Decoupler Pathway Inference

tools/tertiary-analysis/decoupler/decoupler_pathway_inference.py

@@ -59,6 +59,11 @@
 parser.add_argument(
     "--min_n", help="Minimum of targets per source. If less, sources are removed.", default=5, type=int
 )
+
+# add activity inference method option
+parser.add_argument(
+    "-m", "--method", help="Activity inference method", default="mlm", required=True
+)
 args = parser.parse_args()
 
 # check that either -o or --output is specified
@@ -82,25 +87,51 @@
 
 
 print(type(args.min_n))
-dc.run_mlm(
-    mat=adata,
-    net=network,
-    source=args.source,
-    target=args.target,
-    weight=args.weight,
-    verbose=True,
-    min_n=args.min_n,
-    use_raw=args.use_raw #Failing at the moment
-)
 
-if args.output is not None:
-    # write adata.obsm[mlm_key] and adata.obsm[mlm_pvals_key] to the output network files
-    combined_df = pd.concat([adata.obsm["mlm_estimate"], adata.obsm["mlm_pvals"]], axis=1)
+if args.method == "mlm":
+    dc.run_mlm(
+        mat=adata,
+        net=network,
+        source=args.source,
+        target=args.target,
+        weight=args.weight,
+        verbose=True,
+        min_n=args.min_n,
+        use_raw=args.use_raw #Failing at the moment
+    )
+
+    if args.output is not None:
+        # write adata.obsm[mlm_key] and adata.obsm[mlm_pvals_key] to the output network files
+        combined_df = pd.concat([adata.obsm["mlm_estimate"], adata.obsm["mlm_pvals"]], axis=1)
+
+        # Save the combined dataframe to a file
+        combined_df.to_csv(args.output + ".tsv", sep="\t")
+
+    # if args.activities_path is specified, generate the activities AnnData and save the AnnData object to the specified path
+    if args.activities_path is not None:
+        acts = dc.get_acts(adata, obsm_key="mlm_estimate")
+        acts.write_h5ad(args.activities_path)
+
+elif args.method == "ulm":
+    dc.run_ulm(
+        mat=adata,
+        net=network,
+        source=args.source,
+        target=args.target,
+        weight=args.weight,
+        verbose=True,
+        min_n=args.min_n,
+        use_raw=args.use_raw #Failing at the moment
+    )
+
+    if args.output is not None:
+        # write adata.obsm[mlm_key] and adata.obsm[mlm_pvals_key] to the output network files
+        combined_df = pd.concat([adata.obsm["ulm_estimate"], adata.obsm["ulm_pvals"]], axis=1)
 
-    # Save the combined dataframe to a file
-    combined_df.to_csv(args.output + "_mlm.tsv", sep="\t")
+        # Save the combined dataframe to a file
+        combined_df.to_csv(args.output + ".tsv", sep="\t")
 
-# if args.activities_path is specified, generate the activities AnnData and save the AnnData object to the specified path
-if args.activities_path is not None:
-    acts = dc.get_acts(adata, obsm_key="mlm_estimate")
-    acts.write_h5ad(args.activities_path)
+    # if args.activities_path is specified, generate the activities AnnData and save the AnnData object to the specified path
+    if args.activities_path is not None:
+        acts = dc.get_acts(adata, obsm_key="ulm_estimate")
+        acts.write_h5ad(args.activities_path)

