Exhibit 99.1
DECODING BIOLOGY TO RADICALLY IMPROVE LIVES RECURSION JP Morgan Healthcare Conference January 10th, 2023
DISCLAIMERS 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 projections about our industry and our company, management’s beliefs and certain assumptions we have made. The words “plan,” “anticipate,” “believe,” “continue,” “estimate,” “expect,” “intend,” “may,” “will” and similar expressions are intended to identify forward-looking statements. Forward-looking statements made in this presentation include statements about Recursion’s use of the proceeds from its private placement, the initiation, timing, progress, results, and cost of our research and development programs and our current and future preclinical and clinical studies, the potential size of the market opportunity for our drug candidates, our ability to identify viable new drug candidates for clinical development and the accelerating rate at which we expect to identify such candidates, our expectation that the assets that will drive the most value for us are those that we will identify in the future using our datasets and tools, and many others. Forward-looking statements made in this presentation are neither historical facts nor assurances of future performance, are subject to significant risks and uncertainties, and may not occur as actual results could differ materially and adversely from those anticipated or implied in the forward-looking statements. For a discussion of factors that could affect our business, please refer to the “Risk Factors” sections in our filings with the U.S. Securities and Exchange Commission, including our most recent Quarterly Report on Form 10-Q and our Annual Report on Form 10-K. This presentation does not purport to contain all the information that may be required to make a full analysis of the subject matter. We undertake no obligation to correct or update any forwardlooking statements, whether as a result of new information, future events or otherwise. Certain information contained in this presentation relates to or is based on studies, publications, surveys and other data obtained from third-party sources and the company’s own internal estimates and research. While the company believes these third-party sources to be reliable as of the date of this presentation, it has not independently verified, and makes no representation as to the adequacy, fairness, accuracy or completeness of, any information obtained from third-party sources. In addition, all of the market data included in this presentation involves a number of assumptions and limitations, and there can be no guarantee as to the accuracy or reliability of such assumptions. Finally, while the company believes its own internal research is reliable, such research has not been verified by any independent source. Any non-Recursion logos or trademarks included herein are the property of the owners thereof and are used for reference purposes only. 2
RECURSION HAS AN OPPORTUNITY FOR ARBITRAGE IN THE DRUG DISCOVERY SPACE 50B 100M RECURSION 500K Eroom’s Law: Drug discovery is becoming slower and more expensive over time Moore’s Law: Computing power becomes faster and less expensive over time 1962 1970 1980 1990 2000 2010 2020 10 1 0.1 NMEs per $B spent (inflation adjusted) Compute Power (Transistors per Microprocessor) Adapted from Scannell et al and Our World in Data 3
Historical tools and the limits of human cognition have led to oversimplifying complex biological systems Traditional Approach to Biology Recursion’s Approach to Biology Well-known primary relationships between key members of five pathways: JAK/STAT | SWI/SNF | TGFβ | RAS | Proteasome All primary relationships found by the Recursion OS between key members of five pathways: JAK/STAT | SWI/SNF | TGFβ | RAS | Proteasome 4 Recursion
Recursion recursion’s map-based approach is designed to set the standard for drug discovery in the 21st century Literature drives discovery. Informs target-based hypotheses Traditional drug discovery Recursion approach Data are an exhaust. Limited to testing hypotheses Linear process. Little cross-program learning or iteration Disparate data generation. Siloed to individual programs and diseases Bespoke processes. Low-dimensional assays & biomarkers Vs Platforms drive discovery. Unbiased & target agnostic Data are our fuel. Shape our hypotheses Virtuous cycles of atoms & bits. Iterative feedback accelerates learning Connected data across programs. Relatable high-dimensional data Industrialized to scale. Automation & standardization 5
