fix: remove conformation only, and stick to conformation range

src/deemian/chem/interactions.py

@@ -13,7 +13,7 @@ class InteractionData:
     subject_2_mol: Chem.rdchem.Mol
     subject_1_df: pd.DataFrame
     subject_2_df: pd.DataFrame
-    conformation: list
+    conformation_range: range
     dataframe: pd.DataFrame = field(default_factory=lambda: pd.DataFrame())
 
     def calculate_electrostatic(self, positive: bool, negative: bool):
@@ -33,7 +33,7 @@ def calculate_electrostatic(self, positive: bool, negative: bool):
         cation_2_df = df2[df2.index.isin(cation_2_ids)]
         anion_2_df = df2[df2.index.isin(anion_2_ids) & ~df2["atom_symbol"].isin(exclude_atom)]
 
-        for conf_num in self.conformation:
+        for conf_num in self.conformation_range:
             conformation_column = "conf_" + str(conf_num)
 
             if (not cation_1_df.empty) and (not anion_2_df.empty):

src/deemian/engine/builder.py

@@ -42,13 +42,11 @@ class Measurement:
     interactions: list = field(default_factory=lambda: [])
     ionizable: dict = field(default_factory=lambda: {"positive": False, "negative": False})
     interacting_subjects: dict = field(default_factory=lambda: {})
-    conformation: list = field(default_factory=lambda: [])
-    conformation_range: list = field(default_factory=lambda: [])
+    conformation_range: range = field(default_factory=lambda: range(1, 2))
     calculation_results: dict = field(default_factory=lambda: {})
 
     def set_conformation_range(self, start, end):
-        self.conformation = list(range(int(start), int(end) + 1))
-        self.conformation_range = [start, end]
+        self.conformation_range = range(int(start), int(end) + 1)
 
     def set_ionizable(self, charge: str, boolean: str):
         if boolean == "true":
@@ -106,11 +104,11 @@ def calculate_interactions(self, id):
             subject_2_mol = self.molecule[subject_2.mol_parent].rdkit_mol
             subject_1_df = subject_1.mol_dataframe
             subject_2_df = subject_2.mol_dataframe
-            conformation = measurement.conformation
-            if not any(conformation):
-                conformation = [1]
+            conformation_range = measurement.conformation_range
 
-            interaction_data = InteractionData(subject_1_mol, subject_2_mol, subject_1_df, subject_2_df, conformation)
+            interaction_data = InteractionData(
+                subject_1_mol, subject_2_mol, subject_1_df, subject_2_df, conformation_range
+            )
 
             interaction_type = measurement.interactions
 

src/deemian/engine/director.py

@@ -32,9 +32,6 @@ def director(steps: Tree, data: DeemianData):
                 elif inst.type == "interacting_subject":
                     measurement.interacting_subjects[inst.name] = (inst.subject_1, inst.subject_2)
 
-                elif inst.type == "conformation":
-                    measurement.conformation.extend(inst.number)
-
                 elif inst.type == "conformation_range":
                     measurement.set_conformation_range(inst.start, inst.end)
 

src/deemian/engine/grammar.lark

@@ -13,7 +13,6 @@ measurement_instruction: "interactions" INTERACTION("," INTERACTION)*
                        | "ionizable" CHARGE BOOLEAN                                       -> include_ionizable
                        | PREPOSITION IDENTIFIER (PREPOSITION IDENTIFIER)?                 -> interacting_subject
                        | PREPOSITION IDENTIFIER (PREPOSITION IDENTIFIER)? "as" IDENTIFIER -> interacting_subject_with_alias
-                       | "conformation" INTEGER("," INTEGER)*                             -> conformation
                        | "conformation" INTEGER "to" INTEGER                              -> conformation_range
 
 presentation_instruction: "interactions" INTERACTION_FORMAT? FILE_NAME -> interaction_output

src/deemian/engine/processor.py

@@ -17,7 +17,6 @@ class InstructionTransformer(Transformer):
     DeemianData = namedtuple("DeemianData", "out_file type", defaults=["deemian_data"])
     InteractionList = namedtuple("InteractionList", "interactions type", defaults=["interaction_list"])
     IncludeIonizable = namedtuple("IncludeIonizable", "charge boolean type", defaults=["include_ionizable"])
-    Conformation = namedtuple("Conformation", "number type", defaults=["conformation"])
     ConformationRange = namedtuple("ConformationRange", "start end type", defaults=["conformation_range"])
     InteractingSubject = namedtuple(
         "InteractingSubject", "subject_1 subject_2 name type", defaults=["interacting_subject"]
@@ -79,10 +78,6 @@ def interacting_subject_with_alias(self, args):
 
         return self.InteractingSubject(subject_1, subject_2, name)
 
