Advertisement

If you have an ACS member number, please enter it here so we can link this account to your membership. (optional)

ACS values your privacy. By submitting your information, you are gaining access to C&EN and subscribing to our weekly newsletter. We use the information you provide to make your reading experience better, and we will never sell your data to third party members.

ENJOY UNLIMITED ACCES TO C&EN

Start-ups

Computational chemistry start-up bags $2.1 million in preseed funding

Two brothers and a friend founded the company to provide quantum mechanics–based services for novel drug discovery

by Aayushi Pratap
December 5, 2024

 

Two people sit with laptops in front of them and the US flag behind them.
Credit: Rowan Scientific
Two of Rowan Scientific's cofounders, Ari Wagen (left) and Corin Wagen

The Boston-based computational chemistry start-up Rowan Scientific has secured $2.1 million in preseed funding from investors including Pillar VC and AI Grant. The firm was formed last year by siblings Corin and Ari Wagen and their friend Eli Mann.

The new venture aims to compete with well-established players in the space, notably Schrödinger. Both firms deploy physics-based computational services that help chemists understand interactions between compounds and protein drug targets. But Corin Wagen, the new firm’s CEO, says Rowan’s tools are built using machine learning (ML) in addition to physics-based methods, enabling users to get the best of both worlds.

“Our method of using ML on quantum mechanics data can predict molecular interactions with high accuracy with relatively low costs,” says Corin, who graduated last year with a PhD in chemistry from Harvard University, where he completed doctoral work in Eric Jacobsen’s laboratory.

Corin says that most computational chemistry competitors use ML sparsely, and predictions made by their ML tools on how compounds and protein drug targets interact aren’t always accurate. Moreover, he says, the accurate ones tend to be time consuming. For instance, predicting the pK a value of a compound, a parameter helpful in understanding how it might interact with a protein, can take over a month of computing time with state-of-the-art quantum mechanics, he says. “Our platform can speed up these predictions using ML, giving accurate data fairly fast.”

Rowan’s ML models are trained on quantum mechanics data, some from in-house experiments and others from publicly available datasets. Over 800 chemists across the globe already use Rowan’s platform, Corin says.

The Rowan CEO says his goal is to make a tool accessible to a range of chemists, not just experts with PhDs in computational chemistry. The other cofounding Wagen brother, Ari, a business administration graduate from Northeastern University who wears multiple hats at Rowan, writes on LinkedIn profile that the start-up seeks to make computational chemistry services as easy to use as Uber, Venmo, or ChatGPT.

Advertisement

Article:

This article has been sent to the following recipient:

0 /1 FREE ARTICLES LEFT THIS MONTH Remaining
Chemistry matters. Join us to get the news you need.