From Data Factory to Better Drugs: Inside Recursion's AI-Native Product Engine

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