# Finding New Drugs Is Laborious. This AI Startup Is Skipping The Lab Work

- URL: https://talkfuse.com/story/finding-new-drugs-is-laborious-this-ai-startup-is-skipping-the-lab-work/
- Published: 2026-11-05T13:00:00+00:00
- Updated: 2026-11-05T13:36:39+00:00
- Original publisher: Wired
- Original article: https://www.wired.com/story/finding-new-drugs-is-laborious-this-ai-startup-is-skipping-the-lab-work/
- Topics: AI, Business, Companies, Government, Health, Medicine, Politics, Technology, UK, World

## Key points

- Potential Sciences is using simulated data to train drug discovery AI.
- The startup has raised seed funding in the tens of millions of dollars.
- Researchers say accurate predictions remain a significant hurdle.

## Summary

Potential Sciences is building AI models for drug discovery using large synthetic datasets generated through physics based simulations. By predicting which molecules are likely to interact with disease related proteins, the startup hopes to reduce reliance on costly, slow laboratory experiments and make it viable to develop treatments for rare conditions and individual patients.

Launched on 5 November, the company has received seed funding worth tens of millions of dollars from SovAI, the UK government’s AI venture capital fund, Twin Path Ventures and others; it has not disclosed the exact amount or its valuation. Its approach aims to overcome the limited size of the Protein Data Bank, a public collection of experimentally determined protein structures used by many researchers. Scientists see promise in simulation, but say accurately predicting molecular interactions remains a major challenge.

---
Summarised by TalkFuse (https://talkfuse.com/). Quote the original publisher for the reporting and link this page for the summary and discussion.