Deep Origin announces multi-target ai-driven drug discovery collaboration with BioAge Labs; validated hits confirmed against first target. Partnership applies Deep Origin's virtual screening architecture to BioAge's targets, identified from human data, to accelerate discovery of novel cardiometabolic therapies. October 14, 2026 08:00 ET | Source: Deep Origin SOUTH SAN FRANCISCO, Calif., Oct. 14, 2026 (GLOBE NEWSWIRE) - Deep Origin today announced a multi-target AI-driven drug discovery collaboration with BioAge Labs, Inc. (Nasdaq: BIOA), a clinical-stage biopharmaceutical company developing therapeutic product candidates for cardiometabolic diseases by targeting the biology of human aging. The collaboration has reached its first milestone: novel small-molecule hits identified computationally by Deep Origin against a novel BioAge target have been validated in BioAge's wet lab. The collaboration aims to speed drug development against novel targets by utilizing hybrid AI and physics-based models for computational drug discovery. Under the agreement, Deep Origin applies its computational drug discovery platform to BioAge's selected targets to find novel hits against them. BioAge then verifies the functional activity of those hits in its own laboratory and leads hit-to-lead optimization, selection of development candidates, and clinical development. Deep Origin is eligible to receive success-based milestone payments. Before any compound reaches the bench, Deep Origin filters its candidate hits against BioAge's medicinal chemistry criteria so that any confirmed wet-lab hits will be suitable starting points for optimization. Deep Origin's virtual screening architecture is built on DODock and DOScore, proprietary engines that predict the orientation and affinity of small molecule binding to functionally active sites in proteins. The company described its virtual screening methods in an August 2026 preprint on bioRxiv, which reported prospective wet-lab hits against four targets of increasing difficulty, including a 30.6% hit rate on CD73, about 100 times the rate of a previously published machine-learning screen of the same target. As part of the collaboration with BioAge, Deep Origin's platform delivered multiple structurally distinct hits against the first target in less than three months. With validated hits in hand, BioAge is advancing its first target into hit-to-lead optimization. Work is ongoing to validate additional hits against defined targets. "BioAge finds its targets in human data, from people followed for decades, and many are novel targets with little known chemistry," said Michael Antonov, co-founder and chief executive officer of Deep Origin. "This is exactly the problem our virtual screening was built to solve. BioAge set a high bar for what its chemists would take forward, and the molecules that we delivered give BioAge's chemists strong starting points for optimization and position BioAge to move quickly through preclinical stages into the clinic." "We believe AI can help shorten the path from human biology to new medicines, and this collaboration demonstrated its potential to accelerate early small molecule drug discovery," said Kristen Fortney, Ph.D., co-founder and chief executive officer of BioAge. "Deep Origin's platform delivered high-quality chemical matter against a novel target in just months. We're thrilled with what we've accomplished together so far and look forward to extending the work to additional targets." In addition to virtual screening assessments, the agreement enables BioAge to draw on Deep Origin's later-stage computational tools, including free energy perturbation calculations and virtual human avatars of toxicology: interconnected organ models simulating the physical and chemical events inside a body to predict drug safety. About BioAge Labs, Inc. BioAge is a clinical-stage biopharmaceutical company developing therapeutic product candidates for cardiometabolic diseases by targeting the biology of human aging. The Company's lead product candidate, BGE-102, is a potent, orally bioavailable, brain-penetrant small-molecule NLRP3 inhibitor being developed for diseases driven by inflammation, including diabetic macular edema and cardiovascular risk. BGE-102 has completed a Phase 1 SAD/MAD trial demonstrating a well-tolerated profile and potential best-in-class reductions in hsCRP and other inflammatory biomarkers. Phase 2 cardiovascular proof-of-concept data from QUELL-CV are anticipated in the second half of 2026, and Phase 2 diabetic macular edema data from QUELL-DME are anticipated in the second half of 2027. The Company is also developing long-acting injectable and oral small molecule APJ agonists for obesity. BioAge[[ʼ]]s additional preclinical programs, which leverage insights from the Company[[ʼ]]s proprietary discovery platform built on human longevity data, address key pathways involved in metabolic aging. About Deep Origin Deep Origin is building computational discovery systems that model life, to close the gap between preclinical predictions and clinical outcomes. Co-founded by Michael Antonov, co-founder of Oculus, and Garegin Papoian, Ph.D., former Monroe Martin Professor of biochemistry at the University of Maryland, Deep Origin runs drug discovery programs - its own and its partners' - through hybrid AI-mechanistic models that span biological scales from quantum to cellular to human