from absci import de_novo_model model = de_novo_model.load_latest() antigen = model.load_pdb("7olz.pdb", chain="A") antibodies = model.predict(antigen, N=300000) from absci_library import codon_optimizer library = codon_optimizer.reverse_translate(library) library.to_csv("covid-antibody-designs.csv") library.to_wet_lab(assay="ACE") from absci import lead_opt_model lead_optimizer = lead_opt_model.load_latest() library.naturalness = lead_optimizer.naturalness(library) lead_optimizer.optimize(library).to_wet_lab(as say="SPR") from absci import genetic_algorithm; parameters=["maximize|binding_affinity:pH=7.5", "minimize|binding_affinity:pH=6.0", "maximize|human_naturalness"]; library = genetic_algorithm.multiparametric_optimization(library, parameters, evolutions=100); library.to_wet_lab(assays=["ACE", "SPR", "Bioassays"]) C O P Y R I G H T © 2 0 2 5 A B S C I C O R P O R A T I O N . A L L R I G H T S R E S E R V E D . CORPORATE PRESENTATION FALL 2025

2C O P Y R I G H T © 2 0 2 5 A B S C I C O R P O R A T I O N . A L L R I G H T S R E S E R V E D . Disclaimers Forward-Looking Statements Statements contained in this press release regarding matters that are not historical facts are “forward-looking statements” within the meaning of the Private Securities Litigation Reform Act of 1995. Because such statements are subject to risks and uncertainties, actual results may differ materially from those expressed or implied by such forward-looking statements. Such statements include, but are not limited to, statements regarding any or all of the following: (i) Absci’s preclinical studies, clinical trials, as well as partnered and internally developed programs, including, without limitation, manufacturing capabilities, status of such studies and trials and expectations regarding data, safety and efficacy generally; (ii) data included in the above-described oral presentation, as well as the ability to use data from ongoing and planned clinical trials for the design and initiation of further clinical trials; (iii) Absci’s strategy, goals, anticipated financial performance and the sufficiency of its cash resources; (iv) regulatory submissions and authorizations, including timelines for and expectations regarding any anticipated regulatory agency decisions; (v) the expected benefits of its collaborations with partners; and (vi) the therapeutic value, development, and commercial potential of antibody therapies, as well as other technologies. Risks that contribute to the uncertain nature of the forward-looking statements include, without limitation, the risks and uncertainties discussed under the heading “Risk Factors” in Absci Corporation’s most recent annual report on Form 10-K and in any other subsequent filings made by Absci Corporation with the U.S. Securities and Exchange Commission. Existing and prospective investors are cautioned not to place undue reliance on these forward-looking statements, which speak only as of the date they are made. We disclaim any obligation or undertaking to update or revise any forward-looking statements contained in this press release, other than to the extent required by law. Market and Statistical Information This presentation also contains estimates and other statistical data made by independent parties and by us relating to market size and growth and other industry data. These data involve a number of assumptions and limitations, and you are cautioned not to give undue weight to such estimates. We have not independently verified the data generated by independent parties and cannot guarantee their accuracy or completeness. Trademark usage This presentation/document/webpage contains references to our trademarks and service marks and to those belonging to third parties. Absci®, ®, SoluPro®, Bionic SoluPro® and SoluPure® are Absci registered trademarks with the U.S. Patent and Trademark Office. We also use various other trademarks, service marks and trade names in our business, including the Absci AI logo mark ( ), the Unlimit with us mark ( ), Denovium, Integrated Drug Creation, HiPrBind, and IgDesign. All other trademarks, service marks or trade names referred to in this presentation/document/webpage are the property of their respective owners. Solely for convenience, the trademarks and trade names in this presentation/document/webpage may be referred to with or without the trademark symbols, but references which omit the symbols should not be construed as any indicator that their respective owners will not assert, to the fullest extent under applicable law, their rights thereto.

3N O N - C O N F I D E N T I A L C O P Y R I G H T © 2 0 2 5 A B S C I C O R P O R A T I O N . A L L R I G H T S R E S E R V E D .C P Y R I G H T © 2 0 2 5 A B S I C O R P O R A T I O N . A L L R I G H T S E S E R V E D . Generative AI Drug Creation™ D I F F E R E N T I A T E D P I P E L I N E A P R O V E N A I × B I O P L A T F O R M LEADING AI MODELS • De novo AI models now unlock first-in-class biology by cracking tough epitopes and difficult-to-drug disease targets PURPOSE BUILT TEAM • 10+ approved drugs by our scientists + AI talent from OpenAI, Google, Tesla, NVIDIA INTEGRATED DATA FLYWHEEL • 77,000+ ft² automated lab generating hundreds of millions of sequence-function datapoints since 2020 A B S - 2 0 1 (anti-prolactin receptor) • Androgenetic Alopecia (AGA): Accelerated Ph1/2a trial on track to initiate December 2025, with interim efficacy readout 2H2026 • Endometriosis (Endo): Indication expansion into endometriosis with anticipated Ph2 initiation in 4Q2026 with PoC readout as early as 2H2027 A B S - 1 0 1 (anti-TL1A) • Phase 1 interim results reported with extended half-life vs 1st gen TL1A competitors; ongoing partnership discussions. E A R L Y P I P E L I N E • Advancing early-stage oncology and I&I programs including ABS- 301, ABS-501,

4C O P Y R I G H T © 2 0 2 5 A B S C I C O R P O R A T I O N . A L L R I G H T S R E S E R V E D . Since 2020 Absci has been amassing high-quality data at scale for AI model training and validation DATA TO TRAIN Proprietary high throughput screening assays generate high- quality data for generative AI model training WET LAB TO VALIDATE 77,000 Sqft+ lab to validate AI-generated designs AI TO CREATE Advanced generative AI models create antibodies and next-gen biologics through de novo design and AI lead optimization 6 WEEK ‘LAB IN THE LOOP’ CYCLES CONTINUOUSLY IMPROVE AI MODELS