MoAgent: A Hypothesis-Driven Multi-Agent Framework for Drug Mechanism of Action Discovery

Determining the mechanism of action (MoA) of novel chemical compounds is a critical yet challenging task in drug discovery. We introduce MoAgent, a multi-agent framework that reframes MoA inference as a hypothesis-driven scientific discovery process. MoAgent integrates multi-modal data from chemical structure, gene expression, and biological pathways, deploying a committee of specialized agents to collaboratively generate and validate mechanistic hypotheses. The framework operates through an iterative cycle of evidence triangulation and hypothesis validation, where a bioinformatician agent assesses causal plausibility using a knowledge graph and a medicinal chemist agent verifies direct target engagement. This synergistic approach moves beyond the limitations of single-modality analysis. Our experiments demonstrate that this integrated, hypothesis-driven strategy significantly enhances the accuracy and reliability of MoA inference, and maintains robust performance even in zero-shot scenarios, while conventional methods fail completely in the absence of prior drug-target information. By emulating scientific reasoning, MoAgent offers a more effective paradigm for accelerating drug discovery.