Recursion

A clip from Recursion CSO Dave Hallett's conversation with Patrick Short, CEO of Sano Genetics, host of The Genetics Podcast, about the real gains and remaining hurdles for AI drug discovery and development. Drawing on his nearly 30 year experience, beginning at Merck in the mid-1990s, Dave shared how AI has fundamentally changed what’s possible – from research capabilities, to molecule design, to clinical trial planning – but noted that it still can’t change the laws of physics. 🔹Highlights include: ▪️How AI has allowed for true multi-parameter optimization Dave said the shift from single-parameter to true multi-parameter optimization is the biggest change he's seen at the bench. A person can hold roughly six or seven variables in their head at once, he said; a computational system can track far more, without recency bias, across active learning loops. The result: "AI has massively compressed the time and the cost that's required to get from an idea to a candidate." Recursion has seen that show up as roughly 80% reductions in compounds made and 50-70% cuts to time-to-candidate on affected programs. ▪️Simulating trials before running them Rather than copying existing clinical trial protocols, Dave shared how Recursion pressure tests inclusion and exclusion criteria through simulation before a study launches — asking which criteria are actually still fit for purpose. Applied to REC-7735, evaluated in the ZINNIA trial, that process expanded the pool of patients the trial could reach by approximately 20%. ▪️Looking forward with pragmatism and optimism Dave was candid about AI’s limitations, too, noting that the industry is "still a long way" from modeling emergent human pathophysiology at the organism scale. He also discussed Recursion's partnership work on the breakthrough neuro map, and offered advice to early-career scientists: build deep domain expertise while remaining "bilingual" across biology, chemistry, and computation. 👉 Check out the full conversation: https://www.youtube.com/watch?v=BD34s2h64lU #techbio #AIdrugdiscovery #clinicaltrials #biotech #genomics

Behind the scenes of Recursion’s AI-native data factory and product engine – the first, and one of the largest, of its kind. CHAPTERS 0:00 — Introduction: Mapping the Haystack Reframing drug discovery from single-hypothesis testing to systematically mapping all of biology; an intro to Recursion's AI-native data factory and recursive learning loop. 1:24 — Building Disease-Relevant Cells at Scale Growing iPSC-derived human neurons at unprecedented scale (over 1 trillion neurons) using protocols developed with Roche/Genentech. 2:26 — Manipulating Cells at the Genetic Level Inside the lab: the Echo acoustic liquid handler, CRISPR-based perturbations, and running up to 2 million experiments a week with intentional randomization. 3:27 — Capturing High-Dimensional Data Imaging and sequencing cells at scale to generate reusable, future-proofed data that trains foundation models. 4:42 — Creating Maps of Biology How foundation models turn perturbations into "fingerprints" and build a searchable map of biology to generate disease hypotheses. 5:59 — Validating Hypotheses at the Bench Closing the loop: de-risking AI-generated hypotheses against the same bar pharma partners hold their own programs to. 6:37 — Designing Molecules with Centaur Introducing the AI-native chemistry engine — generative de novo design, and the ~90%-fewer-compounds efficiency stat. 7:58 — Exploring Novel Chemical Space How tools like Nesso-1 and AI retrosynthesis expand what a chemist can design and predict, compressing a full design cycle to about a day. 9:12 — Automated Design-Make-Test Labs Recursion's chemistry design platform performs automated synthesis, purification, and digital tracking in one connected system. 10:09 — Automated Testing and the Feedback Loop Plain-language experiment requests, halved pharmacology costs, and closing the loop between prediction and synthesis. 11:08 — Entering the Clinic: Introducing ClinTech Bringing the same data-driven approach into clinical development, starting with patient selection. 11:24 — Predicting Patient Response with Cardinal AI Matching lab-tested cancer cells to real patient tumors to predict benefit — and uncovering biomarkers. 12:25 — Solving the Enrollment Bottleneck How the Site Finder tool uses real-world data to identify trial sites and improve enrollment rates by 30–60%. 13:25 — Real-Time Trial Decision-Making The ClinTech biometrics engine speeding up dose-escalation decisions and contextualizing results against real-world evidence. 14:55 — Closing: The Recursive System in Practice Recap of Recursion's end-to-end AI product engine and its role in accelerating medicines already in the clinic today. #AI #drugdiscovery #drugdesign #biology #chemistry #TechBio #AIdrugdiscovery