| Next changeset 1:cc21614b6693 (2019-08-13) |
|
Commit message:
planemo upload for repository https://github.com/ebi-gene-expression-group/container-galaxy-sc-tertiary/ commit 9bf9a6e46a330890be932f60d1d996dd166426c4 |
|
added:
retrieve-scxa.xml |
| b |
| diff -r 000000000000 -r cd6b80f62fcc retrieve-scxa.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/retrieve-scxa.xml Wed Apr 03 12:01:53 2019 -0400 |
| [ |
| @@ -0,0 +1,117 @@ +<?xml version="1.0" encoding="utf-8"?> +<tool id="retrieve_scxa" name="EBI SCXA Data Retrieval" version="v0.0.1+galaxy1"> + <description>Retrieves expression matrixes and metadata from EBI Single Cell Expression Atlas (SCXA)</description> + <requirements> + <requirement type="package" version="1.18">gnu-wget</requirement> + </requirements> + <command detect_errors="exit_code"><![CDATA[ + +#if str($matrix_type) == "tpm": + +wget -O exp_quant.zip + 'https://www.ebi.ac.uk/gxa/sc/experiment/${accession}/download/zip?fileType=quantification-filtered&accessKey=' && +unzip exp_quant.zip; +mv '${accession}'.expression_tpm.mtx ${matrix_mtx} && +awk '{OFS="\t"; print \$2,\$2}' '${accession}'.expression_tpm.mtx_rows > ${genes_tsv} && +cut -f2 '${accession}'.expression_tpm.mtx_cols > ${barcode_tsv}; + +#else if str($matrix_type) == "raw": + +wget -O ${matrix_mtx} 'ftp://ftp.ebi.ac.uk/pub/databases/microarray/data/atlas/sc_experiments/${accession}/${accession}.aggregated_filtered_counts.mtx'; +wget -qO - 'ftp://ftp.ebi.ac.uk/pub/databases/microarray/data/atlas/sc_experiments/${accession}/${accession}.aggregated_filtered_counts.mtx_cols' | cut -f2 > ${barcode_tsv}; +wget -qO - 'ftp://ftp.ebi.ac.uk/pub/databases/microarray/data/atlas/sc_experiments/${accession}/${accession}.aggregated_filtered_counts.mtx_rows' + | awk '{OFS="\t"; print \$2,\$2}' > ${genes_tsv}; + +#end if + +wget -O exp_design.tsv + 'https://www.ebi.ac.uk/gxa/sc/experiment/${accession}/download?fileType=experiment-design&accessKey='; + +]]></command> + + <inputs> + <param name="accession" type="text" value="E-GEOD-100058" label="SC-Atlas experiment accession" help="EBI Single Cell Atlas accession for the experiment that you want to retrieve."/> + <param name="matrix_type" type="select" label="Choose the type of matrix to download" help="Raw filtered counts or (non-filtered) TPMs"> + <option value="raw" selected="true">Raw filtered counts</option> + <option value="tpm">TPMs</option> + </param> + </inputs> + + <outputs> + <data name="matrix_mtx" format="txt" label="${tool.name} on ${on_string} ${accession} matrix.mtx (${matrix_type.value_label})"/> + <data name="genes_tsv" format="tsv" label="${tool.name} on ${on_string} ${accession} genes.tsv (${matrix_type.value_label})"/> + <data name="barcode_tsv" format="tsv" label="${tool.name} on ${on_string} ${accession} barcodes.tsv (${matrix_type.value_label})"/> + <data name="design_tsv" format="tsv" from_work_dir="exp_design.tsv" label="${tool.name} on ${on_string} ${accession} exp_design.tsv"/> + </outputs> + + <tests> + <test> + <param name="accession" value="E-GEOD-100058"/> + <param name="matrix_type" value="tpm"/> + <output name="matrix_mtx" file="E-GEOD-100058.expression_tpm.mtx" ftype="txt"/> + <output name="genes_tsv" file="E-GEOD-100058.genes.tsv" ftype="tsv"/> + <output name="barcode_tsv" file="E-GEOD-100058.barcodes.tsv" ftype="tsv"/> + <output name="design_tsv" file="E-GEOD-100058.exp_design.tsv" ftype="tsv"/> + </test> + </tests> + + <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 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. + +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. + +: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. + +]]></help> + <citations> + <citation type="doi">10.1093/nar/gkv1045</citation> + </citations> +</tool> |