-    def conformation(self, args):
-        conformation_list = [int(arg.value) for arg in args]
-        return self.Conformation(conformation_list)
-
     def conformation_range(self, args):
         return self.ConformationRange(args[0].value, args[1].value)
 

src/deemian/writer/bundle.py

@@ -21,13 +21,8 @@ def write_metadata(metadata, measurement_data):
         interacting_subject = dict(name=name, subjects=subjects, results=parquet_result)
         metadata_copy.measurement["interacting_subjects"].append(interacting_subject)
 
-    if measurement_data.conformation_range:
-        metadata_copy.measurement["conformation_range"] = measurement_data.conformation_range
-    else:
-        if measurement_data.conformation:
-            metadata_copy.measurement["conformation"] = measurement_data.conformation
-        else:
-            metadata_copy.measurement["conformation"] = [1]
+    conf_range = measurement_data.conformation_range
+    metadata_copy.measurement["conformation_range"] = [conf_range.start, conf_range.stop - 1]
 
     # setup the original metadata, because the running time is used by main script
     metadata.end_time = time.time()

tests/data/n1-oseltamivir-5nzn.txt

@@ -9,7 +9,6 @@ measure protein_ligand [
 	ionizable positive true
 	ionizable negative true
 	between oseltamivir and protein_A
-    conformation 1
 ]
 
 present protein_ligand [

tests/test_chem_interaction.py

@@ -5,7 +5,7 @@
 
 @pytest.fixture
 def interaction_data_n1(oseltamivir_corrected, n1, oseltamivir_corrected_df, n1_protein_A):
-    interaction_data = InteractionData(oseltamivir_corrected, n1, oseltamivir_corrected_df, n1_protein_A, [1])
+    interaction_data = InteractionData(oseltamivir_corrected, n1, oseltamivir_corrected_df, n1_protein_A, range(1, 2))
 
     return interaction_data
 

tests/test_engine_builder.py

@@ -54,8 +54,7 @@ def test_deemian_data_measurement():
     measurement.set_ionizable("positive", "true")
     measurement.set_ionizable("negative", "false")
     measurement.interacting_subjects["oseltamivir:protein_A"] = ("oseltamivir", "protein_A")
-    measurement.set_conformation_range("1", "4")
-    measurement.conformation.extend([5])
+    measurement.set_conformation_range("1", "5")
 
     with patch.object(data, "calculate_interactions", return_value=1):
         result = data.calculate_interactions("protein_ligand")
@@ -65,7 +64,7 @@ def test_deemian_data_measurement():
         == """Measurement(interactions=['all'], \
 ionizable={'positive': True, 'negative': False}, \
 interacting_subjects={'oseltamivir:protein_A': ('oseltamivir', 'protein_A')}, \
-conformation=[1, 2, 3, 4, 5], conformation_range=['1', '4'], \
+conformation_range=range(1, 6), \
 calculation_results={})"""
     )
     assert result == 1
@@ -94,7 +93,6 @@ def test_deemian_data_calculate_interactions():
     measurement.set_ionizable("positive", "true")
     measurement.set_ionizable("negative", "true")
     measurement.interacting_subjects["oseltamivir:protein_A"] = ("oseltamivir", "protein_A")
-    measurement.conformation.extend([1])
 
     with patch("deemian.engine.builder.InteractionData") as int_data:
         data.calculate_interactions("protein_ligand")
@@ -105,7 +103,7 @@ def test_deemian_data_calculate_interactions():
                     "neuraminidase:rdkitmol",
                     "oseltamivir:pd.DataFrame",
                     "protein_A:pd.DataFrame",
-                    [1],
+                    range(1, 2),
                 ),
                 call().calculate_electrostatic(positive=True, negative=True),
             ]

