Mercurial > repos > iuc > modify_loom
diff macros.xml @ 0:c8e4d0b9ae8c draft
"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/anndata/ commit dc9d19d1f902f3ed54009cd0e68c8518c284b856"
author | iuc |
---|---|
date | Mon, 06 Jan 2020 13:43:38 -0500 |
parents | |
children | 81a28c2705b0 |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/macros.xml Mon Jan 06 13:43:38 2020 -0500 @@ -0,0 +1,80 @@ +<macros> + <token name="@VERSION@">0.6.22.post1</token> + <token name="@GALAXY_VERSION@">galaxy1</token> + <xml name="requirements"> + <requirements> + <requirement type="package" version="@VERSION@">anndata</requirement> + <requirement type="package" version="2.0.17">loompy</requirement> + <requirement type="package" version="2.9.0">h5py</requirement> + <yield /> + </requirements> + </xml> + <xml name="citations"> + <citations> + <citation type="doi">10.1186/s13059-017-1382-0</citation> + </citations> + </xml> + <xml name="version_command"> + <version_command><![CDATA[python -c "import anndata as ad;print('anndata version: %s' % ad.__version__); import loompy;print('\nloompy version: %s' % loompy.__version__)"]]></version_command> + </xml> + <token name="@CMD@"><![CDATA[ +cat '$script_file' && +python '$script_file' + ]]> + </token> + <token name="@LOOMCMD@"><![CDATA[ +mkdir ./output && +mkdir ./attributes && +python '$__tool_directory__/loompy_to_tsv.py' -f '${hd5_format.input}' + ]]> + </token> + <token name="@CMD_imports@"><![CDATA[ +import anndata as ad + ]]> + </token> + <token name="@HELP@"><![CDATA[ +**AnnData** + +AnnData provides a scalable way of keeping track of data together with learned annotations. It is used within `Scanpy <https://github.com/theislab/scanpy>`__, for which it was initially developed. + +AnnData stores a data matrix `X` together with annotations of observations `obs`, variables `var` and unstructured annotations `uns`. + +.. image:: https://falexwolf.de/img/scanpy/anndata.svg + + +AnnData stores observations (samples) of variables (features) in the rows of a matrix. This is the convention of the modern classics +of statistics (`Hastie et al., 2009 <https://web.stanford.edu/~hastie/ElemStatLearn/>`__) and machine learning (Murphy, 2012), the convention of dataframes both in R and Python and the established statistics +and machine learning packages in Python (statsmodels, scikit-learn). + +More details on the `AnnData documentation +<https://anndata.readthedocs.io/en/latest/anndata.AnnData.html>`__ + + +**Loom data** + +Loom files are an efficient file format for very large omics datasets, consisting of a main matrix, optional additional layers, a variable number of row and column annotations, and sparse graph objects. + +.. image:: https://linnarssonlab.org/loompy/_images/Loom_components.png + + +Loom files to store single-cell gene expression data: the main matrix contains the actual expression values (one column per cell, one row per gene); row and column annotations contain metadata for genes +and cells, such as Name, Chromosome, Position (for genes), and Strain, Sex, Age (for cells). + + ]]> + </token> + <xml name="params_chunk_X"> + <conditional name="chunk"> + <param name="info" type="select" label="How to select the chunk?"> + <option value="random">Random chunk of defined size</option> + <option value="specified">Specified indices</option> + </param> + <when value="random"> + <param name="size" type="integer" value="1000" label="Size of chunk to randomly select"/> + <param name="replace" type="boolean" truevalue="True" falsevalue="False" checked="true" label="Random sampling of indices with replacement?"/> + </when> + <when value="specified"> + <param name="list" type="text" value="" label="List of comma-separated indices to return"/> + </when> + </conditional> + </xml> +</macros>