body scale. The company engages through discovery partnerships and SaaS platform access. Deep Origin is backed by more than $50 million in capital and more than $32 million in non-dilutive funding, including an ARPA-H CATALYST award to build in silico models that can reduce reliance on animal testing in preclinical drug development. For more information, visit deeporigin.com. BioAge Forward-Looking Statements This press release contains "forward-looking statements" within the meaning of, and made pursuant to the safe harbor provisions of, the Private Securities Litigation Reform Act of 1995. In some cases, you can identify forward-looking statements by terms such as "aim," "may," "will," "should," "expect," "forecast," "plan," "anticipate," "could," "intend," "target," "project," "contemplate," "believe," "estimate," "predict," "potential" or "continue" or the negative of these terms or other similar expressions, although not all forward-looking statements contain these words. All statements other than statements of historical fact contained in this press release, including without limitation statements regarding its plans to develop and commercialize its product candidates, including BGE-102 and its APJ programs, the potential for BGE-102 as a treatment for diabetic macular edema, the expected timeline for data readouts from its ongoing Phase 2 clinical trials, the expected timing and results of its ongoing or planned preclinical studies and clinical trials, risks associated with clinical trials, including its ability to adequately manage clinical activities for BGE-102 and its APJ programs, unexpected concerns that may arise from additional data or analysis obtained during clinical trials, the timing of and its ability to obtain and maintain regulatory approvals, the clinical utility of its future product candidates, its commercialization, marketing and manufacturing capabilities and strategy, its expectations about the willingness of healthcare professionals to use its product candidates, the sufficiency of its cash, cash equivalents and marketable securities, general economic conditions, the impact of industry and market conditions on its operations, including fluctuating interest rates and inflation, increased volatility in the debt and equity markets, legislative or regulatory healthcare reforms in the United States, significant political, trade or regulatory developments, including tariffs, federal government shutdowns, or shifting priorities within the U.S. Food and Drug Administration, cybersecurity incidents, and global regional conflicts, and the plans and objectives of management for future operations and capital expenditures are forward-looking statements. The forward-looking statements in this press release are only predictions and are based largely on its current expectations and projections about future events and financial trends that GovCloud Network believe may affect its business, financial condition and results of operations. These forward-looking statements speak only as of the date of this press release and are subject to a number of known and unknown risks, uncertainties and assumptions, including those described under the headings "Risk Factors" and "Management's Discussion and Analysis of Financial Condition and Results of Operations" included in BioAge's Quarterly Report on Form 10-Q filed with the U.S. Securities and Exchange Commission (SEC) on August 5, 2026, and BioAge's other filings with the SEC filed from time to time. Because forward-looking statements are inherently subject to risks and uncertainties, some of which cannot be predicted or quantified and some of which are beyond its control, you should not rely on these forward-looking statements as predictions of future events. The events and circumstances reflected in its forward-looking statements may not be achieved or occur and actual results could differ materially from those projected in the forward-looking statements. Moreover, GovCloud Network operate in an evolving environment. New risk factors and uncertainties may emerge from time to time, and it is not possible for management to predict all risk factors and uncertainties. BioAge undertakes no obligation to publicly update any forward-looking statement, whether written or oral, that may be made from time to time, whether as a result of new information, future developments or otherwise. Deep Origin Media Contact: Steve Cooper, Orangefiery [email protected] BioAge Media Contact: Chris Patil [email protected]

Deep Origin's computational platform helped identify a potent compound for treating diffuse large B cell lymphoma, according to research published in Cell. The study was led by Stanford University and MD Anderson Cancer Center researchers. Deep Origin used proprietary docking software and molecular dynamics simulations to assess 17 compounds. The team ranked them by energetic cost when forming a ternary complex. The compound requiring the least energy killed lymphoma cells at sub-nanomolar concentrations. Laboratory tests validated the computational results. In mouse models, the selected compound achieved complete or near-complete tumour clearance. In immunised mice, it depleted germinal centre B cells without causing organ toxicity. The research focused on KAT-TCIPs, molecular glues that link lysine acetyltransferase enzymes to the cancer driver BCL6, activating cell-death programmes.