From 4990a52ac6fd3d97434a24051e5828c86c8a802c Mon Sep 17 00:00:00 2001
From: Pablo Moreno <pcm32@users.noreply.github.com>
Date: Tue, 20 Aug 2024 13:26:27 +0100
Subject: [PATCH] Adds PySCENIC wrappers (#328)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

* pyscenic grn passing tests

* Minor improvements to grn

* Shed file for pyscenic

* ctx passing tests (test files unavailable for CI though)

* AUCell passing tests locally

* Comestic changes

* Apply suggestions from bgruening's code review

Co-authored-by: Björn Grüning <bjoern@gruenings.eu>

* Formatting and others

* Test data, formatting, arboretum option

* Fix tests

* ctx missing documentation

* Use macros

* Boolean variables

* Tool version macro and missing boolean

* Apply suggestions from Bjeorn's code review

Co-authored-by: Björn Grüning <bjoern@gruenings.eu>

* Hopefully fixes test for ctx

* Missing boolean changes

---------

Co-authored-by: Björn Grüning <bjoern@gruenings.eu>
---
 tools/tertiary-analysis/pyscenic/.shed.yml    |  21 +++
 .../pyscenic/get_test_data.sh                 |  28 ++++
 tools/tertiary-analysis/pyscenic/macros.xml   |  15 ++
 .../pyscenic/pyscenic_aucell.xml              | 104 +++++++++++++
 .../pyscenic/pyscenic_ctx.xml                 | 139 ++++++++++++++++++
 .../pyscenic/pyscenic_grn.xml                 |  98 ++++++++++++
 6 files changed, 405 insertions(+)
 create mode 100644 tools/tertiary-analysis/pyscenic/.shed.yml
 create mode 100644 tools/tertiary-analysis/pyscenic/get_test_data.sh
 create mode 100644 tools/tertiary-analysis/pyscenic/macros.xml
 create mode 100644 tools/tertiary-analysis/pyscenic/pyscenic_aucell.xml
 create mode 100644 tools/tertiary-analysis/pyscenic/pyscenic_ctx.xml
 create mode 100644 tools/tertiary-analysis/pyscenic/pyscenic_grn.xml

