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

Pfizer doubles down on AI partnership with antibody-drug conjugate deal

Artificial intelligence start-up PostEra will help the drugmaker design new payloads

by Rowan Walrath
January 7, 2025

Pfizer's headquarter building is viewed from the street, with the company's logo displayed above revolving glass doors.
Credit: Ron Adar/Shutterstock
Pfizer headquarters in New York City

Pfizer is expanding its collaboration with the start-up PostEra, which applies artificial intelligence to medicinal chemistry. The pharmaceutical giant will pay the smaller firm up to $350 million to use software models to design new small molecules as well as antibody-drug conjugates, or ADCs.

ADCs are new territory within the PostEra-Pfizer partnership. The two companies have been working together since late 2020, when Pfizer tapped 1-year-old PostEra to design small molecules using machine learning for an undisclosed amount of money. Just over a year later, Pfizer expanded the partnership to antivirals and cancer drugs, paying PostEra $13 million up front and promising up to $248 million in milestone payments. The new deal includes $12 million up front.

PostEra’s main offering is generative chemistry software: machine learning models that take chemical information and use it to propose molecules with properties that make them better able to go after a specific target and, crucially, can be made in a real-world laboratory.

“All the way back in the early days of PostEra, one of the drums we kept banging on was how important it was for machine learning models to take into account the synthesizability of the chemicals they’re generating,” says Aaron Morris, the start-up’s cofounder and CEO. “This concern and passion for synthesis, I think, also translates into helping make ADCs.”

ADCs are made up of an antibody, a small-molecule payload, and a linker. The new phase of the Pfizer partnership will focus specifically on optimizing payloads.

Morris says that PostEra has already hit preclinical milestones about 40% faster than Pfizer had anticipated. The start-up recently published a peer-reviewed paper describing a compound that prevented SARS-CoV-2 from replicating in mice by blocking the virus’s papain-like protease (PLpro), a target different from the main protease (Mpro) that the Pfizer drug Paxlovid hits (Sci. Adv. 2024, DOI: 10.1126/sciadv.ado4288). That compound went from “a cold start” to in vivo proof of concept in about 8 months, says Alpha Lee, PostEra’s cofounder and chief science officer.

The start-up separately has agreements with Amgen, for up to five small molecules, and with the US National Institutes of Health (NIH). PostEra coleads an Antiviral Drug Discovery (AViDD) Center for Pathogens of Pandemic Concern with the NIH funding, although that’s slated to run out in a few months. Lee says he and other AViDD Center leaders are looking for money to continue the work, which has focused on antivirals for coronaviruses, flaviviruses, and picornaviruses. Outside these collaborations, PostEra has four wholly owned preclinical programs in “women’s health and fertility,” per its website.

“Those three partnerships . . . have really become the cornerstone, basically, of how PostEra is ultimately trying to serve the benefits of patients outside of our internal pipeline,” Morris says.

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.