Hsien-Da Huang

MetExPred predicts drug metabolism and excretion by integrating molecular and protein representations, achieving strong performance across multiple endpoints.

MIRCID improves drug mechanism modeling by integrating inferred hub miRNAs with gene expression and TF activity, showing better performance than TF activity alone.

This study evaluates two microbial antioxidant formulations for their ability to reduce ROS and protect human skin cells from oxidative stress.

The paper develops an AI-driven platform to analyze RRBE's photoprotective mechanisms, identifying key bioactive compounds and their targets through computational and experimental validation.

The paper identifies sRNA-mediated feed-forward loops in E. coli that modulate gene regulation through distinct dose-response profiles, showing how sRNAs enhance regulatory diversity and efficiency.

The paper evaluates imputation performance in East and Southeast Asian populations, showing that recent selection affects variant detection and polygenic risk score estimation.

DeepADR predicts adverse drug reaction frequency using early-stage data by integrating chemical, biological, and semantic information with a Kolmogorov-Arnold Network.

KinasePhos 3.0 improves phosphorylation site prediction by expanding kinase classification and building 771 models, achieving average accuracy of 87.2%.

This study shows that DNMT3b dysfunction leads to centromere instability through R-loop-mediated DNA breaks and XPG/XPF cleavage.