Slide 1: Corporate Presentation Summer 2024
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"
Slide 2: Disclaimers
C O P Y R I G H T © 2 0 2 4 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 . 2 Disclaimers Forward-Looking Statements Certain statements in this presentation that are not historical facts are considered forward-looking within the meaning of the Private Securities Litigation Refo
Slide 3: Absci is a Data-First Generative AI Drug Creation Company
C O P Y R I G H T © 2 0 2 4 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 . Absci is a Data-First Generative AI Drug Creation Company Our Integrated AI & Wet Lab Platform Aims to Engineer Better Biologics Faster • Ultra-Efficient Discovery • Best-in-Class Properties • Access Di
Slide 4: The Drug Discovery Paradigm is Ripe for Disruption
C O P Y R I G H T © 2 0 2 4 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 . 4 L O N G I T E R A T I V E P R O C E S S R E S U L T I N G I N D R U G C A N D I D A T E S W I T H S U B O P T I M A L A T T R I B U T E S L I M I T E D C O N T R O L O F A T T R I B U T E S O F T H E
Slide 5: Why Hasn't Generative AI Transformed Biologic Drug Discovery?
C O P Y R I G H T © 2 0 2 4 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 . 5 W H Y H A S N ’ T G E N E R A T I V E A I T R A N S F O R M E D B I O L O G I C D R U G D I S C O V E R Y ? Unlocking the Potential of Generative AI in Biology Requires Scalable Biological Data S M A
Slide 6: Absci is Solving the Problem of Scalable Biological Data
C O P Y R I G H T © 2 0 2 4 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 . T H E S O L U T I O N Absci’s E. coli SoluPro cell line generates billions of cells, expressing proteins of interest Absci’s ACE Assay™ technology generates data at >4,000x the throughput of traditional
Slide 7: Integrated Drug Creation Platform: Lab-in-a-Loop
7C O P Y R I G H T © 2 0 2 4 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 . A I T O C R E A T E Advanced generative AI models used to create antibodies and next-gen biologics through de novo design and optimization • De novo antibody creation is prompted with antigen structure
Slide 8: Integrated Drug Creation Platform to Engineer Optimal Drug Attributes
8C O P Y R I G H T © 2 0 2 4 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 . D A T A T O T R A I N G E N E R A T I V E A I M O D E L S W E T L A B T O V A L I D A T E D E S I R E D F U N C T I O N A N D P R O P E R T I E S A I T O C R E A T E N O V E L B I O T H E R A P E U T I
Slide 9: First to design and validate novel antibodies using zero-shot generative AI
C O P Y R I G H T © 2 0 2 4 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 . 9 Absci is the first to design and validate novel antibodies* using zero-shot generative AI Used artificial intelligence to simultaneously optimize multiple parameters important to drug discovery and de
Slide 10: Leveraging Generative AI to Access Novel Biology and Design Therapeutics
C O P Y R I G H T © 2 0 2 4 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 . 10 Leveraging Generative AI Capabilities to Access Novel Biology and Rapidly Design Therapeutics with Best-in-Class Properties . . D E N O V O A I F O U N D A T I O N M O D E L A I L E A D O P T I M I Z
Slide 11: Integrated Drug Creation Platform Leveraging AI End-to-End
C O P Y R I G H T © 2 0 2 4 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 . 11 Integrated Drug CreationTM Platform Leveraging AI Throughout the End-to-End Drug Discovery Process T A R G E T D I S C O V E R Y W I T H N O V E L A P P R O A C H E S Reverse Immunology for target di
Slide 12: Generative AI Drug Creation workflow
12C O P Y R I G H T © 2 0 2 4 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 . Generative AI Drug Creation™ workflow TARGET OF INTEREST De novo AI Pre-Clinical Development FUNCTION CONFIRMED CandidateLead OPTIMIZED FOR: Affinity, specificity, developability…. Absci works with it
Slide 13: Platform Enables Differentiated Biologics, Faster at Lower Cost
C O P Y R I G H T © 2 0 2 4 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 . 13 Platform Enables the Potential to Deliver Differentiated Biologics, Faster at Lower Cost V A L U E D R I V E R S ENABLING FIRST-IN-CLASS A C C E S S N O V E L D I S E A S E B I O L O G Y Ability to a
