Indiana University

Cell type annotation model mapping human single-cell and spatial transcriptomes onto one hierarchical typology of 381 types across 23 tissues.

Generative model for self-tracked menstrual health data, encoding cycles and symptom logs as token sequences for synthetic cohorts and forecasting.

Graph neural network counting recurring cell-type neighborhood motifs in spatial transcriptomics and proteomics, linking topology to phenotype.

Molecular formula identification from tandem mass spectra at 88.3% top-1 accuracy, more than 10x faster than fragmentation-tree search.