| Next changeset 1:7ae183da3f07 (2020-09-10) |
|
Commit message:
"planemo upload for repository https://github.com/ebi-gene-expression-group/container-galaxy-sc-tertiary/tree/develop/tools/tertiary-analysis/scanpy commit 62f47287c7e8449c59a1f1f454852ddc669b1b1e-dirty" |
|
added:
scanpy-integrate-mnn.xml scanpy_macros.xml scanpy_macros2.xml |
| b |
| diff -r 000000000000 -r 873449082a29 scanpy-integrate-mnn.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/scanpy-integrate-mnn.xml Mon Sep 07 13:10:40 2020 +0000 |
| [ |
| @@ -0,0 +1,120 @@ +<?xml version="1.0" encoding="utf-8"?> +<tool id="scanpy_integrate_mnn" name="Scanpy MNN" version="@TOOL_VERSION@+galaxy0" profile="@PROFILE@"> + <description>correct batch effects by matching mutual nearest neighbors</description> + <macros> + <import>scanpy_macros2.xml</import> + </macros> + <expand macro="requirements"/> + <command detect_errors="exit_code"><![CDATA[ +#if $batch_key + ln -s '${input_obj_file}' input.h5 && + PYTHONIOENCODING=utf-8 scanpy-integrate mnn + --batch-key '${batch_key}' + #if $batch_layer + --batch-layer '${batch_layer}' + #end if + #if $key_added + --key-added '${key_added}' + #end if + #if $var_subset + #set var_subsets = ' '.join(["--var-subset '{name}' '{values}'".format(**$v) for $v in $var_subset]) + ${var_subsets} + #if $settings.default == "false" + #if $settings.n_neighbors + --n-neighbors '${settings.n_neighbors}' + #end if + #if $settings.sigma + --sigma '${settings.sigma}' + #end if + #if not $settings.cos_norm_in + ${settings.cos_norm_in} + #end if + #if $settings.svd_dim + --svd-dim '${settings.svd_dim}' + #end if + #if not $settings.var_adj + ${settings.var_adj} + #end if + #if $settings.compute_angle + ${settings.compute_angle} + #end if + #if $settings.svd_mode + --svd-mode '${settings.svd_mode}' + #end if + #end if +#end if + @INPUT_OPTS@ + @OUTPUT_OPTS@ +#else + echo "No batch variables passed, simply passing original input as output unchanged."; + cp '${input_obj_file}' '${output_h5}' +#end if +]]></command> + + <inputs> + <expand macro="input_object_params"/> + <expand macro="output_object_params"/> + <param name="batch_key" type="text" argument="--batch-key" label="The name of the column in adata.obs that differentiates among experiments/batches."> + <sanitizer> + <valid initial="string.printable"/> + </sanitizer> + </param> + <param name="batch_layer" type="text" argument="--batch-layer" label="Layer to batch correct. By default corrects the contents of .X."> + <sanitizer> + <valid initial="string.printable"/> + </sanitizer> + </param> + <param name="key_added" argument="--key-added" type="text" optional="true" label="Key under which to add the computed results." help="By default a new layer will be created called 'mnn', 'mnn_{layer}' or 'mnn_{layer}_{key_added}' where those parameters were specified. A value of 'X' causes batch-corrected values to overwrite the original content of .X."/> + <repeat name="var_subset" title="The subset of vars (list of str) to be used when performing MNN correction" min="0"> + <param name="name" type="text" value="" label="Name of the categorical variable to filter on" help="e.g. 'highly_variable'"/> + <param name="values" type="text" value="" label="Category or comma-separated list of categories" help="e.g. 'True'"/> + </repeat> + <conditional name="settings"> + <param name="default" type="boolean" checked="true" label="Use programme defaults"/> + <when value="true"/> + <when value="false"> + <param name="n_neighbors" argument="--n-neighbors" type="integer" value="20" label="Number of mutual nearest neighbors."/> + <param name="sigma" argument="--sigma" type="float" value="1.0" label="Sigma" help="The bandwidth of the Gaussian smoothing kernel used to compute the correction vectors." /> + <param name="cos_norm_in" argument="--no-cos-norm-in" type="boolean" truevalue="" falsevalue="--no-cos-norm-in" checked="True" + label="Perform cosine normalization prior to computing corrected expression values?" /> + <param name="svd_dim" argument="--svd-dim" type="integer" optional="true" label="Number of dimensions to use for summarizing biological substructure within each batch." help="If not set, biological components will not be removed from the correction vectors."