Potential Sciences is developing an artificial intelligence-driven approach to drug discovery that uses physics-based simulations to generate large chemical datasets. The startup hopes its AI models can predict which molecules will interact effectively with disease-related proteins, allowing unsuitable drug candidates to fail earlier and reducing the cost and time associated with laboratory experiments.
Potential Sciences plans to simulate interactions at several levels of complexity, beginning with atoms and progressing to small molecules, amino acids and proteins. It intends to use the resulting data to train AI models and predictive systems capable of identifying highly targeted drugs for specific diseases.
“We want molecules that will never work in the clinic to fail quickly,” Hatem Helal, the company’s founder and CEO, told WIRED. “That means we can more accurately predict how they will behave when they interact with human biology.”
Using AI to pursue tailored treatments
Founded on November 5, the startup said it has secured tens of millions of dollars in seed funding from investors including SovAI, the UK government’s AI venture capital fund, and Twin Path Ventures. The founders declined to disclose the exact amount raised or the company’s valuation.
If the approach works as Potential Sciences hopes, it could accelerate the development of treatments for a wide range of diseases. Helal said that lowering experimental costs could make it economically feasible for drug companies to pursue treatments for rare conditions that have previously gone untreated.
“We want to enable more tailored treatments for diseases, the idea being that medicines can be one-off combinations of molecules tailored to a person’s unique biology,” he said.
Questions about protein engineering
The central challenge is whether Potential Sciences can accurately predict how well its drug candidates will bind to disease-related proteins. Achieving that will require significant progress in protein engineering.
“I’m confident it will be an improvement,” said Peter Wallins, a chemistry professor at Rice University. But, he added, “engineering is at the level of the Romans, not the Renaissance, in terms of how protein engineering is done.”
Industry figures such as Demis Hassabis, who won the Nobel Prize in Chemistry for his work with Google DeepMind, have said for a long time that advances in AI will eventually drive major scientific breakthroughs, just as technology has recently opened new possibilities in mathematics. Startups such as Potential Sciences hope drug discovery will be among the first scientific fields transformed by those advances.
Source: www.wired.com
