Ribavirin

Phase 1 Study Designed to Evaluate the Safety, Tolerability and Pharmacokinetics of AT-587 in Healthy Volunteers AT-587 is a Potential First-in Class Treatment for Hepatitis E Virus, a Serious Liver Disease with No Approved Therapies Study Initiation Represents an Important Milestone Advancing Atea’s Antiviral Pipeline Focusing on First- or Best-in-Class Product Candidates in Areas of High Unmet Medical Need BOSTON, July 14, 2026 (GLOBE NEWSWIRE) -- Atea Pharmaceuticals, Inc. (Nasdaq: AVIR) (Atea or Company), a late-stage clinical biopharmaceutical company engaged in the discovery and development of oral antiviral therapeutics for serious viral diseases, today announced the initiation of a first-in-human Phase 1 clinical trial evaluating AT-587, for the treatment of hepatitis E virus (HEV) infection. AT-587 is a proprietary oral antiviral nucleotide analog being developed for the treatment of HEV, a potentially serious liver disease that can lead to chronic infection, cirrhosis and liver failure in certain patient populations. In particular, at-risk populations include immunocompromised individuals, such as transplant recipients and patients taking immunosuppressants, among others. There are currently no approved treatments for HEV. “HEV is a significant health concern, particularly among immunocompromised patients who are at heightened risk for chronic infection and rapidly progressive liver disease, and the initiation of our Phase 1 trial represents an opportunity to address a substantial unmet need,” said Jean-Pierre Sommadossi, PhD, founder and chief executive officer of Atea Pharmaceuticals. “Supported by encouraging preclinical data demonstrating potent antiviral activity, we believe AT-587 has the potential to become an important therapeutic option for patients, particularly transplant recipients and immunocompromised patients living with HEV. Advancing AT-587 into the clinic builds on our deep expertise in antiviral drug development and represents another step in expanding Atea’s viral hepatitis franchise.” The Phase 1 trial is a randomized, double-blind, placebo-controlled, sequential dose-escalation study designed to evaluate the safety, tolerability and pharmacokinetics (PK) of AT-587 in healthy volunteers. The study includes both single ascending dose (SAD) and multiple ascending dose (MAD) components, as well as an embedded food-effect assessment. Part A of the study will evaluate single ascending doses of AT-587 administered under fasting conditions, with one cohort incorporating both fasting and fed administration to assess food effect. Part B of the study will evaluate multiple ascending doses of AT-587 administered once daily or twice daily for seven days, with dose selection informed by safety and PK data generated in Part A. Dose escalation decisions will be guided by ongoing review of emerging safety and PK data, providing flexibility to adapt the doses as clinical experience with AT-587 evolves. EASL 2026: AT-587 In Vitro Results Demonstrate High Antiviral Potency Against HEV and In Vivo Efficacy Results presented at EASL Congress 2026 demonstrated the promising preclinical antiviral potency of AT-587 against HEV. Studies demonstrated that AT-587 is a potent inhibitor of HEV replication being 30- to 150-fold more potent in vitro against HEV than sofosbuvir and ribavirin. Ribavirin is currently used off label as a treatment for HEV. AT-587 showed no toxicity in in vitro studies. AT-587 was also active against flaviviruses, rubella and chikungunya. Additional data presented at EASL Congress 2026 showed that AT-587 inhibits HEV genotype 3 activity in vivo . Using an HEV genotype 3 infected gerbil model, samples from the treated groups had significantly lower HEV RNA levels than the control group. Notably, AT-587 also retained high potency against ribavirin (G1634R) and sofosbuvir (A1343V) clinical resistance strains in vitro , further underscoring the potential of AT-587 as a first-in-class therapy and differentiating its pro existing off-label treatment options. About HEV HEV is a single stranded ribonucleic acid (ssRNA) virus which infects the liver and remains an under-recognized global health challenge with an estimated 20 million acute infections annually. Waterborne transmission of HEV genotypes 1 and 2 causes mostly acute