Recursion Pharmaceuticals, Inc. · NASDAQ:RXRX
Recursion Pharmaceuticals — Investor Day (January 2023)
143 slides from Recursion Pharmaceuticals's investor day presentation, Jan 25, 2023
Slide 1: Recursion Download Day
Slide 2: Agenda
Breakfast (8:30 – 9:30 AM) Welcome Tina Larson, President & COO R. Martin Chavez PhD, Chairman State of Recursion Chris Gibson PhD, Co-Founder & CEO Recursion OS Imran Haque PhD, VP of Data Science Lina Nilsson PhD, VP of Product Pre-Clinical Opportunities Laura Schaevitz PhD, SVP and Head of Resear
Slide 3: Welcome Remarks
Welcome Remarks Tina M. Larson President and COO of Recursion Download Day 2023
Slide 4: Welcome Remarks
Welcome Remarks R. Martin Chavez PhD Chairperson of Recursion Download Day 2023
Slide 5: State of Recursion
Download Day 2023 State of Recursion Chris Gibson PhD Co-Founder / CEO
Slide 6: Forward-looking statements
This presentation and any accompanying discussion and documents contain information that includes or is based upon "forward-looking statements" within the meaning of the Securities Litigation Reform Act of 1995. These forward-looking statements are based on our current expectations, estimates and pr
Slide 7: Eroom's Law: drug discovery slower and more expensive
7 0.1 1 10 20201962 1970 1980 1990 2000 2010 NMEs per $B spent (inflation adjusted) Eroom’s Law: Drug discovery is becoming slower and more expensive over time Recursion Founded Adapted from Scannell et al and Our World in Data
Slide 8: Moore's Law vs Eroom's Law
8 0.1 1 10 50B 100M 500K 1K 20201962 1970 1980 1990 2000 2010 Compute Power (Transistors per Microprocessor)NMEs per $B spent (inflation adjusted) Moore’s Law: Computing power becomes faster and less expensive over time Eroom’s Law: Drug discovery is becoming slower and more expensive over time Adap
Slide 9: Moore's Law vs Eroom's Law: Opportunity
9Adapted from Scannell et al and Our World in Data 0.1 1 10 50B 100M 500K 1K 20201962 1970 1980 1990 2000 2010 Compute Power (Transistors per Microprocessor)NMEs per $B spent (inflation adjusted) Moore’s Law: Computing power becomes faster and less expensive over time Eroom’s Law: Drug discovery is
Slide 10: Hypothesis 1
10 Hypothesis 1: In biology, structure suits function; by applying sophisticated analysis techniques to images of human cells, a new scale of biological insight can be unlocked
Slide 11: Hypothesis 2
11 Hypothesis 2: By industrializing a small number of extraordinarily data-rich assays using automation and computation, biology and chemistry can be mapped and navigated, turning drug discovery into an efficient search problem
Slide 12: Machine Learning and Automation
Machine Learning and Automation 12
Slide 13: Machine Learning and Automation
Machine Learning and Automation 13
Slide 14: Traditional versus ideal discovery pipeline
Traditional discovery pipeline Ideal discovery pipeline Broaden the funnel of potential target hypotheses & therapeutic starting points Identify failures earlier in the research cycle when they are relatively inexpensive, to rapidly narrow the neck of the funnel Accelerate delivery of high- potentia
Slide 15: Failing faster, spending less, going faster
Preliminary data shown is the average of all our programs since late 2017. All industry data adapted from Paul, et al. Nature Reviews Drug Discovery. (2010) 9, 203–214 Screen — Hit ID — Validated Lead — Advanced Candidate — Development Candidate — Industry Recursion Failing faster and earlier to › ›
Slide 16: 2022 highlights
Initiated 5 clinical trials in 2022 (3 Ph2, 2 Ph1) • Includes Ph1 FAP study completed by Recursion Novel oncology programs (Target Alpha, Target Gamma) nearing IND-enabling studies Advancing collaborations in Fibrosis (Bayer) and Neuroscience (Roche-Genentech) • $13B in potential milestones across 5
Slide 17: Recursion leads the rise of AI-enabled drug discovery
Recursion leads the rise of Al-enabled drug discovery TOP TECH ENABLED DRUG DISCOVERY (TEDD) COMPANIES: FROST & SULLIVAN ANALYSIS Mature internal pipeline, large strategic partnerships, advanced computational resources Abcellera @ @ Recursion @exscientia Schrodinger @ @ Relay Therapeutics @ Valo Hea
Slide 18: Strong financials and upcoming milestones
Strong Financials ~$550M in cash and cash equivalents at the end of 2022 with potential for increased revenue in the near term Pipeline • Guidance on top-line readout for Ph2 CCM program • Guidance on interim Ph2 safety readout for NF2 program • Guidance on Ph1 C diff readout • Trial update on Ph2 F
Slide 19: Our Mission: Decode Biology to Radically Improve Lives
Our Mission: Decode Biology to Radically Improve Lives
Slide 20: Impact
Impact
Slide 21: RecursionOS
RecursionOS® Lina Nilsson PhD Vice President, Product Download Day 2023 Imran Haque PhD Vice President, Data Science
Slide 22: Platform-driven versus literature-driven discovery
