Recursion
Industrial-scale AI drug discovery on 60 petabytes of biology.
About
Recursion (recursion.com, NASDAQ: RXRX) is a clinical-stage TechBio company whose Recursion OS combines automated wet-lab experiments — millions of cell assays per week — with machine learning over a 60+ petabyte proprietary dataset to find drug targets and design molecules.
Its pipeline spans oncology, rare disease, and neuroscience, with REC-4881 reporting Phase 1b/2 data in familial adenomatous polyposis and a Roche/Genentech collaboration worth up to $12B across 40 programs. Like all AI drug discovery platforms, its value rests on clinical results that are still playing out.
What it can do
- Recursion OS discovery platform
- High-throughput phenomic screening
- 60+ petabyte biology/chemistry dataset
- AI target and molecule design
- Clinical development pipeline
Setup
- Engage via partnership or collaboration inquiry.
- Define disease area and data-sharing terms.
- Run phenomic screens on Recursion's automated platform.
- Prioritize targets from ML-derived biology maps.
- Co-develop candidates into clinical trials.
Prerequisites
Pharma/biotech partnership agreement.
Use cases
Works with
Trust score — 8/10
Scored 8/10 (verified tier, metrics-v1). Evidence: NASDAQ RXRX; 60+ petabyte dataset; BioHive supercomputing; REC-4881 Phase 1b/2 FAP data; Roche/Genentech collaboration up to $12B; Exscientia merger scaled data and pipeline. Manual review: industrial-scale platform with clinical readouts; value still proving out in clinic. License: Proprietary platform; pharma partnerships..
How the trust score is built
Full methodology →- Adoption · stars/downloads, log-scaled vs peers
- 8.0/10
- Maintenance · recency, releases, issue load
- 8.0/10
- Openness · license + docs
- 6.0/10
- Manual review · sanity read + red-flag check
- 8.0/10
- · NASDAQ RXRX; 60+ petabyte dataset; BioHive supercomputing
- · REC-4881 Phase 1b/2 FAP data; Roche/Genentech collaboration up to $12B
- · Exscientia merger scaled data and pipeline
- · manual review: industrial-scale platform with clinical readouts; value still proving out in clinic
Sources
Every fact above was checked against these sources. Where a claim comes from the provider and couldn't be independently verified, the text says so.