diff normalize.xml @ 12:0ac2f7d40040 draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/scanpy/ commit c21958f44b81d740191999fb6015d5ae69538ee0

--- a/normalize.xml	Wed Sep 22 21:06:01 2021 +0000
+++ b/normalize.xml	Wed Jul 31 18:08:37 2024 +0000
@@ -1,9 +1,9 @@
-<tool id="scanpy_normalize" name="Normalize" version="@galaxy_version@" profile="@profile@">
-    <description>with scanpy</description>
-    <expand macro="bio_tools"/>
+<tool id="scanpy_normalize" name="Normalize" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@profile@">
+    <description>and impute with scanpy</description>
     <macros>
         <import>macros.xml</import>
     </macros>
+    <expand macro="bio_tools"/>
     <expand macro="requirements"/>
     <expand macro="version_command"/>
     <command detect_errors="exit_code"><![CDATA[
@@ -17,17 +17,17 @@
 #if $method.method == "pp.normalize_total"
 sc.pp.normalize_total(
     adata,
-    #if str($method.target_sum)!= ''
+    #if str($method.target_sum) != ''
     target_sum=$method.target_sum,
     #end if
     exclude_highly_expressed=$method.exclude_highly_expressed.exclude_highly_expressed,
     #if $method.exclude_highly_expressed.exclude_highly_expressed == "True"
     max_fraction=$method.exclude_highly_expressed.max_fraction,
     #end if
-    #if str($method.key_added) != ''
+    #if $method.key_added
     key_added='$method.key_added',
     #end if
-    #if str($method.layers) != ''
+    #if $method.layers
         #if str($method.layers) != 'all'
     layers[str(x.strip()) for x in str($method.layers).split(',')],
         #else
@@ -65,6 +65,29 @@
     plot=False,
     copy=False)
 
+#else if $method.method == "external.pp.magic"
+sc.external.pp.magic(
+    adata=adata,
+    name_list='$method.name_list',
+    knn=$method.knn,
+    #if str($method.decay) != ''
+    decay=$method.decay,
+    #end if
+    #if str($method.knn_max) != ''
+    knn_max=$method.knn_max,
+    #end if
+    #if $method.t == -1
+    t='auto',
+    #else
+    t=$method.t,
+    #end if
+    #if str($method.n_pca) != ''
+    n_pca=$method.n_pca,
+    #end if
+    solver='$method.solver',
+    knn_dist='$method.knn_dist',
+    random_state=$method.random_state,
+    copy=False)
 #end if
 