diff --git a/tools/tertiary-analysis/pyscenic/.shed.yml b/tools/tertiary-analysis/pyscenic/.shed.yml
new file mode 100644
index 00000000..f4c05268
--- /dev/null
+++ b/tools/tertiary-analysis/pyscenic/.shed.yml
@@ -0,0 +1,21 @@
+categories:
+ - Transcriptomics
+ - RNA
+ - Sequence Analysis
+description: "PySCENIC scripts based on usage at https://pyscenic.readthedocs.io/"
+long_description: |
+        pySCENIC is a lightning-fast python implementation of the SCENIC pipeline (Single-Cell rEgulatory Network Inference and Clustering) 
+        which enables biologists to infer transcription factors, gene regulatory networks and cell types from single-cell RNA-seq data.
+name: suite_pyscenic
+owner: ebi-gxa
+remote_repository_url: https://github.com/ebi-gene-expression-group/container-galaxy-sc-tertiary/
+type: unrestricted
+auto_tool_repositories:
+  name_template: "{{ tool_id }}"
+  description_template: "Wrapper for the pySCENIC tool suite: {{ tool_name }}"
+suite:
+  name: "suite_pyscenic"
+  description: "PySCENIC scripts based on usage at https://pyscenic.readthedocs.io/"
+  long_description: |
+    pySCENIC is a lightning-fast python implementation of the SCENIC pipeline (Single-Cell rEgulatory Network Inference and Clustering) 
+    which enables biologists to infer transcription factors, gene regulatory networks and cell types from single-cell RNA-seq data.
diff --git a/tools/tertiary-analysis/pyscenic/get_test_data.sh b/tools/tertiary-analysis/pyscenic/get_test_data.sh
new file mode 100644
index 00000000..5cf84555
--- /dev/null
+++ b/tools/tertiary-analysis/pyscenic/get_test_data.sh
@@ -0,0 +1,28 @@
+#!/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://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
+
+  if [ ! -f $fname ]; then
+    echo "$fname not available locally, downloading.."
+    wget -O $fname --retry-connrefused --waitretry=1 --read-timeout=20 --timeout=15 -t 3 $link
+  fi
+}
+
+# get matrix data
+mkdir -p test-data
+pushd test-data
+get_data $TF_DATA_LINK "allTFs_hg38.txt"
+get_data $MOTIF2TF_LINK "motifs.tbl"
+get_data $RANKING_LINK "genome-ranking_v2.feather"
+get_data $LOOM_INPUT_LINK "expr_mat.loom"
+get_data $REGULONS_LINK regulons.tsv
+get_data $TF2TARGETS_LINK tf2targets.tsv
\ No newline at end of file
diff --git a/tools/tertiary-analysis/pyscenic/macros.xml b/tools/tertiary-analysis/pyscenic/macros.xml
new file mode 100644
index 00000000..1979d46e
--- /dev/null
+++ b/tools/tertiary-analysis/pyscenic/macros.xml
@@ -0,0 +1,15 @@
+<macros>
+    <token name="@TOOL_VERSION@">0.12.1</token>
+    <xml name="requirements">
+        <requirements>
+            <container type="docker">
+            aertslab/pyscenic:@TOOL_VERSION@
+        </container>
+        </requirements>
+    </xml>
+    <xml name="citations">
+        <citations>
+            <citation type="doi">10.1038/nmeth.4463</citation>
+        </citations>
+    </xml>
+</macros>
diff --git a/tools/tertiary-analysis/pyscenic/pyscenic_aucell.xml b/tools/tertiary-analysis/pyscenic/pyscenic_aucell.xml
new file mode 100644
index 00000000..e9c079ba
--- /dev/null
+++ b/tools/tertiary-analysis/pyscenic/pyscenic_aucell.xml
@@ -0,0 +1,104 @@
+<tool id="pyscenic_aucell" name="PySCENIC AUCell" profile="21.09" version="@TOOL_VERSION@+galaxy0">
+    <description>calculates AUCell to find relevant regulons/gene sets</description>
+    <macros>
+        <import>macros.xml</import>
+    </macros>
+    <expand macro="requirements"/>
+    <command><![CDATA[
+        ln -s '${expression_mtx_fname}' expr_mat.loom &&
+        ln -s '${signatures_fname}' regulons.tsv &&
+
+        pyscenic aucell expr_mat.loom regulons.tsv
+           -o aucell.tsv
+        $transpose
+        $weights
+       --num_workers \${GALAXY_SLOTS:-1}
+        #if $seed
+           --seed '${seed}'
+        #end if
+        #if str($rank_threshold):
+           --rank_threshold '${rank_threshold}'
+        #end if
+        #if $auc_threshold
+           --auc_threshold '${auc_threshold}'
+        #end if
+        #if $nes_threshold
+           --nes_threshold '${nes_threshold}'
+        #end if
+        #if $cell_id_attribute
+           --cell_id_attribute '${cell_id_attribute}'
+        #end if
+        #if $gene_attribute
+           --gene_attribute '${gene_attribute}'
+        #end if
+        $sparse
+
+        && mv aucell.tsv '${output}'
+    ]]></command>
+    <inputs>
+        <param name="expression_mtx_fname" format="loom" type="data" label="Expression Matrix File" help="The file that contains the expression matrix for the single-cell experiment. Supported formats: csv (rows=cells x columns=genes) or loom (rows=genes x columns=cells)."/>
+        <param name="signatures_fname" type="data" format="csv,tabular" label="Gene Signatures/Regulons File" help="The file that contains the gene signatures (usually the precomputed regulons). Currently only csv/tsv supported, could be extended."/>
+        <param type="boolean" name="transpose" label="Transpose Expression Matrix" truevalue="-t" falsevalue="" help="Use this if the matrix is cell x genes instead of genes x cells as expected"/>
