refactor(validation): use ml_id as primary ID, add chembl_id field

2026-03-19 11:44:56 +08:00
parent 360cbc487e
commit bb42044faf
7 changed files with 1234 additions and 13 deletions
--- a/validation_output/summary_statistics.json
+++ b/validation_output/summary_statistics.json
@@ -0,0 +1,24 @@
+{
+  "total_molecules": 1097,
+  "by_classification": {
+    "non_standard_macrocycle": 617,
+    "standard_macrolactone": 459,
+    "not_macrolactone": 21
+  },
+  "by_ring_size": {
+    "14.0": 301,
+    "16.0": 187,
+    "15.0": 161,
+    "12.0": 141,
+    "19.0": 85,
+    "18.0": 80,
+    "13.0": 67,
+    "20.0": 24,
+    "17.0": 19
+  },
+  "by_status": {
+    "skipped": 638,
+    "success": 367,
+    "failed": 92
+  }
+}