Loading
A model trained on billions of cell microscopy images to read what a drug or gene knockout does to a cell.
Phenom-2 is Recursion's phenomics foundation model, a masked autoencoder vision transformer trained on Cell Painting microscopy images that learns to read what a drug or gene knockout does to a cell's appearance. Released in 2024 with 1.9B parameters and trained on 8B images, it converts cell images into embeddings that can be compared across perturbations to infer mechanism and find drug candidates. Together with Boltz-2 and the Recursion OS platform it drives the company's oncology pipeline, including the CDK7 inhibitor REC-617. The scale of proprietary phenomics data is its strength; clinical translation is still to prove, since no drug discovered this way has yet completed late-stage trials. For a newcomer: Phenom-2 looks at pictures of cells to tell what a treatment did to them, and Recursion uses it to hunt for cancer drugs.
Phenom-2 is a masked autoencoder ViT over Cell Painting images.
Query for this technology: (TITLE:"Phenom-2 and Recursion OS" OR ABSTRACT:"Phenom-2 and Recursion OS") AND (cancer OR tumor OR tumour OR oncology OR carcinoma OR lymphoma OR leukemia OR leukaemia OR myeloma OR sarcoma OR melanoma OR glioma). Results are unfiltered search hits about Phenom-2 and Recursion OS, not a curated reading list.
Shares Recursion Pharmaceuticals, Drug discovery roadmap: screening in mice → maps of dependency → designing in silico, AI in oncology roadmap: pattern readers → foundation models → agents in the workflow, AI-driven drug & target discovery and the tag foundation-model.
Shares Recursion Pharmaceuticals, Drug discovery roadmap: screening in mice → maps of dependency → designing in silico, AI-driven drug & target discovery.
Shares Drug discovery roadmap: screening in mice → maps of dependency → designing in silico, AI in oncology roadmap: pattern readers → foundation models → agents in the workflow, AI-driven drug & target discovery and the tag foundation-model.
Shares CRISPR functional genomics, Drug discovery roadmap: screening in mice → maps of dependency → designing in silico, AI in oncology roadmap: pattern readers → foundation models → agents in the workflow and the tag foundation-model.
Shares Drug discovery roadmap: screening in mice → maps of dependency → designing in silico, AI in oncology roadmap: pattern readers → foundation models → agents in the workflow, AI-driven drug & target discovery.
Shares Drug discovery roadmap: screening in mice → maps of dependency → designing in silico, AI in oncology roadmap: pattern readers → foundation models → agents in the workflow, AI-driven drug & target discovery and the tag foundation-model.
Shares Drug discovery roadmap: screening in mice → maps of dependency → designing in silico, AI in oncology roadmap: pattern readers → foundation models → agents in the workflow, AI-driven drug & target discovery and the tag foundation-model.
Shares Drug discovery roadmap: screening in mice → maps of dependency → designing in silico, AI in oncology roadmap: pattern readers → foundation models → agents in the workflow, AI-driven drug & target discovery and the tag foundation-model.