name="clustnr" value="10" />
                        <param name="bootnr" value="30" />
                        <param name="rseed" value="17000" />
                    </expand>
                </section>
                <section name="outlier" >
                    <param name="outminc" value="3" />
                    <param name="outlg" value="5" />
                    <param name="final" value="true" />
                    <expand macro="test_nondef" >
                        <param name="probthr" value="0.01" />
                        <param name="outdistquant" value="0.5" />
                        <param name="rfseed" value="12345" />
                        <param name="nbfactor" value="5" />
                        <param name="nbtree" value="10" />
                    </expand>
                </section>
                <section name="tsne" >
                    <param name="perplexity" value="20" />
                    <param name="knn" value="6" />
                    <expand macro="test_nondef" >
                        <param name="initial_cmd" value="false" />
                        <param name="rseed_tsne" value="15555" />
                        <param name="rfseed_fr" value="15555" />
                    </expand>
                </section>
            </conditional>
            <output name="outgenelist" value="intestinal_advanced.genelist" />
            <output name="outpdf" value="intestinal_advanced.pdf" compare="sim_size" delta="150" />
        </test>
    </macro>
    <token name="@FILTNORM_CHEETAH@"><![CDATA[
## Perform do.filter
use.filtnormconf = TRUE

## Perform do.cluster, do.outlier, do.clustmap, mkgenelist
use.cluster = FALSE

in.table = read.table(
    '${intable}',
    stringsAsFactors = F,
    na.strings=c("NA", "-", "?", "."),
    sep='\t',
    header=TRUE,
    row.names=1
)

## Hidden flag to use test data instead
## see: test-data/use.intestinal

use.test.data = (names(in.table)[1] == "test")

sc = NULL
if (use.test.data) {
  sc = SCseq(intestinalData)
  message("Loading test data from library")
} else {
  sc = SCseq(in.table)
}


filt = formals(filterdata)
filt.ccc = formals(CCcorrect)
filt.use.ccorrect = FALSE
filt.lbatch.regexes = NULL

filt.geqone = as.logical( '$filt.hist_geq_one' )
filt\$mintotal = as.integer( '$filt.mintotal' )
filt\$minexpr = as.integer( '$filt.minexpr' )
filt\$minnumber = as.integer( '$filt.minnumber' )
#if str($filt.use.def) == "no":
filt\$knn = as.integer( '$filt.use.knn' )
filt\$ccor = as.numeric( '$filt.use.ccor' )
filt\$bmode = as.character( '$filt.use.bmode' )
    #if $filt.use.LBatch_regexes:
filt.lbatch.regexes = string2textvector( '$filt.use.LBatch_regexes' )
    #end if
    #if $filt.use.CGenes:
filt\$CGenes = string2textvector( '$filt.use.CGenes' )
    #end if
    #if $filt.use.FGenes:
filt\$FGenes = string2textvector( '$filt.use.FGenes' )
    #end if
    #if str($filt.use.ccc.use) == "yes"
filt.use.ccorrect = TRUE
        #if $filt.use.ccc.vset:
filt.ccc\$vset = string2textvector( '$filt.use.ccc.vset' )
        #end if
        #if $filt.use.ccc.ncomp:
filt.ccc\$nComp = as.integer( '$filt.use.ccc.ncomp' )
        #end if
filt.ccc\$pvalue = as.numeric( '$filt.use.ccc.pvalue' )
filt.ccc\$quant = as.numeric( '$filt.use.ccc.quant' )
filt.ccc\$dimR = as.logical( '$filt.use.ccc.dimr' )
filt.ccc\$mode = as.character( '$filt.use.ccc.mode.value' )
filt.ccc\$logscale = as.logical( '$filt.use.ccc.logscale' )
    #end if
#end if

out.pdf = '${outpdf}'
out.rdat = '${outrdat}'

]]></token>
    <token name="@CLUSTER_CHEETAH@"><![CDATA[

in.rdat = readRDS('${inputrds}')

sc = in.rdat

## Perform do.filter
use.filtnormconf = FALSE

## Perform do.cluster, do.outlier, do.clustmap, mkgenelist
use.cluster = TRUE


clust.compdist = formals(compdist)
clust.clustexp = formals(clustexp)
clust.compdist\$metric = as.character( '$clust.metric' )
clust.clustexp\$FUNcluster = as.character( '$clust.funcluster' )

#if str($clust.use.def) == "no":

clust.compdist\$FSelect = as.logical( '$clust.use.fselect' )
    #if $clust.use.knn:
clust.compdist\$knn = as.integer( '$clust.use.knn' )
    #end if
clust.clustexp\$sat = as.logical( '$clust.use.sat' )
    #if $clust.use.samp:
clust.clustexp\$samp = as.integer( '$clust.use.samp' )
    #end if
    #if $clust.use.cln:
clust.clustexp\$cln = as.integer( '$clust.use.cln' )
clust.clustexp\$clustnr = as.integer( '$clust.use.clustnr' )
clust.clustexp\$bootnr = as.integer( '$clust.use.bootnr' )
##clust.clustexp\$rseed = as.integer( '$clust.use.rseed' )
    #end if
#end if

outlier.use.randomforest = FALSE
outlier.findoutliers = formals(findoutliers)
outlier.clustheatmap = formals(clustheatmap)
outlier.rfcorrect = formals(rfcorrect)

outlier.findoutliers\$outminc = as.integer( '$outlier.outminc' )
outlier.findoutliers\$outlg = as.integer( '$outlier.outlg' )
outlier.rfcorrect\$final = as.logical( '$outlier.final' )

#if str($outlier.use.def) == "no":
    #if $outlier.use.nbtree:
outlier.rfcorrect\$nbtree = as.integer( '$outlier.use.nbtree' )
    #end if
outlier.findoutliers\$probthr = as.numeric( '$outlier.use.probthr' )
outlier.findoutliers\$outdistquant = as.numeric( '$outlier.use.outdistquant' )
##outlier.rfcorrect\$rfseed = as.integer( '$outlier.use.rfseed' )
outlier.rfcorrect\$nbfactor = as.integer( '$outlier.use.nbfactor' )
#end if

cluster.comptsne = formals(comptsne)
cluster.compfr = formals(compfr)

cluster.comptsne\$perplexity = as.integer( '$tsne.perplexity' )
cluster.compfr\$knn = as.integer( '$tsne.knn' )
#if str($tsne.use.def) == "no":
cluster.comptsne\$initial_cmd = as.logical( '$tsne.use.initial_cmd' )
cluster.comptsne\$rseed = as.integer( '$tsne.use.rseed_tsne' )
cluster.compfr\$rseed = as.integer( '$tsne.use.rseed_fr' )
#end if

genelist.tablelim = as.integer( '$extra.tablelim' )
genelist.plotlim = as.integer( '$extra.plotlim' )
genelist.foldchange = as.integer( '$extra.foldchange' )
genelist.pvalue = as.numeric( '$extra.pvalue' )

out.pdf = '${outpdf}'
out.rdat = '${outrdat}'
out.genelist = '${outgenelist}'

]]>
    </token>
</macros>