Mercurial > repos > ebi-gxa > anndata_ops

changeset 26:825dfd66e3fb draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/ebi-gene-expression-group/container-galaxy-sc-tertiary/tree/develop/tools/tertiary-analysis/scanpy commit 6c9d530aa653101e9e21804393ec11f38cddf027-dirty
author ebi-gxa
date Thu, 16 Feb 2023 13:28:31 +0000
parents a36d7a315be7
children 7ebc22f77d86
files anndata_operations.xml scanpy_macros2.xml
diffstat 2 files changed, 86 insertions(+), 24 deletions(-) [+]
line wrap: on
line diff
--- a/anndata_operations.xml	Thu Oct 28 09:55:27 2021 +0000
+++ b/anndata_operations.xml	Thu Feb 16 13:28:31 2023 +0000
@@ -1,5 +1,5 @@
 <?xml version="1.0" encoding="utf-8"?>
-<tool id="anndata_ops" name="AnnData Operations" version="@TOOL_VERSION@+galaxy0" profile="@PROFILE@">
+<tool id="anndata_ops" name="AnnData Operations" version="@TOOL_VERSION@+galaxy9" profile="@PROFILE@">
   <description>modifies metadata and flags genes</description>
   <macros>
     <import>scanpy_macros2.xml</import>
@@ -45,11 +45,19 @@
 ]]></command>
   <configfiles>
     <configfile name="operations">
+import gc
 import scanpy as sc
 import anndata
 from numpy import all
 import logging
 
+def make_column_values_unique(df, field, new_field=None, suffix = '-duplicate-'):
+  if new_field is None:
+    new_field = f"{field}_u"
+  appendents = (suffix + df.groupby(field).cumcount().astype(str).replace('0','')).replace(suffix, '')
+  df[new_field] = df[field].astype(str) + appendents.astype(str)
+  return df
+
 adata = sc.read('input.h5')
 
 #if $copy_adata_to_raw:
@@ -60,14 +68,22 @@
 qc_vars = list()
 
 #for $i, $s in enumerate($modifications)
+#if $s.make_unique:
+adata.obs = make_column_values_unique(adata.obs, field='${s.from_obs}', new_field='${s.to_obs}', suffix = "_d")
+#else
 adata.obs['${s.to_obs}'] = adata.obs['${s.from_obs}']
+#end if
 #if not $s.keep_original:
 del adata.obs['${s.from_obs}']
 #end if
 #end for
 
 #for $i, $s in enumerate($var_modifications)
+#if $s.make_unique:
+adata.var = make_column_values_unique(adata.var, field='${s.from_var}', new_field='${s.to_var}', suffix = "_d")
+#else
 adata.var['${s.to_var}'] = adata.var['${s.from_var}']
+#end if
 #if not $s.keep_original:
 del adata.var['${s.from_var}']
 #end if
@@ -84,6 +100,21 @@
     logging.warning('No genes starting with {} found, skip calculating expression of {} genes'.format('${flag.startswith}', '${flag.flag}'))
 #end for
 
+#if $field_unique:
+field_unique = '${field_unique}'
+made_unique = 0
+if field_unique in adata.var_keys(): 	    
+  adata.var = make_column_values_unique(adata.var, field_unique, suffix = "_d")
+  made_unique += 1
+if field_unique in adata.obs_keys():
+  adata.obs = make_column_values_unique(adata.obs, field_unique, suffix = "_d")
+  made_unique += 1
+	 
+if made_unique == 0:
+  logging.error("Specified field to be made unique is not in var or obs.")
+  sys.exit(1)  
+#end if	
+	    
 #if $copy_r.default and $copy_r.r_source:
 ad_s = sc.read('r_source.h5')
 if not all(adata.obs.index.isin(ad_s.obs.index)):
@@ -92,6 +123,7 @@
 else:
   adata.raw = ad_s[adata.obs.index]
 del ad_s
+gc.collect()
 #end if
 
