Mercurial > repos > iuc > snapatac2_plotting

changeset 0:0cfd2d2f7351 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/snapatac2 commit be132b56781bede5dc6e020aa80ca315546666cd
author iuc
date Thu, 16 May 2024 13:15:05 +0000
parents
children fecf9664c885
files macros.xml plotting.xml
diffstat 2 files changed, 416 insertions(+), 0 deletions(-) [+]
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/macros.xml	Thu May 16 13:15:05 2024 +0000
@@ -0,0 +1,187 @@
+<macros>
+	<token name="@TOOL_VERSION@">2.5.3</token>
+    <token name="@VERSION_SUFFIX@">0</token>
+    <token name="@PROFILE@">23.0</token>
+    <xml name="requirements">
+        <requirement type="package" version="@TOOL_VERSION@">snapatac2</requirement>
+        <requirement type="package" version="5.18.0">plotly</requirement>
+        <requirement type="package" version="0.2.1">python-kaleido</requirement>
+        <requirement type="package" version="0.19.19">polars</requirement>
+        <requirement type="package" version="14.0.1">pyarrow</requirement>
+        <requirement type="package" version="0.11.3">python-igraph</requirement>
+        <requirement type="package" version="0.8.33">hdbscan</requirement>
+        <requirement type="package" version="0.0.9">harmonypy</requirement>
+        <requirement type="package" version="1.7.4">scanorama</requirement>
+        <yield />
+    </xml>
+
+    <token name="@PREP_ADATA@"><![CDATA[
+        cp '$method.adata' 'anndata.h5ad' &&
+        ]]>
+    </token>
+
+    <token name="@CMD@"><![CDATA[
+        cat '$script_file' > '$hidden_output' &&
+        python '$script_file' >> '$hidden_output' &&
+		touch 'anndata_info.txt' &&
+		cat 'anndata_info.txt' @CMD_prettify_stdout@
+        ]]>
+    </token>
+
+    <token name="@CMD_prettify_stdout@"><![CDATA[ | sed -r '1 s|AnnData object with (.+) = (.*)\s*|\1: \2|g' | sed "s|'||g"  | sed -r 's|^\s*(.*):\s(.*)|[\1]\n-    \2|g' | sed 's|, |\n-    |g'
+    ]]></token>
+
+    <token name="@CMD_imports@"><![CDATA[
+import snapatac2 as sa
+import os
+    ]]>
+    </token>
+    <xml name="sanitize_query" token_validinitial="string.printable">
+        <sanitizer>
+            <valid initial="@VALIDINITIAL@">
+                <remove value="&apos;" />
+            </valid>
+        </sanitizer>
+    </xml>
+
+    <xml name="inputs_anndata">
+        <param name="adata" type="data" format="h5ad" label="Annotated data matrix"/>
+    </xml>
+
+    <token name="@CMD_read_inputs@"><![CDATA[
+
+adata = sa.read('anndata.h5ad', backed = None)
+]]>
+    </token>
+
+    <xml name="dimentions_plot">
+        <param argument="width" type="integer" value="500" label="Width of the plot"/>
+		<param argument="height" type="integer" value="400" label="Height of the plot"/>
+    </xml>
+
+    <xml name="param_groupby">
+        <param argument="groupby" type="text" label="The key of the observation grouping to consider">
+            <expand macro="sanitize_query" />
+        </param>
+    </xml>
+
+    <xml name="out_file">
+        <param name="out_file" type="select" optional="true" label="Type of output file">
+            <option value="png" selected="true">PNG</option>
+            <option value="svg">SVG</option>
+            <option value="pdf">PDF</option>
+		</param>
+    </xml>
+    <token name="@CMD_anndata_write_outputs@"><![CDATA[
+adata.write('anndata.h5ad')
+with open('anndata_info.txt','w', encoding='utf-8') as ainfo:
+    print(adata, file=ainfo)
+]]>
+    </token>
+    <xml name="inputs_common_advanced">
+        <section name="advanced_common" title="Advanced Options" expanded="false">
+            <param name="show_log" type="boolean" checked="false" label="Output Log?" />
+        </section>
+    </xml>
+    <xml name="params_render_plot">
+        <param argument="width" type="integer" value="600" label="Width of the plot"/>
+        <param argument="height" type="integer" value="400" label="Height of the plot"/>