Platforms drive discovery. Unbiased & target agnostic Literature drives discovery. Informs target-based hypotheses Data are our fuel. Shape our hypotheses Data are an exhaust. Limited to testing hypotheses Virtuous cycles of atoms & bits. Iterative feedback accelerates learning Linear process. Littl
Slide 23: Machine Learning and Automation
Machine Learning and Automation 23
Slide 24: Biological, Automation and Computational Tools
Biological Tools Automation Tools Computational Tools 24
Slide 25: Biological Tools
25 Proprietary high-dimensional data Biological Tools >500 Billion High-quality neurons produced in-house in 2022 using completely novel techniques. Model and manipulate disease biology
Slide 26: Automation Tools
26 Automation Tools >19PB Proprietary high-dimensional data Create scalable, repeatable and reliable laboratory processes 2.2 Million Wet-lab experiments per week Up to
Slide 27: Computational Tools
Computational Tools Extract, organize and analyze highly structured data >21 Petabytes Proprietary high-dimensional data
Slide 28: Omics levels and phenomics
28Image adapted from D’Orazio, M., et al. Nature Scientific Reports 2022. RNA Level Transcriptomics DNA Level (Population-Scale) Genomics Protein Level Proteomics Metabolates Level Metabolomics Organism Level Invivomics Cell Level Phenotypes Phenomics Built and scaled AspirationalExploratory
Slide 29: Maps of Biology & Chemistry
Maps of Biology & Chemistry Imran Haque Vice President, Data Science Download Day 2023
Slide 30: Breast cancer map
Breast Cancer @ croatrser @ zexH9 ton § YY 751 @ y aon @ y svt @ k Loxos @ | teouvns SROAPI ? @ an sci @ axis @ ForR 30
Slide 31: Breast cancer map
ano | Breast Cancer © crommier @ 2x49 swarcer @ vor @ 31
Slide 32: Breast cancer map
weowns @ 4 2 am —@ toreR2 — © Breast Cancer ney ca SReAp, org 32
Slide 33: 33
33
Slide 34: 34
34
Slide 35: Traditional target-based screens
35 Traditional target-based screens A single target 1 million compounds
Slide 36: The entire genome
36 1 million compounds The entire genome
Slide 37: Machine Learning and Automation
Machine Learning and Automation 37
Slide 38: Modeling disease and detecting changes with ML
Model diseases with diverse biological and chemical tools Detect and analyze subtle changes using ML algorithms Combine datasets to reveal known & novel relationships in our Maps of Biology Capture holistic and high-dimensional snapshots of cellular states 38
Slide 39: Multiple high-dimensional datasets validate disease model
Multiple high-dimensional datasets validate and expand the total biological understanding of the disease model and hits 39
Slide 40: Relationships in maps become hits
40 Relationships revealed in our maps become ‘hits’ for potential programs 1 Up to Transcriptome profiles every week Transcriptomic assays validate a hypothesis with additional high-dimensional, unbiased data 2 Detects more relationships between disease-relevant genes and each compound 3 Disease com
Slide 41: Digital animal studies
Digital animal studies build high- dimensional signatures of animal behavior and health 41
Slide 42: Traditional vs Digital Animal Studies
42 Traditional Animal Studies Recursion’s Digital Animal Studies
Slide 43: Traditional vs Digital Animal Studies
an im al Gr ou p 1 Gr ou p 2 Gr ou p 3 Time 43 • Limited data generation • Low-dimensional assays • Influenced by human intervention • Time-consuming • Expensive Traditional Animal Studies Recursion’s Digital Animal Studies • Continuous data generation • High-dimensional assays • Unbiased • Faster •
Slide 44: Digital tolerability timeline
44 ~2 months Real-time <1 week 1 year 1 week 6-8 weeks Recursion Disease Induction Liability InVivomics Digital Tolerability
Slide 45: Industrialized Optimization
Industrialized Optimization Candidate Evaluation Predictive DMPK Automated Microsynthesis 45
Slide 46: Improving efficiency of the DMTA cycle
46 Our approach will improve the efficiency of the DMTA chemistry cycle, reducing the number of cycles, shrinking the time required, and increasing throughput for each cycle. The Impact: Reduce time to candidate selection from months to weeks Make Test Design Analyze Automated Microsynthesis Automat
Slide 47: Digital Chemistry Platform: Design
47 Digital Chemistry Platform Design Multi-objective generative chemistry MOGFNs outperform other benchmarked algorithms in numerous multi-objective settings in chemistry. rxrx.ai/neurips-2022 Multi-Objective GFlowNets
Slide 48: Foundation models for low-data prediction
48 Foundation models for low-data prediction MolE achieves #1 or #2 performance on 14 of 22 Therapeutics Data Commons ADMET tasks, including all distribution and metabolism tasks, and #1 in 9 of 22. rxrx.ai/neurips-2022 Analyze Digital Chemistry Platform MolE: a molecular foundation model for drug d
Slide 49: Automated DMPK Testing Facility
49 Test Automated DMPK Testing Facility Automated DMPK Testing Recursion proprietary DMPK module designed to test up to 500 compounds / week on three critical DMPK assays, to drive programs and fuel machine learning.