Slide 14: Internal Pipeline of Potential First-in-Class and Best-in-Class Assets
C O P Y R I G H T © 2 0 2 4 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 . 14 Internal Pipeline of Potential First-in-Class and Best-in-Class Assets P I P E L I N E H I G H L I G H T S POTENTIAL “BEST-IN-CLASS” POTENTIAL “FIRST-IN-CLASS” DERMATOLOGY / UNDISCLOSED INFL. BOWEL D
Slide 15: ABS-101 TL1A: Clinically Validated Mechanism in Large Underserved Market
C O P Y R I G H T © 2 0 2 4 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 . 15 Inflammation Fibrosis Clinically Validated Mechanism of Action in Large Underserved Market A B S - 1 0 1 T L 1 A D A T A H I G H L I G H T S T L 1 A : D R 3 S I G N A L I N G C L I N I C A L L Y S H
Slide 16: Potential Best-in-Class TL1A mAb Designed using Generative AI
C O P Y R I G H T © 2 0 2 4 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 . 16 Potential Best-in-Class TL1A mAb Designed using Generative AI A B S - 1 0 1 T L 1 A D A T A H I G H L I G H T S AI-designed TL1A program designed to achieve superior therapeutic properties over clini
Slide 17: AI Platform Designed Leads Span Diverse Epitopes
C O P Y R I G H T © 2 0 2 4 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 . 17 AI Platform Designed Leads Span Diverse Set of Epitopes Leading to IP Differentiation and Superior Preclinical Profile A B S - 1 0 1 T L 1 A D A T A H I G H L I G H T S * Epitope binning by BLI compe
Slide 18: Potential Best-in-Class TL1A mAb Designed using Generative AI
C O P Y R I G H T © 2 0 2 4 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 . 18 TL1A Target identified Function confirmed Multi-parametrically optimized Functionally validated D E N O V O A I A I L E A D - O P T I M I Z A T I O N Hits Lead Candidate Potential Best-in-Class TL1A
Slide 19: AI Platform Designed Advanced Leads with High Affinity and Superior Potency
C O P Y R I G H T © 2 0 2 4 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 . 19 A ve ra ge IC 50 ( nM ) AI Platform Designed Advanced Leads with High Affinity and Superior Potency A B S - 1 0 1 T L 1 A D A T A H I G H L I G H T S H I G H A F F I N I T Y m A B s W I T H P R E S E
Slide 20: AI Epitope Selection Enables High Affinity to TL1A Monomer and Trimer
C O P Y R I G H T © 2 0 2 4 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 . 20 AI Epitope Selection Enables High Affinity to Both the TL1A Monomer and Trimer E P I T O P E S E L E C T E D E N A B L E D H I G H A F F I N I T Y B I N D I N G T O B O T H T H E T L 1 A M O N O M E
Slide 21: Favorable in vitro Profile and PK for Longer Dosing Intervals
C O P Y R I G H T © 2 0 2 4 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 . 21 Favorable in vitro Profile and PK Profile for Longer Dosing Intervals Extended half-life in vitro compared to competitors# Increased recycling in in vitro FcRn Assay1 PK data in Tg32 mice show lead c
Slide 22: Extended Half-life in Non-Human Primates
C O P Y R I G H T © 2 0 2 4 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 . 22 A B S - 1 0 1 T L 1 A D A T A H I G H L I G H T S Extended half-life of 2-3-fold over clinical competitors to support Q8W-Q12W dosing interval. ABS-101 shows enhanced biodistribution in NHPs, compare
Slide 23: AI Platform Designed ABS-101 Aims for Optimal Therapeutic Profile
C O P Y R I G H T © 2 0 2 4 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 . 23 AI Platform Designed ABS-101 Aims for Optimal Therapeutic Profile A B S - 1 0 1 T L 1 A D A T A H I G H L I G H T S A T T R I B U T E A B S - 1 0 1 P R O G R A M * M E R C K ( P R O M E T H E U S ) M
Slide 24: Projected Timeline to Potential Best-in-Class Molecule
C O P Y R I G H T © 2 0 2 4 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 . 24 A B S - 1 0 1 T L 1 A D A T A H I G H L I G H T S Projected Timeline to Potential Best-in-Class Molecule AI-Designed Advanced Leads have Demonstrated: ü High Affinity ü High Potency ü Long Half-Life
Slide 25: Over $900M + Royalties of Deal Value in H2 2023