+        <expand macro="out_file"/>
+    </xml>
+    <xml name="param_shift">
+    	<param argument="shift_left" type="integer" value="4" label="Insertion site correction for the left end" help="Note this has no effect on single-end reads"/>
+    	<param argument="shift_right" type="integer" value="-5" label="Insertion site correction for the right end" help="Note this has no effect on single-end reads"/>
+    </xml>
+    <xml name="param_chunk_size" tokens="size">
+    	<param argument="chunk_size" type="integer" value="@SIZE@" label="chunk size"/>
+    </xml>
+	<xml name="min_max_frag_size">
+		<param argument="min_frag_size" type="integer" optional="true" value="" label="Minimum fragment size to include"/>
+		<param argument="max_frag_size" type="integer" optional="true" value="" label="Maximum fragment size to include"/>
+	</xml>
+	<xml name="params_data_integration">
+		<param argument="use_rep" type="text" value="X_spectral" label="The key for the matrix"/>
+		<param argument="use_dims" type="text" optional="true" value="" label="The dimensions used for computation">
+			<expand macro="sanitize_query"/>
+		</param>
+		<param argument="groupby" type="text" optional="true" value="" label="The key of the observation grouping to consider">
+            <expand macro="sanitize_query" />
+        </param>
+		<param argument="key_added" type="text" optional="true" value="" label="If specified, add the result to adata.obsm with this key"/>
+	</xml>
+    <xml name="param_n_comps">
+s        <param argument="n_comps" type="integer" value="30" label="Number of dimensions to keep" help="The result is insensitive to this parameter when `weighted_by_sd` is set, as long as it is large enough, e.g. 30."/>
+    </xml>
+    <xml name="param_random_state">
+        <param argument="random_state" type="integer" value="0" label="Seed of the random state generator"/>
+    </xml>
+    <xml name="param_key_added" tokens="key_added">
+        <param argument="key_added" type="text" value="@KEY_ADDED@"  label="`adata.obs` key under which t add cluster labels"/>
+    </xml>
+    <xml name="param_use_rep">
+        <param argument="use_rep" type="text" value="X_spectral" label="Use the indicated representation in `.obsm`"/>
+    </xml>
+    <xml name="genome_fasta">
+        <param argument="genome_fasta" type="text" label="A fasta file containing the genome sequences or a Genome object"/>
+    </xml>
+    <xml name="background">
+        <param argument="background" type="text" optional="true" value="" label="A list of regions to be used as the background">
+			<expand macro="sanitize_query"/>
+		</param>
+    </xml>
+    <xml name="mat">
+        <param argument="peak_mat" type="data" format="h5ad" optional="true" label="AnnData or AnnDataSet object storing the cell by peak count matrix"/>
+		<param argument="gene_mat" type="data" format="h5ad" optional="true" label="AnnData or AnnDataSet object storing the cell by gene count matrix"/>
+    </xml>
+    <xml name="param_network">
+        <param argument="network" type="text" label="network"/>
+    </xml>
+    <xml name="param_n_iterations">
+        <param argument="n_iterations" type="integer" value="-1" label="How many iterations of the Leiden clustering algorithm to perform"
+            help="Positive values above 2 define the total number of iterations to perform, -1 has the algorithm run until it reaches its optimal clustering."/>
+    </xml>
+
+    <xml name="citations">
+        <citations>
+            <citation type="doi">10.1038/s41592-023-02139-9</citation>
+        </citations>
+    </xml>
+    <xml name="render_plot_test">
+    	<param name="width" value="650"/>
+        <param name="height" value="450"/>
+    </xml>
+    <xml name="render_plot_matching_text">
+    	<has_text_matching expression="width = 650"/>
+        <has_text_matching expression="height = 450"/>
+    </xml>
+    <xml name="param_counting_strategy">