tools/tertiary-analysis/decoupler/decoupler_pathway_inference.xml

@@ -1,6 +1,6 @@
 <tool id="decoupler_pathway_inference" name="Decoupler Pathway Inference" version="1.4.0+galaxy0" profile="20.05" license="MIT">
     <description>
-        Pathway inference using the Decoupler.
+        of functional genesets/pathways based on MLM with scRNA-seq data.
     </description>
     <requirements>
         <requirement type="package" version="1.4.0">decoupler</requirement>
@@ -10,22 +10,27 @@
             -i '$input_anndata'
             -n '$input_network_file'
             --min_n "$min_n"
+            --method '$method'
             $use_raw
             --output "inference"
             $write_activities_path
     </command>
     <inputs>
         <param name="input_anndata" type="data" format="h5ad" label="Input AnnData file" />
-        <param name="input_network_file" type="data" format="tabular" label="Input Network file" />
-        <param name="min_n" type="integer" min="0" value="5" label="Minimum of targets per source. If less, sources are removed" />
-        <param name="use_raw" type="boolean" truevalue="--use_raw" falsevalue="" checked="false" label="Whether to use the raw part of the AnnData object" />
+        <param name="input_network_file" type="data" format="tabular" label="Input Network file" help="Network file is tabular file with Source, Target and Weight. Source is a transcription factor(s) with specific regulation to target genes, either positive or negative." />
+        <param name="min_n" type="integer" min="0" value="5" label="Minimum of targets per source." help="If targets are less than minimum, sources are removed" />
+        <param name="method" type="select" label="Activity inference method">
+            <option value="mlm" selected="true">MLM</option>
+            <option value="ulm">ULM</option>
+        </param>
+        <param name="use_raw" type="boolean" truevalue="--use_raw" falsevalue="" checked="false" label="Use the raw part of the AnnData object" />
         <param name="write_activities_path" type="boolean" truevalue="--activities_path anndata_activities_path.h5ad" falsevalue="" checked="true" label="Write the modified AnnData object" />
     </inputs>
     <outputs>
         <data name="output_ad" format="h5ad" from_work_dir="anndata_activities_path.h5ad" label="${tool.name} on ${on_string}: Output AnnData file">
             <filter>write_activities_path</filter>
         </data>
-        <data name="output_table_mlm" format="tabular" from_work_dir="inference_mlm.tsv" label="${tool.name} on ${on_string}: Output MLM estimate table" />
+        <data name="output_table" format="tabular" from_work_dir="inference.tsv" label="${tool.name} on ${on_string}: Output estimate table" />
     </outputs>
     <tests>
         <!-- Hint: You can use [ctrl+alt+t] after defining the inputs/outputs to auto-scaffold some basic test cases. -->
@@ -34,14 +39,33 @@
         <param name="input_anndata" value="pbmc3k_processed.h5ad"/>
         <param name="input_network_file" value="progeny_test.tsv"/>
         <param name="min_n" value="0"/>
+        <param name="method" value="mlm"/>
         <param name="use_raw" value="false"/>
         <param name="write_activities_path" value="true"/>
         <output name="output_ad">
             <assert_contents>
                 <has_h5_keys keys="obsm/mlm_estimate"/>
             </assert_contents>
         </output>
-        <output name="output_table_mlm">
+        <output name="output_table">
+            <assert_contents>
+                <has_n_columns n="5"/>
+            </assert_contents>
+        </output>
+    </test>
+    <test>
+        <param name="input_anndata" value="pbmc3k_processed.h5ad"/>
+        <param name="input_network_file" value="progeny_test_2.tsv"/>
+        <param name="min_n" value="0"/>
+        <param name="method" value="ulm"/>
+        <param name="use_raw" value="false"/>
+        <param name="write_activities_path" value="true"/>
+        <output name="output_ad">
+            <assert_contents>
+                <has_h5_keys keys="obsm/ulm_estimate"/>
+            </assert_contents>
+        </output>
+        <output name="output_table">
             <assert_contents>
                 <has_n_columns n="5"/>
             </assert_contents>
@@ -57,13 +81,22 @@ Usage
 
 **Description**
 
-This tool scores cells using the AUCell method for gene sets.
+This tool extracts pathway activity inference using decoupler.
 
 **Input**
 
 The input file should be an AnnData object in H5AD format. The tool accepts an H5AD file containing raw or normalized data.
 
-The tool also takes network file containing a collection of pathways and their target genes, with weights for each interaction
+The tool also takes network file containing a collection of pathways and their target genes, with weights for each interaction.
+        Example:
+        ```
+                source    target    weight
+            0    T1    G01    1.0
+            1    T1    G02    1.0
+            2    T1    G03    0.7
+            3    T2    G04    1.0
+            4    T2    G06    -0.5
+        ```
 
 You can also specify whether to use the raw data in the AnnData object instead of the X matrix using the "use_raw" parameter and Minimum of targets per source using "min_n".
 