Recursion Initiated 4 clinical trials in the first 3 quarters of 2022 (3 Ph2, 1 Ph1) Planning a 5th clinical trial to initiate (Ph2) Novel oncology programs (Target Alpha, Target Gamma) nearing IND-enabling studies Advancing collaborations in Fibrosis (Bayer) and Neuroscience (Roche-Genentech) • $13B in potential milestones across 50+ possible programs plus royalties We believe that we have built one of the largest proprietary & relatable in-vitro biological and chemical datasets on Earth • >21 petabytes of data and >3 trillion searchable relationships maturing the techbio value proposition in 2022 6
Recursion our pipeline reflects the scale and breadth of our approach Phase 1 Phase 2 Phase 3 (APC; est. 50K) AXIN1/APC MUTANT CANCERS (AXIN1/APC mutant cancers; est. 32K) KRAS/STK11-DRIVEN CHECKPOINT RESISTANCE (KRAS/STK11; est. 11K) MYC-DRIVEN ONCOLOGY (MYC; est. 54K1) CANCER IMMUNOTHERAPY TARGET ALPHA (Multiple; 72K2) CANCER IMMUNOTHERAPY TARGET BETA (Multiple; 15K2) HRD-NEGATIVE OVARIAN CANCER TARGET GAMMA (HRD-negative ovarian cancer; 13K) Rare & Other CEREBRAL CAVERNOUS MALFORMATION (CCM; est. 360K3) NEUROFIBROMATOSIS TYPE 2 (NF2; est. 33K4) CLOSTRIDIUM DIFFICILE COLITIS (est. 730K) Partnership Programs MULTIPLE PROGRAMS ADVANCING SIMULTANEOUSLY More than a dozen early discovery and research programs in oncology, neuroscience, inflammation & immunology, and rare disease All populations defined above are US and EU5 incidence unless otherwise noted. EU5 is defined as France, Germany, Italy, Spain and UK. (1) Our program has the potential to address a number of indications driven by MYC alterations, totalling 54,000 patients in the US and EU5 annually. We have not finalized a target product profile for a specific indication. (2) Our program has the potential to address a number of indications in this space. (3) Prevalence for hereditary and sporadic symptomatic population. (4) Annual US and EU5 incidence for all NF2-driven meningiomas. 7 7 Therapeutic Area Indication Late Discovery FAMILIAL ADENOMATOUS POLYPOSIS Preclinical
Recursion mapping and navigating the complex systems of biology and chemistry has demonstrated leading indicators of efficiency Failing faster and earlier to › › spend less › Cost to IND ($M) 25 20 15 10 5 0 Industry 40 30 20 10 0 › and go faster Screen Hit ID Validated Lead Advanced Candidate Development Candidate Stage 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 8 80% 75% 85% 64% 39% 50% 62% time to validated lead (mo)
How we build and navigate maps of biology and chemistry to turn drug discovery into a search problem recursion
We build biological and chemical datasets to map relationships across scales and understand the connectivity of the system recursion Organism Level Invivomics Cell Level Phenotypes Phenomics Metabolates Level Metabolomics Protein Level Proteomics RNA Level Transcriptomics DNA Level (Population-Scale) Genomics Built and scaled Exploratory Aspirational Image adapted from D’Orazio, M., et al. Nature Scientific Reports 2022. 10
Recursion Robotic Automation at Scale Up to 2.2 Million wet-lab experiments per week profiling genes and compounds, we believe we are one of the largest phenomics (human cellular image-based) data producers 2.2 Million Week Diverse Biological and Chemical Inputs 48 different human cell types >1.7 Million >500 Billion small molecule library, we believe this scale is on par with some large pharma companies hiPSC-derived cells produced in 2022, we believe that we are one of the largest hiPSC- derived cell producers High-Dimensional Validation 150 Up to 100 15K near whole exomes per week, we believe we are one of the largest transcriptomics data producers 50 log2(FC) Recursion OS Enables quality, relatability and scale of data >21 Petabytes Digitization of Biology and Chemistry >21 Petabytes of proprietary high- dimensional data, we believe this is one of the largest relatable in vitro biological and chemical datasets Recursion Top 500 ML-Based Analysis Top 500 supercomputer across any industry (TOP500 List, Nov 2022), we leverage vast neural networks and multiomics approaches to extract features and drive insights >3 Trillion Novel Insights at Scale ML-Based Relationships relatable hypotheses across multiple biological and chemical contexts 11
