Biology subjects

Yun, H.-y.

Publications and source records attributed to Yun, H.-y..

3 recordsLinked to original sources

bioRxiv2026

Model-Driven Hybrid AI Framework for End-to-End Autonomous Decision-Making in Drug Development

Decision-making in drug development spans heterogeneous stages from molecular design to clinical optimization, yet computer-aided workflows across stages remain fragmented, limiting traceability from evidence-derived clinical questions to simulation scenarios and decision endpoints. We present a model-driven hybrid AI framework for end-to-end decision support that treats PICO (Participants, Intervention, Comparison, Outcome) as a machine-actionable specification to define scenarios and align endpoints across modules. Given a PICO-defined clinical question and a drug SMILES, the framework infers PBPK-ready parameters from structure, generates exposure via mechanistic PBPK simulation, and links exposure outputs to clinic-facing therapeutic drug monitoring (TDM) decision support using an open-source NLME-based Clinical Pharmacokinetic Consultant Service (CPCS). We additionally implement an LLM-based PICO extraction layer to structure clinical abstracts into P/I/C/O elements for systematic evidence ingestion. Results include backbone verification for DTI-guided intrinsic clearance prediction under fold-error bounds and PBPK trajectory plausibility, and external validation of the hybrid AI-PBPK pipeline showing substantial dispersion for several endpoints. An input-controlled comparison between PhysioSim and PK-Sim on N = 9 drugs yields similarly degraded accuracy under identical AI-predicted inputs, suggesting upstream parameter quality as a dominant constraint. For evidence ingestion, prompting-only PICO extraction achieves F1 of 0.687 on EBM-NLP and 0.552 on TB-PICO. For clinical utility, CPCS improves TDM performance over a PKS baseline on phenobarbital and vancomycin, reducing MAPE by approximately 26-60% depending on configuration. Overall, the framework provides a modular, traceable blueprint linking evidence-defined questions to exposure simulation and TDM decision support while preserving mechanistic interpretability. Future work will integrate outcome-aligned time-to-event modeling and federated learning to close the PICO-to-outcome loop and improve parameter inference under multi-site governance.

pharmacology and toxicology↗

bioRxiv2026

Real world data based evaluation of a novel target-mediated drug disposition approximation model

Target-mediated drug disposition (TMDD) models have been widely used to describe nonlinear pharmacokinetic profiles driven by high-affinity, low-capacity drug-target binding. A pTMDD model, derived by applying the Pade approximation of the quasi-steady-state (QSS) model (qTMDD) was previously proposed. Although pTMDD model showed a comparable estimation accuracy while maintaining computational efficiency, further validation in realistic clinical scenarios and comprehensive performance evaluations have been needed to assess its practical applicability. Here, we evaluated the pTMDD model using five clinical datasets and extended the previous study that focused on simulations. Using the full TMDD as a reference, the approximation models were compared in terms of the parameter estimation results (parameter estimates, relative standard error values and model diagnostics) and computational efficiency (estimation and bootstrap runtimes). The pTMDD model, previously validated in simulation settings, also preserved the estimation accuracy while reducing the computation time of the clinical data. Both pTMDD and qTMDD remained close to the full TMDD model, whereas Michaelis-Menten TMDD (mTMDD) model showed substantial discrepancies especially at low doses, including biased estimates for key TMDD-related parameters (e.g., kdeg, kint, krec, and kup) and higher objective function values. Moreover, pTMDD was faster than qTMDD in four of the five cases compared to the full TMDD. The time savings were particularly pronounced for larger datasets, supporting the computational efficiency of pTMDD. Q2PCONV, an R Shiny application that converts NONMEM code from qTMDD to pTMDD, was also developed, thereby making this new approximation more accessible to researchers. The findings support pTMDD as a practical alternative to existing TMDD approximation models. Author SummaryTarget-mediated drug disposition (TMDD) models describe a high-affinity, low-capacity binding between drug and its target. To avoid overparameterization, approximation models have been used. The two primary models are Michaelis-Menten model (mTMDD), which is accurate only at high doses, and Quasi-steady-state (qTMDD), which is accurate in wider ranges but requires longer runtime. We have proposed a new approximation model named pTMDD. Here, we evaluated pTMDD using five real clinical trial datasets to assess its practical usefulness. pTMDD produced parameter estimates closer to those from the full TMDD model and showed lower uncertainty than both the full TMDD and mTMDD models. In terms of computational efficiency, pTMDD reduced estimation time by an average of 11% and bootstrap time by an average of 6% relative to qTMDD across cases. In addition, we also developed an R shiny application to help researchers apply pTMDD in practice. Our work supports pTMDD as a practical and efficient tool for TMDD modeling in drug development.

pharmacology and toxicology↗

bioRxiv2026

Exact formula of the total quasi-steady state approximation in competitive target-mediated drug disposition

Competitive target-mediated drug disposition (competitive TMDD) arises when two drugs compete for the same target receptor. These dynamics can be characterized by the full competitive TMDD model; yet, its complexity motivated the use of a reduced model, which is invalid under high receptor concentrations. While this problem can be resolved by using the total quasi-steady state approximation (tQSSA), which remains valid for all receptor conditions, the exact formula of the tQSSA-based reduced model--competitive qTMDD--has remained unknown for 15 years, as it requires solving a cubic equation and the nontrivial task of identifying a biologically meaningful solution. Consequently, researchers have relied on numerical approximation methods, which impose substantial computational costs to maintain accuracy and thereby hinder their practical use in complex real-world applications. To address this problem, we derive--for the first time--a real-valued exact formula for competitive qTMDD by leveraging analytic properties of cubic equations and geometric characteristics of their roots in the complex plane. This exact formula improved computational speed by more than 11-fold compared to previous numerical approximation methods, thereby enabling Bayesian inference using competitive qTMDD, which had been impractical due to excessive computational time. When applied to real-world data from clinical trials, competitive qTMDD estimated pharmacological parameter estimates comparable to those from the full competitive TMDD model while requiring only 30-43% of the computation time. Importantly, this estimation using competitive qTMDD remained consistently accurate regardless of data sparsity, whereas the previous reduced model produced biased estimates under sparse sampling conditions. By ensuring precise biological interpretation of drug systems even in complex real-world scenarios, the exact formula of competitive qTMDD has the potential to significantly streamline the drug development and clinical testing process. Our exact formula also consists entirely of real-valued terms, allowing seamless integration into existing pharmacometrics software. Author SummaryCompetitive target-mediated drug disposition (competitive TMDD) occurs when two drugs compete for the same target receptor. Analyzing this interaction has faced a dilemma for 15 years: choosing between a full model that is accurate but computationally intensive, and a reduced model that is fast but often loses accuracy under real-world clinical conditions. Researchers tried to solve this dilemma by deriving an accurate reduced model; however, it was mathematically challenging. As a result, they had to rely on numerical approximations--which require substantial computational power to maintain the accuracy needed for clinical use, making them impractical in real-world scenarios. In this study, we derive a first-ever exact formula for the new reduced model that is accurate across all biological conditions. This formula computes more than 11 times faster than previous numerical methods, making advanced statistical analyses--such as Bayesian inference--feasible for the first time in this context. When applied to real-world clinical data for Anakinra and rhIL-7-hyFc, our method yielded parameter estimates as accurate as the full model but required significantly less computation time. This breakthrough provides a more accurate biological interpretation and better guidance for determining the right drug dose, potentially accelerating drug development and reducing associated costs.

pharmacology and toxicology↗