self-limiting hepatitis in developing regions, whereas foodborne transmission of HEV genotype 3 predominates in the US and Europe and may cause chronic hepatitis in immunocompromised patients, which can lead to cirrhosis in three to five years. There is a growing number of immunocompromised patients, a population that includes solid organ transplant and hematopoietic stem cell transplant recipients and patients with hematologic malignancies such as multiple myeloma. Each year, in the US and Europe, 3% of the approximately 665,000 patients who have these underlying medical conditions are at risk of developing chronic HEV. There is currently no approved antiviral therapy for HEV, and current off-label treatments, including ribavirin, have limited efficacy and tolerability, underscoring a clear and urgent unmet medical need. Atea’s initial HEV clinical efforts will focus on developing AT-587 for the treatment of immunocompromised patients with chronic HEV. About Atea Pharmaceuticals Atea is a late-stage clinical biopharmaceutical company focused on discovering, developing and commercializing oral antiviral therapies to address the unmet medical needs of patients with serious viral infections. Leveraging Atea’s deep understanding of antiviral drug development, nucleos(t)ide chemistry, biology, biochemistry and virology, Atea has built a proprietary nucleos(t)ide prodrug platform to develop novel product candidates to treat ssRNA viruses, which are a prevalent cause of serious viral diseases. Atea plans to continue to build its pipeline of antiviral product candidates by augmenting its nucleos(t)ide platform with other classes of antivirals that may be used in combination with its nucleos(t)ide product candidates. Atea’s Phase 3 program is evaluating the FDC regimen of BEM, a nucleotide analog polymerase inhibitor, and RZR, an NS5A inhibitor, to treat HCV. AT-587, a nucleotide analog, is in Phase 1 development for the treatment of HEV. For more information, please visit Forward-Looking Statements This press release includes “forward-looking statements” within the meaning of the Private Securities Litigation Reform Act of 1995. Forward-looking statements in this press release include but are not limited to statements regarding the potential to develop a product for the treatment of HEV, anticipated milestone events and timelines for clinical trials, future results of operations and business strategy. When used herein, words including “expected,” “should,” “anticipated,” “believe,” “will,” “plans,” and similar expressions are intended to identify forward-looking statements. In addition, any statements or information that refer to expectations, beliefs, plans, projections, objectives, performance or other characterizations of future events or circumstances, including any underlying assumptions, are forward-looking. All forward-looking statements are based upon Atea’s current expectations and various assumptions. Atea believes there is a reasonable basis for its expectations and beliefs, but they are inherently uncertain. Atea may not realize its expectations, and its beliefs may not prove correct. Actual results could differ materially from those described or implied by such forward-looking statements as a result of various important factors, including, without limitation, uncertainties inherent in the drug discovery and development process and the regulatory submission or approval process, unexpected or unfavorable safety or efficacy data or results observed during clinical trials or in data readouts; delays in or disruptions to clinical trials or our business; our reliance on third parties over which we may not always have full control; dependence on the success of Atea’s most advanced product candidate, in particular the regimen of bemnifosbuvir and ruzasvir for the treatment of HCV; as well as the other important factors discussed under the caption “Risk Factors” in Atea’s Quarterly Report on Form 10-Q for the quarter ended March 31, 2026 as such factors may be updated from time to time in its other filings with the SEC, which are accessible on the SEC’s website at These and other important factors could cause actual results to differ materially from those indicated by the forward-looking statements made in this press release. Any such forward-looking statements represent management’s estimates as of the date of this press release. While Atea may elect to update such forward-looking statements at some point in the future, except as required by law, it disclaims any obligation to do so, even if subsequent events cause our views to change. These forward-looking statements should not be relied upon as representing Atea’s views as of any date subsequent to the date of this press release. Contacts Jonae Barnes SVP, Investor Relations and Corporate Communications 617-818-2985 barnes.jonae@ateapharma.com Joyce Allaire LifeSci Advisors jallaire@lifesciadvisors.com

