Test data, formatting, arboretum option

ebi-gene-expression-group · Aug 16, 2024 · 2f2e46e · 2f2e46e
1 parent e075901
commit 2f2e46e
Show file tree

Hide file tree

Showing 4 changed files with 37 additions and 20 deletions.
diff --git a/tools/tertiary-analysis/pyscenic/get_test_data.sh b/tools/tertiary-analysis/pyscenic/get_test_data.sh
@@ -1,9 +1,12 @@
 #!/usr/bin/env bash
 TF_DATA_LINK='https://raw.githubusercontent.com/aertslab/scenic-nf/master/example/allTFs_hg38.txt'
 MOTIF2TF_LINK='https://raw.githubusercontent.com/aertslab/scenic-nf/master/example/motifs.tbl'
-RANKING_LINK='https://raw.githubusercontent.com/aertslab/scenic-nf/master/example/genome-ranking.feather'
+RANKING_LINK='https://zenodo.org/records/13328724/files/genome-ranking_v2.feather'
 LOOM_INPUT_LINK='https://raw.githubusercontent.com/aertslab/scenic-nf/master/example/expr_mat.loom'
 
+REGULONS_LINK='https://zenodo.org/records/13328724/files/regulons.tsv'
+TF2TARGETS_LINK='https://zenodo.org/records/13328724/files/tf2targets.tsv'
+
 function get_data {
   local link=$1
   local fname=$2
@@ -18,9 +21,8 @@ function get_data {
 mkdir -p test-data
 pushd test-data
 get_data $TF_DATA_LINK "allTFs_hg38.txt"
-#unzip mtx.zip
-#rm -f mtx.zip
-
 get_data $MOTIF2TF_LINK "motifs.tbl"
-get_data $RANKING_LINK "genome-ranking.feather"
-get_data $LOOM_INPUT_LINK "expr_mat.loom"
+get_data $RANKING_LINK "genome-ranking_v2.feather"
+get_data $LOOM_INPUT_LINK "expr_mat.loom"
+get_data $REGULONS_LINK regulons.tsv
+get_data $TF2TARGETS_LINK tf2targets.tsv
diff --git a/tools/tertiary-analysis/pyscenic/pyscenic_aucell.xml b/tools/tertiary-analysis/pyscenic/pyscenic_aucell.xml
@@ -51,7 +51,7 @@
         <param name="nes_threshold" type="float" label="NES Threshold" help="The Normalized Enrichment Score (NES) threshold for finding enriched features (default: 3.0)." optional="true"/>
         <param name="cell_id_attribute" type="text" label="Cell ID Attribute" help="The name of the column attribute that specifies the identifiers of the cells in the loom file." optional="true"/>
         <param name="gene_attribute" type="text" label="Gene Attribute" help="The name of the row attribute that specifies the gene symbols in the loom file." optional="true"/>
-        <param name="sparse" type="boolean" label="Sparse Matrix" truevalue="--sparse" falsevalue="" help="If set, load the expression data as a sparse matrix. Currently applies to the grn inference step only." optional="true"/>
+        <param name="sparse" type="boolean" label="Sparse Matrix" truevalue="--sparse" falsevalue="" help="If set, load the expression data as a sparse matrix. Currently applies to the grn inference step only."/>
     </inputs>
     <outputs>
         <data name="output" format="tsv" label="${tool.name} on ${on_string}: AUCell scores for regulons or gene sets."/>

diff --git a/tools/tertiary-analysis/pyscenic/pyscenic_ctx.xml b/tools/tertiary-analysis/pyscenic/pyscenic_ctx.xml
@@ -69,9 +69,8 @@
 #if $gene_attribute
     --gene_attribute '${gene_attribute}'
 #end if
-#if $sparse
-    --sparse
-#end if
+$sparse
+
 &&
 
