Mercurial > repos > iuc > anndata_import
view import.xml @ 4:080eab96d846 draft
"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/anndata/ commit 41e70af176ea64ef0bd45a6e980e21bdba80e739"
author | iuc |
---|---|
date | Sat, 18 Jan 2020 03:36:57 -0500 |
parents | b5c7ba11401d |
children | 32e547223c9e |
line wrap: on
line source
<tool id="anndata_import" name="Import Anndata and loom" version="@VERSION@+@GALAXY_VERSION@"> <description>from different format</description> <macros> <import>macros.xml</import> <xml name="params_10x"> <param name="barcodes" type="data" format="tabular,txt" label="Barcodes"/> <param name="var_names" type="select" label="Variables index"> <option value="gene_symbols">gene_symbols</option> <option value="gene_ids">gene_ids</option> </param> <param name="make_unique" type="boolean" truevalue="True" falsevalue="False" checked="true" label="Make the variable index unique by appending '-1', '-2'?"/> <param name="gex_only" type="boolean" truevalue="True" falsevalue="False" checked="true" label="Keep only 'Gene Expression' data and ignore other feature types?"/> </xml> </macros> <expand macro="requirements"> <requirement type="package" version="1.4.4.post1">scanpy</requirement> </expand> <expand macro="version_command"/> <command detect_errors="exit_code"><![CDATA[ #if $hd5_format.filetype == 'anndata' #if $hd5_format.in.adata_format == 'mtx' mkdir mtx #if $hd5_format.in.tenx.use == 'legacy_10x' && cp '$hd5_format.in.matrix' 'mtx/matrix.mtx' && cp '$hd5_format.in.tenx.genes' 'mtx/genes.tsv' && cp '$hd5_format.in.tenx.barcodes' 'mtx/barcodes.tsv' #else if $hd5_format.in.tenx.use == 'v3_10x' && cp '$hd5_format.in.matrix' 'mtx/matrix.mtx' && gzip 'mtx/matrix.mtx' && cp '$hd5_format.in.tenx.features' 'mtx/features.tsv' && gzip 'mtx/features.tsv' && cp '$hd5_format.in.tenx.barcodes' 'mtx/barcodes.tsv' && gzip 'mtx/barcodes.tsv' #end if && #else if $hd5_format.in.adata_format == 'umi_tools' gzip '$hd5_format.in.input' && #end if @CMD@ #if $hd5_format.in.adata_format == 'mtx' && rm -rf mtx #end if #else: python '$__tool_directory__/tsv_to_loompy.py' -c '${hd5_format.coldata}' -r '${hd5_format.rowdata}' -f '${hd5_format.mainmatrix}' #if $hd5_format.other_files: '${hd5_format.other_files}' #end if #end if ]]></command> <configfiles> <configfile name="script_file"><![CDATA[ @CMD_imports@ #if $hd5_format.filetype == 'anndata' #if $hd5_format.in.adata_format == 'loom' adata = ad.read_loom( '$hd5_format.in.input', sparse=$hd5_format.in.sparse, cleanup=$hd5_format.in.cleanup, X_name='$hd5_format.in.x_name', obs_names='$hd5_format.in.obs_names', var_names='$hd5_format.in.var_names') #else if $hd5_format.in.adata_format == 'tabular' #set delimiter=$hd5_format.in.input.metadata.delimiter #if $delimiter != ',' #set delimiter='\\t' #end if adata = ad.read_csv( '$hd5_format.in.input', delimiter='$delimiter', first_column_names=$hd5_format.in.first_column_names) #else if $hd5_format.in.adata_format == 'mtx' #if $hd5_format.in.tenx.use == 'no' adata = ad.read_mtx(filename='$hd5_format.in.matrix') #else import scanpy as sc adata = sc.read_10x_mtx( 'mtx', var_names='$hd5_format.in.tenx.var_names', make_unique=$hd5_format.in.tenx.make_unique, cache=False, gex_only=$hd5_format.in.tenx.gex_only) #end if #else if $hd5_format.in.adata_format == 'umi_tools' adata = ad.read_umi_tools('${hd5_format.in.input}.gz') #end if adata.write('anndata.h5ad') #end if ]]></configfile> </configfiles> <inputs> <conditional name="hd5_format"> <param name="filetype" type="select" label="hd5 format to be created"> <option value="anndata" selected="true">Anndata file</option> <option value="loom">Loom file</option> </param> <when value="anndata"> <conditional name="in"> <param name="adata_format" type="select" label="Format for the annotated data matrix"> <option value="loom">Loom</option> <option value="tabular">Tabular, CSV, TSV</option> <option value="mtx">Matrix Market (mtx), from Cell ranger or not</option> <option value="umi_tools">UMI tools</option> </param> <when value="loom"> <param name="input" type="data" format="loom" label="Annotated data matrix"/> <param name="sparse" type="boolean" truevalue="True" falsevalue="False" checked="true" label="Is the data matrix to read sparse?"