Slide 50: Automated Microsynthesis
50 Automated Microsynthesis MakeRobotic Synthesis Automation of chemical synthesis will enable broader SAR and faster turnaround time for active learning cycles.
Slide 51: Scalable Reliable Relatable
Scalable Reliable Relatable 51
Slide 52: Pre-clinical Opportunities
Pre-clinical Opportunities Laura Schaevitz PhD Senior Vice President, Head of Research Download Day 2023
Slide 53: Recursion OS enables differentiated capacity to interrogate
The Recursion OS enables a differentiated capacity to interrogate... +<——————— Human Genes + Human Genes 53
Slide 54: Challenging biology and complex datasets
… Challenging biology Patient genetics Complex genetic screens … Complex datasets Undruggable targets Recovery of function 54
Slide 55: Target Alpha
Target Alpha: Potential first-in-class NCE with novel MOA to enhance anti-PD-(L)1 response
Slide 56: Target Alpha: immunotherapy need and goal
1. Cancer.gov 2. Haslam, A.; et al. JAMA Netw Open. 2019, 2, e192535. 2. Valentin,J.; et al. Journal of Oncology, Volume 2021, Article ID 5524685. 3. Ghisoni,E.; et al. European Journal of Cancer 149, 2021, 153; 4. Evaluate Pharma 1.9M US patients diagnosed with cancer in 20221 Recursion’s Goal Pre-
Slide 57: Target Alpha: dual-targeting checkpoint modifier identified
1 Manguso et al., 2017, Lawson et al., 2020 Evaluation of 110 sensitization and resistance markers from public pooled CRISPR screens1 in the Recursion Map Identification of novel dual-targeting checkpoint modifier Pre-clinical: Target α BIRC2 BIRC2 family Gene A Gene A inhibitor (250 nM) Gene A Gene
Slide 58: Target Alpha: tumor clearance
Potentiation of immunotherapy Immunological memory Pre-clinical: Target α In vivo response: tumor clearance1.9M US patients diagnosed with cancer in 20221 High proportion of treatment-limiting IRAE (Ex: 46%-melanoma3) No response in 88% of patients 44% eligible for checkpoint immunotherapy2 (2022 es
Slide 59: Target Alpha: immune cell response
Pre-clinical: Target α Total CD45+ M2 Macrophages LAG3+ CD8 In vivo response: tumor clearance1.9M US patients diagnosed with cancer in 20221 High proportion of treatment-limiting IRAE (Ex: 46%-melanoma3) No response in 88% of patients 44% eligible for checkpoint immunotherapy2 (2022 est. spend: $48
Slide 60: Target Alpha: cytokine response
Pre-clinical: Target α IFN-ɣCXCL10 In vivo response: cytokine 1.9M US patients diagnosed with cancer in 20221 High proportion of treatment-limiting IRAE (Ex: 46%-melanoma3) No response in 88% of patients 44% eligible for checkpoint immunotherapy2 (2022 est. spend: $48 Billion4) 601. Cancer.gov 2. Ha
Slide 61: Target Alpha: cytokine response
1. Cancer.gov 2. Haslam, A.; et al. JAMA Netw Open. 2019, 2, e192535. 2. Valentin,J.; et al. Journal of Oncology, Volume 2021, Article ID 5524685. 3. Ghisoni,E.; et al. European Journal of Cancer 149, 2021, 153; 4. Evaluate Pharma Pre-clinical: Target α IFN-ɣCXCL10 In vivo response: cytokine 1.9M US
Slide 62: Target Alpha: SAR and phenotype
Medicinal chemistry efforts deployed to improve potency1 Cellular and biochemical assays show clear SAR2 Phenotype maintained as NCE progress3 Pre-clinical: Target α Core 1 CR O -b as ed u ni va ria te re ad ou ts Target Phenotype Compound 1B Compound 1C Compound 1A Compound 1A Compound 1B Compound
Slide 63: Target Alpha: Core 2 cellular activity
Core 2Core 1 Dramatic improvement in cellular activity could easily redirect chemistry efforts Pre-clinical: Target α CR O -b as ed u ni va ria te re ad ou ts Compound 1A Compound 1A Compound 1B Compound 1B Compound 1C Compound 1C Target Phenotype Compound 1B Compound 1C Compound 1A Compound 2B Comp
Slide 64: Target Alpha: divergent phenotype
Core 2Core 1 Dramatic improvement in cellular activity could easily redirect chemistry efforts Map-detected a divergent phenotype Pre-clinical: Target α CR O -b as ed u ni va ria te re ad ou ts Compound 1A Compound 1B Compound 1C Compound 2A Compound 2B Target Phenotype Compound 1B Compound 1C Compo
Slide 65: Target Alpha: CDK9 annotation
Compound 2A Compound 2B Target Phenotype Compound 1B Compound 1C Compound 1A Despite activity in target and cellular assays, the compound series generated a clearly separate phenotype 1 Synthesis efforts immediately realigned on original series core2 New series annotated as CDK9 inhibitor by map inf
Slide 66: Target Alpha: dual targeting compound
Pre-clinical: Target α 66 Unbiased discovery of an exciting dual targeting compound that appears to both enhance anti-PD1 response, while also decreasing peripheral inflammation 1 Recursion OS augmented our medicinal chemistry team enabling efficient optimization efforts on a molecule with essential
