Models (5)
Sequence-based discrete-diffusion framework that designs peptide binders with specified agonist or antagonist behavior against GPCR targets.
A transcriptomics-native single-cell foundation model that couples batch-invariant representation learning with probabilistic virtual-cell generation.
Reverse-distilled ESM-2 checkpoints (up to 15B) producing Matryoshka-style nested embeddings that scale consistently and reach state of the art on ProteinGym.
Motif-specific protein-protein interaction targeting framework that designs de novo peptide binders to disordered regions and conserved epitopes from sequence alone.
An R package that uses GPT-4 to annotate cell types in scRNA-seq data from marker genes, matching expert accuracy across hundreds of cell types and tissues.