[Feature] Management Command to Compute and Store Reaction <-> Rule Associations (#453)

Co-authored-by: Tim Lorsbach <tim@lorsba.ch> Reviewed-on: enviPath/enviPy#453
2026-08-14 20:45:12 +12:00
parent 2d3dca6a75
commit fedd1b5280
6 changed files with 235 additions and 15 deletions
--- a/epdb/management/commands/reaction_rule_mapping.py
+++ b/epdb/management/commands/reaction_rule_mapping.py
@ -0,0 +1,97 @@
+import logging
+
+from django.core.management.base import BaseCommand
+from django.db import transaction
+from uuid import uuid4
+from epdb.models import Package, ReactionExplanation
+from utilities.chem import FormatConverter
+from django.utils import timezone
+
+
+logger = logging.getLogger(__name__)
+
+
+class Command(BaseCommand):
+    def add_arguments(self, parser):
+        parser.add_argument(
+            "--rule-package",
+            action="append",
+            default=["32de3cf4-e3e6-4168-956e-32fa5ddb0ce1"],
+            type=str,
+            help="UUID to process. Can be specified multiple times.",
+        )
+
+        parser.add_argument(
+            "--reaction-package",
+            action="append",
+            default=[
+                "32de3cf4-e3e6-4168-956e-32fa5ddb0ce1",  # BBD
+                "f05e38d8-e9b4-4c3e-b0d8-9ab29966eccf",  # Sediment
+                "521c547a-fd2a-491c-ad5b-7eaa1577fb65",  # Sludge
+                "5882df9c-dae1-4d80-a40e-db4724271456",  # Soil
+                "87a49584-d937-482c-9c33-25928dcb02a8",  # PFAS
+            ],
+            type=str,
+            help="UUID to process. Can be specified multiple times.",
+        )
+
+        parser.add_argument(
+            "--dry-run",
+            default=False,
+            action="store_true",
+            help="Perform dry run",
+        )
+
+    @transaction.atomic
+    def handle(self, *args, **options):
+        RUN_UUID = uuid4()
+        RUN_START = timezone.now()
+
+        rule_packages = Package.objects.filter(uuid__in=options["rule_package"])
+        reaction_packages = Package.objects.filter(uuid__in=options["reaction_package"])
+
+        rules = []
+        for rule_package in rule_packages:
+            rules.extend(rule_package.get_applicable_rules())
+
+        reactions = []
+        for reaction_package in reaction_packages:
+            reactions.extend(reaction_package.reactions)
+
+        logger.debug(f"Collected {len(rules)} rules and {len(reactions)} reactions.")
+
+        for i, reaction in enumerate(reactions):
+            logger.debug(f"Reaction {i} / {len(reactions)}")
+            for j, rule in enumerate(rules):
+                reactants, products = reaction.smirks().split(">>")
+
+                if len(reactants.split(".")) > 1:
+                    logger.debug(f"Skipping reaction {reaction.uuid} as it has multiple reactants.")
+                    break
+
+                products = products.split(".")
+
+                # Run reaction with rule
+                rule_products = rule.apply(reactants)
+
+                # Check if products match (in both directions if extras are not allowed)
+                for product_set in rule_products:
+                    covered, exact = FormatConverter.smiles_covered_by(
+                        products,
+                        product_set.product_set,
+                        standardize=True,
+                        canonicalize_tautomers=True,
+                        return_exact_match=True,
+                    )
+
+                    if covered and not options["dry-run"]:
+                        logger.debug(f"Reaction {reaction.uuid} explained by rule {rule.uuid}")
+                        re = ReactionExplanation()
+                        re.run_uuid = RUN_UUID
+                        re.run_start = RUN_START
+                        re.reaction = reaction
+                        re.rule = rule
+                        re.exact = exact
+                        re.save()
+                        # Its explained, if there are more sets skip them
+                        break