Slide 67: Target Gamma
Target Gamma: Novel CDK12-adjacent target, RBM39, for potentially treating HRD-negative ovarian cancer
Slide 68: Target Gamma: PARP in ovarian cancer
Platinum-Sensitive Ovarian Cancer Patients HRD BRCAMUT BRCAWT mPFS (PARP vs. Placebo): 22 mo (HR, 0.40; 95% CI, 0.27-0.62) 20 mo (HR, 0.50; 95% CI, 0.31-0.83) 50% HRP 8 mo (HR, 0.68; 95% CI, 0.49-0.94) 50% 65%35% NCT02655016, N=733 patients with newly diagnosed, advanced ovarian cancer who responded
Slide 69: Target Gamma: RBM39 and CDK12
• CDK12 has been advanced as a target to improve response in the HR-proficient setting • Selective inhibition of CDK12 over other CDKs, especially CDK13, is very challenging • Inhibition of target RBM39 (for example, with REC-65029) may mimic inhibition of CDK12 while mitigating toxicity due to CDK1
Slide 70: Target Gamma: PDX efficacy
Vehicle Olaparib REC-65029 REC-65029 +olaparib Increase in rate to CR, durability in combinationTumor volume Pre-clinical: Target γ Vehicle Olaparib REC-65029 REC-65029 +olaparib OV0273 PDX – REC-65029 dosed at 85 mg/kg PO, BID, olalparib dosed at 90mg/kg PO QD; ** p<0.01 **** p<0.0001 relative to v
Slide 71: Target Gamma: tolerability
Pre-clinical: Target γ REC-0065029 is tolerated at an efficacious dose 1 Digital tolerability uncovers safety concern for REC- 1170204 at an efficacious dose 2 REC-1321245 demonstrates improved tolerability at efficacious doses 3 71
Slide 72: Pre-clinical next steps
72 Target Alpha and Gamma reaching IND-enabling studies in 2023 Continuing to augment our digital chemistry and predictive capabilities (property assessment, DMPK, ADMET, etc.) Continuing to drive potential first-in-disease or first-in-class programs at greater automation and scale Pre-clinica
Slide 73: RxRx3 Dataset & MolRec Application
RxRx3 Dataset & MolRec Application Ben Mabey Chief Technology Officer Download Day 2023
Slide 74: RxRx3: Phenomics Map of Biology
RxRx3: Phenomics Map of Biology • Spans CRISPR knockouts of most of the human genome, ~17k genes • 1,600 FDA approved and commercially available bioactive compounds at 8 concentrations and tens of thousands of control images • 2.2 million images and deep learning embeddings of HUVEC cells, over 100T
Slide 75: Compound-specific data in MolRec
75 Compound-specific data viewable in MolRec ™ ADMET & More >250K Transcriptomics Experiments InVivomics Video Data Phenomics Data Spanning 175 million Experiments and 48 Human Cell Types RxRx3
Slide 76: MolRec overview
MolRec™ is a simplified version of one of Recursion’s internal compound intelligence tools • A demo/freemium app to illustrate what can be done with this data. This is not our flagship internal Map App. • We are providing this tool for basic exploration of compound/compound and compound/gene relatio
Slide 77: Blinded genes for sneak peek
The majority of the genes (~16k) are anonymized / blinded to facilitate a "sneak peek" 77
Slide 78: RxRx3: Transformational for the ML field
RxRx3: Transformational for the ML field Recursion Data Universe, >21 PB ADMET & More >250K Transcriptomics Experiments InVivomics Video Data Phenomics Data Spanning 175 million Experiments and 48 Human Cell Types <1% 10 GB-~1TB > Bio/Chem Phenomic Maps JUMPCP Autonomous Driving ‘Waymo Open Dataset
Slide 79: Goals of the RxRx3 release
• Offer a glimpse of the power of Recursion’s internal data and tools to pique the interest of potential partners • Provide the largest dataset of its kind to date to enrich the field and foster the next generation of computational biologists • Discover new methods and bright talent that we can brin
Slide 80: Clinical Programs
Clinical Programs Shafique Virani MD Chief Business Officer & Interim Chief Medical Officer Download Day 2023
Slide 81: Partnership and pipeline strategy
Partnership strategy Discovery Partnerships Partner in complex therapeutic areas requiring large financial commitment and competitive market dynamics Leverage partner knowledge and clinical development capabilities 81 Fibrosis Other large, intractable areas of biology Neuroscience *and a single onco
Slide 82: Pipeline by therapeutic area and indication
PreclinicalLate Discovery Oncology Rare & Other All populations defined above are US and EU5 incidence unless otherwise noted. EU5 is defined as France, Germany, Italy, Spain and UK. (1) Our program has the potential to address a number of indications driven by MYC alterations, totalling 54,000 pati
Slide 83: REC-994 for Cerebral Cavernous Malformations
