Wuhan Sports University

Protein language model adding long-range contact supervision to ESM2 via LoRA, improving all eight protein-level tasks with no structural input.

Protein structure prediction model that weights residues by protein-language-model importance scores to improve accuracy on hard AlphaFold2 targets.

Bulk transcriptome foundation model, 150M parameters over ~20,000 protein-coding genes. Imputes masked expression at Pearson r = 0.954.