On May 6, 2026 Pathos AI, a clinical-stage AI and technology company advancing its own pipeline of cancer therapies, reported the acquisition of a majority stake in DeuterOncology, a Belgium-based company developing DO-2, a third-generation MET kinase inhibitor for patients with MET-altered cancers. The asset was systematically identified, evaluated, and advanced to acquisition through the Pathos Foundry platform.
Schedule your 30 min Free 1stOncology Demo!
Discover why more than 1,500 members use 1stOncology™ to excel in:
Early/Late Stage Pipeline Development - Target Scouting - Clinical Biomarkers - Indication Selection & Expansion - BD&L Contacts - Conference Reports - Combinatorial Drug Settings - Companion Diagnostics - Drug Repositioning - First-in-class Analysis - Competitive Analysis - Deals & Licensing
Schedule Your 30 min Free Demo!
Identified by Foundry
As part of its core operations, Pathos utilizes Foundry to continuously analyze large-scale clinical and scientific datasets, including conference proceedings, regulatory filings, published trial data, and proprietary real-world evidence. This enables Pathos to identify high-potential, undervalued oncology assets in a systematic and unbiased way.
In late 2025, Foundry flagged DO-2 as a top-ranked candidate based on its mechanism of action, pharmacokinetic profile, early clinical signal, and probability of success relative to the competitive landscape. Foundry then evaluated its clinical merit, translational feasibility, competitive positioning, and acquisition viability to generate a composite recommendation. The entire process, from initial identification to management’s final investment decision, was completed in a fraction of the time required by traditional due diligence.
"The traditional approach to finding clinical assets is built on relationships, conference presence, and reputation. Foundry is built on data," said Iker Huerga, CEO of Pathos AI. "It evaluates every asset purely on its merits — mechanism, pharmacokinetics, clinical signal, and probability of success. DO-2 scored at the top of our models. Ultimately, the best molecule wins."
A Highly Differentiated MET Inhibitor
MET inhibitors are an established therapeutic class for MET-altered Non-Small Cell Lung Cancer (NSCLC), but every approved agent is limited by peripheral edema rates of 62-82%, frequently requiring dose reductions and treatment discontinuation.
DO-2’s deuterated structure and "fast on / fast off" binding kinetics deliver potent MET inhibition for 8-12 hours per day. This provides sufficient target coverage for robust antitumor activity without causing the sustained endothelial damage that drives chronic edema.
In a Phase 1 study of 28 patients, DO-2 demonstrated 100% tumor shrinkage in all evaluable MET exon 14 skipping NSCLC patients (10/10). It also demonstrated a superior safety profile with zero Grade 4 adverse events, and a peripheral edema rate of just 5% (versus 62-82% for competitors), and a highly convenient 60 mg once-daily oral dose. Patent exclusivity extends to December 2040.
"Pathos’s ability to recognize the potential of this program through rigorous, data-driven analysis is exactly the kind of conviction that will bring DO-2 to the patients who need it," said Dr. Timothy Perera, Founder and CEO of DeuterOncology.
Powered by Foundry
Foundry doesn’t just find drugs. It develops them. The platform is composed of thousands of AI agents working in parallel, powered by the Pathos Oncology Foundation Model. These agents identify undervalued assets and propose portfolio decisions for management. Throughout the entire development lifecycle, Foundry continuously analyzes the totality of emerging data to ensure Pathos programs maintain the highest possible probability of success while directly supporting clinical trial execution.
The same system that identified DO-2 will now guide its clinical development. DO-2 is one of four major portfolio decisions made through Foundry in Q1 2026 alone.
"We are not interested in process automation. We are redesigning drug development from first principles," said Huerga. "DO-2 is proof that the system works."
(Press release, Pathos AI, MAY 6, 2026, View Source [SID1234665238])