C O P Y R I G H T © 2 0 2 4 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 . 25 Over $900M + Royalties of Deal Value in H2 2023 R E C E N T P A R T N E R S H I P S “This collaboration is an exciting opportunity to utilize Absci's de novo AI antibody creation platform to design a
Slide 26: Driving Growth Through Industry-Leading Collaborations
C O P Y R I G H T © 2 0 2 4 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 . 26 P A R T N E R S H I P S A I D R U G D I S C O V E R Y C O L L A B O R A T I O N S I N T E R N A L A S S E T P I P E L I N E C O L L A B O R A T I O N S D A T A & C O M P U T E C O L L A B O R A T I O
Slide 27: Leadership Team of Innovators Across AI and Biotech
C O P Y R I G H T © 2 0 2 4 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 . 27 Leadership Team of Innovators Across AI and Biotech to Transform Drug Discovery W O R L D C L A S S T E A M Trademarks, service marks or trade names referred to herein are the intellectual property o
Slide 28: Absci's Talent and Infrastructure for Better Biologics Faster
C O P Y R I G H T © 2 0 2 4 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 . 28 >160 77,000+ Square Feet >$520M Unlimiters with deep experience in AI, drug discovery, immunology, and synthetic biology State-of-the-art drug creation and wet lab space in Vancouver WA, Absci AI Res
Slide 29: Integrated Drug Creation Platform Leveraging AI
C O P Y R I G H T © 2 0 2 4 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 . 29 Integrated Drug CreationTM Platform Leveraging AI Throughout the End-to-End Drug Discovery Process T A R G E T D I S C O V E R Y W I T H N O V E L A P P R O A C H E S Reverse Immunology for target di
Slide 30: de novo Designed Antibodies
C O P Y R I G H T © 2 0 2 4 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 . 30 de novo Designed Antibodies de novo antibody design using generative AI T A R G E T D I S C O V E R Y W I T H N O V E L A P P R O A C H E S Reverse Immunology for target discovery A I - G U I D E D L
Slide 31: Generative AI Drug Creation Workflow
31C O P Y R I G H T © 2 0 2 4 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 . Generative AI Drug Creation™ Workflow TARGET OF INTEREST De novo AI Pre-Clinical Development FUNCTION CONFIRMED CandidateLead OPTIMIZED FOR: Affinity, specificity, developability, etc. Absci works wit
Slide 32: De novo drug creation with zero-shot generative AI
C O P Y R I G H T © 2 0 2 4 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 . 32 Antibody scaffold sequence De novo antibody designs Wet lab assays ACE Assay™ data SPR assay data Target antigen structure Validated de novo binders Target epitope Antibody scaffold sequence De novo
Slide 33: Example: de novo design of HER2 antibodies
C O P Y R I G H T © 2 0 2 4 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 . 33 Example: de novo design of HER2 antibodies Demonstration of ‘zero shot’ model by designing HCDR3 and HCDR123 for HER2 Assessed multiple parameters: • Binding rates • Sequence diversity • Immunogenici
Slide 34: AI Generated Diverse, Novel & High Affinity Binders
C O P Y R I G H T © 2 0 2 4 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 . 34 AI Generated Diverse, Novel & High Affinity Binders that Outperforms Biological Baseline D E N O V O D E S I G N O F H E R 2 A N T I B O D I E S SIZE OF SEARCH SPACE: MILLIONS BILLIONS TRILLIONS QUAD
Slide 35: Global Epitope Landscaping and Local Interface Evolution
35C O P Y R I G H T © 2 0 2 4 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 . G L O B A L E P I T O P E L A N D S C A P I N G L O C A L I N T E R F A C E E V O L U T I O N Epitope landscaping and interface evolution can be used to improve affinity, potency and to potentially un
Slide 36: AI-Guided Lead Optimization
C O P Y R I G H T © 2 0 2 4 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 . 36 AI-Guided Lead Optimization From de novo design to multiparametric lead optimization using AI T A R G E T D I S C O V E R Y W I T H N O V E L A P P R O A C H E S Reverse Immunology for target discove
Slide 37: Generative AI Drug Creation Workflow