+        <param argument="counting_strategy" type="select" label="he strategy to compute feature counts">
+            <option value="fragment">fragment</option>
+            <option value="insertion" selected="true">insertion</option>
+            <option value="paired-insertion">paired-insertion</option>
+        </param>
+    </xml>
+
+    <token name="@CMD_params_data_integration@"><![CDATA[
+use_rep = '$method.use_rep',
+#if $method.use_dims != ''
+#set $dims = ([x.strip() for x in str($method.use_dims).split(',')])
+use_dims=$dims,
+#end if
+#if $method.groupby != ''
+#set $groupby = ([x.strip() for x in str($method.groupby).split(',')])
+groupby=$groupby,
+#end if
+#if $method.key_added != ''
+key_added = '$method.key_added',
+#end if
+    ]]>
+    </token>
+
+    <token name="@CMD_params_render_plot@"><![CDATA[
+    width = $method.width,
+    height = $method.height,
+    out_file = 'plot.$method.out_file',
+    ]]>
+    </token>
+</macros>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/plotting.xml	Thu May 16 13:15:05 2024 +0000
@@ -0,0 +1,229 @@
+<tool id="snapatac2_plotting" name="SnapATAC2 Plotting" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@">
+    <macros>
+        <import>macros.xml</import>
+    </macros>
+    <requirements>
+        <expand macro="requirements"/>
+    </requirements>
+    <command detect_errors="exit_code"><![CDATA[
+@PREP_ADATA@
+@CMD@
+	]]></command>
+    <configfiles>
+        <configfile name="script_file"><![CDATA[
+@CMD_imports@
+@CMD_read_inputs@
+
+#if $method.method == 'pl.frag_size_distr'
+	#if $method.log_scale
+fig = sa.pl.frag_size_distr(adata, show=False)
+fig.update_yaxes(type="log")
+sa.pl.render_plot(fig, @CMD_params_render_plot@)
+	#else
+sa.pl.frag_size_distr(adata, @CMD_params_render_plot@)
+	#end if
+#else if $method.method == 'pl.tsse'
+sa.pl.tsse(
+    adata,
+    min_fragment = $method.min_fragment,
+    @CMD_params_render_plot@
+)
+#else if $method.method == 'pl.umap'
+sa.pl.umap(
+	adata,
+	color = '$method.color',
+	use_rep = '$method.use_rep',
+	marker_size = $method.marker_size,
+	marker_opacity = $method.marker_opacity,
+	sample_size = $method.sample_size,
+	@CMD_params_render_plot@
+)
+#else if $method.method == 'pl.regions'
+sa.pl.regions(
+	adata,
+	groupby = '$method.groupby',
+	peaks = '$method.peaks',
+	@CMD_params_render_plot@
+)
+#else if $method.method == 'pl.spectral_eigenvalues'
+sa.pl.spectral_eigenvalues(
+	adata,
+	@CMD_params_render_plot@
+)
+#end if
+	]]></configfile>
+    </configfiles>
+    <inputs>
+        <conditional name="method">
+            <param name="method" type="select" label="Method used for plotting">
+                <option value="pl.frag_size_distr">Plot fragment size distribution, using 'pl.frag_size_distr'</option>
+                <option value="pl.tsse">Plot the TSS enrichment vs. number of fragments density figure, using 'pl.tsse'</option>
+                <option value="pl.umap">Plot the UMAP embedding, using 'pl.umap'</option>
+                <option value="pl.spectral_eigenvalues">Plot the eigenvalues of spectral embedding, using 'pl.spectral_eigenvalues'</option>
+            </param>
+            <when value="pl.frag_size_distr">
+                <expand macro="inputs_anndata"/>
+                <param name="log_scale" type="boolean" checked="False" label="Change the y-axis (fragment counts) to log scale"/>
+                <expand macro="params_render_plot"/>
+            </when>
+            <when value="pl.tsse">
+                <expand macro="inputs_anndata"/>
+                <param argument="min_fragment" type="integer" value="500" label="Minimum number of unique fragments"/>
+                <expand macro="params_render_plot"/>
+            </when>
+            <when value="pl.umap">
+                <expand macro="inputs_anndata"/>
+                <param argument="color" type="text" value="" optional="true" label="Color"/>
