Recursion Pharmaceuticals

Protein-ligand binding affinity prediction from sequence and SMILES, without MSAs. Coarse-grained cofolding runs over 10x faster than Boltz-2.

Transcriptomics foundation model from Recursion that masks and reconstructs RNA-seq gene expression counts to learn reusable sample embeddings.

Open model that jointly predicts biomolecular structure and small-molecule binding affinity, approaching FEP+ accuracy in seconds on a single GPU.

Cell Painting microscopy foundation model, a channel-agnostic masked autoencoder producing morphological embeddings for zero-shot phenotypic analysis.