REC-994 for the Treatment of Symptomatic Cerebral Cavernous Malformations (CCM) Target / MOA Superoxide Scavenger Molecule Type Small Molecule Lead Indication(s) Cerebral Cavernous Malformations Status Phase 2 Designation(s) US & EU Orphan Drug Source of Insight Recursion OS
Slide 84: CCM: unmet need
84 • Large unmet need for a novel nonsurgical treatment • Vascular malformations (cavernomas) in the brain and spinal cord • High-risk for hemorrhage creates “ticking time bomb” • Progressive increase in CCM size and number over time in those with familial disease • Debilitating symptoms, including
Slide 85: CCM: orphan indication prevalence
85 Non-oncology Orphan Indication Product U.S. + EU5 Prevalence Cerebral cavernous malformation (CCM) REC-994 (Recursion) >1,800,000 (Symptomatic: ~360,000) Idiopathic pulmonary fibrosis (IPF) Esbriet (pirfenidone) >160,000 Cystic fibrosis (CF) VX-669/ VX-445 + Tezacaftor + Ivacaftor - Vertex >55,00
Slide 86: CCM: patient population
86 Source: Angioma Alliance ; Flemming KD, et al . Population-Based Prevalence of Cerebral Cavernous Malformations in Older Adults: Mayo Clinic Study of Aging. JAMA Neurol. 2017 Jul 1;74(7):801-805. doi: 10.1001/jamaneurol.2017.0439. PMID: 28492932; PMCID: PMC5647645 ; Spiegler S, et al Cerebral Cav
Slide 87: CCM: novel therapeutic approach
87 • Symptoms associated with both increased size of lesions, but also inflammation or activation of lesions within the immunopriviledged environment of the brain • Lesions arise from the capillary bed and are not high-pressure (e.g. the lesion growth is unlikely to be primarily driven by the law of
Slide 88: CCM
Clinical: CCM Storkebaum, et al. Cerebrovascular disorders: molecular insights and therapeutic opportunities. Nature Neuroscience, 2011 88
Slide 89: CCM: repurposed drug identification
Clinical: CCM Gibson, et al. Strategy for identifying repurposed drugs for the treatment of cerebral cavernous malformation. Circulation, 2015 89
Slide 90: CCM: siCCM2 cell images
Clinical: CCM siCTRL siCCM2 Gibson, et al. Strategy for identifying repurposed drugs for the treatment of cerebral cavernous malformation. Circulation, 2015 90
Slide 91: CCM: image-based rescue
Clinical: CCM Gibson, et al. Strategy for identifying repurposed drugs for the treatment of cerebral cavernous malformation. Circulation, 2015 siCTRL siCCM2 siCCM2 + Simvastatin siCCM2 + Cholecalciferol siCCM2 + REC-994 To the human eye, Simvastatin looks like the only potential rescue in this panel
Slide 92: CCM: preclinical studies
92 Source:: Data above from Gibson, et al. Strategy for identifying repurposed drugs for the treatment of cerebral cavernous malformation. Circulation, 2015 or Recursion internal data (Ccm1 mouse model) Preclinical Studies: REC-994 reduces lesion burden and ameliorates vascular defects in genetic mo
Slide 93: CCM: REC-994 mechanism
Healthy REC-994 ImpactCCM Clinical: CCM • Endothelial cell activation • Smooth muscle proliferation • Leukocyte adhesion • Platelet aggregation By regulating SOD2, CCM1 (KRIT1) & CCM2 suppress: CCM1 or CCM2 loss of function leads to activated endothelium: • Decreased cell-cell junctional integrity a
Slide 94: REC-994 Phase 1 safety
REC-994 Phase 1 Studies - well-tolerated with no dose-dependent adverse events in SAD and MAD Clinical: CCM MAD Study Placebo 50 mg 200 mg 400 mg 800 mg Total Number of TEAEs Total Subjects with ≥ one TEAE 5 4 0 0 10 3 4 3 15 4 Severity Mild Moderate Severe 3 1 0 0 0 0 3 0 0 3 0 0 3 1 0 Relationship
Slide 95: CCM Phase 2 trial design
95 Phase 2 trial initiated in Q1 2022 Source: https://www.clinicaltrials.gov/ct2/show/NCT05130866?term=recursion&draw=2&rank=3; https://www.SycamoreCCM.com/ Screening & Randomization 1:1:1 Treatment Follow-up Enroll 60 400mg 200mg Placebo 12 Months Treatment Period Visits: Days 1 & 2 Months 1, 3, 6,
Slide 96: REC-2282 for NF2 Mutated Meningiomas
REC-2282 for the Treatment of Progressive Neurofibromatosis Type 2 (NF2) Mutated Meningiomas Target / MOA HDAC Inhibitor Molecule Type Small Molecule Lead Indication(s) NF2 Mutated Meningiomas Status Phase 2/3 Designation(s) Fast Track; US and EU Orphan Drug Source of Insight Recursion OS
Slide 97: NF2: patient population and no approved therapy
97 Source: https://rarediseases.org/rare-diseases/neurofibromatosis-2 Patient Population – Large and Diagnosable No Approved Medical Therapy • Rare autosomal dominant tumor syndrome resulting from biallelic inactivation of the NF2 gene which leads to deficiencies in the tumor suppressor protein merl
Slide 98: NF2 meningioma patient numbers
98 • Threatens mortality; if amenable, surgical excision is primary intervention • Many patients have multiple meningiomas that exhibit heterogenous behavior and asynchronous growth • Stasis or shrinkage of tumor could improve prognosis Clinical: NF2 ● Most tumors are benign and slow growing but loc
