Research
At onepot, we focus on the intersection of artificial intelligence and automated chemical synthesis. We develop computational methods and robotic systems that enable high-throughput experimentation at unprecedented scale, with applications in drug discovery and materials science.
Current research areas include reaction prediction using graph neural networks, closed-loop optimization for synthesis planning, and the development of foundation models trained on large-scale experimental data. Our work aims to accelerate the discovery and production of novel molecules while reducing the time and cost associated with traditional synthesis methods.
Publications
AI Agents in Drug Discovery
Srijit Seal, Dinh Long Huynh, Moudather Chelbi, Sara Khosravi, Ankur Kumar, Mattson Thieme, Isaac Wilks, Mark Davies, Jessica Mustali, Yannick Sun, Nick Edwards, Daniil Boiko, Andrei Tyrin, Douglas W. Selinger, Ayaan Parikh, Rahul Vijayan, Shoman Kasbekar, Dylan Reid, Andreas Bender, Ola Spjuth
Artificial intelligence (AI) agents are emerging as transformative tools in drug discovery, with the ability to autonomously reason, act, and learn through complicated research workflows. Building on large language models (LLMs) coupled with perception, computation, action, and memory tools, these agentic AI systems could integrate diverse biomedical data, execute tasks, carry out experiments via robotic platforms, and iteratively refine hypotheses in closed loops. This work provides a conceptual and technical overview of agentic AI architectures, ranging from ReAct and Reflection to Supervisor and Swarm systems, and illustrates their applications across key stages of drug discovery, including literature synthesis, toxicity prediction, automated protocol generation, small-molecule synthesis, drug repurposing, and end-to-end decision-making.
Are we close to the AI revolution in small molecule synthesis? Enabling autonomous synthesis with AI agents and automation
onepot team, Onepot AI, Inc., South San Francisco, CA
We present an AI-enabled platform for multi-step autonomous synthesis of small molecules, combining automated hardware with AI agents that employ large language models for literature review, reaction planning, and experimental analysis. Case studies demonstrate ultrafast synthesis from a 2.7B chemical space and accelerated two-step synthesis of custom libraries.
Interested in pushing the boundaries of AI-driven synthesis?Join our research team