Jie Hu

The paper presents an LLM-based workflow for extracting enzyme kinetic data from literature, achieving high accuracy and efficiency.

The paper investigates the role and mechanisms of leptomeningeal collaterals in human distal MCA territory ischemia using experimental and computational methods.

InstructPLM aligns a protein language model with structure instructions to generate diverse proteins, improving performance over existing models in sequence recovery and activity.

This paper investigates the hybrid nature of task-evoked neural activity using intracranial EEG and Deep Learning LSTM models, showing that poststimulus activity is influenced more by prestimulus dynamics than the external stimulus itself.

The paper constructs a high-confidence Asian variant benchmark using multiple sequencing methods and identifies novel variants in challenging regions.