Rex Ying

The paper introduces UKBioBERT, a DNA language model pre-trained on UK BioBank variants, which improves gene expression prediction and enables eQTL identification when combined with sequence-to-function models.

spRefine denoises and imputes spatial transcriptomics data using a reference-free deep learning framework, improving data integration and revealing new aging-related biological insights.

ImmunoStruct improves immunogenicity prediction by integrating peptide-MHC sequence, structure, and biochemical data, showing better performance than existing methods.

A masked-expression Transformer trained on 983 paired H&E and spatial transcriptomics slides predicts 38,984 genes from histology without fine-tuning, leading HEST-Bench and improving survival and mutation prediction.

UNICORN improves gene expression and multi-omic phenotype prediction using multi-task learning with foundation model embeddings and custom loss functions.

spEMO integrates histopathology and spatial multi-omic data using foundation models, improving performance in spatial analysis and medical report generation.