DrugAgent: Automating AI-aided Drug Discovery Programming through LLM Multi-Agent Collaboration
This addresses a bottleneck for practitioners in pharmaceutical research by automating specialized programming, though it is an incremental improvement over existing multi-agent methods applied to a new domain.
The paper tackles the problem of translating theoretical AI ideas into robust implementations for drug discovery by introducing DrugAgent, a multi-agent framework that automates ML programming, achieving a 4.92% relative improvement in ROC-AUC over baselines in drug-target interaction tasks.
Recent progress in Large Language Models (LLMs) has drawn attention to their potential for accelerating drug discovery. However, a central problem remains: translating theoretical ideas into robust implementations in the highly specialized context of pharmaceutical research. This limitation prevents practitioners from making full use of the latest AI developments in drug discovery. To address this challenge, we introduce DrugAgent, a multi-agent framework that automates machine learning (ML) programming for drug discovery tasks. DrugAgent employs an LLM Planner that formulates high-level ideas and an LLM Instructor that identifies and integrates domain knowledge when implementing those ideas. We present case studies on three representative drug discovery tasks. Our results show that DrugAgent consistently outperforms leading baselines, including a relative improvement of 4.92% in ROC-AUC compared to ReAct for drug-target interaction (DTI). DrugAgent is publicly available at https://anonymous.4open.science/r/drugagent-5C42/.