 #if $copy_x.default and len($copy_x.xlayers) > 0:
@@ -107,6 +139,7 @@
   logging.error("X source ${i} AnnData file is not compatible to be merged to main AnnData file, different cell names.")
   sys.exit(1)
 del ad_s
+gc.collect()
 #end for
 #end if
 
@@ -120,13 +153,13 @@
     suffix=''
     if l_to_copy in adata.layers:
         suffix = "_${i}"
-
     adata.layers[l_to_copy+suffix] = ad_s.layers[l_to_copy]
   #end for
 else:
   logging.error("Layer source ${i} AnnData file is not compatible to be merged to main AnnData file, different cell names.")
   sys.exit(1)
 del ad_s
+gc.collect()
 #end for
 #end if
 
@@ -149,6 +182,7 @@
   logging.error("Observation source ${i} AnnData file is not compatible to be merged to main AnnData file, different cell names.")
   sys.exit(1)
 del ad_s
+gc.collect()
 #end for
 #end if
 
@@ -169,6 +203,7 @@
   logging.error("Embedding source ${i} AnnData file is not compatible to be merged to main AnnData file, different cell names.")
   sys.exit(1)
 del ad_s
+gc.collect()
 #end for
 #end if
 
@@ -188,6 +223,7 @@
   logging.error("Uns source ${i} AnnData file is not compatible to be merged to main AnnData file, different cell names.")
   sys.exit(1)
 del ad_s
+gc.collect()
 #end for
 #end if
 