tests/test_engine_director.py

@@ -13,7 +13,6 @@
 DeemianData = namedtuple("DeemianData", "out_file type", defaults=["deemian_data"])
 InteractionList = namedtuple("InteractionList", "interactions type", defaults=["interaction_list"])
 IncludeIonizable = namedtuple("IncludeIonizable", "charge boolean type", defaults=["include_ionizable"])
-Conformation = namedtuple("Conformation", "number type", defaults=["conformation"])
 ConformationRange = namedtuple("ConformationRange", "start end type", defaults=["conformation_range"])
 InteractingSubject = namedtuple(
     "InteractingSubject", "subject_1 subject_2 name type", defaults=["interacting_subject"]
@@ -53,7 +52,6 @@ def steps_simple() -> Tree:
                         name="oseltamivir:protein_A",
                         type="interacting_subject",
                     ),
-                    Conformation(number=[1], type="conformation"),
                 ],
             ),
             Tree(
@@ -197,7 +195,6 @@ def test_engine_director_simple(steps_simple):
             call.add_measurement().interacting_subjects.__setitem__(
                 "oseltamivir:protein_A", ("oseltamivir", "protein_A")
             ),
-            call.add_measurement().conformation.extend([1]),
             call.calculate_interactions("protein_ligand"),
             call.write_readable_output("protein_ligand", "protein_ligand.txt", "detailed_conf_first"),
             call.write_deemian_data("protein_ligand", "protein_ligand.dd"),

tests/test_engine_processor.py

@@ -136,7 +136,6 @@ def test_measure_transform(n1_transformed, spike_transformed, vps_transformed):
     n1_ionizable1 = n1_measure.children[2]
     n1_ionizable2 = n1_measure.children[3]
     n1_interacting_subject = n1_measure.children[4]
-    n1_conformation = n1_measure.children[5]
 
     spike_measure = spike_transformed.children[1]
     spike_interacting_subject_as = spike_measure.children[4]
@@ -156,8 +155,6 @@ def test_measure_transform(n1_transformed, spike_transformed, vps_transformed):
     assert n1_interacting_subject.subject_2 == "protein_A"
     assert n1_interacting_subject.name == "oseltamivir:protein_A"
     assert n1_interacting_subject.type == "interacting_subject"
-    assert n1_conformation.number == [1]
-    assert n1_conformation.type == "conformation"
 
     assert spike_interacting_subject_as.subject_1 == "spike_rbm"
     assert spike_interacting_subject_as.subject_2 == "ace2_hotspot31"

tests/test_writer_bundle.py

@@ -43,31 +43,18 @@ def test_writer_bundle_dict_factory(metadata_obj):
     assert metadata_keys == expected_keys
 
 
-def test_writer_bundle_write_metadata(metadata_obj, measurement_data):
-    measurement_data.conformation = [1]
-
-    metadata_file = write_metadata(metadata_obj, measurement_data)
-    metadata_file_name = metadata_file[0]
-    metadata_io = metadata_file[1]
-    metadata_json = json.loads(metadata_io.read())
-
-    assert metadata_file_name == "deemian.json"
-    assert metadata_json["measurement"]["interacting_subjects"][0]["results"] == "oseltamivir_protein_A.parquet"
-    assert metadata_json["measurement"]["conformation"] == [1]
-
-
 def test_writer_bundle_write_metadata_no_conformation(metadata_obj, measurement_data):
     metadata_file = write_metadata(metadata_obj, measurement_data)
     metadata_file_name = metadata_file[0]
     metadata_io = metadata_file[1]
     metadata_json = json.loads(metadata_io.read())
 
     assert metadata_file_name == "deemian.json"
-    assert metadata_json["measurement"]["conformation"] == [1]
+    assert metadata_json["measurement"]["conformation_range"] == [1, 1]
 
 
 def test_writer_bundle_write_metadata_conformation_range(metadata_obj, measurement_data):
-    measurement_data.conformation_range = [1, 20]
+    measurement_data.conformation_range = range(1, 21)
 
     metadata_file = write_metadata(metadata_obj, measurement_data)
     metadata_file_name = metadata_file[0]