Finding New Drugs Is Laborious. This AI Startup Is Skipping The Lab Work
Potential Sciences, a startup backed by the UK government, is betting that training AI models on computer-generated biochemical data can speed up the plodding process of developing new drugs.
Potential Sciences, a new AI startup, aims to streamline drug discovery by bypassing traditional lab experimentation. The company plans to create extensive chemical datasets using principles of physics to simulate interactions between atoms, molecules, and complex proteins. By training AI models on this data, Potential Sciences hopes to identify highly targeted drugs for specific diseases, avoiding costly and time-consuming lab tests.
The startup's founder, Hatem Helal, believes this approach will enable the development of more bespoke treatments tailored to individual human biology. Potential Sciences has secured tens of millions in seed funding from the UK government's AI venture capital fund, SovAI, and other investors. If successful, this strategy could accelerate the development of treatments for various diseases, including rare conditions.
However, the accuracy of AI predictions in drug discovery remains uncertain, requiring significant advancements. Industry experts acknowledge the potential of AI in revolutionizing scientific breakthroughs, but emphasize that the challenge lies in predicting drug binding with high precision. Despite the potential benefits, AI drug discovery faces intense competition and the ongoing challenge of testing drug safety and efficacy before reaching the market.
Written by urgent.news from Wired's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
