Finding New Drugs Is Laborious. This AI Startup Is Skipping The Lab Work
Using physics simulations to generate synthetic data addresses a major bottleneck in AI drug discovery—the scarcity of experimental training data—while highlighting the UK government's direct investment in scientific AI.
Reported by Wired ·
What happened
British startup Potential Sciences has launched with tens of millions of dollars in seed funding from the UK government's SovAI fund and Twin Path Ventures. The company aims to train AI models for drug discovery using large-scale synthetic datasets generated by physics-based molecular simulations, rather than relying solely on existing experimental databases.
Who it’s about
- Potential Sciences
- Hatem Helal
- SovAI
- Twin Path Ventures
Source
More on science
Get a brief picked for you
Sign in to follow topics and companies, save stories and search the archive.
Sign in