@@ -224,8 +260,9 @@
           <valid initial="string.printable"/>
         </sanitizer>
       </param>
-      <param name="to_obs" type="text" label="New name" help="New name in observations that you want to change"/>
+      <param name="to_obs" type="text" label="New name" help="New name in observations that you want to change to"/>
       <param name="keep_original" type="boolean" label="Keep original" help="If activated, it will also keep the original column" checked="false"/>
+      <param name="make_unique" type="boolean" label="Make values in the field unique" help="If activated, it will make the values in the column unique by appending '_dnum' on each repeated value." checked="false"/>
     </repeat>
     <repeat name="var_modifications" title="Change field names in AnnData var" min="0">
       <param name="from_var" type="text" label="Original name" help="Name in var that you want to change">
@@ -235,6 +272,7 @@
       </param>
       <param name="to_var" type="text" label="New name" help="New name in var that you want to change"/>
       <param name="keep_original" type="boolean" label="Keep original" help="If activated, it will also keep the original column" checked="false"/>
+      <param name="make_unique" type="boolean" label="Make values in the field unique" help="If activated, it will make the values in the column unique by appending '_dnum' on each repeated value." checked="false"/>
     </repeat>
     <param name="gene_symbols_field" value='index' type="text" label="Gene symbols field in AnnData" help="Field inside var.params where the gene symbols are, normally 'index' or 'gene_symbols'"/>
     <repeat name="gene_flags" title="Flag genes that start with these names">
@@ -242,6 +280,7 @@
       <param name="flag" type="text" label="Var name" help="Name of the column in var.names where this boolean flag is stored, for example 'mito' for mitochondrial genes."/>
     </repeat>
     <param name="top_genes" label="Number of top genes" value='50' help="to calculate percentage of the flagged genes in that number of top genes. Used by sc.pp.calculate_qc_metrics (integer)." type="integer"/>
+    <param name="field_unique" type="text" optional="true" label="Field in var or obs to make unique" help="Field inside var or obs to be made unique by appending a suffix (useful for gene symbols in var). A new field will be added with the '_u' suffix. It happens after all the above operations."/>
     <conditional name="copy_r">
       <param name="default" type="boolean" checked="false" label="Copy adata.X to adata.raw"/>
       <when value="true">
@@ -310,8 +349,6 @@
   <tests>
     <test>
       <param name="input_obj_file" value="find_cluster.h5"/>
-      <param name="input_format" value="anndata"/>
-      <param name="color_by" value="louvain"/>
       <output name="output_h5ad" file="anndata_ops.h5" ftype="h5ad" compare="sim_size"/>
     </test>
     <test>
@@ -325,8 +362,29 @@
       </output>
     </test>
     <test>
+      <param name="input_obj_file" value="anndata_ops.h5"/>
+      <repeat name="var_modifications" >
+        <param name="from_var" value = "gene_symbols" />
+        <param name="to_var" value = "gene_symbols_unique" />
+        <param name="make_unique" value = "True" />
+      </repeat>
+      <output name="output_h5ad" ftype="h5ad">
+        <assert_contents>
+          <has_h5_keys keys="var/gene_symbols_unique" />
+        </assert_contents>
+      </output>
+    </test>
+    <test>
+      <param name="input_obj_file" value="anndata_ops.h5"/>
+      <param name="field_unique" value = "gene_symbols" />
+      <output name="output_h5ad" ftype="h5ad">
+        <assert_contents>
+          <has_h5_keys keys="var/gene_symbols_u" />
+        </assert_contents>
+      </output>
+    </test>
+    <test>
       <param name="input_obj_file" value="find_cluster.h5"/>
-      <param name="input_format" value="anndata"/>
       <conditional name="copy_r">
         <param name="default" value="true"/>
         <param name="r_source" value="read_10x.h5"/>
@@ -334,39 +392,37 @@
       <output name="output_h5ad" file="anndata_ops_raw.h5" ftype="h5ad" compare="sim_size">
         <assert_contents>
           <has_h5_keys keys="raw/X" />
-	</assert_contents>
+        </assert_contents>
       </output>
     </test>
     <test>
       <param name="input_obj_file" value="normalise_data.h5"/>
-      <param name="input_format" value="anndata"/>
       <conditional name="copy_x">
         <param name="default" value="true"/>
         <repeat name="xlayers">
-	  <param name="x_source" value='filter_genes.h5'/>
-	  <param name="dest" value='filtered'/>
-	</repeat>
+          <param name="x_source" value='filter_genes.h5'/>
+          <param name="dest" value='filtered'/>
+        </repeat>
       </conditional>
       <output name="output_h5ad" file="anndata_ops_xlayer.h5" ftype="h5ad" compare="sim_size">
         <assert_contents>
           <has_h5_keys keys="layers/filtered" />
-	</assert_contents>
+        </assert_contents>
       </output>
     </test>
     <test>
       <param name="input_obj_file" value="find_cluster.h5"/>
-      <param name="input_format" value="anndata"/>
       <conditional name="copy_l">
         <param name="default" value="true"/>
         <repeat name="layers">
-	  <param name="contains" value='filtered'/>
-	</repeat>
-	<param name="layer_sources" value='anndata_ops_xlayer.h5'/>
+          <param name="contains" value='filtered'/>
+        </repeat>
+        <param name="layer_sources" value='anndata_ops_xlayer.h5'/>
       </conditional>
       <output name="output_h5ad" file="anndata_ops_layer.h5" ftype="h5ad" compare="sim_size">
         <assert_contents>
           <has_h5_keys keys="layers/filtered" />
-	</assert_contents>
+        </assert_contents>
       </output>
     </test>
   </tests>
@@ -378,11 +434,12 @@
 
 Performs the following operations:
 
-* Change observation/var fields, mostly for downstreaming processes convenience. Multiple fields can be changed as one.
+* Change observation/var fields, mostly for downstreaming processes convenience. Multiple fields can be changed at once.
 * Flag genes that start with a certain text: useful for flagging mitochondrial, spikes or other groups of genes.
 * For the flags created, calculates qc metrics (pct_<flag>_counts).
 * Calculates `n_genes`, `n_counts` for cells and `n_cells`, `n_counts` for genes.
 * For top <N> genes specified, calculate qc metrics (pct_counts_in_top_<N>_genes).
+* Make a specified column of var or obs unique (normally useful for gene symbols).
 * Copy from a set of compatible AnnData objects (same cells and genes):
   * Observations, such as clustering results.
   * Embeddings, such as tSNE or UMAPs.
@@ -392,6 +449,7 @@
 
 History
 -------
+1.8.1+galaxy10: Adds field to be made unique in obs or var.
 