All Human Genes with Significant Effects in this Cellular Context →→ Genome-scale mapping Recursion This is a whole-genome arrayed CRISPR knock-out Map generated in primary human endothelial cells Every gene is represented in a pairwise way (each is present in columns and rows) Dark Red indicates phenotypic similarity according to our neural networks while Dark Blue indicates phenotypic anti- similarity (which in our experience often suggests negative regulation) We can add the phenotypes of hundreds of thousands of small molecules at multiple doses and query and interact with these maps using a web application Can show 100s of examples of known biology and chemistry 12
DOCK9 SLC39A1 ASB7 MEGF8 PRKCH SOCS3 PHF13 PPP1R9B TNKS1BP1 ZMYM3 FAM49B STK24 YWHAB IL6ST IL6R STAT3 IL6 JAK1 STAT3 ILGR ILGST WHAB STK24 FAM49B One such example—the JAK/STAT pathway clustered by strength of interaction, including both similar genes (red) and opposite genes (blue) Can wade into areas of novel biology and chemistry... 13
Enhancer module INTS13- Int-PP2A (phosphatase module) INTS8 -INTS14 INTSS INTS10 Endonuclease module Central backbone INTS4 INTS11 INTS7- INTS9 SOSS complex -INTS1 INTS3 (N terminus) INIP INTS2 INTS6 Assembled complex -PP2A-C PPZA-A NABP1/2 INTS6 (C terminus) INTS3 dimer (C terminus) Endonuclease module Int-PP2A (phosphatase module) Central backbone Phenomics TVN (below diagram) vs. Centerscale (above diagram) INTS9 INTS11 INTS4 INTS7 Similar INTS2 INTS8 INTS1 INTS6 Opposite C7orf26 INTS10 Maps reveal known and novel biology In 2022, new independent research identified a previously unknown gene, C7orf26, as part of the Integrator complex Maps jointly developed by Recursion and Genentech replicated this same result Demonstrates accuracy and consistency across different map building approaches O Recursion. Genentech A Member of the Roche Group Recursion INTS13 INTS14 Trademarks are the property of their respective owners and used for informational purposes only. 14
Value driven by partnerships, clinical and preclinical programs Recursion
How we create value using our maps of biology and chemistry Discovery Partnerships Partnership strategy Partner in complex therapeutic areas requiring large financial commitment and competitive market dynamics Leverage partner knowledge and clinical development capabilities • Fibrosis • Neuroscience *and a single oncology indication • Other large, intractable areas of biology Recursion OS Internal Pipeline Pipeline strategy Build wholly-owned pipeline in indications with potential for accelerated path to approval • Oncology Rare Disease 16
Our existing partnerships represent some of the most significant scientific collaborations in biopharma Recursion • Α BAYER BAYER (Announced Sep 2020; Expanded Dec 2021) Fibrosis $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 I I Roche Genentech A Member of the Roche Group (Announced Dec 2021) Neuroscience *and a single oncology indication • $150M upfront and up to or exceeding $500M in research milestones and data usage options • Up to or exceeding $300M in possible milestones per program for up to 40 programs Mid to high single-digit tiered royalties on net sales • Recursion owns or co-owns all algorithmic improvements Trademarks are the property of their respective owners and used for informational purposes only. 17
