annotate sc3-prepare.xml @ 0:9a2b61bfdaa9 draft default tip

planemo upload for repository https://github.com/ebi-gene-expression-group/container-galaxy-sc-tertiary/ commit 9bf9a6e46a330890be932f60d1d996dd166426c4

<?xml version="1.0" encoding="utf-8"?>
<tool id="sc3_prepare" name="SC3 Prepare" version="@TOOL_VERSION@+galaxy0">
  <description>a sc3 SingleCellExperiment object</description>
  <macros>
    <import>sc3-macros.xml</import>
  </macros>
  <expand macro="requirements" />
  <command detect_errors="exit_code"><![CDATA[
sc3-sc3-prepare.R -i '${scater_log}' -o '${sc3_prepared}' -t 1

#if $gene_filter.use:
    -f TRUE
    -p '${gene_filter.pct_dropout_min}'
    -q '${gene_filter.pct_dropout_max}'
#end if
#if $d_region_min:
    -d '${d_region_min}'
#end if
#if $d_region_max:
    -d '${d_region_max}'
#end if
#if $svm_num_cells:
    -n '${svm_num_cells}'
#end if
#if $svm_train_inds:
    -r '${svm_train_inds}'
#end if
#if $svm_max:
    -m '${svm_max}'
#end if
#if $seed:
    -s '${seed}'
#end if
#if $kmeans_nstart:
    -k '${kmeans_nstart}'
#end if
#if $kmeans_iter_max:
    -a '${kmeans_iter_max}'
#end if

  ]]></command>

  <inputs>
    <param name="scater_log" type="data" format="rdata" label="Serialised SingleCellExperiment object normalised by scater"/>

    <conditional name="gene_filter">
      <param name="use" argument="--gene-filter" type="boolean" label="Perform gene filtering?"
             help="A boolean variable which defines whether to perform gene filtering before SC3 clustering."/>
      <when value="true">
        <param name="pct_dropout_min" argument="--pct-dropout-min" type="integer" value="10" label="Minimum percent of dropouts"
               help="An integer value. Genes with percent of dropouts smaller than this value are filtered out before clustering."/>
        <param name="pct_dropout_max" argument="--pct-dropout-max" type="integer" value="90" label="Maximum percent of dropouts"
               help="An integer value. Genes with percent of dropouts larger than this value are filtered out before clustering."/>
      </when>
      <when value="false"/>
    </conditional>

    <param name="d_region_min" argument="--d-region-min" type="float" value="0.04" optional="true"
           label="Minimum number of eigenvectors used for kmeans clustering as a fraction of the total number of cells"/>

    <param name="d_region_max" argument="--d-region-max" type="float" value="0.07" optional="true"
           label="Maximum number of eigenvectors used for kmeans clustering as a fraction of the total number of cells"/>

    <param name="svm_num_cells" argument="--svm-num-cells" type="integer" optional="true"
           label="Number of randomly selected training cells to be used for SVM prediction."/>

    <param name="svm_train_inds" argument="--svm-train-inds" type="data" format="txt" optional="true"
           label="Text file with one integer per line defining indices of training cells that should be used for SVM training"/>

    <param name="svm_max" argument="--svm-max" type="integer" value="5000"
           label="The number of cells below which SVM are not run"/>

    <param name="seed" argument="--rand-seed" type="integer" value="1" optional="true" label="Seed of the random number generator"
           help="SC3 is a stochastic method, so setting the rand_seed to a fixed values can be used for reproducibility purposes."/>

    <param name="kmeans_nstart" argument="--kmeans-nstart" type="integer" optional="true" label="Number of random starts for kmeans"
           help="When unspecified, default to 1000 for up to 2000 cells and 50 for more than 2000 cells."/>

    <param name="kmeans_iter_max" argument="--kmeans-iter-max" type="integer" optional="true" label="Maximum number of iterations for kmeans"
           help="When unspecified, default to 1e+9."/>
  </inputs>

  <outputs>
    <data name="sc3_prepared" format="rdata" label="${tool.name} on ${on_string}: serialised sc3 SingleCellExperiment object"/>
  </outputs>

  <tests>
    <test>
      <param name="scater_log" value="scater_log.rdata"/>
      <output name="sc3_prepared" file="sc3_prepared.rdata"/>
    </test>
  </tests>

  <help><![CDATA[

==================================================================================
This function prepares an object of SingleCellExperiment class for SC3 clustering.
==================================================================================
It creates and populates the following items of the sc3 slot of the metadata(object):

- kmeans_iter_max: the same as the kmeans_iter_max argument.
- kmeans_nstart: the same as the kmeans_nstart argument.
- n_dim: contains numbers of the number of eigenvectors to be used in kmeans clustering.
- rand_seed: the same as the rand_seed argument.
- svm_train_inds: if SVM is used this item contains indexes of the training cells to be used for SC3 clustering and further SVM prediction.
- svm_study_inds: if SVM is used this item contains indexes of the cells to be predicted by SVM.
- n_cores: the same as the n_cores argument.

@HELP@

@VERSION_HISTORY@
]]></help>
   <expand macro="citations" />
</tool>