LLMs can discover useful features from molecular data better than direct reasoning, and this feature-discovery approach beats expert chemists at ranking binding poses—a critical step in drug design.
Pyrite is a benchmark for ranking protein-ligand binding poses in drug discovery, where LLM-based agents outperform human experts. The paper introduces two AI approaches: one that reasons about poses directly, and another that generates code to discover predictive features, achieving up to 74% accuracy on 1,500 pose pairs.