/> <param name="cleanup" type="boolean" truevalue="True" falsevalue="False" checked="false" label="Cleanup?"/> <param name="x_name" type="text" value="spliced" label="X_name"/> <param name="obs_names" type="text" value="CellID" label="obs_names"/> <param name="var_names" type="text" value="Gene" label="var_names"/> </when> <when value="tabular"> <param name="input" type="data" format="tabular,csv,tsv" label="Annotated data matrix"/> <param name="first_column_names" type="boolean" truevalue="True" falsevalue="False" checked="true" label="Does the first column store the row names?"/> </when> <when value="mtx"> <param name="matrix" type="data" format="mtx" label="Matrix"/> <conditional name="tenx"> <param name="use" type="select" label="Use 10x Genomics formatted mtx"> <option value="no">No</option> <option value="legacy_10x">Output from Cell Ranger v2 or earlier versions</option> <option value="v3_10x">Output from Cell Ranger v3 or later versions</option> </param> <when value="no"/> <when value="legacy_10x"> <param name="genes" type="data" format="tabular" label="Genes"/> <expand macro="params_10x"/> </when> <when value="v3_10x"> <param name="features" type="data" format="tabular" label="Features"/> <expand macro="params_10x"/> </when> </conditional> </when> <when value="umi_tools"> <param name="input" type="data" format="tabular" label="condensed count matrix from UMI tools"/> </when> </conditional> </when> <when value="loom"> <param name="mainmatrix" type="data" format="tabular" label="File for main layer of loom file." help="All subsequent tsv must be the same dimensions as this file. When converted back to tsv using hd5 export, this will be labeled as 'mainmatrix.tsv'"/> <param name="other_files" type="data" format="tabular" multiple="true" optional="true" label="Add layers" help="Adds layers of same dimension to the loom file. When converted to tsv using hd5 export, these layers will retain their names."/> <param name="coldata" type="data" format="tabular" label="Tsv of column data." help="First row is column attributes, subsequent are values."/> <param name="rowdata" type="data" format="tabular" label="Tsv of row data." help="First row is row attributes, subsequent are values."/> </when> </conditional> </inputs> <outputs> <data name="anndata" format="h5ad" from_work_dir="anndata.h5ad" label="Anndata import on ${on_string}"> <filter>hd5_format['filetype'] == 'anndata'</filter> </data> <data name="loomdata" format="loom" from_work_dir="converted.loom" label="Loom import on ${on_string}"> <filter>hd5_format['filetype'] == 'loom'</filter> </data> </outputs> <tests> <test expect_num_outputs="1"> <conditional name="in"> <param name="adata_format" value="loom"/> <param name="input" value="krumsiek11.loom" /> <param name="sparse" value="True"/> <param name="cleanup" value="False"/> <param name="x_name" value="spliced"/> <param name="obs_names" value="CellID" /> <param name="var_names" value="Gene"/> </conditional> <assert_stdout> <has_text_matching expression="ad.read_loom"/> <has_text_matching expression="sparse=True"/> <has_text_matching expression="cleanup=False"/> <has_text_matching expression="X_name='spliced'"/> <has_text_matching expression="obs_names='CellID'"/> <has_text_matching expression="var_names='Gene'"/> </assert_stdout> <output