A Collaborative Framework Integrating Large Language Model and Chemical Fragment Space: Mutual Inspiration for Lead Design

TL;DR

AutoLeadDesign is a novel framework that combines large language models and chemical fragment space to enhance the exploration and design of lead compounds in drug discovery, outperforming baseline methods and demonstrating clinical relevance.

Contribution

The paper introduces AutoLeadDesign, a new AI-driven framework that integrates domain knowledge from language models with chemical fragments for efficient lead compound design.

Findings

AutoLeadDesign outperforms baseline methods in experiments.

Successfully designed lead compounds for PRMT5 and SARS-CoV-2 PLpro.

Generated compounds show mechanism-validated inhibitory patterns.

Abstract

Combinatorial optimization algorithm is essential in computer-aided drug design by progressively exploring chemical space to design lead compounds with high affinity to target protein. However current methods face inherent challenges in integrating domain knowledge, limiting their performance in identifying lead compounds with novel and valid binding mode. Here, we propose AutoLeadDesign, a lead compounds design framework that inspires extensive domain knowledge encoded in large language models with chemical fragments to progressively implement efficient exploration of vast chemical space. The comprehensive experiments indicate that AutoLeadDesign outperforms baseline methods. Significantly, empirical lead design campaigns targeting two clinically relevant targets (PRMT5 and SARS-CoV-2 PLpro) demonstrate AutoLeadDesign's competence in de novo generation of lead compounds achieving expert-competitive design efficacy. Structural analysis further confirms their mechanism-validated inhibitory patterns. By tracing the process of design, we find that AutoLeadDesign shares analogous mechanisms with fragment-based drug design which traditionally rely on the expert decision-making, further revealing why it works. Overall, AutoLeadDesign offers an efficient approach for lead compounds design, suggesting its potential utility in drug design.