MADD: Multi-Agent Drug Discovery Orchestra
This work addresses the problem of limited accessibility to advanced AI tools for wet-lab researchers in drug discovery, representing an incremental improvement by integrating multi-agent systems with existing methods.
The researchers tackled the challenge of making complex AI tools accessible for hit identification in drug discovery by developing MADD, a multi-agent system that builds and executes customized pipelines from natural language queries, demonstrating superior performance over existing LLM-based solutions across seven cases and releasing hit molecules for five targets.
Hit identification is a central challenge in early drug discovery, traditionally requiring substantial experimental resources. Recent advances in artificial intelligence, particularly large language models (LLMs), have enabled virtual screening methods that reduce costs and improve efficiency. However, the growing complexity of these tools has limited their accessibility to wet-lab researchers. Multi-agent systems offer a promising solution by combining the interpretability of LLMs with the precision of specialized models and tools. In this work, we present MADD, a multi-agent system that builds and executes customized hit identification pipelines from natural language queries. MADD employs four coordinated agents to handle key subtasks in de novo compound generation and screening. We evaluate MADD across seven drug discovery cases and demonstrate its superior performance compared to existing LLM-based solutions. Using MADD, we pioneer the application of AI-first drug design to five biological targets and release the identified hit molecules. Finally, we introduce a new benchmark of query-molecule pairs and docking scores for over three million compounds to contribute to the agentic future of drug design.