Artificial Intelligence, BioPharma

Marriage of Artificial Intelligence & Biology Spawns RNA-Targeting Startup Atomic AI

Atomic AI combines artificial intelligence analysis with wet lab experiments to discover small molecules capable of drugging RNA. The startup, based on technology initially developed at Stanford, is backed by a $35 million Series A round of financing.

mRNA

The expanse of disease-causing proteins is fertile hunting ground for drug research. Many biotech startups are trying to find small molecules capable of binding to these targets. That’s great when it works, but many protein targets remain elusive, said Raphael Townsend, founder and CEO Atomic AI. Rather than pursue disease-causing proteins, Townsend’s startup aims for a different target: the RNA that carry instructions for making these proteins. Atomic AI uses artificial intelligence to find ways to drug RNA and it’s now out of stealth backed by $35 million.

“By targeting the RNA instead, you’re giving yourself new ways of targeting these untreatable diseases,” Townsend said.

The Series A round of financing announced Wednesday was led by Playground Global.

In order to drug RNA, scientists need to first get a better understanding of it. Proteins are relatively well understood, with hundreds of thousands of known protein structures, Townsend said. By comparison, the human transcriptome, the complete set of all RNA, is poorly understood. The hundreds of known RNA structures are less well mapped out compared to proteins, Townsend said. That’s key because there’s growing recognition that RNA plays a major role in disease on its own, he added.

Proteins fold and change shape, which can make them difficult to hit with a small molecule. But RNA is significantly more flexible making it more of a moving target, Townsend said. The technology of San Francisco-based Atomic AI maps out the transcriptome with an approach that combines wet lab experiments with computational analysis. Data generated by the wet lab are used to train the AI to discover novel targets on the three-dimensional structure of RNA, Townsend said. The AI makes predictions that inform additional wet lab experiments. Those results feed additional AI analysis, continuing a virtuous cycle.

Atomic AI’s technology is based on research stemming from Townsend’s PhD work at Stanford University. That research was published in the journal Science in 2021, the same year Atomic AI formed. Since then, the company has made advances with its algorithms and its wet lab, Townsend said. The technology, now called Platform for AI-driven RNA Structure Exploration (PARSE) has also improved in speed and accuracy.

The new capital enables Atomic AI to scale the platform, enabling the startup to become a drug discovery organization, Townsend said. The company will begin to narrow down the targets it will pursue. Townsend declined to identify specific diseases Atomic AI could pursue, but he said the technology could be used to discover small molecules for use in oncology, neurodegenerative disorders, cardiology, rare disease, and infectious disease. The startup’s initial research will focus on identifying the parts of the transcriptome that are even targetable, Townsend said.

Atomic AI isn’t the first biotech aiming to drug RNA, and in addition to having an earlier start some of these startups already have partnerships with big pharma companies. The most advanced program of Arrakis Therapeutics is an oncology compound in lead optimization. The Waltham, Massachusetts-based company has a drug discovery alliance with Roche. Skyhawk Therapeutics is another Waltham-based company developing RNA-targeting small molecules. That company has alliances with Bristol Myers Squibb, Merck, and Takeda Pharmaceutical. Rather than directly target RNA, Remix Therapeutics is developing drugs that target parts of the cell that process it. Nearly a year ago, Cambridge, Massachusetts-based Remix inked a research alliance with a Johnson & Johnson subsidiary. More recently, Boulder, Colorado-based Arpeggio Biosciences unveiled a $17 million Series A round of funding.

Townsend recognizes the other companies pursuing RNA-targeting small molecules, but he says what sets Atomic AI apart is the wet lab component of its platform. Companies that take a purely AI approach to RNA will have difficulty because there’s just not much RNA data out there for these technologies to analyze, he explained.

Now that Atomic AI is out of stealth, Townsend said he’s looking for potential partnerships. While the startup’s internal research will focus on developing small molecule drugs, Townsend said partnerships will focus on using PARSE to develop new RNA-based medicines. The platform’s ability to predict how RNA folds and forms new structures can be used to design new RNA medicines, he explained. The technology also holds potential for improving certain aspects of RNA-based medicines, such as stability. For example, a more stable RNA molecule could avoid the ultra-cold storage required of the messenger RNA-based Covid-19 vaccines.

Atomic AI initially raised $7 million in a 2021 seed financing led by 8VC. That firm also invested in the Series A round, which included the participation of Factory HQ; Greylock; NotBoring; AME Cloud Ventures; and angel investors including former GitHub CEO Nat Friedman; Doug Mohr; Curai CEO Neal Khosla; and Patrick Hsu, a University of California, Berkeley professor, and Arc Institute co-founder.

Image by libre de droit, Getty Images

Shares0
Shares0