+                <param argument="use_rep" type="text" value="X_umap" label="Use the indicated representation in .obsm"/>
+                <param argument="marker_size" type="float" value="" optional="true" label="Size of the dots"/>
+                <param argument="marker_opacity" type="float" value="1" label="Opactiy of the dots"/>
+                <param argument="sample_size" type="integer" value="" optional="true" label="Number of cells to use"/>
+                <expand macro="params_render_plot"/>
+            </when>
+            <when value="pl.spectral_eigenvalues">
+                <expand macro="inputs_anndata"/>
+                <expand macro="params_render_plot"/>
+            </when>
+        </conditional>
+        <expand macro="inputs_common_advanced"/>
+    </inputs>
+    <outputs>
+        <data name="out_png" format="png" from_work_dir="plot.png" label="PNG plot from ${tool.name} (${method.method}) on ${on_string}">
+            <filter>method['out_file'] == 'png'</filter>
+        </data>
+        <data name="out_pdf" format="pdf" from_work_dir="plot.pdf" label="PDF plot from ${tool.name} (${method.method}) on ${on_string}">
+            <filter>method['out_file'] == 'pdf'</filter>
+        </data>
+        <data name="out_svg" format="svg" from_work_dir="plot.svg" label="SVG plot from ${tool.name} (${method.method}) on ${on_string}">
+            <filter>method['out_file'] == 'svg'</filter>
+        </data>
+        <data name="hidden_output" format="txt" label="Log file" hidden="true">
+            <filter>advanced_common['show_log']</filter>
+        </data>
+    </outputs>
+    <tests>
+        <test expect_num_outputs="2">
+            <!-- pl.frag_size_distr -->
+            <conditional name="method">
+                <param name="method" value="pl.frag_size_distr"/>
+                <param name="adata" location="https://zenodo.org/records/11199963/files/pp.import_data.pbmc_500_chr21.h5ad"/>
+                <param name="log_scale" value="True"/>
+                <param name="out_file" value="pdf"/>
+                <expand macro="render_plot_test"/>
+            </conditional>
+            <section name="advanced_common">
+                <param name="show_log" value="true"/>
+            </section>
+            <output name="out_pdf" location="https://zenodo.org/records/11199963/files/pl.frag_size_distr.pdf" ftype="pdf" compare="sim_size" delta_frac="0.1"/>
+            <output name="hidden_output">
+                <assert_contents>
+                    <has_text_matching expression="sa.pl.frag_size_distr"/>
+                    <has_text_matching expression="fig.update_yaxes"/>
+                    <expand macro="render_plot_matching_text"/>
+                </assert_contents>
+            </output>
+        </test>
+        <test expect_num_outputs="2">
+            <!-- pl.tsse -->
+            <conditional name="method">
+                <param name="method" value="pl.tsse"/>
+                <param name="adata" location="https://zenodo.org/records/11199963/files/metrics.tsse.pbmc_500_chr21.h5ad"/>
+                <param name="min_fragment" value="500"/>
+                <param name="out_file" value="png"/>
+                <expand macro="render_plot_test"/>
+            </conditional>
+            <section name="advanced_common">
+                <param name="show_log" value="true"/>
+            </section>
+            <output name="hidden_output">
+                <assert_contents>
+                    <has_text_matching expression="sa.pl.tsse"/>
+                    <has_text_matching expression="min_fragment = 500"/>
+                    <expand macro="render_plot_matching_text"/>
+                </assert_contents>
+            </output>
+            <output name="out_png" location="https://zenodo.org/records/11199963/files/pl.tsse.png" ftype="png" compare="sim_size" delta_frac="0.1"/>
+        </test>
+        <test expect_num_outputs="2">