Our pipeline reflects the scale and breadth of our approach Therapeutic Area Indication Oncology FAMILIAL ADENOMATOUS POLYPOSIS (APC; est. 50K) Rare & Other Partnership Programs MULTIPLE PROGRAMS ADVANCING SIMULTANEOUSLY AXIN1/APC MUTANT CANCERS (AXIN1/APC mutant cancers; est. 32K) KRAS/STK11-DRIVEN CHECKPOINT RESISTANCE (KRAS/STK11; est. 11K) MYC-DRIVEN ONCOLOGY (MYC; est. 54K1) CANCER IMMUNOTHERAPY TARGET ALPHA (Multiple; 72K2) CANCER IMMUNOTHERAPY TARGET BETA (Multiple; 15K2) HRD-NEGATIVE OVARIAN CANCER TARGET GAMMA (HRD-negative ovarian cancer, 13K) CEREBRAL CAVERNOUS MALFORMATION (CCM; est. 360K³) NEUROFIBROMATOSIS TYPE 2 (NF2; est. 33K4) CLOSTRIDIUM DIFFICILE COLITIS (est. 730K) Late Discovery Preclinical Phase 1 Phase 2 Phase 3 More than a dozen early discovery and research programs in oncology, neuroscience, inflammation & immunology, and rare disease âš« Recursion 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 patients in the US and EU5 annually. We have not finalized a target product profile for a specific indication. (2) Our program has the potential to address a number of indications in this space. (3) Prevalence for hereditary and sporadic symptomatic population. (4) Annual US and EU5 incidence for all NF2-driven meningiomas. 18
Phase 2 Trial Underway—REC-994 for Cerebral Cavernous Malformation (CCM) PREVALENCE ~360,000 Symptomatic US + EU5, >1 million patients worldwide live with these lesions today CAUSE LOF mutations in genes CCM1, CCM2 & CCM3, key for maintaining the structural integrity of the vasculature due to unknown mechanisms PATHOPHYSIOLOGY Vascular malformations of the CNS leading to focal neurological deficits, hemorrhage and other symptoms OUR REASON TO BELIEVE Efficacy in Recursion OS as well as functional validation via scavenging of massive superoxide accumulation in cellular models; reduction in lesion number with chronic administration in mice KEY ELEMENTS • Targeting sporadic and familial symptomatic CCM patients with CCM1, CCM2, and CCM3 mutations Phase 2 clinical trial initiated in Q1 2022 Phase 2a Study Design: • Once daily oral dosing US & EU Orphan Drug Designation Endpoints CCM Confirmed with MRI 1:1:1 High Dose Low Dose 52-Week Treatment 1°—Safety and Tolerability Placebo 2°—Imaging, neuro assessments and PROS Open Label Extension Julia—living with CCM Recursion 19
Phase 2/3 Trial Underway—REC-2282 for NF2-Mutated Progressive Meningioma PREVALENCE ~33,000 US + EU5 CAUSE LOF mutations in NF2 tumor suppressor gene PATHOPHYSIOLOGY Inherited rare CNS tumor syndrome leading to loss of hearing and mobility, other focal neurologic deficits OUR REASON TO BELIEVE Efficacy in Recursion OS, cellular, and animal models; suppression of aberrant ERK, AKT, and S6 pathway activation in a Phase 1 PD Study in NF2 patient tumors KEY ELEMENTS Targeting familial and sporadic NF2 meningioma patients Phase 2/3 clinical trial initiated in Q2 2022 Oral bioavailability and CNS exposure together are unique among clinical-stage HDAC inhibitors Fast-Track and US Orphan Drug Designation Progressive NF2- mutated meningioma 1:1 REC-2282 40mg REC-2282 60mg Phase 2 6 x 1 Mo. Cycles Interim Analysis 20 x 1 Mo. Cycles Progressive NF2- mutated meningioma REC-2282 Placebo 1°—PFS 2°—TTR, DOR & ORR 26 x 1 Mo. Cycles 20 Adaptive Phase 2/3 Study Design Phase 3 Ricki – living with NF2
Phase 2 Trial Underway—REC-4881 for Familial Adenomatous Polyposis (FAP) PREVALENCE ~50,000 PATHOPHYSIOLOGY US + EU5 Polyps throughout the GI tract with extremely high risk of malignant transformation CAUSE Inactivating mutations in the tumor suppressor gene APC OUR REASON TO BELIEVE Efficacy in the Recursion OS shows that specific MEK 1/2 inhibitors had an effect in context of APC LOF. Subsequent mouse model APCmin showed potent reduction in polyps and dysplastic adenomas • Oral Dosing Fast-Track and US & EU Orphan Drug Designation • Targeting Classical FAP patients (w/ APC mutation) KEY ELEMENTS • Phase 2 clinical trial initiated in Q3 2022 Phase 2 Study Design: Endpoints FAP with APC mutation 2:2:1 High Dose 1°—A Polyp burden at 12M Open confirmed Low Dose Placebo 48 Week Treatment 2°—PL, Safety, polyp # and Label histological grade Extension 21
