University of Hawaiʻi at Mānoa

Multi-task cellular foundation model predicting drug sensitivity, perturbation expression and drug-protein binding from one pretrained checkpoint.

Single-cell foundation model tokenizing expression profiles with a residual-VQ autoencoder to generate new cells of a type from held-out examples.

Long-context protein language model that reads whole viral genomes, using interaction-guided sparse attention over contexts of 61,000 amino acids.

mRNA language model embedding the joint 5' UTR and coding sequence to predict translation efficiency, expression level, and transcript stability.