AI-Based Drug Discovery Company Atomwise Sets Its Sights on Inflammatory Disease Market

By Uduak Thomas

Atomwise, which has historically used its AI platform to help drug developers identify compounds for their pipelines, is entering a new phase of its journey. This week, it announced the nomination of its first AI-driven development candidate, a small molecule focused on TYK2 inhibition, officially marking its transition into a pharmaceutical company.

Neely Mozaffarian, MD, PhD, a veteran in the inflammatory disease drug discovery market, has joined the company as its chief medical officer responsible for driving the TYK2 inhibitor as well as other drugs in the Atomwise pipeline into clinical trials.

“We’re thrilled that Neely has joined us to advance our first candidate into the clinic. This is a major milestone for Atomwise, as we become a pharmaceutical company focused on discovering and advancing our own proprietary pipeline,” Abraham Heifets, CEO and co-founder of Atomwise said in a statement. “We believe the best path to discovering first-in-class and best-in-class medicines is to explore unique and untapped chemical space, which is what our AI enables. If you want to differentiate, it helps to start different.”

Atomwise’s evolution into an AI-driven pharma company aligns with its overall mission to invent a better way to discover medicines that improve patients’ outcomes For Heifets, that means identifying small molecule drugs that are first in class and best in class. “These are really the only two ways of providing value to patients and they are also the only ways of capturing value,” he said in an interview with GEN.  In order to do that, “you have to be able to find molecules where nobody else has found them…and you have to provide meaningful differentiation from what’s out there,” he said. “That’s what patients need and so that’s what we focused on.” 

Initially, Atomwise focused on working with drug discovery and development partners interested in using its proprietary AI/ML drug discovery platform, AtomNet®, to identify potential small molecule candidates from millions of synthesizable compounds. It was the right approach for the company, according to Heifets, who comes from a computer science background, because it allowed them to adopt a high volume, low touch business model for the last several years that leveraged its strengths in artificial intelligence and machine learning. 

Over the years, “we [tried] to be very creative and flexible in the kind of deals that we were doing…all driven by the idea of playing to [our] strong suit,” he said. Atomwise forged partnerships with large and small pharmaceutical companies as well as academic groups. Last year, they signed an agreement with Sanofi to use AtomNet for computational discovery and research. Under the terms of the agreement, Sanofi agreed to pay Atomwise $20 million upfront to identify, synthesize, and advance lead compounds for up to five undisclosed targets which will be exclusive to Sanofi. Subsequent payments pegged to key research, development, and sales milestones could total more than $1 billion in addition to royalties for products developed through the collaboration. And in 2019, the company announced drug discovery partnerships with both Hansoh Pharma and Eli Lilly.

But Atomwise is moving away from a purely collaborative model and focusing on building a pipeline of drug assets internally. It began working on the pipeline some years ago culminating in the nomination of its first candidate—an orally bioavailable and allosteric TYK2 inhibitor discovered using its AI platform. TYK2 is a key mediator in cytokine signaling pathways linked to a broad range of immune-mediated inflammatory conditions. By modulating the TYK2 pathway, this compound could be used to treat various autoimmune and autoinflammatory diseases. Atomwise plans to submit an investigational new drug application for the drug in submission in the second half of 2024.

“We [have] always focused on accessing new parts of chemical space that hadn’t been explored. And so that was what our technology had always been optimized for,” Heifets explained. Taking this approach means “you have an obligation, a duty to prove that those molecules that you’re finding don’t have some hidden liability.” Being able to advance the TYK2 inhibitor into the clinic is “a validation of the whole [Atomwise] platform. That the kinds of things that we find can be valuable and meaningful.” 

Mozaffarian was hired to shepherd the TYK2 inhibitor and other compounds in Atomwise’s pipeline into clinical trials and beyond. She brings over 25 years of experience in immunology and autoimmunity programs covering all phases of drug development, working on both small and large molecules, with companies such as GentiBio, Janssen, Gilead, Eli Lilly, and AbbVie to the role. Last year, the company hired Gavin Hirst, PhD, a 30-year veteran of the biopharmaceutical industry, as its CSO. He is responsible for setting the strategic vision for Atomwise’s drug discovery efforts as well as providing scientific oversight of its research and development pipeline

Atomwise’s novel approach to finding small molecules was part of what attracted Mozaffarian to the CMO position. Drugs that successfully pass through clinical development have to be more effective than current treatments while simultaneously being just as safe if not safer than existing alternatives. “The hope is always that you can make a therapy that is better than existing therapies for the patient. But it’s really difficult if the drug is not very different from the drugs that are currently out there,” she said in an interview with GEN. “[Atomwise is] able to create, design, and screen hundreds of thousands of molecules to ensure that they can find something that has the qualities that one would look for in a new investigational therapy. The odds that it will have better characteristics for patients increase.”

Among her responsibilities as CMO, Mozaffarian is responsible for thinking through which diseases make sense to pursue for the TYK2 inhibitor as well as which patient populations Atomwise should consider for the drug. The drug could potentially be used to treat conditions such as inflammatory bowel disease, systemic lupus erythematosus, psoriasis, and psoriatic arthritis. She will also support efforts to build on the company’s understanding of the drug based on information about its structure and other preclinical data in ways that improve its performance in patients. She will also be responsible for getting the drug into clinical trials and managing the logistics of the process including working with regulatory bodies and liaising with clinicians to enroll patients at various trial sites. 

It’s a lot for a small company like Atomwise to take on. Large pharma companies typically have large teams of people dedicated to developing new small molecule drugs and much of the infrastructure for moving viable candidates through the clinical development process is already in place. Having worked for small startups as well as large pharma companies, Mozaffarian has the requisite experience to help build out the team and resources that Atomwise needs to move its candidates through clinical development, something she is looking forward to doing. 

“Obviously there are a lot of very talented people here and we are going to add to them in a thoughtful manner,” she said. Atomwise has numerous connections within industry and academia so finding the right talent won’t be difficult. The company is also based in a biotech hotspot on the west coast which has a large pool of people with the kinds of skills and expertise that Atomwise might need. 

Mozaffarian is also looking forward to working on other candidates in the Atomwise pipeline. In the next few years, In addition to inflammatory disease, the company is also focused on targets in oncology and immunology. “It’s one thing to say on paper that we can design things differently and they have novel structures and behave differently in preclinical studies. Ultimately, we have to demonstrate what that means for the patient down the line,” she said. 

And Atomwise will have its work cut out for it as there are a number of competitors for the TYK2 inhibitor already available on the market. That is perhaps the biggest challenge, according to Mozaffarian. “We are not setting out to make a me-too version of an existing therapy. So figuring out, based on the data we have and are in the process of obtaining preclinically, what that means for where we can go [is] going to be the challenge.”