 mv regulons.tsv '${output}'
@@ -97,7 +96,7 @@ mv regulons.tsv '${output}'
         <param type="boolean" name="mask_dropouts" label="Mask Dropouts" optional="true" help="Mask dropouts in the expression matrix."/>
         <param type="text" name="cell_id_attribute" label="Cell ID Attribute" optional="true" help="The name of the attribute in the loom expression matrix that contains cell IDs."/>
         <param type="text" name="gene_attribute" label="Gene Attribute" optional="true" help="The name of the attribute in the loom expression matrix that contains gene names."/>
-        <param type="boolean" name="sparse" label="Sparse" optional="true" help="Use a sparse matrix for the gene regulatory network inference step."/>
+        <param name="sparse" type="boolean" label="Sparse Matrix" truevalue="--sparse" falsevalue="" help="If set, load the expression data as a sparse matrix. Currently applies to the grn inference step only."/>
     </inputs>
     <outputs>
         <data name="output" format="tabular" label="${tool.name} on ${on_string}: table of enriched motifs and target genes"/>

diff --git a/tools/tertiary-analysis/pyscenic/pyscenic_grn.xml b/tools/tertiary-analysis/pyscenic/pyscenic_grn.xml
@@ -1,15 +1,19 @@
 <tool id="pyscenic_grn" name="PySCENIC GRN" version="0.12.1+galaxy0" profile="21.09">
-    <description>Gene regulatory network inference using PySCENIC</description>
+    <description>infers gene regulatory networks</description>
     <requirements>
         <container type="docker">
             aertslab/pyscenic:0.12.1
         </container>
     </requirements>
     <command detect_errors="exit_code">
         <![CDATA[
-        ln -s '${expression_mtx}' expr_mat.loom && 
-        ln -s '${tfs_fname}' tfs.txt &&
-        pyscenic grn 
+            ln -s '${expression_mtx}' expr_mat.loom && 
+            ln -s '${tfs_fname}' tfs.txt &&
+            #if $use_arboretum
+                arboreto_with_multiprocessing.py
+            #else
+                pyscenic grn 
+            #end if
             -o tf2targets.tsv
             #if $transpose
             -t
@@ -27,24 +31,24 @@
             #if $gene_attribute
             --gene_attribute '${gene_attribute}'
             #end if
-            #if $sparse
-            --sparse
-            #end if
+            $sparse
+            
             expr_mat.loom tfs.txt &&
             mv tf2targets.tsv '${tf2targets}'
         ]]>
     </command>
     <inputs>
         <param name="expression_mtx" type="data" format="loom" label="Expression Matrix Loom File" help="In format rows=genes x columns=cells"/>
         <param name="tfs_fname" type="data" format="txt" label="Transcription Factors File" help="Simple text file, one transcription factor symbol per line"/>
-        <param name="transpose" type="boolean" default_value="false" label="Transpose Expression Matrix"/>
+        <param name="use_arboretum" type="boolean" label="Use arboretum" checked="false" help="Uses the arboretum approach instead of pyscenic grn call, which can be better for multi processing"/>
+        <param name="transpose" type="boolean" default_value="false" label="Transpose Expression Matrix" help="Use this if the matrix is cell x genes instead of genes x cells as expected"/>
         <param name="method" type="select" label="Method">
             <option value="genie3">GENIE3</option>
             <option value="grnboost2" selected="true">GRNBoost2</option>
         </param>
         <param name="cell_id_attribute" type="text" optional="true" label="Cell ID Attribute"/>
         <param name="gene_attribute" type="text" optional="true" label="Gene Attribute"/>
-        <param name="sparse" type="boolean" optional="true" label="Load as Sparse Matrix"/>
+        <param name="sparse" type="boolean" label="Sparse Matrix" truevalue="--sparse" falsevalue="" help="If set, load the expression data as a sparse matrix. Currently applies to the grn inference step only."/>
         <param name="seed" type="integer" optional="true" label="Seed"/>
     </inputs>
     <outputs>
@@ -62,6 +66,18 @@
                 </assert_contents>
             </output>
         </test>
+        <test expect_num_outputs="1">
+            <param name="expression_mtx" value="expr_mat.loom"/>
+            <param name="tfs_fname" value="allTFs_hg38.txt"/>
+            <param name="use_arboretum" value="true"/>
+            <param name="seed" value="1"/>
+            <output name="tf2targets" file="tf2targets_arboretum.tsv" compare="sim_size" delta_frac="0.2">
+                <!-- file="tf2targets.tsv" compare="sim_size" delta_frac="0.2"/> -->
+                <assert_contents>
+                    <has_n_lines n="1006973"/>
+                </assert_contents>
+            </output>
+        </test>
     </tests>
     <help><![CDATA[
         This tool runs the `pyscenic grn` command to infer gene regulatory networks.