37C O P Y R I G H T © 2 0 2 4 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 . Generative AI Drug Creation™ Workflow TARGET OF INTEREST De novo AI Pre-Clinical Development FUNCTION CONFIRMED CandidateLead OPTIMIZED FOR: Affinity, specificity, developability, etc. Absci works wit
Slide 38: Re-engineer clinically approved antibody for three SARS-CoV-2 variants
C O P Y R I G H T © 2 0 2 4 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 . 38 Re-engineer clinically approved antibody for binding towards three SARS-CoV-2 variants Improve binding towards beta without loss of binding towards alpha and delta alpha N501Y N501Y beta L452R E484QE
Slide 39: Model training hold-out data sets demonstrate strong performance
C O P Y R I G H T © 2 0 2 4 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 . Model training Hold out data sets demonstrate strong model performance following training with AI-predicted affinity correlating well with experimental measurements >75k ACE Assay™ data points per train
Slide 40: SPR measurements
C O P Y R I G H T © 2 0 2 4 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 . 40 SPR measurements 0.10.1 0.1 3 Binders predicted to have the best binding towards all three SARS-CoV-2 variants are assessed in the lab by SPR 79% (31/39) of evaluated predictions exhibit higher bindi
Slide 41: AI co-optimized binding to multiple SARS-CoV-2 variants
C O P Y R I G H T © 2 0 2 4 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 . 41 SPR KD A C E A ss ay Sc or e™ Large quality data sets Model training Model predictions SPR validation Predicted 1 Pr ed ic te d 2 Fab nM KD (fold improvement) alpha RBD beta RBD delta RBD Parental an
Slide 42: De novo design & AI-guided lead optimization for improved functionalities
42C O P Y R I G H T © 2 0 2 4 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 . Half-life extension Epitope selection DE NOVO DESIGN & AI-GUIDED LEAD OPTIMIZATION FOR IMPROVED THERAPEUTIC FUNCTIONALITIES • Extend half-life through augmenting Fc-mediated recycling • Reduces dosing
Slide 43: Target Discovery: Reverse Immunology
C O P Y R I G H T © 2 0 2 4 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 . 43 Target Discovery Reverse Immunology platform unifies target and antibody discovery in a single workflow enabling potential “first-in-class” biotherapeutics T A R G E T D I S C O V E R Y W I T H N O V
Slide 44: Reverse Immunology: Target and Antibody Discovery Simultaneously
C O P Y R I G H T © 2 0 2 4 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 . 44 Reverse Immunology: Target and Antibody Discovery Simultaneously T A R G E T D I S C O V E R Y Pre-Clinical Development Affinity, specificity MoA ASSAYS INDICATION OF INTEREST DRUG CANDIDATE FUNCTION
Slide 45: Tertiary lymphoid structures and clinical outcomes
C O P Y R I G H T © 2 0 2 4 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 . The presence of TLS is associated with longer progression-free survival and better response to immune checkpoint inhibitors [2,3]. • Rapidly growing evidence illustrates correlation between TLS- derived
Slide 46: Computationally reconstructed antibodies from human TLS biopsies
C O P Y R I G H T © 2 0 2 4 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 . 46 Computationally reconstructed antibodies from human TLS biopsies High-throughput proteomics screening technology covering the human proteome close to completeness A B S - 3 0 1 : R E C O N S T R U C
Slide 47: ABS-301 blocks a novel immunosuppressive target in human cells
C O P Y R I G H T © 2 0 2 4 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 . 47 ABS-301 blocks a novel immunosuppressive target in human cells ABS-301: Patient-derived Antibody Blocks a Novel Immunosuppressive Target T A R G E T D I S C O V E R Y : A B S - 3 0 1 Hypothesis: Tumo
Slide 48: ABS-301 has Broad Potential in Immuno-oncology
C O P Y R I G H T © 2 0 2 4 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 . 48 ABS-301 has Broad Potential in Immuno-oncology T A R G E T D I S C O V E R Y : A B S - 3 0 1 1. Siegel et al, CA, 2023, 73 (1), 17-48 2. Evaluate Pharma 3. Baxter et al, Br J Cancer 125, 1068–1079 (2
Slide 49: This revolution is only just beginning.
This revolution is only just beginning. 49ABSCI CORPORATION 2024 ALL RIGHTS RESERVED