 @CMD_anndata_write_outputs@
@@ -79,6 +102,7 @@
                 <option value="pp.recipe_zheng17">Normalization and filtering as of Zheng et al. (2017), using 'pp.recipe_zheng17'</option>
                 <option value="pp.recipe_weinreb17">Normalization and filtering as of Weinreb et al (2017), using 'pp.recipe_weinreb17'</option>
                 <option value="pp.recipe_seurat">Normalization and filtering as of Seurat et al (2015), using 'pp.recipe_seurat'</option>
+                <option value="external.pp.magic">Denoising using Markov Affinity-based Graph Imputation of Cells (MAGIC) API 'external.pp.magic'</option>
             </param>
             <when value="pp.normalize_total">
                 <param argument="target_sum" type="float" value="" optional="true" label="Target sum" help="If not provided, after normalization, each observation (cell) has a total count equal to the median of the total counts (cells) before normalization."/>
@@ -119,6 +143,29 @@
             <when value="pp.recipe_seurat">
                 <expand macro="param_log"/>
             </when>
+            <when value="external.pp.magic">
+                <param name="name_list" type="select" label="Denoised genes to return" help="Selecting all genes may require a large amount of memory">
+                    <option value="all_genes">All genes</option>
+                    <option value="pca_only">PCA only</option>
+                </param>
+                <param argument="knn" type="integer" min="1" value="5" label="Number of nearest neighbors on which to build kernel" help=""/>
+                <param argument="decay" type="integer" optional="true" value="1" label="Set decay rate of kernel tails" 
+                    help="If not set, alpha decaying kernel is not used" />
+                <param argument="knn_max" type="integer" min="1" optional="true" value="" label="Maximum number of nearest neighbors with nonzero connection"
+                    help="If not set, will be set to 3 * knn" />
+                <param argument="t" type="integer" min="-1" value="3" label="Power to which the diffusion operator is powered. This sets the level of diffusion"
+                    help="If ‘-1’, this parameter is selected according to the Procrustes disparity of the diffused data." />
+                <param argument="n_pca" type="integer" value="100" optional="true" label="Number of principal components to use for calculating neighborhoods"
+                    help="For extremely large datasets, using n_pca less than 20 allows neighborhoods to be calculated in roughly log(n_samples) time. If not set, no PCA is performed." />
+                <param name="solver" type="select" label="Which solver to use" help="Selecting all genes may require a large amount of memory">
+                    <option value="exact">"exact", the implementation described in van Dijk et al. (2018) </option>
+                    <option value="approximate">"approximate", is faster that performs imputation in the PCA space and then projects back to the gene space</option>
+                </param>
+                <param name="knn_dist" type="select" label="Distance metric to use for the data" help="See scipy.spatial.distance.pdist documentation for more options https://docs.scipy.org/doc/scipy/reference/generated/scipy.spatial.distance.pdist.html">
+                    <expand macro="distance_metric_options"/>
+                </param>
+                <expand macro="param_random_state"/>
+            </when>
         </conditional>
         <expand macro="inputs_common_advanced"/>
     </inputs>
@@ -126,8 +173,8 @@
         <expand macro="anndata_outputs"/>
     </outputs>
     <tests>
-        <test>
-            <!-- test 0 -->
+        <test expect_num_outputs="2">
+            <!-- test 1 -->
             <param name="adata" value="krumsiek11.h5ad" />
             <conditional name="method">
                 <param name="method" value="pp.normalize_total"/>
@@ -151,8 +198,8 @@
             </output>
             <output name="anndata_out" file="pp.normalize_total.krumsiek11.h5ad" ftype="h5ad" compare="sim_size"/>
         </test>
-        <test>
-            <!-- test 1 -->
+        <test expect_num_outputs="2">
+            <!-- test 2 -->
             <param name="adata" value="random-randint.h5ad"/>
             <conditional name="method">
                 <param name="method" value="pp.recipe_zheng17"/>
@@ -171,8 +218,8 @@
             </output>
             <output name="anndata_out" file="pp.recipe_zheng17.random-randint.h5ad" ftype="h5ad" compare="sim_size" delta="1000000" delta_frac="0.15"/>
         </test>
-        <test>
-            <!-- test 2 -->
+        <test expect_num_outputs="2">
+            <!-- test 3 -->
             <param name="adata" value="paul15_subsample.h5ad" />
             <conditional name="method">
                 <param name="method" value="pp.recipe_weinreb17"/>
@@ -199,8 +246,8 @@
             </output>
             <output name="anndata_out" file="pp.recipe_weinreb17.paul15_subsample.updated.h5ad" ftype="h5ad" compare="sim_size"/>
         </test>
-        <test>
-            <!-- test 3 -->
+        <test expect_num_outputs="2">
+            <!-- test 4 -->
             <param name="adata" value="pp.recipe_zheng17.random-randint.h5ad" />
             <conditional name="method">
                 <param name="method" value="pp.recipe_seurat"/>
@@ -217,6 +264,53 @@
             </output>
             <output name="anndata_out" file="pp.recipe_seurat.recipe_zheng17.h5ad" ftype="h5ad" compare="sim_size" delta="1000000" delta_frac="0.25"/>
         </test>
+        <test expect_num_outputs="2">
+            <!-- test 5 -->
+            <param name="adata" value="krumsiek11.h5ad" />
+            <conditional name="method">
+                <param name="method" value="external.pp.magic"/>
+                <param name="name_list" value="all_genes"/>
+                <param name="t" value="-1"/>
+                <param name="n_pca" value="5"/>
+            </conditional>
+            <section name="advanced_common">
+                <param name="show_log" value="true" />
+            </section>
+            <output name="hidden_output">
+                <assert_contents>
+                    <has_text_matching expression="external.pp.magic"/>
+                    <has_text_matching expression="name_list='all_genes'"/>
+                    <has_text_matching expression="t='auto'"/>
+                    <has_text_matching expression="n_pca=5"/>
+                </assert_contents>
+            </output>
+            <output name="anndata_out" file="external.pp.magic.all_genes.krumsiek11.h5ad" ftype="h5ad" compare="sim_size"/>
+        </test>
+        <test expect_num_outputs="2">
+            <!-- test 6 -->
+            <param name="adata" value="krumsiek11.h5ad" />
+            <conditional name="method">
+                <param name="method" value="external.pp.magic"/>
+                <param name="name_list" value="pca_only"/>
+                <param name="t" value="3"/>
+                <param name="n_pca" value="5"/>
+            </conditional>
+            <section name="advanced_common">
+                <param name="show_log" value="true" />
+            </section>
+            <output name="hidden_output">
+                <assert_contents>
+                    <has_text_matching expression="external.pp.magic"/>
+                    <has_text_matching expression="name_list='pca_only'"/>
+                    <has_text_matching expression="t=3"/>
+                    <has_text_matching expression="n_pca=5"/>
+                </assert_contents>
+            </output>
+            <output name="anndata_out" file="external.pp.magic.pca_only.krumsiek11.h5ad" ftype="h5ad" compare="sim_size"/>
+            <assert_stdout>
+                <has_text text="X_magic"/>
+            </assert_stdout>
+        </test>
     </tests>
     <help><![CDATA[
 Normalize total counts per cell (`pp.normalize_per_cell`)
@@ -228,7 +322,7 @@
 Similar functions are used, for example, by Seurat, Cell Ranger or SPRING.
 