tools/tertiary-analysis/decoupler/test-data/progeny_test_2.tsv

@@ -0,0 +1,71 @@
+source	target	weight	p_value
+Androgen	TMPRSS2	11.490631	0.0
+Androgen	NKX3-1	10.622551	2.2e-44
+Androgen	MBOAT2	10.472733	4.6e-44
+Androgen	KLK2	10.176186	1.94441e-40
+Androgen	SARG	11.386852	2.79021e-40
+EGFR	LZTFL1	-1.8738769	2.0809955e-18
+EGFR	PHLDA2	3.5051384	2.0530624e-17
+EGFR	DUSP6	12.6293125	6.537324e-17
+EGFR	DUSP5	7.9430394	6.86669e-17
+EGFR	PHLDA1	6.619626	3.4106933e-16
+Estrogen	GREB1	17.240173	0.0
+Estrogen	RET	10.718027	0.0
+Estrogen	TFF1	14.430255	0.0
+Estrogen	HEY2	11.482369	3.1e-44
+Estrogen	RAPGEFL1	10.544896	5.2e-43
+Hypoxia	FAM162A	8.335551	0.0
+Hypoxia	NDRG1	22.08712	0.0
+Hypoxia	ENO2	14.32694	0.0
+Hypoxia	PDK1	13.120449	0.0
+Hypoxia	ANKRD37	8.484976	0.0
+JAK-STAT	OAS1	15.028714	1.058e-41
+JAK-STAT	HERC6	8.769676	1.3450407e-38
+JAK-STAT	OAS3	10.618842	1.2143582e-37
+JAK-STAT	PLSCR1	8.481604	8.955206e-37
+JAK-STAT	DDX60	12.198234	9.150971e-36
+MAPK	DUSP6	16.859016	0.0
+MAPK	SPRED2	3.5018346	0.0
+MAPK	SPRY2	9.481585	9.19e-43
+MAPK	ETV5	5.9887094	6.7425e-41
+MAPK	EPHA2	6.3140125	3.7492e-40
+NFkB	NFKB1	9.513637	0.0
+NFkB	CXCL3	22.946114	0.0
+NFkB	NFKB2	5.5155754	0.0
+NFkB	NFKBIA	11.444533	0.0
+NFkB	BCL2A1	14.416924	0.0
+PI3K	MLANA	-9.985743	1.84e-43
+PI3K	PMEL	-6.5903482	6.8747866e-36
+PI3K	FAXDC2	-12.421274	3.297515e-34
+PI3K	HSD17B8	-8.601571	9.948224e-34
+PI3K	CTSF	-9.172143	1.0235212e-31
+TGFb	LINC00312	4.428987	2.0074443e-17
+TGFb	TSPAN2	5.502326	3.1451768e-16
+TGFb	SMAD7	7.6311436	7.3087106e-16
+TGFb	NOX4	5.913813	3.8292238e-15
+TGFb	COL4A1	6.3374896	9.052501e-15
+TNFa	CSF2	8.35548	0.0
+TNFa	CXCL5	10.0813675	0.0
+TNFa	NFKBIE	10.356205	0.0
+TNFa	TNFAIP3	35.40072	0.0
+TNFa	EFNA1	18.63111	0.0
+Trail	FRMPD1	-2.2346141	9.378505e-07
+Trail	WT1-AS	2.2251053	2.0316747e-06
+Trail	WNT8A	-1.8469616	3.795469e-05
+Trail	GPR18	3.240805	6.1090715e-05
+Trail	TEC	2.0513217	6.32898e-05
+VEGF	CRACD	-4.87119	6.7185365e-25
+VEGF	VWA8	-3.6068044	1.4495265e-18
+VEGF	NLGN1	-5.618075	2.6587072e-18
+VEGF	NRG3	-5.823747	1.0848074e-16
+VEGF	KCNK10	2.8833063	1.8129868e-16
+WNT	BMP4	5.936831	2.511717e-10
+WNT	SIGLEC6	2.0207362	2.347858e-09
+WNT	NPY2R	1.3872339	8.666917e-09
+WNT	CSF3R	1.9323153	3.0219417e-07
+WNT	KRT23	4.1216116	5.463989e-07
+p53	GLS2	6.452465	7.444302e-37
+p53	MDM2	8.193488	2.1194304e-35
+p53	ZNF79	4.020263	4.5987433e-34
+p53	FDXR	11.994496	5.589482e-32
+p53	LCE1B	11.813737	7.8095406e-30