AIBullisharXiv – CS AI · 7h ago7/10
🧠
Symbolic Neural Generation with Applications to Lead Discovery in Drug Design
Researchers introduce Symbolic Neural Generators (SNGs), a hybrid neurosymbolic model combining inductive logic programming with large language models to generate molecules meeting formal correctness criteria. The system demonstrates performance comparable to state-of-the-art drug discovery methods on benchmark problems and generates promising inhibitor candidates for poorly understood drug targets.