Phase 1 Trial Underway — REC-3964 for Clostridium difficile Colitis PREVALENCE ~730,000 US + EU5 CAUSE Release of C. difficile toxins by colonizing bacterium causes degradation of colon cell junction, toxin transit to bloodstream, and morbidity to host PATHOPHYSIOLOGY Highly recurrent infectious disease with severe diarrhea, colitis, and risk of toxic megacolon, sepsis, and death OUR REASON TO BELIEVE Recursion OS identified a new chemical entity for recurrent C. difficile infection and potentially prophylaxis via glycosyl transferase inhibition with potential to be orally active KEY ELEMENTS • Orally active small molecule toxin effect inhibitor • Non-antibiotic approach with potential for combination with SOC and other therapies for recurrent disease • Designed for selective antitoxin pharmacology to target infection with minimal off – target systemic effects • Phase 1 clinical trial initiated in Q3 2022 Part A Phase 1 Study Design: Healthy subjects Part B Single Ascending Dose – randomized, double-blind, placebo-controlled (6 dose levels) Multiple Ascending Dose – randomized, double-blind, placebo-controlled (5 dose levels) Endpoints Safety, tolerability, and PK Colleen – overcame recurrent C diff. – 22
New Clinical Program—REC-4881 for the potential treatment of AXIN1/APC mutant cancers PREVALENCE ~32,000 CAUSE US + EU5 LOF mutations in AXIN1/APC tumor suppressor genes PATHOPHYSIOLOGY Alterations in the WNT pathway are found in a wide variety of tumors and confer poor prognosis and resistance to standard of care OUR REASON TO BELIEVE Efficacy in the Recursion OS and favorable results in PDX models harboring AXIN1/APC mutations vs. wild- type leading to a significant PFS benefit in HCC and Ovarian tumors Significant association between AXIN/APC mutation & response in combined HCC + Ovarian PDX models (p=0.001) Mutant wildtype Single agent REC-4881 leads to a significant PFS benefit in HCC and Ovarian PDX models harboring AXIN1/APC mutations AXIN1/APC Mutant 60% TGI is considered a benchmark for clinical efficacy REC-4881 Untreated Average TGI: “71% mutant vs ≈48% wildtype Median TGI:≈72% mutant vs ≈47% wildtype p=0.0009 AXIN1/APC Wildtype REC-4881 Untreated Time after treatment (d) p = 0.23 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; 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. Combined HCC + Ovarian PDX mouse models Note: prevalence figures represent higher of either AXINI or APC alteration frequency for solid tumors in 21; obtained from cbioportal.org Gross morphology of HCC 23 recursion
Recursion Target α: Potential first-in-class NCE with novel MOA to enhance anti-PD-(L)1 response • Goal: Identify novel compounds capable of enhancing the therapeutic benefit of checkpoint therapy without concomitant inflammatory side effects Phenomap insight: Novel compound (REC-648918) identified with similarity to knockout of potential immunotherapy resistance gene targets (Gene A, Gene B) Result: Reduction in tumor growth vs anti-PD-1 alone in both CT26 checkpoint resistance and EMT6 models – including 40% and 80% complete response in combination in each model, respectively Tumor volume (mm³) CT26 2000 Vehicle aPD1 1500 1000 500 REC-0648918 aPD1+REC-0648918 Similar Opposite REC-Gene B 648918 BIRC2 Gene A Gene A IFN-Y plasma • Efficacy demonstrated in CT26 checkpoint resistance mouse model tumor 80 3 • Complete response (CR) in 4 of 10 mice was observed, with resistance to re-challenge in 3 of 4 mice 60 40 20 • Similar results were observed in the EMT-6 syngeneic model where 8 of 10 mice achieved CR and resisted rechallenge 0 Vehicle Anti-mPD-1 Combo Vehicle Anti-mPD-1 Combo 0 5 10 15 Day 20 25 BIRC2 REC-648918 Gene B Immunotherapy-induced markers of inflammation are reduced in the periphery • IFN-y increased in plasma under immunotherapy but was suppressed in combination with REC-648918 • Higher relative levels of IFN-y were maintained under combination treatment CT26: mouse colon carcinoma. REC-648918 was dosed PO, QD for weeks at 100mg/kg. Anti-PD-1 was dosed IP, BIW for 5 weeks at 10mg/kg. 10 mice per group, dosing initiated when tumors reached 80 mm3; p<0.05** p<0.01 **** p<0.0001; * Combination treatment in EMT6 resulted in 8 CR and 8 rejections on re-challenge 24
Target : Novel CDK12-adjacent target for potentially treating HRD-negative ovarian cancer • Goal: Identify potential first-in-class tumor-targeted precision therapeutic NCE with novel MOA capable of potentially treating HRD-negative (HR proficient) ovarian cancer Phenomap insight: Inhibition of target Gene A (for example, with REC-65029) may mimic inhibition of CDK12 while mitigating toxicity due to CDK13 inhibition Result: REC-65029 when dosed as a single agent and in combination with olaparib in a BRCA-proficient PDX model showed durable efficacy – including 100% complete response Similar Opposite BRCA-proficient ovarian cancer PDX Log2 tumor volume (mm³) 32768- 1024- 32- 1- Tumor reduction CDK13 WHT’O REC-65029 0.25μM 1.0μM 2.5μM Gene A CDK12 Increased rate to CR, durability in combination 150 + Vehicle 100- *** * 50- Treatment end 0.03125- 0 5 10 15 20 25 0 20 Days 40 60 80 Days OV0273 PDX – REC-65029 dosed at 85 mg/kg PO, BID, claparib dosed at 90mg/kg PO QD; ** p<0.01 **** p<0.0001 relative to vehicle 25 REC-65029+olaparib REC-65029
