comparison seurat_find_clusters.xml @ 1:bdabb6af06e4 draft

planemo upload for repository https://github.com/ebi-gene-expression-group/container-galaxy-sc-tertiary/ commit 0463f230d18201c740851d72e31a5024f391207f

0:8ea738667314

<tool id="seurat_find_clusters" name="Seurat FindClusters" version="2.3.1+galaxy1">
    <description>find clusters of cells</description>
    <macros>
        <import>seurat_macros.xml</import>
    </macros>
    <expand macro="requirements" />
    <expand macro="version" />
    <command detect_errors="exit_code"><![CDATA[
        seurat-find-clusters.R

        --input-object-file '$input'
        --output-object-file '$output'
        --output-text-file output_tab

        #if $genes_use:
          --genes-use '$genes_use'
        #end if

        #if str($adv.reduction_type):
          --reduction-type '$adv.reduction_type'
        #end if

        #if str($adv.dims_use):
          --dims-use \$(seq -s , 1 '$adv.dims_use')
        #end if

        #if str($adv.k_num_clusters):
          --k-param '$adv.k_num_clusters'
        #end if

        #if str($adv.prune_snn):
          --prune-snn '$adv.prune_snn'
        #end if

        #if str($adv.resolution):
          --resolution '$adv.resolution'
        #end if

        #if str($adv.algorithm):
          --algorithm '$adv.algorithm'
        #end if

  ## TODO add pdf support as optional
  ]]></command>

      <inputs>
        <param name="input" argument="--input-object-file" type="data" format="rdata" label="Seurat RDS object" help="Seurat object produced by Seurat run PCA or other." />
        <expand macro="genes-use-input"/>
          <section name="adv" title="Advanced Options">
            <param name="reduction_type" argument="--reduction-type" optional="true" type="select" label="Dimensional reduction type" help="dimensional reduction technique to use in construction of SNN graph. (e.g. 'pca', 'ica'). PCA by default.">
              <option value="pca" selected="true">PCA</option>
              <option value="ica">ICA</option>
            </param>
            <expand macro="dims-use-input"/>
            <param name="k_num_clusters" argument="--k-param" optional="true" type="integer" label="Number of clusters (k) to compute" help="Defines k for the k-nearest neighbor algorithm."/>
            <param name="prune_snn" argument="--prune-snn" optional="true" type="float" label="Prune SNN cutoff" help="Sets the cutoff for acceptable Jaccard distances when computing the neighborhood overlap for the SNN construction. Any edges with values less than or equal to this will be set to 0 and removed from the SNN graph. Essentially sets the strigency of pruning (0 — no pruning, 1 — prune everything). Defaults to 1/15."/>
            <param name="resolution" argument="--resolution" optional="true" type="float" label="Resolution" help="Value of the resolution parameter, use a value above (below) 1.0 if you want to obtain a larger (smaller) number of communities. Defaults to 0.8."/>
            <param name="algorithm" argument="--algorithm" optional="true" type="select" label="Modularity organization algorithm">
              <option value="1" selected="true">Louvain</option>
              <option value="2">Louvain algorithm with multilevel refinement</option>
              <option value="3">SLM algorithm</option>
            </param>
          </section>
      </inputs>
      <outputs>
          <!-- <data name="out_pdf" format="pdf" from_work_dir="out.pdf" label="${tool.name} on ${on_string}: Plots" /> -->
          <data name="output" format="rdata" from_work_dir="*.rds" label="${tool.name} on ${on_string}: Seurat RDS"/>
          <data name="output_tab" format="csv" from_work_dir="output_tab" label="${tool.name} on ${on_string}: CSV Seurat Clusters"/>
      </outputs>

    <tests>
        <!-- Ensure count matrix input works -->
        <test>
            <param name="input" ftype="rdata" value="out_runpca.rds"/>
            <output name="output" ftype="rdata" value="out_findclust.rds" compare="sim_size"/>
        </test>
    </tests>
    <help><![CDATA[
.. class:: infomark

**What it does**

Seurat_ is a toolkit for quality control, analysis, and exploration of single cell RNA sequencing data.
It is developed and maintained by the `Satija Lab`_ at NYGC. Seurat aims to enable users to identify and
interpret sources of heterogeneity from single cell transcriptomic measurements, and to integrate diverse
types of single cell data.