+        <param name="weights" type="boolean" label="Use Weights for Recovery Analysis" truevalue="-w" falsevalue="" help="Use weights associated with genes in recovery analysis. Relevant when gene signatures are supplied as json format."/>
+        <param name="seed" type="integer" label="Seed for Ranking" help="Seed for the expression matrix ranking step. The default is to use a random seed." optional="true"/>
+        <param name="rank_threshold" type="integer" label="Rank Threshold" help="The rank threshold used for deriving the target genes of an enriched motif (default: 5000)." optional="true"/>
+        <param name="auc_threshold" type="float" label="AUC Threshold" help="The threshold used for calculating the AUC of a feature as fraction of ranked genes (default: 0.05)." optional="true"/>
+        <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."/>
+    </inputs>
+    <outputs>
+        <data name="output" format="tabular" label="${tool.name} on ${on_string}: AUCell scores for regulons or gene sets."/>
+    </outputs>
+    <tests>
+        <test expect_num_outputs="1">
+            <param name="expression_mtx_fname" value="expr_mat.loom"/>
+            <param name="signatures_fname" value="regulons.tsv"/>
+            <output name="output">
+                <assert_contents>
+                    <has_n_lines n="101"/>
+                    <has_text text="CEBPB"/>
+                </assert_contents>
+            </output>
+        </test>
+    </tests>
+    <help>
+        <![CDATA[
+          Run PySCENIC aucell command to analyze single-cell gene expression data.
+    
+          **Input Parameters:**
+    
+          - **expression_mtx_fname**: The name of the file that contains the expression matrix for the single cell experiment. Two file formats are supported: csv (rows=cells x columns=genes) or loom (rows=genes x columns=cells).
+    
+          - **signatures_fname**: The name of the file that contains the gene signatures. Three file formats are supported: gmt, yaml, or dat (pickle).
+    
+          **Options:**
+    
+          - **-o, --output**: Output file/stream, a matrix of AUC values. Two file formats are supported: csv or loom. If loom file is specified, it will contain the original expression matrix and the calculated AUC values as extra column attributes.
+    
+          - **-t, --transpose**: Transpose the expression matrix if supplied as csv (rows=genes x columns=cells).
+    
+          - **-w, --weights**: Use weights associated with genes in recovery analysis. Is only relevant when gene signatures are supplied as json format.
+    
+          - **--seed**: Seed for the expression matrix ranking step. The default is to use a random seed.
+    
+          **Motif Enrichment Arguments:**
+    
+          - **--rank_threshold**: The rank threshold used for deriving the target genes of an enriched motif (default: 5000).
+    
+          - **--auc_threshold**: The threshold used for calculating the AUC of a feature as fraction of ranked genes (default: 0.05).
+    
+          - **--nes_threshold**: The Normalized Enrichment Score (NES) threshold for finding enriched features (default: 3.0).
+    
+          **Loom File Arguments:**
+    
+          - **--cell_id_attribute**: The name of the column attribute that specifies the identifiers of the cells in the loom file.
+    
+          - **--gene_attribute**: The name of the row attribute that specifies the gene symbols in the loom file.
+    
+          - **--sparse**: If set, load the expression data as a sparse matrix. Currently applies to the grn inference step only.
+        ]]>
+      </help>
+    <expand macro="citations"/>
+</tool>
diff --git a/tools/tertiary-analysis/pyscenic/pyscenic_ctx.xml b/tools/tertiary-analysis/pyscenic/pyscenic_ctx.xml
new file mode 100644
index 00000000..82abf371
--- /dev/null
+++ b/tools/tertiary-analysis/pyscenic/pyscenic_ctx.xml
@@ -0,0 +1,139 @@
+<tool id="pyscenic_ctx" name="PySCENIC CTX" profile="21.09" version="@TOOL_VERSION@+galaxy0">
+    <description>
+        computes active regulons based on a gene regulatory network
+    </description>
+    <macros>
+        <import>macros.xml</import>
+    </macros>
+    <expand macro="requirements"/>
+    <command><![CDATA[
+    #set PySCENIC_DB = "db.genes_vs_motifs.rankings.feather"
+    ln -s '${module_fname}' tf2targets.tsv &&
+    ln -s '${expression_mtx}' expr_mat.loom &&
+    ln -s '${database_fname}' ${PySCENIC_DB} &&
+
+    pyscenic ctx tf2targets.tsv ${PySCENIC_DB} 
+        --expression_mtx_fname expr_mat.loom
+    --output regulons.tsv
+$no_pruning
+#if $chunk_size
+    --chunk_size '${chunk_size}'
+#end if
+    --mode custom_multiprocessing
+    --num_workers \${GALAXY_SLOTS:-1}
+$all_modules
+$transpose
+#if $rank_threshold
+    --rank_threshold '${rank_threshold}'
+#end if
+#if $auc_threshold
+    --auc_threshold '${auc_threshold}'
+#end if
+#if $nes_threshold
+    --nes_threshold '${nes_threshold}'
+#end if
+#if $min_orthologous_identity
+    --min_orthologous_identity '${min_orthologous_identity}'
+#end if
+#if $max_similarity_fdr
+    --max_similarity_fdr '${max_similarity_fdr}'
+#end if
+#if $annotations_fname
+    --annotations_fname '${annotations_fname}'
+#end if
+#if $thresholds
+    --thresholds '${thresholds}'
+#end if
+#if $top_n_targets
+    --top_n_targets '${top_n_targets}'
