Beibei Huang

DL4DR predicts drug response across breast cancer cell lines using a residual fusion model that combines genomic data with molecular representations, achieving high accuracy and generalization.

The paper introduces an agentic computational framework to reconstruct immune dynamics in pancreatic cancer using H&E histology, identifying three temporally ordered immune-stromal states in mouse models.

This paper uses H&E slides and deep learning to reconstruct LUAD progression, identifying immune reprogramming and architectural fragmentation as key early malignant transitions.

The paper develops a sequence-based chaos game representation combined with deep learning for peptide/protein classification, showing superior performance in hemolytic/non-hemolytic peptide and HIV protease mutant classification.

JavaDL predicts cancer drug responses using chemical features with a Java-based deep learning model, achieving high accuracy and robustness in big data analysis.