Morgridge Institute for Research

Vision transformer trained with DINO self-supervision to segment micronuclei in DNA-stained fluorescence images across cell lines and microscopes.

Text-guided molecule generation by linking a pretrained scientific text encoder to a frozen molecular language model with a cross-attention adapter.

Genome language model that embeds a genome as a set of contextualized protein embeddings, pretrained on over 100,000 viruses for viromics.

Protein language models pretrained on Rosetta biophysics simulations rather than evolutionary data, then finetuned on small experimental assays.