Hanli Jiang

ETAP-CLF uses ESM3 embeddings and transformer attention to classify proteins into binary categories, achieving high AUROC scores across different biological processes.

The paper develops a deep learning model to predict mutation density in metastatic cancers using chromatin accessibility data from primary tumors, showing lineage-linked chromatin context influences regional mutagenesis.

SenSeqNet detects cellular senescence from protein sequences with 83.55% accuracy using a hybrid LSTM-CNN architecture and ESM-2 embeddings.