AmesNet’s Task-Conditioned Learning architecture outperforms FDA, MIT, Tencent, and the University of Sydney models in both sensitivity and balanced accuracy on out-of-domain chemical data on a public dataset; AmesNet is built on top of ChemPrint, the core and proprietary deep-learning engine of the GALILEO platform that powers the company’s drug pipeline. SAN DIEGO — Model Medicines , an AI-first biotechnology company developing first-in-class therapeutics against multi-indication biological choke points, today announced that the company’s AmesNet™ agent, a deep learning model for predicting Ames test mutagenicity, has been peer-reviewed and published in the American Chemical Society (ACS) journal, Chemical Research in Toxicology (CRT). AmesNet™ demonstrated best-in-class performance across all benchmarked approaches in predicting chemical safety on out-of-domain data. The agent outperformed models from the FDA (DeepAmes/NCTR/CDER), MIT (ChemProp), Tencent (GROVER), and the University of Sydney [1] . The model uses a novel AI architecture called Task-Conditioned Learning (TCL) and is built on GALILEO™, the same AI platform Model Medicines uses to discover and de-risk its drug pipeline. Key Highlights: Peer-Reviewed Validation: American Chemical Society (ACS) publication, Chemical Research in Toxicology (CRT), a 1st Quartile CiteScore Journal. Best-in-Class Performance: Late stage Ames test failures jeopardize an estimated $10 million in capital and multiple years of developmental progress per candidate. AmesNet™ detects compounds that models from the FDA, MIT, Tencent, and the University of Sydney miss. AmesNet recovered 106 more true positives than the FDA’s DeepAmes agent across 13 mutagenic substructure classes. The publicly available benchmark set contained 560 Ames true positives. New Modeling Paradigm: Task-Conditioned Learning (TCL) architecture captures assay-context-dependent mutagenicity that all prior “unconditioned” models either don’t account for or average away. TCL Encoder-Swap: Integrating competitor agents into Model Medicines’ TCL framework improved their performance. Early-Stage Screening Enabled: AmesNet’s performance enables high-confidence Ames screening at scale during early discovery, pulling preclinical safety assessment forward from a late-stage bottleneck to a continuous input in compound prioritization. Platform Extension: AmesNet™ is the first public release from Model Medicines' multi-modal suite of ADMET GALILEO™ agents. Validated Engine Behind the Pipeline: AmesNet™ is part of the end-to-end AI drug discovery and development platform, GALILEO™, which Model Medicines used to discover its two lead assets, MDL-001 and MDL-4102. Open Science: All data and code (STL, uMTL, gMTL, TCL encoder swaps, and bootstrapping) are available in the following GitHub repository: github.com/Model-Medicines/TCL-Ames . Publication: The peer-reviewed article is available here: doi.org/10.1021/acs.chemrestox.6c00082 . “Peer-review and publication of the AmesNet™ toxicology agent in the prestigious toxicology journal American Chemical Society CRT underscores the importance and success of our foundational GALILEO™ platform," said Daniel Haders, PhD, CEO of Model Medicines. "AmesNet demonstrates that Model Medicines can predict toxicity with world-class, regulatory grade accuracy in entirely novel chemical spaces - outcompeting the best models in the world on a public dataset. AmesNet was built on our GALILEO platform and utilizes our ChemPrint agent. The same platform and agent discovered our lead, first-in-class assets, MDL-001 and MDL-4102, and the novel broad-spectrum Thumb-1 drug target. The explicit implication is that the GALILEO platform and the ChemPrint