Value driven by our team and our milestones Recursion
What it takes to make this happen — a new kind of team and culture ~ 500 Employees Team Members 43% Advanced degrees Life Sciences-biology, chemistry, development, etc. Technology-data science, software engineering, automation, etc. Strategic Operations 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 Community Impact altitude lab Founding Partner, Life Science Accelerator biohive. Founding Member, Life Science Collective Committed to ESG Excellence Corporate ESG Performance Prime 43% 55% 1% Parity Pledge Signer-gender Female Male Non-Binary parity and people of color parity RATED BY ISS ESG Data shown reflective of Q3 2022 and Recursion’s 2022 ESG report 27
Recursion What’s next for Recursion Milestones Achieved • Initiated 4 clinical trials in 3 quarters • Phase 2 clinical trial evaluating REC-994 for the potential treatment of CCM • Phase 2/3 clinical trial evaluating REC-2282 for the potential treatment of NF2 • Phase 2 clinical trial evaluating REC-4881 for the potential treatment of FAP . Phase 1 clinical trial evaluating REC-3964 for the potential treatment of Clostridium difficile Colitis • Nominated REC-4881 as a clinical program for the potential treatment of AXIN1/APC mutant cancers; Phase 2 trial in planning • Announced transformational collaboration with Roche-Genentech focused on neuroscience • Expanded Bayer collaboration to use mapping and navigating techniques to explore fibrotic diseases Upcoming Potential Milestones Near-Term • Potential option exercises for partnership programs • Potential option exercises for map building initiatives or data sharing • Potential for additional INDs and clinical starts • Potential for additional partnership(s) in large, intractable areas of biology Potential for consolidation of technologies, talent and assets to accelerate the Recursion OS Medium-Term • Multiple POC readout(s) for Al-discovered programs • Potential additional partnership(s) in large, intractable areas of biology • Potential additional option exercises for partnership programs • Potential significant option exercises for map building or data sharing Recursion OS moves towards Autonomous Map Building and Navigation with automated chemical synthesis, digital chemistry and predictive ADMET tools Strong Financials ~$600M in cash and cash equivalents at the end of Q3 2022 (includes recent equity offering) 28
Impact RECURSION 29
Additional scientific and business context RECURSION
Recursion STK11: Opposition of STK11-loss as an immunotherapy resistance marker enhances response to immunotherapy Goal: Identify compounds that oppose STK11-KO to enhance checkpoint therapy Phenomap insight: Novel class of compounds (REC-64151) inferred to rescue loss of STK11 Result: REC-64151 enhances anti-PD1 (aPD1) response in KRAS/P53-driven lung adenocarcinoma line with enhanced mutational burden STK11 Similar Opposite Rec-64151 REC-64151 0.25M 2.5M Log 2 Tumor Volume (mm³) KP + mutagenesis 1024- 256- 64- 16- 4- 1- Vehicle -a-PD-1 Q2Dx4 10 mpk REC-0064151 150 mpk QD REC-0064151 75 mpk + aPD-1 REC-0064151 150 mpk + aPD-1 125- 100- 75- 50- 25- % CRs of Tumor Bearing Mice 125 100 75 50 25 0 4- 1. 1 0 20 30 Study Day CRs Day 23 CRs Day 30 aPD1 REC-0064151 75 mpk + aPD1 REC-0064151 150 mpk + aPD1 Complete Responses 31
