view retrieve-scxa.xml @ 3:a4bfd4a146ec draft

planemo upload for repository https://github.com/ebi-gene-expression-group/container-galaxy-sc-tertiary/ commit f6a8d0f8eb4225276e3db9e5ca04b7d11bac5bf6-dirty
author ebi-gxa
date Thu, 16 Jul 2020 10:48:16 +0000
parents d4755a95c52d
children e36cb0413c39
line wrap: on
line source

<tool id="retrieve_scxa" name="Atlas import: get experiment data" version="1.0.0+galaxy0"  profile="@PROFILE@">
    <description>Retrieve expression matrices and metadata from EBI Single Cell Expression Atlas (SCXA)</description>
    <macros>
         <import>atlas-retrieve-macros.xml</import>
    </macros>
    <expand macro="requirements" />
    <command detect_errors="exit_code"><![CDATA[
        ln -s "${accession_code}_${matrix_type}/10x_data/matrix.mtx" matrix.mtx &&
        ln -s "${accession_code}_${matrix_type}/10x_data/genes.tsv" genes.tsv &&
        ln -s "${accession_code}_${matrix_type}/10x_data/barcodes.tsv" barcodes.tsv &&
        ln -s "${accession_code}_${matrix_type}/sdrf.txt" sdrf.txt &&
        ln -s "${accession_code}_${matrix_type}/condensed-sdrf.tsv" condensed-sdrf.tsv &&
        ln -s "${accession_code}_${matrix_type}/idf.txt" idf.txt &&
        ln -s "${accession_code}_${matrix_type}/marker_genes_${number_of_clusters}.tsv" marker_genes_${number_of_clusters}.tsv &&
        ln -s "${accession_code}_${matrix_type}/exp_design.tsv" exp_design.tsv &&

        get_experiment_data.R --accesssion-code "${accession_code}" --matrix-type "${matrix_type}" --get-sdrf "${get_sdrf}" --get-condensed-sdrf "${get_condensed_sdrf}" --get-marker-genes "${get_marker_genes}"

        #if $config_file 
        --config-file "${config_file}"
        #end if        
        #if $get_exp_design
        --get-exp-design "${get_exp_design}" 
        #end if 
        #if $decorated_rows 
        --decorated-rows "${decorated_rows}" 
        #end if
        #if $use_default_expr_names 
        --use-default-expr-names "${use_default_expr_names}" 
        #end if
        #if $get_idf 
        --get-idf "${get_idf}" 
        #end if
        #if $number_of_clusters 
        --number-of-clusters  "${number_of_clusters}" 
        #end if
    ]]></command>
    <inputs>
        <param type="text" name="accession_code" label="SC-Atlas experiment accession" value="E-GEOD-100058" help="EBI Single Cell Atlas accession for the experiment that you want to retrieve." />
        <param type="select" name="matrix_type" label="Choose the type of matrix to download" help="Type of matrix to be imported">
            <option value="RAW">Raw</option>
            <option value="FILTERED">Filtered Counts</option>
            <option value="TPM">TPM-normalised</option>
            <option value="CPM">CPM-normalised</option>
        </param>
        <param type="boolean" name="get_sdrf" checked="false" label="Import SDRF file" help="Boolean indicating whether SDRF file needs to be imported" />
        <param type="boolean" name="get_exp_design" checked="false" label="Import experiment design file" help="Boolean indicating whether experiment design file needs to be imported" />
        <param type="boolean" name="get_idf" checked="false" label="Import IDF file" help="Boolean indicating whether IDF file needs to be imported" />
        <param type="boolean" name="get_condensed_sdrf" checked="false" label="Get condensed SDRF file" help="Boolean indicating whether condensed SDRF file needs to be imported" />
        <param type="boolean" name="get_marker_genes" checked="false" label="Import marker genes" help="Boolean indicating whether marker genes should be imported" />
        <param type="data" name="config_file" label="Config file" optional="true" format="yml" help="Config file with user-provided parameters" />
        <param type="boolean" name="decorated_rows" checked="false" label="Decorated rows" help="Boolean indicating whether a decorated version of the rows should be imported" />
        <param type="boolean" name="use_default_expr_names" checked="false"  label="Use default expr names" help="Should default (non 10x-type) file names be used for expression data? Default: FALSE" />
        <param type="integer" name="number_of_clusters" value="0" label="Number of clusters" help="Number of clusters in marker genes file" />
    </inputs>
    <outputs>
        <data name="expr_mtx" format="txt" from_work_dir="matrix.mtx" label="${tool.name} on ${on_string} ${accession_code} matrix.mtx (${matrix_type.value_label})" />
        <data name="barcodes" format="txt" from_work_dir="barcodes.tsv" label="${tool.name} on ${on_string} ${accession_code} barcodes.tsv (${matrix_type.value_label})" />
        <data name="genes" format="txt" from_work_dir="genes.tsv" label="${tool.name} on ${on_string} ${accession_code} genes.tsv (${matrix_type.value_label})" />
        <data name="sdrf" format="txt" from_work_dir="sdrf.txt" label="${tool.name} on ${on_string} ${accession_code} sdrf.txt (${matrix_type.value_label})" >
            <filter>get_sdrf</filter>
        </data>
        <data name="condensed_sdrf" format="txt" from_work_dir="condensed-sdrf.tsv" label="${tool.name} on ${on_string} ${accession_code} condensed-sdrf.tsv (${matrix_type.value_label})" >
            <filter>get_condensed_sdrf</filter>
        </data>
        <data name="idf" format="txt" from_work_dir="idf.txt" label="${tool.name} on ${on_string} ${accession_code} idf.txt (${matrix_type.value_label})">
            <filter>get_idf</filter>
        </data>
        <data name="marker_genes" from_work_dir="marker_genes_${number_of_clusters}.tsv" format="txt"  >
            <filter>get_marker_genes</filter>
        </data>
        <data name="exp_design" from_work_dir="exp_design.tsv" format="txt"  >
            <filter>get_exp_design</filter>
        </data>
    </outputs>
    <help><![CDATA[
=================================================================================
Gene expression analysis in single cells across species and biological conditions
=================================================================================