+            <!-- pl.umap -->
+            <conditional name="method">
+                <param name="method" value="pl.umap"/>
+                <param name="adata" ftype="h5ad" location="https://zenodo.org/records/11199963/files/tl.leiden.pbmc_500_chr21.h5ad"/>
+                <param name="color" value="leiden"/>
+                <param name="use_rep" value="X_umap"/>
+                <param name="marker_size" value="1"/>
+                <param name="marker_opacity" value="0.8"/>
+                <param name="sample_size" value="100"/>
+                <expand macro="render_plot_test"/>
+                <param name="out_file" value="svg"/>
+            </conditional>
+            <section name="advanced_common">
+                <param name="show_log" value="true"/>
+            </section>
+            <output name="hidden_output">
+                <assert_contents>
+                    <has_text_matching expression="sa.pl.umap"/>
+                    <has_text_matching expression="color = 'leiden'"/>
+                    <has_text_matching expression="use_rep = 'X_umap'"/>
+                    <has_text_matching expression="marker_size = 1"/>
+                    <has_text_matching expression="marker_opacity = 0.8"/>
+                    <has_text_matching expression="sample_size = 100"/>
+                    <expand macro="render_plot_matching_text"/>
+                </assert_contents>
+            </output>
+            <output name="out_svg" location="https://zenodo.org/records/11199963/files/pl.umap.svg" ftype="svg" compare="sim_size" delta_frac="0.1"/>
+        </test>
+        <test expect_num_outputs="2">
+            <!-- pl.spectral_eigenvalues -->
+            <conditional name="method">
+                <param name="method" value="pl.spectral_eigenvalues"/>
+                <param name="adata" ftype="h5ad" location="https://zenodo.org/records/11199963/files/tl.spectral.pbmc_500_chr21.h5ad"/>
+                <expand macro="render_plot_test"/>
+                <param name="out_file" value="pdf"/>
+            </conditional>
+            <section name="advanced_common">
+                <param name="show_log" value="true"/>
+            </section>
+            <output name="hidden_output">
+                <assert_contents>
+                    <has_text_matching expression="sa.pl.spectral_eigenvalues"/>
+                    <expand macro="render_plot_matching_text"/>
+                </assert_contents>
+            </output>
+            <output name="out_pdf" location="https://zenodo.org/records/11199963/files/pl.spectral_eigenvalues.pdf" ftype="pdf" compare="sim_size" delta_frac="0.1"/>
+        </test>
+    </tests>
+    <help><![CDATA[
+Plot fragment size distribution, using `pl.frag_size_distr`
+===========================================================
+
+Plot fragment size distribution.
+
+`metrics.frag_size_distr` must be ran first in order to use this function.
+
+Plot the TSS enrichment vs. number of fragments density figure, using `pl.tsse`
+===============================================================================
+
+Plot the TSS enrichment vs. number of fragments density figure.
+
+More details on the `SnapATAC2 documentation
+<https://kzhang.org/SnapATAC2/api/_autosummary/snapatac2.pl.tsse.html>`__
+
+Plot the UMAP embedding, using `pl.umap`
+========================================
+
+Plot the UMAP embedding.
+
+More details on the `SnapATAC2 documentation
+<https://kzhang.org/SnapATAC2/api/_autosummary/snapatac2.pl.umap.html>`__
+
+Plot the eigenvalues of spectral embedding, using `pl.spectral_eigenvalues`
+===========================================================================
+
+Plot the eigenvalues of spectral embedding.
+
+More details on the `SnapATAC2 documentation
+<https://kzhang.org/SnapATAC2/api/_autosummary/snapatac2.pl.spectral_eigenvalues.html>`__
+    ]]></help>
+    <expand macro="citations"/>
+</tool>