name="anndata" value="import.loom.krumsiek11.h5ad" ftype="h5ad" compare="sim_size"/> </test> <test expect_num_outputs="1"> <conditional name="in"> <param name="adata_format" value="tabular"/> <param name="input" value="adata.csv"/> <param name="first_column_names" value="true"/> </conditional> <assert_stdout> <has_text_matching expression="ad.read_csv"/> <has_text_matching expression="delimiter=','"/> <has_text_matching expression="first_column_names=True"/> </assert_stdout> <output name="anndata" value="import.csv.h5ad" ftype="h5ad" compare="sim_size"/> </test> <test expect_num_outputs="1"> <conditional name="in"> <param name="adata_format" value="tabular"/> <param name="input" value="adata.tsv"/> <param name="first_column_names" value="true"/> </conditional> <assert_stdout> <has_text_matching expression="ad.read_csv"/> <has_text_matching expression="delimiter='\\t'"/> <has_text_matching expression="first_column_names=True"/> </assert_stdout> <output name="anndata" value="import.tsv.h5ad" ftype="h5ad" compare="sim_size"/> </test> <!--<test expect_num_outputs="1"> <conditional name="in"> <param name="adata_format" value="mtx"/> <param name="matrix" value="matrix_10x_v1.2.0.mtx"/> <conditional name="tenx"> <param name="use" value="no"/> </conditional> </conditional> <output name="anndata" value="import.mtx.no_10x.h5ad" ftype="h5ad" compare="sim_size"/> </test> <test> <conditional name="in"> <param name="adata_format" value="mtx"/> <param name="matrix" value="matrix_10x_v1.2.0.mtx"/> <conditional name="tenx"> <param name="use" value="legacy_10x"/> <param name="genes" value="genes_10x_v1.2.0.tsv"/> <param name="barcodes" value="barcodes_10x_v1.2.0.tsv"/> <param name="var_names" value="gene_symbols"/> <param name="make_unique" value="true"/> <param name="gex_only" value="true"/> </conditional> </conditional> <output name="anndata" value="import.mtx.legacy_10x.h5ad" ftype="h5ad" compare="sim_size"/> </test> <test> <conditional name="in"> <param name="adata_format" value="mtx"/> <param name="matrix" value="matrix_10x_v3.0.0.mtx"/> <conditional name="tenx"> <param name="use" value="v3_10x"/> <param name="features" value="features_10x_v3.0.0.tsv"/> <param name="barcodes" value="barcodes_10x_v3.0.0.tsv"/> <param name="var_names" value="gene_symbols"/> <param name="make_unique" value="true"/> <param name="gex_only" value="true"/> </conditional> </conditional> <output name="anndata" value="import.mtx.v3_10x.h5ad" ftype="h5ad" compare="sim_size"/> </test>!--> <test expect_num_outputs="1"> <param name="filetype" value="anndata"/> <conditional name="in"> <param name="adata_format" value="umi_tools"/> <param name="input" value="umi_tools.tsv"/> </conditional> <output name="anndata" value="import.umi_tools.h5ad" ftype="h5ad" compare="sim_size"/> </test> <test expect_num_outputs="1"> <param name="filetype" value="loom"/> <param name="mainmatrix" value="firstlayer.tsv"/> <param name="other_files" value="secondlayer.tsv"/> <param name="coldata" value="cols.tsv"/> <param name="rowdata" value="rows.tsv"/> <output name="loomdata" value="converted.loom.test" ftype="loom" compare="sim_size"/> </test> </tests> <help><![CDATA[ **What it does** This tool creates an AnnData or loom dataset from several input types: - Loom (`read_loom method <https://anndata.readthedocs.io/en/latest/anndata.read_loom.html>`__) - Tabular (`read_csv method <https://anndata.readthedocs.io/en/latest/anndata.read_csv.html>`__) - Matrix Market (mtx), from Cell ranger or not (`read_mtx method <https://anndata.readthedocs.io/en/latest/anndata.read_mtx.html>`__) - UMI tools (`read_umi_tools method <https://anndata.readthedocs.io/en/latest/anndata.read_umi_tools.html>`__) @HELP@ ]]></help> <expand macro="citations"/> </tool>