Pathos AI signs two cancer deals with Alphamab and AZ
Iker Huerga, Pathos AI's chief executive.
Pathos AI has added to its pipeline of cancer drugs by licensing a bispecific antibody-drug conjugate (ADC) for solid tumours from China's Alphamab in a deal worth up to $2.2 billion, and partnering with AstraZeneca on a breast cancer candidate.
Pathos is paying $125 million upfront for rights outside Greater China to Alphamab's JSKN016, which targets TROP2 and HER3 and has the potential to be a first-in-class treatment, according to the New York-based biotech company. The agreement comes with milestone payments of up to $2.09 billion plus royalties on any eventual sales.
In China, JSKN016 is in phase 3 testing for triple-negative breast cancer (TNBC), with earlier-stage studies on the go in HER2-negative breast cancer, lung cancer, and other TROP2- and HER3-expressing solid tumour types.
The deal with AZ – terms of which have not been disclosed – will see Pathos take responsibility for early clinical development of AZD4241, a PROTAC (proteolysis-targeting chimaera) targeting the oestrogen receptor that is currently in preclinical testing. The drug will be developed for HR-positive, HER2-negative breast cancer.
Both drugs were identified using Pathos' Foundry platform, a foundation model trained on massive datasets spanning everything from text and omics data to medical imaging that is used to select promising clinical candidates for licensing or acquisition.
The company has been collaborating with AZ and Tempus on the oncology-focused foundation model that underpins Foundry since April 2025, and the co-development deal for AZD4241 is an early result of that alliance.
"The bottleneck in oncology is not finding molecules. It is proving they work in the right patients," said Iker Huerga, Pathos' chief executive.
"AZD4241 has a compelling mechanism. Foundry's job is to design the trial that proves it – matching this drug to the patients whose biology demands it," he added. "That is how we compress time. Patients are waiting."
The two drug candidates add to a growing pipeline at Pathos, currently led by CBP/p300 inhibitor pocenbrodib, licensed from Novo Nordisk, which is in early-stage clinical development for metastatic castration-resistant prostate cancer and relapsed/refractory multiple myeloma (RRMM).
The company is also running phase 1/2 trials of P-500, a selective, brain-penetrant PRMT5 inhibitor for advanced solid tumours, including high-grade glioma and uveal melanoma, that was acquired from Prelude Therapeutics in 2024.
Rounding out its current R&D portfolio is MET kinase inhibitor DO-2, in early clinical development for MET-altered non-small-cell lung cancer (NSCLC), which originates from Pathos' acquisition of a majority stake in Belgian biotech DeuterOncology in May.
Advancing all those candidates will require quite a lot of cash, and Pathos told Endpoints this week that it is currently raising up to $300 million in a Series E, which follows an impressive $365 million fourth-round financing completed in May of last year.
