Revert return type to List for ProteinGroups.get_protein_groups

Author: MatthewThe

Makefile

@@ -20,6 +20,12 @@ test:
 integration_test:
 	python3 -um picked_group_fdr --mq_evidence $(DATA)/evidence.txt --fasta $(DATA)/db.fasta --enzyme trypsinp --min-length 6 --protein_groups_out ${DATA}/proteinGroups.txt --method picked_protein_group_mq_input --do_quant
 
+fragpipe_test:
+	cd data/fragpipe_example && ./run_picked_group_fdr.sh
+
+sage_test:
+	cd data/sage_example && ./run_picked_group_fdr.sh
+
 pipeline_test: DOCKER_CMD=
 pipeline_test: IMAGE=
 pipeline_test: LOCAL_DIR=$(DATA)

docs/release_checklist.md

@@ -1,4 +1,5 @@
 1. test if unit and system tests pass: `make test; make integration_test; make pipeline_test`
+   test if fragpipe and sage system tests pass: `make fragpipe_test; make sage_test`
 2. check if docker image works: `make build; make all`
 3. update version number: `poetry version <major/minor/patch>`
 4. add information to changelog on master `git log --pretty="%s"`

picked_group_fdr/protein_groups.py

@@ -125,9 +125,9 @@ def get_protein_group_idxs(
 
     def get_protein_groups(
         self, proteins: List[str], check_idx_valid: bool = True
-    ) -> Set[int]:
+    ) -> List[List[str]]:
         protein_group_idxs = self.get_protein_group_idxs(proteins, check_idx_valid)
-        return {self.protein_groups[idx] for idx in protein_group_idxs}
+        return [self.protein_groups[idx] for idx in protein_group_idxs]
 
     def merge_groups(self, superset_protein: str, protein: str):
         """Merge two protein groups"""

tests/unit_tests/test_helpers.py

@@ -24,23 +24,42 @@ def test_is_shared_peptide_true():
     assert helpers.is_shared_peptide({1, 2, 3}) == True
 
 
-def test_is_shared_peptide_true():
+def test_is_shared_peptide_true_strings():
+    assert helpers.is_shared_peptide([["proteinA"], ["proteinB", "proteinC"]]) == True
+
+
+def test_is_shared_peptide_true_with_missing():
     assert helpers.is_shared_peptide({1, 2, 3, -1}) == True
 
 
 def test_is_shared_peptide_false():
     assert helpers.is_shared_peptide({3}) == False
 
 
+def test_is_shared_peptide_false_strings():
+    assert helpers.is_shared_peptide([["proteinB", "proteinC"]]) == False
+
+
 def test_is_missing_in_protein_groups_true():
     assert helpers.is_missing_in_protein_groups({-1}) == True
 
 
+def test_is_missing_in_protein_groups_true_strings():
+    assert helpers.is_missing_in_protein_groups([]) == True
+
+
 def test_is_missing_in_protein_groups_false():
     assert helpers.is_missing_in_protein_groups({1}) == False
 
 
-def test_is_missing_in_protein_groups_false():
+def test_is_missing_in_protein_groups_false_strings():
+    assert (
+        helpers.is_missing_in_protein_groups([["proteinA"], ["proteinB", "proteinC"]])
+        == False
+    )
+
+
+def test_is_missing_in_protein_groups_false_with_missing():
     assert helpers.is_missing_in_protein_groups({1, -1}) == False