Yueming Hu

AWmeta improves transcriptomic meta-analysis by adaptively weighting studies, yielding more accurate differentially expressed genes with fewer samples and reduced false positives.

HPInet predicts host-pathogen protein-protein interactions using a transformer-based model, achieving high accuracy and identifying key residues from sequence data.

The paper identifies 21 OMP families in E. coli showing mosaic evolution, including 16 new families, and links their variable regions to immunogenicity and antigenicity.

This paper introduces T6CNN, a model that improves T6SE prediction by integrating signal sequences, evolutionary data, and pre-trained features, achieving higher accuracy, sensitivity, and specificity than existing tools.

This study reconstructs ancient Salmonella chromosomes and shows genetic rearrangements affect gene expression and chromosomal conformation across lineages.

This study benchmarks APA detection tools in single-cell and spatial transcriptomes, finding SCAPE and scAPAtrap perform best across multiple metrics.

This study systematically analyzes single-cell data to show how transposable elements dynamically regulate the endothelial-to-hematopoietic transition through epigenetic changes and inflammatory signaling.

T4SEpp predicts bacterial type IV secreted effectors using protein language models and integrates multiple modules, achieving high sensitivity and specificity.

The paper introduces a recursive Hidden Markov Model profile-alignment strategy to identify new bacterial type III secreted effectors, finding 155 effectors and 59 proteins with N-terminal signal sequences across 27 genera.