Weill Cornell Medicine

Self-supervised transformer fusing Enformer DNA embeddings with ATAC-seq accessibility into reusable 256-dimensional genomic window embeddings.

DARPin binder design constrained to the ankyrin-repeat consensus grammar, pairing a fine-tuned inverse-folding model with two structure oracles.

Tandem mass spectrum prediction that builds explicit fragmentation pathways, mapping unknown spectra onto 800 million predicted PubChem spectra.

Self-supervised foundation model that embeds cancer genomes from somatic SNVs and copy-number alterations across 33 tumor types for tumor subtyping.

Single-cell transcriptomics model fine-tuned on 1.12M CAR-T profiles to annotate T cell subtypes and predict therapy response and neurotoxicity.

Universal foundation model that jointly generates diagnostic text and segments the corresponding targets across ten biomedical imaging modalities.

Inverse molecular design conditioned on transcriptomics, generating small molecules intended to revert a diseased cell to a healthy expression state.

Keypoint-based foundation model for brain MRI registration, pretrained on over 100,000 3D volumes for rigid, affine, and deformable alignment.