Seurat clustering use SNN method to determine different clusters in your dataset. In order to construct a
SNN graph, you must have perform a PCA before launch this tool (you can use Seurat dimensional reduction).
It will search k (30) nearest neighbors for each cells and link cells to each other if they shared the
same neighbors. You can modulate the resolution in order to get larger (resolution superior to 1) or smaller
(inferior to 1) clusters.

-----

**Inputs**

1:bdabb6af06e4

<tool id="seurat_find_clusters" name="Seurat FindClusters" version="@SEURAT_VERSION@_@VERSION@+galaxy0">
    <description>find clusters of cells</description>
    <macros>
        <import>seurat_macros.xml</import>
    </macros>
    <expand macro="requirements" />
    <expand macro="version" />
    <command detect_errors="exit_code"><![CDATA[
        seurat-find-clusters.R

        @INPUT_OBJECT@
        @OUTPUT_OBJECT@
        --output-text-file output_tab

        #if str($adv.resolution):
          --resolution '$adv.resolution'
        #end if

        #if str($adv.algorithm):
          --algorithm '$adv.algorithm'
        #end if

        #if str($adv.modularity_fxn):
          --modularity-fxn '$adv.modularity_fxn'
        #end if

        #if str($adv.method):
          --method '$adv.method'
        #end if

        #if str($adv.graph_name):
          --graph-name '$adv.graph_name'
        #end if

        #if str($adv.nrandom_starts):
          --nrandom-starts '$adv.nrandom_starts'
        #end if

        $adv.group_singletons



  ## TODO add pdf support as optional
  ]]></command>

      <inputs>
        <expand macro="input_object_params"/>
        <expand macro="output_object_params"/>
          <section name="adv" title="Advanced Options">
            <param name="resolution" argument="--resolution" optional="true" type="float" label="Resolution" help="Value of the resolution parameter, use a value above (below) 1.0 if you want to obtain a larger (smaller) number of communities. Defaults to 0.8."/>
            <param name="algorithm" argument="--algorithm" optional="true" type="select" label="Modularity organization algorithm">
              <option value="1" selected="true">Louvain</option>
              <option value="2">Louvain algorithm with multilevel refinement</option>
              <option value="3">SLM algorithm</option>
              <option value="4">Leiden</option>
            </param>
            <param name="modularity_fxn" argument="--modularity-fxn" optional="true" type="select" label="Modularity function">
              <option value="1" selected="true">Standard</option>
              <option value="2">Alternative</option>
            </param>
            <param name="method" argument="--method" type="select" label="Method for Leiden" help="Method for leiden  (defaults to matrix which is fast for small datasets). Select iGraph to avoid casting large data to a dense matrix.">
              <option value="matrix" selected="true">Matrix</option>
              <option value="igraph">iGraph</option>
            </param>
            <param name="graph_name" argument="--graph-name" type="text" value="RNA_nn" label="Graph Name" help="Name of graph to use for the clustering algorith."/>
            <param name="nrandom_starts" argument="--nrandom-starts" type="integer" optional="true" label="Random starts" help="Number of random starts, 10 by default."/>
            <param name="group_singletons" argument="--group-singletons" type="boolean" truevalue="--group-singletons" falsevalue="" checked="false" label="Group singletons" help="Group singletons into nearest cluster. If FALSE, assign all singletons to a 'singleton' group."/>
            <param name="random_seed" argument="--random-seed" type="integer" optional="true" label="Random seed" help="Seed of the random number generator"/>
          </section>

      </inputs>
      <outputs>
          <!-- <data name="out_pdf" format="pdf" from_work_dir="out.pdf" label="${tool.name} on ${on_string}: Plots" /> -->
          <expand macro="output_files"/>
          <data name="output_tab" format="csv" from_work_dir="output_tab" label="${tool.name} on ${on_string}: CSV Seurat Clusters"/>
      </outputs>

    <tests>
        <!-- Ensure count matrix input works -->
        <test>
            <param name="input" ftype="rdata" value="out_runpca.rds"/>
            <output name="rds_seurat_file" ftype="rdata" value="out_findclust.rds" compare="sim_size"/>
        </test>
    </tests>
    <help><![CDATA[
.. class:: infomark

**What it does**

Identify clusters of cells by a shared nearest neighbor (SNN) modularity optimization
based clustering algorithm. First calculate k-nearest neighbors and construct t
he SNN graph (using Seurat find neighbours).
Then optimize the modularity function to determine clusters.
For a full description of the algorithms, see Waltman and van Eck (2013)
The European Physical Journal B.

@SEURAT_INTRO@

-----

**Inputs**