Slide 99: REC-2282 rescue of NF2 knockdown cells
99 NF2 knockdown cells Healthy Cells REC-2282 REC-2282 identified as rescuing HUVEC cells treated with NF2 Co nt ro l N F2 si RN A HUVEC, human umbilical vein endothelial cells; NF2, neurofibromatosis type 2; siRNA, small interfering RNA. Clinical: NF2 99
Slide 100: NF2 and mTOR signaling mechanism
100 AKT, protein kinase B; eIF4F, eukaryotic initiation factor 4F; HDAC, histone deacetylase; mTor, mammalian target of rapamycin; mTORC1; mammalian target of rapamycin complex 1; NF2, neurofibromatosis type 2; PI3K, phosphoinositide 3-kinase; PP1, protein phosphate 1; Ras, reticular activating syst
Slide 101: REC-2282 in vivo efficacy
101 REC-2282 preclinical studies demonstrated clear in-vivo efficacy in multiple NF2 tumor types Shrinks vestibular schwannoma xenografts in nude mice Prevents growth & regrowth of NF2- deficient meningioma model in mice Vehicle % Change tumor vol. REC-2282 % Change tumor vol. % c ha ng e in tu m or
Slide 102: REC-2282 clinical safety and PFS
• Evaluable Patients: CNS Solid Tumors: NF2 N=5; Non-CNS Solid Tumors: N=10 • PFS: CNS solid tumors = 9.1 months; Non-CNS solid tumors = 1.7 months • Best overall response = SD in 8/15 patients (53%; 95% CI 26.6–78.7) • Longest duration of follow-up without progression: > 27 months (N=1) • Most comm
Slide 103: REC-2282 first-in-class HDAC inhibitor
103 1Sborov DW, et al. A phase 1 trial of the HDAC inhibitor AR-42 in patients with multiple myeloma and T- and B-cell lymphomas. Leuk Lymphoma. 2017 Oct;58(10):2310-2318. 2Collier KA, et al. A phase 1 trial of the histone deacetylase inhibitor AR-42 in patients with neurofibromatosis type 2-associa
Slide 104: NF2 Phase 2/3 trial design
Phase 2/3 trial initiated in Q2 2022 Outcome Measures Enrollment Criteria • MRI-confirmed progressive meningioma • Either of the below • Sporadic meningioma with confirmed NF2 mutation • Confirmed diagnosis of NF2 disease • Primary: Safety and tolerability • Progression-free survival • Time to progr
Slide 105: REC-4881 for FAP
REC-4881 for the Treatment of Familial Adenomatous Polyposis (FAP) Target / MOA MEK Inhibitor Molecule Type Small Molecule Lead Indication(s) Familial Adenomatous Polyposis Status Phase 2 Designation(s) Fast Track; US and EU Orphan Drug Source of Insight Recursion OS
Slide 106: FAP patient population
106 Patient Population – Easily Identifiable Clinical: FAP ~50,000 Diagnosed US + EU5 patients • Autosomal dominant tumor predisposition syndrome caused by a mutation in the APC gene • Classic FAP (germline mutation) : • Hundreds to thousands of polyps in colon and upper GI tract • Extraintestinal m
Slide 107: FAP: no approved medical therapy
107 No Approved Medical Therapy • Standard of care: colectomy during adolescence (with or without removal of rectum) • Post-colectomy, patients still at significant risk of polyps progressing to GI cancer • Significant decrease in quality-of-life post-colectomy: continued endoscopies and surgical in
Slide 108: REC-4881 rescues APC knockdown cells
108 REC-4881 rescued phenotypic defects of cells with APC knockdown 0.1 µM REC-4881 • Compared to thousands of other molecules tested, REC-4881 rescued phenotypic defects substantially better (including better rescue than other MEK inhibitors) for APC specific knockdown • Findings validated in tumor
Slide 109: REC-4881 mechanism
109 Goitre et al., PLoS ONE, 2010. 3 3 REC-4481 inhibits MEK 1/2 and recovers the destabilization of RAS by the β-Catenin destruction complex, restoring the cell back to a Wnt-off like state 2 1 Orally Bioavailable, Small Molecule MEK Inhibitor Disease State REC-4881 Impact Clinical: FAP 109
Slide 110: REC-4881 in vivo efficacy
110 APC, adenomatosis polyposis coli; ERK, extracellular signal-regulated kinase; FAP, familial adenomatous polyposis. Clinical: FAP ↓ High-Grade Dysplasia 2• In-vivo efficacy in APCmin mouse model • Apcmin = FAP disease model • Mice treated once daily for 8 weeks After 8 weeks of treatment: ↓ Polyp
Slide 111: REC-4881 Phase 1 healthy volunteer results
111 Note: AE, adverse event; MEK, mitogen-activated protein kinase; NHV, normal healthy volunteer; pERK, phosphorylated extracellular signal-regulated kinase; SAE, serious adverse event. REC-4881-101: Single-center, double-blind, placebo- controlled, dose-escalation study in healthy volunteers • Gro
Slide 112: FAP Phase 2 trial design and update
112 Clinical: FAP Phase 2 trial initiated in Q3 2022 Outcome Measures Enrollment Criteria • Confirmed APC mutation • Post-colectomy/proctocolectomy • No GI cancer present • Polyps in either duodenum (including ampulla of Vater) or rectum/pouch • Primary: • Part 1: PK • Part 2: % Change from Baseline