+#end if
+#if $top_n_regulators
+    --top_n_regulators '${top_n_regulators}'
+#end if
+#if $min_genes
+    --min_genes '${min_genes}'
+#end if
+$mask_dropouts
+#if $cell_id_attribute
+    --cell_id_attribute '${cell_id_attribute}'
+#end if
+#if $gene_attribute
+    --gene_attribute '${gene_attribute}'
+#end if
+$sparse
+
+]]></command>
+    <inputs>
+        <param type="data" name="module_fname" format="tabular" label="Module File" help="Signatures or the co-expression modules. Usually the output from pyscenic grn."/>
+        <param type="data" name="database_fname" label="Database File" help="Regulatory feature databases. Supported formats: feather"/>
+        <param type="data" name="annotations_fname" format="tabular" label="Annotations File" help="File that contains the motif annotations to use."/>
+        <param type="data" name="expression_mtx" format="loom" label="Expression Matrix" help="The expression matrix for the single cell experiment."/>
+        <param type="boolean" name="no_pruning" label="No Pruning" truevalue="--no_pruning" falsevalue="" help="Do not perform pruning, i.e. find enriched motifs."/>
+        <param type="integer" name="chunk_size" label="Chunk Size" optional="true" help="The size of the module chunks assigned to a node in the dask graph (default: 100)."/>
+        <param type="boolean" name="all_modules" label="All Modules" truevalue="--all_modules" falsevalue="" help="Include positive and negative regulons in the analysis (default: no, i.e. only positive)."/>
+        <param type="boolean" name="transpose" label="Transpose Expression Matrix" truevalue="-t" falsevalue="" help="Use this if the matrix is cell x genes instead of genes x cells as expected"/>
+        <param type="float" name="rank_threshold" label="Rank Threshold" optional="true" help="The rank threshold used for deriving the target genes of an enriched motif."/>
+        <param type="float" name="auc_threshold" label="AUC Threshold" optional="true" help="The threshold used for calculating the AUC of a feature as fraction of ranked genes."/>
+        <param type="float" name="nes_threshold" label="NES Threshold" optional="true" help="The Normalized Enrichment Score (NES) threshold for finding enriched features."/>
+        <param type="float" name="min_orthologous_identity" label="Minimum Orthologous Identity" optional="true" help="Minimum orthologous identity to use when annotating enriched motifs."/>
+        <param type="float" name="max_similarity_fdr" label="Maximum Similarity FDR" optional="true" help="Maximum FDR in motif similarity to use when annotating enriched motifs."/>
+        <param type="text" name="thresholds" label="Thresholds" optional="true" help="Thresholds to use for selecting the features (e.g., motifs)."/>
+        <param type="integer" name="top_n_targets" label="Top N Targets" optional="true" help="The number of top targets to retain for each feature."/>
+        <param type="integer" name="top_n_regulators" label="Top N Regulators" optional="true" help="The number of top regulators to retain for each feature."/>
+        <param type="integer" name="min_genes" label="Minimum Genes" optional="true" help="The minimum number of genes a module needs to have to be considered for regulatory network analysis."/>
+        <param type="boolean" name="mask_dropouts" label="Mask Dropouts" truevalue="--mask_dropouts" falsevalue="" 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 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" from_work_dir="regulons.tsv" label="${tool.name} on ${on_string}: table of enriched motifs and target genes"/>
+        <!-- Define other output formats as needed -->
+    </outputs>
+    <tests>
+        <test expect_num_outputs="1">
+            <param name="module_fname" value="tf2targets.tsv"/>
+            <param name="expression_mtx" value="expr_mat.loom"/>
+            <param name="database_fname" value="genome-ranking_v2.feather"/>
+            <param name="annotations_fname" value="motifs.tbl"/>
+            <output name="output" file="regulons.tsv" compare="sim_size" delta_frac="0.2"/>
+        </test>
+    </tests>
+    <help><![CDATA[
+        .. class:: infomark
+           :name: warning
+        
+           **pySCENIC ctx: Contextualize GRN**
+        
+        This tool refines gene regulatory networks (GRNs) by pruning targets that do not have an enrichment for a corresponding motif of the transcription factor (TF). This process effectively separates direct from indirect targets based on the presence of cis-regulatory footprints.
+        
+        **Inputs:**
+        
+        - **Module File**: A file containing the signature or co-expression modules. Supported formats include CSV, TSV (adjacencies), YAML, GMT, and DAT (modules).
+        - **Database Files**: One or more regulatory feature databases. Supported formats include feather or db (legacy).
+        - **Annotations File**: A file containing the motif annotations to use.
+        
+        **Optional Parameters:**
+        
+        - **No Pruning**: Do not perform pruning, i.e., find enriched motifs.
+        - **Chunk Size**: The size of the module chunks assigned to a node in the dask graph (default: 100).
