For Daniil Boiko and Andrei Tyrin, the idea for Onepot AI came from a shared frustration. They observed that the best ideas in drug discovery were often blocked not by biology, but by synthesis. Synthesis is the process of creating new molecules using chemical reactions. It is like a recipe where small pieces and ingredients come together to form a larger molecule. As one might expect, it is quite difficult to create the small molecules that build bigger ones.
Boiko, a Ph.D. candidate studying machine learning in chemistry at Carnegie Mellon, realized that drug hunters were skipping promising ideas simply because the chemical molecules needed to create the drugs seemed too hard to make. He noted that these compounds never even got a chance to be tested.
For Tyrin, his time working on computational pipelines for drug discovery made him realize how far behind the field was. He saw that models could generate ideas in hours, but it could take months for the lab to catch up. Boiko stated that the world was throwing money into molecular design while almost ignoring the harder problem of actually making the molecules.
There was also a geopolitical angle. Boiko explained that global supply chains are becoming vulnerable, and the United States is entering a trade war and innovative competition with China. He felt it was clear that small molecule synthesis needed to be rebuilt from the ground up in the United States.
Boiko and Tyrin came together to create Onepot, a company that is home to the small-molecule synthesis lab POT-1. They also built Phil, an AI organic chemist, to help run experimental analysis and speed up the process of compound synthesis for their early commercial partners. These partners are biotech and pharma companies currently trying out their technology.
The company recently came out of stealth with thirteen million dollars in funding, including pre-seed money and a seed round led by Fifty Years. Tyrin explained that currently, pharma and biotech companies either build entire teams of chemists in-house or work with contract research organizations overseas. Human chemists can spend months of research to create a single compound at a cost of thousands of dollars. This process involves significant trial and error, studying various compounds, and collecting data on biological activity. The main limiting factor is not testing these compounds, but making them in the first place. Their goal is to compress this down to days.
Tyrin described the product as straightforward. Onepot has a catalogue of molecules it can make. Clients choose which compounds they want, and then Onepot’s technology synthesizes the molecules and ships them to the customer for use in their own experiments. The physical products are shipped as dry compounds or solutions in plates or vials.
The backend of the product is where Boiko and Tyrin focus on dissecting the problems of chemical synthesis to find which combinations of molecules work together. They built a lab where they let LLM agents access molecule recipes for training so the agents can also learn what works in compound building. When executing experiments in the lab, they capture every single detail of the process, including temperature and ingredients. This ensures experiences are reproducible even if someone runs them ten years from now. This also means their agents generate hypotheses from real-world experiments rather than literature data mined from the internet.
Boiko described the fundraising process as hectic. They met their lead investor through an introduction, and a meeting that was supposed to be short turned into a multi-hour whiteboard session about industrializing synthesis. Other participants in the funding round include Khosla Ventures, Speedinvest, OpenAI co-founder Wojciech Zaremba, and Google’s Chief Scientist Jeff Dean.
The new capital will be used to build a second lab in San Francisco so the team can take on more customers. It will also expand the team and its compound discovery engine. On the service side, Boiko and Tyrin view WuXi AppTec and Enamine as competitors.
Overall, Boiko and Tyrin hope to make drug discovery at least two times faster and change the perception of what is possible by tapping into chemistry that scientists once thought was off limits. Boiko concluded that you are not just speeding up drug discovery, but expanding the design space for what drugs and materials can be. The drug that we have not discovered yet might be out there, waiting for us to find it.