/> + <param name="var_adj" argument="--no-var-adj" type="boolean" truevalue="" falsevalue="--no-var-adj" checked="True" + label="Adjust variance of the correction vectors?" help="Note this step takes most computing time." /> + <param name="compute_angle" argument="--compute-angle" type="boolean" truevalue="--compute-angle" falsevalue="" checked="False" + label="Compute the angle between each cell’s correction vector and the biological subspace of the reference batch?" /> + <param name="svd_mode" argument="--svd-mode" type="select" label="SVD mode" help="'svd' computes SVD using a non-randomized SVD-via-ID algorithm, while 'rsvd' uses a randomized version. 'irlb' performs truncated SVD by implicitly restarted Lanczos bidiagonalization (forked from https://github.com/airysen/irlbpy)." > + <option value="rsvd" selected="true">rsvd</option> + <option value="svd">svd</option> + <option value="irlb">irlb</option> + </param> + </when> + </conditional> + </inputs> + + <outputs> + <expand macro="output_data_obj" description="Batch-corrected for ${batch_key}"/> + </outputs> + + <tests> + <test> + <param name="input_obj_file" value="find_cluster.h5"/> + <param name="input_format" value="anndata"/> + <param name="output_format" value="anndata"/> + <param name="batch_key" value="louvain"/> + <output name="output_h5" file="mnn.h5" ftype="h5" compare="sim_size"/> + </test> + </tests> + + <help><![CDATA[ + .. class:: infomark + + **What it does** + + Corrects for batch effects by fitting linear models, gains statistical power via an EB framework where information is borrowed across genes. + + @HELP@ + + @VERSION_HISTORY@ +]]></help> + <expand macro="citations"/> +</tool> |
| b |
| diff -r 000000000000 -r 873449082a29 scanpy_macros.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/scanpy_macros.xml Mon Sep 07 13:10:40 2020 +0000 |
| [ |
| @@ -0,0 +1,109 @@ +<macros> + <token name="@TOOL_VERSION@">1.3.2</token> + <token name="@HELP@">More information can be found at https://scanpy.readthedocs.io</token> + <token name="@PLOT_OPTS@"> +#if $do_plotting.plot + -P output.png + --projectio $do_plotting.projection + --components $do_plotting.components + #if $do_plotting.color_by + --color-by $do_plotting.color_by + #end if + #if $do_plotting.groups + --group $do_plotting.groups + #end if + #if $do_plotting.use_raw + --use-raw + #end if + #if $do_plotting.palette + --palette $do_plotting.palette + #end if + #if $do_plotting.edges + --edges + #end if + #if $do_plotting.arrows + --arrows + #end if + #if not $do_plotting.sort_order + --no-sort-order + #end if + #if $do_plotting.frameoff + --frameoff + #end if +#end if + </token> + <xml name="requirements"> + <requirements> + <requirement type="package" version="0.0.5">scanpy-scripts</requirement> + <yield/> + </requirements> + </xml> + <token name="@EXPORT_MTX_OPTS@"> + ${export_mtx} + </token> + <token name="@VERSION_HISTORY@"><![CDATA[ +**Version history** + +1.3.2+galaxy1: Normalise-data and filter-genes: Exposes ability to output 10x files. + +1.3.2+galaxy0: Initial contribution. Ni Huang and Pablo Moreno, Expression Atlas team https://www.ebi.ac.uk/gxa/home at +EMBL-EBI https://www.ebi.ac.uk/ and Teichmann Lab at Wellcome Sanger Institute. + ]]></token> + <xml name="citations"> + <citations> + <citation type="doi">10.1186/s13059-017-1382-0</citation> + <citation type="bibtex"> + @misc{githubscanpy-scripts, + author = {Ni Huang, EBI Gene Expression Team}, + year = {2018}, + title = {Scanpy-scripts: command line interface for Scanpy}, + publisher = {GitHub}, + journal = {GitHub repository}, + url = {https://github.com/ebi-gene-expression-group/scanpy-scripts}, + }</citation> + <yield /> + </citations> + </xml> + <xml name="input_object_params"> + <param name="input_obj_file" argument="--input-object-file" type="data" format="h5" label="Input object in hdf5 format"/> + <param name="input_format" argument="--input-format" type="select" label="Format of input object"> + <option value="anndata" selected="true">AnnData format hdf5</option> + <option value="loom">Loom format hdf5, current support is incomplete</option> + </param> + </xml> + <xml name="output_object_params"> + <param name="output_format" argument="--output-format" type="select" label="Format of output object"> + <option value="anndata" selected="true">AnnData format hdf5</option> + <option value="loom">Loom format hdf5, current support is defective</option> + </param> + </xml> + <xml name="output_plot_params"> + <param