agent are one of, if not the most productive, accurate and creative platform and agent in AI Drug Discovery.” Background: The Ames Testing Bottleneck The Ames test is a decades-old laboratory assay that uses bacteria to check whether a chemical can cause mutations in DNA. These “mutagens” carry an early warning that they may cause cancer. For that reason, the Ames test is a required genotoxicity assay for all novel small-molecule therapeutics prior to human clinical trials. GLP-compliant testing often exceeds $10,000 per compound and requires approximately 2 grams of material, making routine screening impractical during early discovery. Developers typically defer testing until regulatory submission, at which point tens of millions of dollars have been sunk into programs. Regulatory agencies have moved to enable AI alternatives: the FDA Modernization Act provides a legal framework for computational models to reduce wet-lab testing, the FDA’s AI4TOX/SafetAI initiatives target AI for toxicological endpoints, and ICH M7 endorses computational Ames prediction. No model has met this mandate. Task-Conditioned Learning (TCL) The Ames test is a battery of experiments across multiple bacterial strains. Each strain is sensitive to a different type of DNA mutation, conducted with and without a liver enzyme fraction (S9) that simulates human drug metabolism. A compound may be mutagenic in one strain but not another, or only when metabolized. All prior AI models are “Unconditioned” and produce a single prediction without conditioning on strain or metabolic activation. AmesNet’s TCL architecture resolves this issue with a dual-branch design: one branch encodes molecular structure; the second encodes assay conditions (strain identity and ±S9 status). The model learns separate decision boundaries for each context rather than averaging across all conditions. Correctly identifying mutagenic compounds, known as sensitivity, is the most critical metric in AI-driven Ames testing. False negatives allow dangerous compounds to advance undetected. Existing models fail on sensitivity because compound classes, such as planar aromatic intercalators and aromatic amines, produce context-dependent signals that Unconditioned Models dilute. Structural enrichment analysis confirms AmesNet™ recovers these classes. AmesNet™ Benchmark Results AmesNet™ was evaluated on a withheld out-of-domain test set of 4,208 data points comprising compounds chemically dissimilar from the training data: Model Source Sensitivity (95% CI) Balanced Accuracy (95% CI) AmesNet™ Model Medicines 0.72 (0.68–0.76) 0.81 (0.78–0.83) STL-DeepAmes FDA / NCTR 0.69 (0.64–0.73) 0.76 (0.73–0.78) gMTL-MLP Univ. of Sydney 0.56 (0.52–0.61) 0.74 (0.71–0.76) uMTL-MLP Univ. of Sydney 0.56 (0.51–0.62) 0.72 (0.70–0.75) STL-GROVER Tencent 0.54 (0.49–0.59) 0.75 (0.73–0.77) STL-ChemProp MIT 0.54 (0.49–0.59) 0.74 (0.72–0.77) STL-MLP Univ. of Sydney 0.48 (0.43–0.53) 0.71 (0.69–0.74) “Current AI models fail because they try to force complex biological problems into a single prompt," notes Tyler Umansky, Head of Platform and Machine Learning and the paper's lead author. "AmesNet proves the power of doing the opposite: separating every variable, discovering winners and losers for each one, and finding the chemistry that wins for all variables. AmesNet is a microcosm of how we approach all of drug discovery, doing the tedious but necessary hard work. It’s how we built our two lead programs and established a pipeline capable of tackling more than 30 indications.” A Paradigm Shift for Ames Screening and Preclinical Development A model with AmesNet’s sensitivity and balanced accuracy in novel chemical space enables high-confidence mutagenicity screening at scale during early drug discovery. This shifts Ames testing from a wet-lab, late-stage gate on a single candidate to a computational filter applied across entire compound libraries at program concept. This repositioning advances preclinical safety assessment by years in the development timeline, and transforms Ames screening from a late-stage binary pass/fail checkpoint into a continuous, scalable input for compound prioritization. AmesNet™ enables developers to eliminate mutagenic liabilities from their pipelines before they become costly. GALILEO™: One Platform, Discovery Through Development AmesNet™ is not a standalone agent. It is the latest capability within GALILEO™, the AI platform Model Medicines uses to discover, optimize, and de-risk its own wholly owned drug pipeline. AmesNet™ and the Company’s drug programs share the same molecular foundation: the encoder that powers AmesNet is the same agent used to discover the company’s two lead assets, MDL-001 and MDL-4102. MDL-001 — a direct-acting, non-nucleoside, broad-spectrum antiviral targeting the conserved viral polymerase mechanism (RdRp Thumb-1 [2] ), with demonstrated preclinical activity across respiratory and hepatic viruses and high-risk co-infections. MDL-001 is being developed across major respiratory infections, including influenza, COVID-19, and RSV, as well as chronic hepatitis infections, including HCV, HBV, and HDV [3] , representing an estimated combined global antiviral market exceeding $30 billion annually. Oral MDL-001 demonstrates preclinical equivalency or superiority against established standards of care, specifically oseltamivir (Tamiflu) for influenza, nirmatrelvir (Paxlovid), molnupiravir (Lagevrio), and remdesivir (Veklury) for SARS-CoV-2, ribavirin for RSV, and sofosbuvir (Sovaldi) for HCV. Regulatory submission is targeted for 2027, with clinical trials estimated to commence in 2027. MDL-4102 — a highly potent and selective BRD4 inhibitor with no measurable activity against BRD2 or BRD3. The program was optimized for BRD4 selectivity, transcriptional impact, and drug-like properties simultaneously. MDL-4102 is designed to overcome the dose-limiting hematologic toxicities that hindered prior pan-BET inhibitors, positioning it as a next-generation transcriptional therapy with the potential for durable efficacy across BRD4-driven malignancies. Beyond oncology, BRD4 biology extends into fibrosis, I&I, CVD, and neurodegenerative diseases, expanding the potential addressable market to more than $60 billion annually across these therapeutic areas. MDL-4102 is positioned as a differentiated, next-generation approach to targeting core disease-driving gene expression programs. Regulatory submission is targeted for 2027. AmesNet™ is the first public release from Model Medicines’ multi-modal suite of ADMET GALILEO™ agents. To date, Model Medicines has only utilized these agents internally to discover its first-in-class therapeutics MDL-001 and MDL-4102. Together, the on/off target and ADMET agents are designed to enable Model Medicines to design, prioritize, and de-risk compounds better than any company in the field. About Model Medicines Model Medicines is an AI-first biotechnology company engineering first-in-class small molecules that target the biological choke points underlying disease. The company's drug franchise lifecycle is powered by GALILEO™, a proprietary end-to-end AI drug discovery and development platform. Through this platform, its core therapeutic programs target high-value mechanistic drivers of pathology, focusing specifically on viral replication via the novel allosteric RdRp Thumb-1 pocket and transcriptional control via the master regulator BRD4. These programs feed into a scalable "Pipeline-in-a-Pill" strategy, anchored by lead assets MDL-001 and MDL-4102 to address over 30 indications across virology, oncology, I&I, CVD, and neurodegenerative diseases. By leveraging large-scale computation to uncover entirely new classes of therapeutics once thought unreachable, Model Medicines is redefining what is possible in modern drug discovery. Learn more at . Media Contact Patrick O’Neill Head of Partnerships & Investor Relations media@modelmedicines.com [1] Umansky TJ, Woods VA, Russell SM, Haders DJ. AmesNet: a task-conditioned deep learning model with enhanced sensitivity and generalization in Ames mutagenicity prediction. Chem Res Toxicol. Published online June 29, 2026. doi:10.1021/acs.chemrestox' multi-modal.6c00082 [2] Woods V, Umansky T, Russell SM, Gallay P, Smith D, Haders D. The RdRp Thumb-1 pocket is a conserved target for broad-spectrum antiviral development. bioRxiv. Preprint posted online June 23, 2026. doi:10.1101/2024.03.29.587401 [3] Woods V, Umansky T, Russell SM, et al. MDL-001: an oral, direct-acting universal antiviral for influenza-like illness (ILI) and chronic hepatitis. Preprint. Posted online January 13, 2025. bioRxiv. doi:10.1101/2025.01.13.632836