MYC: Platform to identify small molecule inhibitors of MYC • Goal: Use the map-based inference platform to identify novel small molecules to mitigate aberrant activation of the MYC pathway Similar Phenomap insight: Phenotypes from the knockout of known MYC pathway phenotypes are highly related in the phenomap. Compounds were identified with inferred relationships to MYC. Result: Identified compounds that selectively induce cell death in c-MYC dependent cell lines, while not affecting cell viability in c-MYC independent cells Opposite actors criptio MYC bosome Selective effect on c-MYC amplified and c-MYC dependent cell line proliferation for two molecules identified using Recursion’s Platform 100- 100- c-Myc Independent Cell Line: âš« PC-12 O in % Proliferation Inhibition -1 REC-142221 Conc. (Log, uM) REC-136467 Conc. (Log, uM) c-Myc Dependent Cell Lines: c-Myc Independent Cell Line: PC-12 c-Myc Dependent Cell Lines: MSTO-211H MV-4-11 HL-60 recursion Opposite Similar MYC cofactors transcription regulations riobsome biogenesis antagonists regulators 32
The biopharmaceutical industry faces pressure amidst declining efficiency in drug discovery Number of Clinical and Preclinical Assets 2,500 Top-20 Pharma Companies Al-Native Drug Discovery Companies 200 2,000 1,500 1,000 500 705 768 708 686 709 602 575 641 519 439 393 333 Number of Clinical and Preclinical Assets 158 150 119 121 100 56 50 28 18 23 10 6 2 4 6 0 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 0 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 Discovery/Preclinical Phase I Phase II Phase III Al-enabled drug discovery efforts have proliferated alongside the declining efficiency of traditional approaches Images adapted from Jayatunga, M., et al. Nature Reviews Drug Discovery 2022. 33 recursion
Recursion Transformational collaborations provide multiple potential value inflection points Illustrative example of potential value inflection points Upfront Fee Value O Technical and Map-Based Milestones Pre-Clinical Milestones Clinical and Approval Milestones through N Programs 2 through N through N Programs 2 through N Programs 2 through N Program 1 Program 1 Program 3 Program 1 Program 1 Collaboration Timeline Royalties & Commercial Milestones Programs 2 through N Programs 2 through N Programs 2 through N Program 1 Program 1 Programs 2 through N Programs 2 through N Programs 2 through N Programs 2 through N Breaking news Program 1 Program 1 34
Recursion COVID-19 research Drug Hydroxychloroquine Lopinavir Ritonavir Remdesivir Prediction Correct? Baricitinib Tofacitinib Ivermectin Fluvoxamine Dexamethasone Recursion Recursion conducted several Al-enabled experiments in April 2020 to investigate therapeutic potential for COVID-19 Included FDA-approved drugs, EMA-approved drugs, and compounds in late-stage clinical trials for the modulation of the effect of SARS-CoV-2 on human cells Experiments were compiled into the RxRx19 dataset (860+ GB of data) and made publicly available to accelerate the development of methods and pandemic treatments. Recursion OS correctly predicted 8 of 9 clinical trials associated with early and late-stage COVID-19 https://www.biorxiv.org/content/10.1101/2020.04.21.054387v1 35
Recursion is a leading TechBio company TOP TECH ENABLED DRUG DISCOVERY (TEDD) COMPANIES: FROST & SULLIVAN ANALYSIS Mature internal pipeline, large strategic partnerships, advanced computational resources Computational focused, known biology Atomwise Schrodinger Insilico Medicine Generate Biomedicines Xtalpi Release Date: March 3, 2022 Recursion engaged Frost & Sullivan to perform this analysis FROST SULLIVAN • Valo Health BenevolentAl Abcellera Recursion Exscientia • Cellarity Eikon Therapeutics Early stage or no internal pipeline, no partnerships, limited computational resources • Relay Therapeutics âš« Insitro Integrated wet+dry-lab, novel bio+chem Nitin Naik-Practice Area Leader, HLS Aarti Chitale-Senior Industry Analyst, HLS Dr. Amol Jadhav- Senior Industry Analyst, HLS FROST & SULLIVAN
Biology and chemistry are complex—data that is scalable and relatable is the Recursion differentiator Year 2018 2019 2020 2021 2022 Total Phenomics Experiments (Millions) 8 24 56 115 175 Total Transcriptomics Experiments (Thousands) NA ÎΑ 2 91 258 Data (PB) 1.8 4.3 6.8 12.9 21.2 Cell Types 12 25 36 38 48 Total Chemical Library¹ (Millions) 0.02 0.1 0.7 1.0 000 1.8 NA 0.02 3 12 12 In Silico Chemistry Library (Billions) Predicted Biological and Chemical Relationships² (Trillions) ÎΑ NA 0.01 0.2 3.1 (1) Includes approximately 500,000 compounds from Bayer’s proprietary library. (2) ‘Predicted Relationships’ refers to the number of Unique Perturbations that have been predicted using our maps. 37 recursion