name="color_by" argument="--color-by" type="text" value="n_genes" label="Color by attributes, comma separated strings"/> + <param name="groups" argument="--groups" type="text" optional="ture" label="Restrict plotting to named groups, comma separated strings"/> + <param name="projection" argument="--projection" type="select" label="Plot projection"> + <option value="2d" selected="true">2D</option> + <option value="3d">3D</option> + </param> + <param name="components" argument="--components" type="text" value="1,2" label="Components to plot, comma separated integers"/> + <param name="palette" argument="--palette" type="text" optional="true" label="Palette"/> + <param name="use_raw" argument="--use-raw" type="boolean" checked="false" label="Use raw attributes if present"/> + <param name="edges" argument="--edges" type="boolean" checked="false" label="Show edges"/> + <param name="arrows" argument="--arrows" type="boolean" checked="false" label="Show arrows"/> + <param name="sort_order" argument="--no-sort-order" type="boolean" checked="true" label="Element with high color-by value plot on top"/> + <param name="frameoff" argument="--frameoff" type="boolean" checked="false" label="Omit frame"/> + </xml> + <xml name="export_mtx_params"> + <param name="export_mtx" argument="--export-mtx" type="boolean" truevalue="--export-mtx ./" falsevalue="" checked="false" label="Save normalised data to 10x format" help="If enabled, it will generate in addition to the main output in Loom or AnnData an export in 10x format of the normalised data."/> + </xml> + <xml name="export_mtx_outputs"> + <data name="matrix_10x" format="txt" from_work_dir="matrix.mtx" label="${tool.name} on ${on_string}: 10x matrix"> + <filter>export_mtx</filter> + </data> + <data name="genes_10x" format="tsv" from_work_dir="genes.tsv" label="${tool.name} on ${on_string}: 10x genes"> + <filter>export_mtx</filter> + </data> + <data name="barcodes_10x" format="tsv" from_work_dir="barcodes.tsv" label="${tool.name} on ${on_string}: 10x barcodes"> + <filter>export_mtx</filter> + </data> + </xml> +</macros> |
| b |
| diff -r 000000000000 -r 873449082a29 scanpy_macros2.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/scanpy_macros2.xml Mon Sep 07 13:10:40 2020 +0000 |
| [ |
| @@ -0,0 +1,146 @@ +<macros> + <token name="@TOOL_VERSION@">1.6.0</token> + <token name="@HELP@">More information can be found at https://scanpy.readthedocs.io</token> + <token name="@PROFILE@">18.01</token> + <token name="@VERSION_HISTORY@"><![CDATA[ +**Version history** + +1.6.0+galaxy0: Update to scanpy-scripts 0.2.13 (running scanpy ==1.6.0) to incorporate new options, code simplifications, and batch integration methods. Jonathan Manning, Expression Atlas team https://www.ebi.ac.uk/gxa/home at +EMBL-EBI https://www.ebi.ac.uk/ + +1.4.3+galaxy10: Update to scanpy-scripts 0.2.10 (running scanpy ==1.4.3) to address bugfixes in run-pca. + +1.4.3+galaxy10: Update to scanpy-scripts 0.2.9 (running scanpy ==1.4.3) to address bugfixes in find-variable-genes. + +1.4.3+galaxy10: Use profile 18.01 for modules. + +1.4.3+galaxy6: Update to scanpy-scripts 0.2.8 (running scanpy ==1.4.3) and wider compatibility with other Galaxy modules. Bug fixes in filtering and plotting improvements. + +1.4.3+galaxy0: Update to scanpy-scripts 0.2.5 (running scanpy ==1.4.3). + +1.4.2+galaxy0: Update to scanpy-scripts 0.2.4 (requires scanpy >=1.4.2). + +1.3.2+galaxy1: Normalise-data and filter-genes: Exposes ability to output 10x files. + +1.3.2+galaxy0: Initial contribution. Ni Huang and Pablo Moreno, Expression Atlas team https://www.ebi.ac.uk/gxa/home at +EMBL-EBI https://www.ebi.ac.uk/ and Teichmann Lab at Wellcome Sanger Institute. + ]]></token> + <token name="@INPUT_OPTS@"> + --input-format '${input_format}' input.h5 + </token> + <token name="@OUTPUT_OPTS@"> +#if str($output_format).startswith('anndata') + --show-obj stdout --output-format anndata output.h5 +#else + --show-obj stdout --output-format loom output.h5 +#end if + </token> + <token name="@PLOT_OPTS@"> +#if $fig_title + --title '${fig_title}' +#end if + --fig-size '${fig_size}' + --fig-dpi ${fig_dpi} + --fig-fontsize ${fig_fontsize} + ${fig_frame} + ./output.png + </token> + <token name="@EXPORT_MTX_OPTS@">${export_mtx}</token> + + <xml name="requirements"> + <requirements> + <requirement type="package" version="0.3.0">scanpy-scripts</requirement> + <yield/> + </requirements> + </xml> + + <xml