Slide 113: REC-4881 for AXIN1/APC Mutant Cancers
REC-4881 for the Treatment of Solid Tumors with AXIN1/APC Mutant Cancers Target / MOA MEK Inhibitor Molecule Type Small Molecule Lead Indication(s) Solid Tumors with AXIN1/APC Mutant Cancers Status Phase 1b/2 Source of Insight Recursion OS
Slide 114: AXIN1/APC: Wnt signaling in solid tumors
114 • Sustained Wnt signaling is a frequent driver event found across a wide variety of solid tumors • Dysregulation of β-catenin destruction complex due to inactivating mutations in AXIN1/APC leads to sustained Wnt signaling promoting cancer progression and survival1 • AXIN1/APC mutant solid tumors
Slide 115: AXIN1/APC patient selection and study design
115 • AXIN1 and APC genes covered by commercially available NGS panels and liquid biopsy detection assays • FDA guidance supports utility of ctDNA as patient selection for the detection of alterations for eligibility criteria and as a stratification factor for trials enrolling marker-positive and ma
Slide 116: REC-4881 dosage hypothesis and differentiation
REC-4881 Dosage Hypothesis: Rescue of AXIN1 may impact tumor progression and/or restore checkpoint sensitivity in cancers driven by AXIN1 loss Recursion Differentiation: REC-4881 rescues tumor suppressor genes APC and AXIN1 • APC and AXIN1 are negative regulators of Wnt signaling • Both proteins for
Slide 117: REC-4881 in vivo mouse model efficacy
Note: REC-4881 dosed at 3 mg/kg QD for up to 21 days. 3 mice per treatment per model (3 x 3 x 3) design Efficacy found in In Vivo Mice Models … … Led to Significant Progression Free Survival p = 0.0009 AXIN1/APC mutant p = 0.23 AXIN1 / APC wildtype Clinical: AXIN1/APC Pr ob ab ili ty o f p ro gr es
Slide 118: AXIN1/APC next steps
118 Finalize design of a Phase 1b/2 biomarker-enriched trial Initiate Phase 1b/2 trial in select tumor types in early 2024 Identify suitable partners for genetic testing capabilities Evaluate REC-4881 in combination with targeted and/or immune modulating agents Clinical: AXIN1/APC 118
Slide 119: REC-3964 for C. difficile Infection
REC-3964 for the Treatment of Clostridium Difficile Infection Target / MOA Selective C. diff Toxin Inhibitor Molecule Type Small Molecule Lead Indication(s) Clostridium Difficile Infection Status Phase 1 Source of Insight Recursion OS
Slide 120: C. diff infection progression
120 Disruption of microbiota and colonization of C. diff Release of C. diff toxins Degradation of colon cell junction & toxin transit to bloodstream Clinical: C. diff Source: McCollum, D,, Rodriguez, JM . Detection, Treatment, and Prevention of Clostridium difficile Infection. Clinical Gastroenterol
Slide 121: C. diff unmet need and cost burden
Source, CDC *NAAT = Nucleic Acid Amplification Test; **rCDI = recurrent CDI • RCDI** occurs in 20-30% of patients treated with standard of care • 40% of those patients will continue to recur with 2+ episodes • >29,000 patients die in the US each year from CDI • Cost burden of up to $4.8bn annually 1
Slide 122: REC-3964 rescue in toxin-treated cells
REC-3964 identified as a NCE that demonstrated strong rescue in HUVEC cells treated with C. diff toxin C. diff toxin B phenotype Healthy Control Disease State Healthy Cells REC-3964 0.1 µM Clinical: C. diff 122
Slide 123: C. diff toxin mechanism
Clinical: C. diff The glucosyltransferase locks Rho family GTPases in the inactive state C.diff toxins bind to cell surface receptors and trigger endocytic event 1 Autocatalytic cleavage event releases C.diff toxin's glucoyltransferase enzymatic domain into the cytosol of the infected cell 2 3 3 1 2
Slide 124: REC-3964 blocks toxin glucosyltransferase
Adapted from Awad et al. 2014 Clinical: C. diff 3 1 2 4 REC-3964 binds and blocks catalytic activity of the toxin’s innate glucosyltransferase, but not the host's 5 5 REC-3964 is Recursion’s 1st Small Molecule NCE to Reach the Clinic 124
Slide 125: REC-3964 barrier integrity and survival
REC-3964 restores gut epithelial barrier integrity, which when disrupted causes inflammation and diarrhea REC-3964 rescues barrier integrity with increasing concentrations REC-3964 improved probability of survival in a hamster model of C. difficile infection Improved probability of survival beyo
Slide 126: Phase 1 SAD/MAD trial update
126 Phase 1 FIH SAD/MAD Trial initiated in Q3 2022 • Enrollment is progressing • In several SAD cohorts and at least one MD cohort, REC-3964 has been extremely safe and well tolerated • Complete safety and PK data readout expected 2H 2023 Trial Design • Randomized, Double-blind Trial Population • He
