MADD: Multi-Agent Drug Discovery Orchestra

TL;DR

MADD is a multi-agent AI system that streamlines drug hit identification from natural language queries, demonstrating superior performance and pioneering AI-driven drug design for multiple targets.

Contribution

The paper introduces MADD, a novel multi-agent framework that automates and enhances drug discovery pipelines from natural language inputs, improving accessibility and efficiency.

Findings

MADD outperforms existing LLM-based methods in seven drug discovery cases.

Successfully applied AI-driven design to five biological targets.

Released a large benchmark dataset of over three million compounds.

Abstract

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.