Researchers have developed MEVO, a novel generative molecular evolutionary framework designed to enhance Structure-Based Drug Design (SBDD). MEVO addresses key challenges in SBDD, including the limited availability of protein-ligand complex data and the difficulty in synthesizing generated molecules. The framework utilizes a reaction-aware generative model trained on reaction routes derived from Enamine Building Blocks, enabling it to produce molecules with corresponding synthesis sketches. By integrating this into an evolutionary strategy, MEVO iteratively refines molecular structures within a synthesizable chemical space, guided by a scoring function that combines approximation with Absolute Binding Free Energy Perturbation (ABFEP) calculations. This approach has demonstrated success in designing potent inhibitors for challenging targets like KRAS$^{ extrm{G12D}}$, achieving affinities comparable to existing active inhibitors. AI
IMPACT Accelerates the discovery of new drugs by improving the efficiency and feasibility of molecular design.
RANK_REASON The cluster contains a research paper detailing a new AI framework for drug design. [lever_c_demoted from research: ic=1 ai=1.0]
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