Slide 127: Partnerships
Download Day 2023 Partnerships Matt Kinn Senior Vice President of Business Development
Slide 128: Partnership and pipeline strategy
Partnership strategy Discovery Partnerships Partner in complex therapeutic areas requiring large financial commitment and competitive market dynamics Leverage partner knowledge and clinical development capabilities 128 Fibrosis Other large, intractable areas of biology Neuroscience *and a single onc
Slide 129: Bayer and Roche/Genentech collaboration terms
Fibrosis Neuroscience *and a single oncology indication • $30M upfront and $50M equity investment • Up to or exceeding $1.2B in milestones for up to or exceeding 12 programs • Mid single-digit royalties on net sales • Recursion owns all algorithmic improvements • $150M upfront and up to or exceeding
Slide 130: Leveraging Recursion OS for fibrosis biology
We are leveraging the Recursion OS in multiple ways to identify novel fibrosis-relevant biology Experiment: perturbations Measurements | Se Imaging —_— ( en Small Gey 9 ale Fibrosis Biological System —_— a a) Inferential Search i... a (commenced 2022) Target predictions Query map for inferences L @
Slide 131: Fibrosis programs: brute force to inferential search
Early DiscoveryScreening Brute Force (commenced 2020) Inferential Search (commenced 2022) Approach Late Discovery Transition to Inferential Search has accelerated new program initiation in 2022 Active Paused / Terminated Pre-programs 131
Slide 132: Inferential search fibrosis progress
100% of projects to be sourced from inferential search in 2023 ~100 fibrosis-relevant genes ready for further study >500,000 Phenoprints Mapped 2 PB of data generated 40 million experiments performed 8 Projects initiated; 4 in 2022
Slide 133: Bayer and Roche/Genentech collaboration terms
Fibrosis Neuroscience *and a single oncology indication • $30M upfront and $50M equity investment • Up to or exceeding $1.2B in milestones for up to or exceeding 12 programs • Mid single-digit royalties on net sales • Recursion owns all algorithmic improvements • $150M upfront and up to or exceeding
Slide 134: Roche & Genentech multi-modal maps
Under our collaboration with Roche & Genentech, we are creating multi- modal maps of cellular biology to elucidate novel targets and starting points Experiment: perturbations Measurements a) Small Ge)” lecules Gastrointestinal cancer Neuroscience Biological Biological Model system 2 system 1 TT te J
Slide 135: Financials & Milestones
Financials & Milestones Michael Secora PhD Chief Financial Officer Download Day 2023
Slide 136: Financial projections and statements of operations
136 • Cash and cash equivalents • Currently projecting ~$550M at the end of 2022 • Operating costs and expenses • Currently projecting ~$275-295M in 2022 • Based on current operations, we project relatively flat operating costs and expenses in the near term • Revenue • Currently projecting ~$30-45M
Slide 137: Funding and partnership timeline
Trademarks are the property of their respective owners and used for informational purposes only. 2014 2016 2017 2018 2019 2020 2021 2022 2023 Recursion Founded Series A: $15M Series B: $60M Series C: $122M Series D: $239M $30M Bayer Upfront IPO: $502M $150M Roche/GNE Upfront PIPE: $150M 2015
Slide 138: Team and ESG highlights
Advanced degreesEmployees Team Members ~500 43% ESG Highlights Inaugural ESG report in 2022 – reporting on Healthcare and Technology Metrics 100% of electricity powering our Biohive-1 supercomputer comes from renewable sources 43% Female Male 55% 1% Non-Binary Parity Pledge Signer - gender parit
Slide 139: Executive team and board of directors
TINA LARSON President & COO Executive Team HEATHER KIRKBY, MBA Chief People Officer BEN MABEY Chief Technology Officer Trademarks are the property of their respective owners and used for informational purposes only. 139 KRISTEN RUSHTON, MBA SVP of Business Operations MICHAEL SECORA, PHD Chief Financ
Slide 140: Strong financials and near- and medium-term milestones
Strong Financials ~$550M in cash and cash equivalents at the end of 2022 with potential for increased revenue in the near term Near-Term • Potential option exercises for partnership programs • Potential option exercises for map building initiatives or data sharing • Potential for additional partners
Slide 141: Machine Learning and Automation
Machine Learning and Automation 141
Slide 142: Q&A
Q&A Chris Gibson PhD & Recursion Executive Team Download Day 2023
Slide 143: Closing Remarks
Closing Remarks Download Day 2023 Zavain Dar Director of Recurison
Recursion Pharmaceuticals — Investor Day (January 2023) on 6ix