DrugCoding automates complex drug discovery tasks with programming agents
DrugCoding: A Scientific Programming Agent for Drug Discovery
Artificial IntelligenceMultiagent Systems
Summary
Drug discovery involves many steps and tools that can be hard to manage together. The authors created DrugCoding, a system that helps plan and handle these complex steps by writing and running code automatically. It also chooses the best specialized models for each task and uses teamwork between agents to get better results. Their tests show DrugCoding is very effective at handling multi-step drug discovery jobs, doing better than other top tools.
What this means in practice
- •For pharmaceutical research teams: Automate and coordinate complex drug discovery workflows by generating and running code that selects and applies specialized models effectively.
- •For biotech software developers: Build integrated drug research platforms that can autonomously plan multi-stage tasks and manage diverse scientific tools through programmable agents.
Authors
Junwei Hu, Zhuohao Lin, Kun Li, Hengnan Zhang
Abstract
Drug discovery involves multiple interconnected research stages, including molecular design, property prediction, and virtual screening. These processes are characterized by complex workflows, interdependent computational tasks, and diverse specialized tools, placing substantial demands on the coordination of scientific models and computational resources. However, existing large language model (LLM)-based scientific agents still face challenges in autonomous planning of complex tasks, adaptive selection of specialized models, and reliable execution of multi-stage scientific computations, limiting their effectiveness in automating complex drug discovery workflows. To address these challenges, we propose DrugCoding, a scientific programming agent system that integrates scientific task planning, adaptive model routing, multi-agent collaboration, and programmatic tool execution. DrugCoding enables autonomous task planning and dynamic model adaptation for complex research objectives. It can flexibly invoke specialized scientific models, autonomously generate and execute code according to task requirements, and leverage multi-agent collaboration to support efficient execution and reliable validation of complex scientific tasks. To evaluate DrugCoding's performance in scientific tool invocation and multi-stage task execution, we conduct multi-turn tool-calling experiments across diverse language models and scientific tool interfaces. Experimental results demonstrate that DrugCoding achieves an average session-level Pass@1 of 97.35% on the full benchmark, outperforming the strongest baseline, Codex, by 9.24%. On the challenging subset, DrugCoding achieves 97.92%, exceeding the strongest baseline.