+        - **Mode**: The mode to be used for computing (default: custom_multiprocessing).
+        - **All Modules**: Include positive and negative regulons in the analysis (default: only positive).
+        - **Transpose**: Transpose the expression matrix (rows=genes x columns=cells).
+        - **Rank Threshold**: The rank threshold used for deriving the target genes of an enriched motif (default: 5000).
+        - **AUC Threshold**: The threshold used for calculating the AUC of a feature as a fraction of ranked genes (default: 0.05).
+        - **NES Threshold**: The Normalized Enrichment Score (NES) threshold for finding enriched features (default: 3.0).
+        - **Min Orthologous Identity**: Minimum orthologous identity to use when annotating enriched motifs (default: 0.0).
+        - **Max Similarity FDR**: Maximum FDR in motif similarity to use when annotating enriched motifs (default: 0.001).
+        - **Thresholds**: The first method to create the TF-modules based on the best targets for each transcription factor (default: 0.75 0.90).
+        - **Top N Targets**: The second method is to select the top targets for a given TF (default: 50).
+        - **Top N Regulators**: The alternative way to create the TF-modules is to select the best regulators for each gene (default: 5 10 50).
+        - **Min Genes**: The minimum number of genes in a module (default: 20).
+        - **Expression Matrix File**: The name of the file that contains the expression matrix for the single-cell experiment. Supported formats include csv (rows=cells x columns=genes) or loom (rows=genes x columns=cells). Required if modules need to be generated.
+        - **Mask Dropouts**: Controls whether cell dropouts (cells in which expression of either TF or target gene is 0) are masked when calculating the correlation between a TF-target pair.
+        - **Cell ID Attribute**: The name of the column attribute that specifies the identifiers of the cells in the loom file.
+        - **Gene Attribute**: The name of the row attribute that specifies the gene symbols in the loom file.
+        - **Sparse**: If set, load the expression data as a sparse matrix. Currently applies to the GRN inference step only.
+        ]]></help>
+    <expand macro="citations"/>
+</tool>
diff --git a/tools/tertiary-analysis/pyscenic/pyscenic_grn.xml b/tools/tertiary-analysis/pyscenic/pyscenic_grn.xml
new file mode 100644
index 00000000..35e84632
--- /dev/null
+++ b/tools/tertiary-analysis/pyscenic/pyscenic_grn.xml
@@ -0,0 +1,98 @@
+<tool id="pyscenic_grn" name="PySCENIC GRN" version="@TOOL_VERSION@+galaxy0" profile="21.09">
+    <description>infers gene regulatory networks</description>
+    <macros>
+        <import>macros.xml</import>
+    </macros>
+    <expand macro="requirements"/>
+    <command detect_errors="exit_code">
+        <![CDATA[
+            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
+            $transpose
+            #if $method
+            -m '${method}'
+            #end if
+            #if $seed
+            --seed '${seed}'
+            #end if
+            --num_workers \${GALAXY_SLOTS:-1}
+            #if $cell_id_attribute
+            --cell_id_attribute '${cell_id_attribute}'
+            #end if
+            #if $gene_attribute
+            --gene_attribute '${gene_attribute}'
+            #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="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" truevalue="-t" falsevalue="" 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" 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>
+        <data name="tf2targets" format="tabular" label="${tool.name} on ${on_string}: gene regulatory network"/>
+    </outputs>
+    <tests>
+        <test expect_num_outputs="1">
+            <param name="expression_mtx" value="expr_mat.loom"/>
+            <param name="tfs_fname" value="allTFs_hg38.txt"/>
+            <param name="seed" value="1"/>
+            <output name="tf2targets">
+                <assert_contents>
+                    <has_n_lines n="1006973"/>
+                </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" ftype="tabular">
+                <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.
+
+        **Inputs:**
+
+        - Expression Matrix File: Loom file containing the expression matrix, (rows=genes x columns=cells)
+        - Transcription Factors File: TXT file with a list of transcription factors.
+        
+        **Options:**
+
+        - Output File: Path to the output file (CSV format).
+        - Transpose Expression Matrix: If selected, transpose the expression matrix.
+        - Method: Algorithm for gene regulatory network reconstruction (default: GRNBoost2).
+        - Seed: Seed value for random state initialization.
+        - Number of Workers: Number of workers to use for computation.
+        - Client or Address: Client or IP address of the dask scheduler.
+        - Cell ID Attribute: Column attribute for cell identifiers in the loom file.
+        - Gene Attribute: Row attribute for gene symbols in the loom file.
+        - Load as Sparse Matrix: Load the expression data as a sparse matrix.
+    ]]></help>
+    <expand macro="citations"/>
+</tool>