Recursion has built many internal tools to map and navigate the trillions of biological and chemical relationships within our massive phenotypic drug discovery dataset. MolRecTM is a simplified version of one such tool built for Compound Intelligence, which allows a user to explore potential relationships between compounds of interest and CRISPR knockouts.

We are providing public access to a basic version of MolRec™️ on top of our RxRx3 dataset, now available for download. RxRx3 is a tiny sliver - less than 1% - of Recursion's Data Universe, consisting of images of Human Umbilical Vein Endothelial Cells (HUVEC) manipulated by known chemical compounds or CRISPR-based gene editing. The underlying dataset is 76 times larger than any previous dataset released by Recursion combined.


genes profiled*

spanning CRISPR knockouts of most of the human genome


known chemical entities at 8 concentrations each

FDA approved and commercially available bioactive compounds at 8 concentrations and tens of thousands of control images


of Recursion’s total dataset

*Approximately 16,000 of these genes are anonymized in the dataset, enabling people to explore and learn from this massive dataset while protecting Recursion’s business interests. Recursion may de-anonymize genes in this dataset in the future.

Powering a new data-driven approach to drug discovery

Instead of looking narrowly at a handful of diseases with existing therapeutic hypotheses, Recursion’s Maps allow us to direct our focus toward unknown or unexplored relationships across biology and chemistry to pursue areas of high unmet need for patients.

In essence, it’s turning drug discovery from a trial-and-error process into a search problem.

Interested in learning more?

Connect with us at

Stay informed about our RxRx datasets
Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.
Connect on social media