 More details on the `scanpy documentation
-<https://icb-scanpy.readthedocs-hosted.com/en/@version@/api/scanpy.pp.normalize_per_cell.html>`__
+<https://scanpy.readthedocs.io/en/stable/api/scanpy.pp.normalize_per_cell.html>`__
 
 
 Normalization and filtering as of Zheng et al. (2017), the Cell Ranger R Kit of 10x Genomics (`pp.recipe_zheng17`)
@@ -247,7 +341,7 @@
 - scale to unit variance and shift to zero mean
 
 More details on the `scanpy documentation
-<https://icb-scanpy.readthedocs-hosted.com/en/@version@/api/scanpy.pp.recipe_zheng17.html>`__
+<https://scanpy.readthedocs.io/en/stable/api/generated/scanpy.pp.recipe_zheng17.html>`__
 
 
 Normalization and filtering as of Weinreb et al (2017) (`pp.recipe_weinreb17`)
@@ -256,7 +350,7 @@
 Expects non-logarithmized data. If using logarithmized data, pass `log=False`.
 
 More details on the `scanpy documentation
-<https://icb-scanpy.readthedocs-hosted.com/en/@version@/api/scanpy.pp.recipe_weinreb17.html>`__
+<https://scanpy.readthedocs.io/en/stable/api/generated/scanpy.pp.recipe_weinreb17.html>`__
 
 
 Normalization and filtering as of Seurat et al (2015) (`pp.recipe_seurat`)
@@ -267,7 +361,21 @@
 Expects non-logarithmized data. If using logarithmized data, pass `log=False`.
 
 More details on the `scanpy documentation
-<https://icb-scanpy.readthedocs-hosted.com/en/@version@/api/scanpy.pp.recipe_seurat.html>`__
+<https://scanpy.readthedocs.io/en/stable/api/generated/scanpy.pp.recipe_seurat.html>`__
+
+
+Markov Affinity-based Graph Imputation of Cells (MAGIC) as of Van Dijk D et al. (2018) (`external.pp.magic`)
+============================================================================================================
+
+MAGIC is an algorithm for denoising and transcript recover of single cells applied to single-cell sequencing data. MAGIC builds a graph from the data and uses diffusion to smooth out noise and recover the data manifold.
+
+The algorithm implemented here has changed primarily in two ways compared to the algorithm described in Van Dijk D et al. (2018). 
+
+- Firstly, we use the adaptive kernel described in Moon et al, (2019) for improved stability.
+- Secondly, data diffusion is applied in the PCA space, rather than the data space, for speed and memory improvements.
+
+More details on the `scanpy documentation
+<https://scanpy.readthedocs.io/en/stable/api/scanpy.external.pp.magic.html>`__
 
     ]]></help>
     <expand macro="citations"/>