BACKGROUND: Alzheimer's disease (AD) is a progressive neurodegenerative disease. Traditional models for estimating AD onset cannot capture nonlinear interactions (epistasis) among the numerous genetic variables that contribute to AD risk. METHODS: We developed a feedforward neural network (FFN)-Weibull survival model to predict AD onset using large-scale single-nucleotide polymorphism (SNP) data. We integrated an XAI technique, Shapley additive explanations (SHAP), to address the black-box nature of deep learning, interpret model predictions, and quantify the contribution of each genetic factor to AD. RESULTS: The FFN model achieved a mean concordance index of 0.647, demonstrating an approximately 3.6% improvement over the traditional linear baseline (0.625). The FFN-SHAP model validated established findings, identifying APOE E4 as a primary AD risk factor. APOE E2 strongly protected against AD. Metabolic-disorder-related SNPs had conflicting effects, suggesting gene-environment interactions influence AD onset. CONCLUSIONS: By effectively bypassing the combinatorial explosion of interaction terms, the predictive power of an FFN combined with XAI provides a robust methodological tool for identifying the genetic basis of complex diseases, even in cohorts with limited sample sizes. Our model generated novel testable hypotheses regarding the intricate roles of gene-gene and gene-environment interactions in AD pathogenesis.

Target-mediated drug disposition (TMDD) is a phenomenon characterized by a drug's high-affinity binding to a target molecule, which significantly influences its pharmacokinetic profile within an organism. The comprehensive TMDD model delineates this interaction, yet it may become overly complex and computationally demanding in the absence of specific concentration data for the target or its complexes. Consequently, simplified TMDD models employing quasi-steady state approximations (QSSAs) have been introduced; however, the precise conditions under which these models yield accurate results require further elucidation. Here, we establish the validity of three simplified TMDD models: the Michaelis-Menten model reduced with the standard QSSA (mTMDD), the QSS model reduced with the total QSSA (qTMDD), and a first-order approximation of the total QSSA (pTMDD). Specifically, we find that mTMDD is applicable only when initial drug concentrations substantially exceed total target concentrations, while qTMDD can be used for all drug concentrations. Notably, pTMDD offers a simpler and faster alternative to qTMDD, with broader applicability than mTMDD. These findings are confirmed with antibody-drug conjugate real-world data. Our findings provide a framework for selecting appropriate simplified TMDD models while ensuring accuracy, potentially enhancing drug development and facilitating safer, more personalized treatments.