Add known fusions file input option

docs/CHANGELOG.rst

@@ -16,6 +16,8 @@ Added
 - Allow filtering ``Sample`` by ``Variant``
 - Allow filtering variant annotations by variant id
 - Add filters to ``Variant`` and ``VariantCall`` objects
+- Add ``known_fusions`` file input to ``arriba`` process and 
+  ``gene-fusion-calling-arriba`` workflow
 
 Changed
 -------

resolwe_bio/processes/fusion_calling/arriba.py

@@ -40,7 +40,7 @@ class Arriba(Process):
     slug = "arriba"
     name = "Arriba"
     process_type = "data:genefusions:arriba"
-    version = "1.0.2"
+    version = "1.1.0"
     category = "Gene fusions"
     scheduling_class = SchedulingClass.BATCH
     entity = {"type": "sample"}
@@ -83,6 +83,13 @@ class Input:
             required=False,
         )
 
+        known_fusions_file = DataField(
+            data_type="file",
+            label="Known fusions file",
+            description="Arriba known fusions file.",
+            required=False,
+        )
+
     class Output:
         """Output fields for Arriba process."""
 
@@ -148,6 +155,9 @@ def run(self, inputs, outputs):
         else:
             args.extend(["-f", "blacklist"])
 
+        if inputs.known_fusions_file:
+            args.extend(["-k", inputs.known_fusions_file.output.file.path])
+
         return_code, stdout, stderr = Cmd["arriba"][args] & TEE(retcode=None)
 
         if return_code:

resolwe_bio/processes/workflows/gene-fusion-calling-arriba.py

@@ -34,7 +34,7 @@ class WorkflowGeneFusionCallingArriba(Process):
 
     slug = "gene-fusion-calling-arriba"
     name = "Gene Fusion Calling with Arriba"
-    version = "1.0.0"
+    version = "1.1.0"
     process_type = "data:workflow:genefusions:arriba"
     category = "Pipeline"
     entity = {"type": "sample"}
@@ -89,6 +89,13 @@ class Input:
             required=False,
         )
 
+        known_fusions_file = DataField(
+            data_type="file",
+            label="Known fusions file",
+            description="Arriba known fusions file.",
+            required=False,
+        )
+
         class ChimericReadsOptions:
             """Chimeric reads options."""
 
@@ -246,6 +253,9 @@ def run(self, inputs, outputs):
         if inputs.blacklist_file:
             arriba_input["blacklist_file"] = inputs.blacklist_file.id
 
+        if inputs.known_fusions_file:
+            arriba_input["known_fusions_file"] = inputs.known_fusions_file.id
+
         fusion_name = (
             f"Fusions ({inputs.bam.name})"
             if inputs.bam

resolwe_bio/tests/processes/test_arriba.py

@@ -51,10 +51,18 @@ def test_arriba_fusion_detection(self):
                 },
             )
 
+            known_fusions_file = self.run_process(
+                process_slug="upload-file",
+                input_={
+                    "src": input_folder / "known_fusions.tsv.gz",
+                },
+            )
+
         arriba_inputs = {
             "bam": bam.id,
             "gtf": gtf_file.id,
             "genome": genome_file.id,
+            "known_fusions_file": known_fusions_file.id,
         }
 
         arriba = self.run_process("arriba", arriba_inputs)

resolwe_bio/tests/workflows/test_fusion_calling_arriba.py

@@ -42,10 +42,18 @@ def test_gene_fusion_workflow_with_bam(self):
                 },
             )
 
+            known_fusions_file = self.run_process(
+                process_slug="upload-file",
+                input_={
+                    "src": input_folder / "known_fusions.tsv.gz",
+                },
+            )
+
         workflow_inputs = {
             "bam": bam.id,
             "gtf": gtf_file.id,
             "genome": genome_file.id,
+            "known_fusions_file": known_fusions_file.id,
         }
 
         self.run_process("gene-fusion-calling-arriba", workflow_inputs)
@@ -101,11 +109,19 @@ def test_gene_fusion_workflow_with_fastq(self):
                 input_={"ref_seq": genome_file.id, "annotation": gtf_file.id},
             )
 
+            known_fusions_file = self.run_process(
+                process_slug="upload-file",
+                input_={
+                    "src": input_folder / "known_fusions.tsv.gz",
+                },
+            )
+
         workflow_inputs = {
             "reads": reads.id,
             "gtf": gtf_file.id,
             "genome": genome_file.id,
             "star_index": star_index.id,
+            "known_fusions_file": known_fusions_file.id,
         }
 
         self.run_process("gene-fusion-calling-arriba", workflow_inputs)