 1.6.0+galaxy0: Moves to Scanpy Scripts 0.3.0 (Scanpy 1.6.0), versioning switched to track Scanpy as other tools.
 
--- a/scanpy_macros2.xml	Thu Oct 28 09:55:27 2021 +0000
+++ b/scanpy_macros2.xml	Thu Feb 16 13:28:31 2023 +0000
@@ -1,9 +1,11 @@
 <macros>
-  <token name="@TOOL_VERSION@">1.8.1+3</token>
+  <token name="@TOOL_VERSION@">1.8.1</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**
+1.8.1+galaxy9: Fixes version label to get versions sorted properly on Galaxy (equivalent to 1.8.1+3+galaxy0). In addition, adds ability to make fields unique in AnnData operations,
+adds additional handler on Scrubblet for workflows convenience, enables Scanpy tools to avoid outputing AnnData/matrix files when not required.
 
 1.8.1+3+galaxy0: Upate to scanpy-scripts 1.1.3 (running scanpy ==1.8.1), including a fix to MTX output and a bugfix for the Scrublet wrapper.
 
@@ -99,18 +101,20 @@
   </xml>
 
   <xml name="output_object_params">
-    <param name="output_format" argument="--output-format" type="select" label="Format of output object">
+    <param name="output_format" argument="--output-format" type="select" label="Format of output object" help="AnnData or Loom. Legacy 'h5' datatypes are useful for interacting with older tools. Choosing 'No packaged matrix output' is useful for cases where auxiliary files are generated (like in marker genes). Do not use when there are no other output files, as the tool will generate no output in Galaxy then.">
       <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>
+      <option value="no_matrix_output">No packaged matrix output</option>
     </param>
   </xml>
 
   <xml name="output_object_params_no_loom">
-    <param name="output_format" argument="--output-format" type="select" label="Format of output object">
+    <param name="output_format" argument="--output-format" type="select" label="Format of output object" help="Legacy 'h5' datatypes are useful for interacting with older tools. Choosing 'No packaged matrix output' is useful for cases where auxiliary files are generated (like in marker genes). Do not use when there are no other output files, as the tool will generate no output in Galaxy then.">
       <option value="anndata_h5ad" selected="true">AnnData format</option>
       <option value="anndata">AnnData format (h5 for older versions)</option>
+      <option value="no_matrix_output">No packaged matrix output (useful for cases where auxiliary files are generated)</option>
     </param>
   </xml>
 
@@ -118,7 +122,7 @@
     <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 ${on_string}: @DESCRIPTION@ AnnData">
+    <data name="output_h5" format="h5" from_work_dir="output.h5" label="${tool.name} on ${on_string}: @DESCRIPTION@ AnnData (h5)">
       <filter>output_format == 'anndata'</filter>
     </data>
   </xml>
@@ -127,13 +131,13 @@
     <data name="output_h5ad" format="h5ad" from_work_dir="output.h5" label="${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 ${on_string}: @DESCRIPTION@ AnnData">
+    <data name="output_h5" format="h5" from_work_dir="output.h5" label="${tool.name} on ${on_string}: @DESCRIPTION@ AnnData (h5)">
       <filter>output_format == 'anndata'</filter>
     </data>
     <data name="output_loom_legacy" format="h5" from_work_dir="output.h5" label="${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 ${on_string}: @DESCRIPTION@ Loom">
+    <data name="output_loom" format="loom" from_work_dir="output.h5" label="${tool.name} on ${on_string}: @DESCRIPTION@ Loom (h5)">
       <filter>output_format == 'loom'</filter>
     </data>
   </xml>