add c3p integration

Author: sfluegel05

chebifier/model_registry.py

@@ -9,6 +9,7 @@
     ResGatedPredictor,
     ChEBILookupPredictor
 )
+from chebifier.prediction_models.c3p_predictor import C3PPredictor
 from chebifier.prediction_models.chemlog_predictor import ChemlogXMolecularEntityPredictor, ChemlogOrganoXCompoundPredictor
 
 ENSEMBLES = {
@@ -25,6 +26,7 @@
     "chebi_lookup": ChEBILookupPredictor,
     "chemlog_element": ChemlogXMolecularEntityPredictor,
     "chemlog_organox": ChemlogOrganoXCompoundPredictor,
+    "c3p": C3PPredictor
 }
 
 

chebifier/prediction_models/c3p_predictor.py

@@ -0,0 +1,27 @@
+from typing import Optional, List
+from pathlib import Path
+
+from c3p import classifier as c3p_classifier
+
+from chebifier.prediction_models import BasePredictor
+
+
+class C3PPredictor(BasePredictor):
+    """
+    Wrapper for C3P (url).
+    """
+
+    def __init__(self, model_name: str, program_directory: Optional[Path]=None, chemical_classes: Optional[List[str]]=None, **kwargs):
+        super().__init__(model_name, **kwargs)
+        self.program_directory = program_directory
+        self.chemical_classes = chemical_classes
+
+    def predict_smiles_list(self, smiles_list: list[str]) -> list:
+        result_list = c3p_classifier.classify(smiles_list, self.program_directory, self.chemical_classes, strict=False)
+        result_reformatted = [dict() for _ in range(len(smiles_list))]
+        for result in result_list:
+            result_reformatted[smiles_list.index(result.input_smiles)][result.class_id.split(":")[1]] = result.is_match
+        print(f"C3P predictions for {len(smiles_list)} SMILES strings:")
+        for i, smiles in enumerate(smiles_list):
+            print(f"{smiles}: {result_reformatted[i]}")
+        return result_reformatted