name="citations"> + <citations> + <yield /> + <citation type="doi">10.1186/s13059-017-1382-0</citation> + <citation type="bibtex"> + @misc{githubscanpy-scripts, + author = {Ni Huang, EBI Gene Expression Team}, + year = {2018}, + title = {Scanpy-scripts: command line interface for Scanpy}, + publisher = {GitHub}, + journal = {GitHub repository}, + url = {https://github.com/ebi-gene-expression-group/scanpy-scripts}, + }</citation> + <citation type="doi">10.1101/2020.04.08.032698</citation> + </citations> + </xml> + + <xml name="input_object_params"> + <param name="input_obj_file" argument="input-object-file" type="data" format="h5,h5ad" label="Input object in AnnData/Loom format"/> + <param name="input_format" argument="--input-format" type="select" label="Format of input object"> + <option value="anndata" selected="true">AnnData format hdf5</option> + <option value="loom">Loom format hdf5</option> + </param> + </xml> + + <xml name="output_object_params"> + <param name="output_format" argument="--output-format" type="select" label="Format of output object"> + <option value="anndata_h5ad" selected="true">AnnData format</option> + <option value="anndata">AnnData format (h5 for older versions)</option> + <option value="loom">Loom format</option> + <option value="loom_legacy">Loom format (h5 for older versions)</option> + </param> + </xml> + + <xml name="output_object_params_no_loom"> + <param name="output_format" argument="--output-format" type="select" label="Format of output object"> + <option value="anndata_h5ad" selected="true">AnnData format</option> + <option value="anndata">AnnData format (h5 for older versions)</option> + </param> + </xml> + + <xml name="output_data_obj_no_loom" token_description="operation"> + <data name="output_h5ad" format="h5ad" from_work_dir="output.h5" label="${tool.name} on ${on_string}: @DESCRIPTION@ AnnData"> + <filter>output_format == 'anndata_h5ad'</filter> + </data> + <data name="output_h5" format="h5" from_work_dir="output.h5" label="${tool.name} on ${on_string}: @DESCRIPTION@ AnnData"> + <filter>output_format == 'anndata'</filter> + </data> + </xml> + + <xml name="output_data_obj" token_description="operation"> + <data name="output_h5ad" format="h5ad" from_work_dir="output.h5" label="${tool.name} on ${on_string}: @DESCRIPTION@ AnnData"> + <filter>output_format == 'anndata_h5ad'</filter> + </data> + <data name="output_h5" format="h5" from_work_dir="output.h5" label="${tool.name} on ${on_string}: @DESCRIPTION@ AnnData"> + <filter>output_format == 'anndata'</filter> + </data> + <data name="output_loom_legacy" format="h5" from_work_dir="output.h5" label="${tool.name} on ${on_string}: @DESCRIPTION@ Loom"> + <filter>output_format == 'loom_legacy'</filter> + </data> + <data name="output_loom" format="loom" from_work_dir="output.h5" label="${tool.name} on ${on_string}: @DESCRIPTION@ Loom"> + <filter>output_format == 'loom'</filter> + </data> + </xml> + + <xml name="output_plot_params"> + <param name="fig_title" argument="--title" type="text" label="Figure title"/> + <param name="fig_size" argument="--fig-size" type="text" value="4,4" label="Figure size as 'width,height', e.g, '7,7'"/> + <param name="fig_dpi" argument="--fig-dpi" type="integer" min="1" value="80" label="Figure dpi"/> + <param name="fig_fontsize" argument="--fig-fontsize" type="integer" min="0" value="10" label="Figure font size"/> + <param name="fig_frame" type="boolean" truevalue="--frameon" falsevalue="--frameoff" checked="false" + label="Show plot frame"/> + </xml> + + <xml name="export_mtx_params"> + <param name="export_mtx" argument="--export-mtx" type="boolean" truevalue="--export-mtx ./" falsevalue="" checked="false" label="Save to 10x mtx format" help="If enabled, it will generate in addition to the main output in Loom or AnnData an export in 10x format."/> + </xml> + + <xml name="export_mtx_outputs"> + <data name="matrix_10x" format="txt" from_work_dir="matrix.mtx" label="${tool.name} on ${on_string}: 10x matrix"> + <filter>export_mtx</filter> + </data> + <data name="genes_10x" format="tsv" from_work_dir="genes.tsv" label="${tool.name} on ${on_string}: 10x genes"> + <filter>export_mtx</filter> + </data> + <data name="barcodes_10x" format="tsv" from_work_dir="barcodes.tsv" label="${tool.name} on ${on_string}: 10x barcodes"> + <filter>export_mtx</filter> + </data> + </xml> +</macros> |