Oregon State University

Mixed-modality metagenomic language model using bidirectional Mamba blocks to embed proteins within 20K tokens of coding and non-coding DNA.

Gut microbiome language model that reads a 16S sample as a sentence of taxa, producing context-sensitive embeddings that transfer across cohorts.

Gut microbiome taxa embeddings that project a 16S V4 ASV table into a shared property space so classifiers transfer between cohorts.