Weimin Zhu

The paper evaluates models for classifying synonymous variants by separating gene context, exon position, and variant-specific effects, finding that gene identity and position are more predictive than the variant itself.

AuditPPI evaluates PPI predictors by transforming language model features into auditable fingerprints, revealing that predictive success does not necessarily reflect biological signal capture.

The paper creates a proteomic map of the human cerebral cortex by analyzing 29 Brodmann areas, identifying cluster-specific and BA-specific proteins and their functional associations.

Phoenix Enhancer improves proteomics data analysis by clustering spectra to identify potential mis-identifications and enhance peptide spectrum match confidence.