Single Cell Expression Atlas supports research in single cell transcriptomics.
The Atlas annotates publicly available single cell RNA-Seq experiments with
ontology identifiers and re-analyses them using standardised pipelines available
through iRAP, our RNA-Seq analysis toolkit. The browser enables visualisation of
clusters of cells, their annotations and supports searches for gene expression
within and across studies.

For more information check https://www.ebi.ac.uk/gxa/sc/home

EBI SCXA Data Retrieval
-----------------------

The data retrieval tool presented here allows the user to retrieve expression matrices
and metadata for any public experiment available at EBI Single Cell Expression Atlas.

To use it, simply set the accession for the desired experiment and choose the type of
matrix that you want to download:

:Raw counts:
  Un-normalised, unfiltered version of the expression data. 

:Filtered counts:
  This should be the default choice for running clustering and another analysis
  methods where you will introduce scaling and normalization of the data. The filtering
  is based on the quality control applied by iRAP prior to pseudo-alignment and quantification.

:TPMs:
  TPM stands for Transcripts Per Kilobase Million, and as the name implies, this has been
  already normalized/scaled. You should keep this in mind when using this data
  on methods that will try to normalise data as part of their procedure. Due to technical
  particularities in the current Atlas SC pipeline, TPMs available here are not filtered.
  **Note: droplet databases won't have TPM data**

:CPMS:
  CPM normalisation stands for Counts Per Kilobase Million. As TPMs, these matrices are already normalised/scaled. You should keep this in mind when using this data on methods that will try to normalise data as part of their procedure.   

Outputs will be:

:Matrix (txt):
  Contains the expression values for genes (rows) and samples/runs/cells (columns),
  in either raw filtered counts or filtered tpms depending on the choice made. This
  text file is formatted as a Matrix Market file, and as such it is accompanied by
  separate files for the gene identifiers and the samples/runs/cells identifiers.

:Genes (tsv):
  Identifiers (column repeated) for the genes present in the matrix of expression,
  in the same order as the matrix rows.

:Barcodes (tsv):
  Identifiers for the cells, samples or runs of the data matrix. The file is ordered
  to match the columns of the matrix.

Optional outputs: 

:Experiment Design file (tsv):
  Contains metadata for the different cells/samples/runs of the experiment.
  Please note that this file is generated before the filtering step, and while not
  often, it might be the case that it contains more cells/samples/runs than the matrix.

:SDRF file (txt):
  Similar to Experiment Design file, contains information on individual cells/sequencing runs. Might contain information on technical duplicates. 

:IDF file (txt): 
  IDF file holds general information about the sequencing experiment and interpretation of the fields in SDRF/metadata files. 
  
:Marker gene file (txt):
  File containing information on marker genes that differentiate cell types present in the sequencing experiment. 

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