Predicting pharmacodynamic effects through early drug discovery with artificial intelligence-physiologically based pharmacokinetic (AI-PBPK) modelling.

A mechanism-based pharmacokinetic/pharmacodynamic (PK/PD) model links the concentration-time profile of a drug with its therapeutic effects based on the underlying biological or physiological processes. Clinical endpoints play a pivotal role in drug development. Despite the substantial time and effort invested in screening drugs for favourable pharmacokinetic (PK) properties, they may not consistently yield optimal clinical outcomes. Furthermore, in the virtual compound screening phase, researchers cannot observe clinical outcomes in humans directly. These uncertainties prolong the process of drug development. As incorporation of Artificial Intelligence (AI) into the physiologically based pharmacokinetic/pharmacodynamic (PBPK) model can assist in forecasting pharmacodynamic (PD) effects within the human body, we introduce a methodology for utilizing the AI-PBPK platform to predict the PK and PD outcomes of target compounds in the early drug discovery stage. In this integrated platform, machine learning is used to predict the parameters for the model, and the mechanism-based PD model is used to predict the PD outcome through the PK results. This platform enables researchers to align the PK profile of a drug with desired PD effects at the early drug discovery stage. Case studies are presented to assess and compare five potassium-competitive acid blocker (P-CAB) compounds, after calibration and verification using vonoprazan and revaprazan.

Predicting Drug-Drug Interactions Involving Rifampicin Using a Semi-mechanistic Hepatic Compartmental Model.

AIMS: To develop a semi-mechanistic hepatic compartmental model to predict the effects of rifampicin, a known inducer of CYP3A4 enzyme, on the metabolism of five drugs, in the hope of informing dose adjustments to avoid potential drug-drug interactions. METHODS: A search was conducted for DDI studies on the interactions between rifampicin and CYP substrates that met specific criteria, including the availability of plasma concentration-time profiles, physical and absorption parameters, pharmacokinetic parameters, and the use of healthy subjects at therapeutic doses. The semi-mechanistic model utilized in this study was improved from its predecessors, incorporating additional parameters such as population data (specifically for Chinese and Caucasians), virtual individuals, gender distribution, age range, dosing time points, and coefficients of variation. RESULTS: Optimal parameters were identified for our semi-mechanistic model by validating it with clinical data, resulting in a maximum difference of approximately 2-fold between simulated and observed values. PK data of healthy subjects were used for most CYP3A4 substrates, except for gilteritinib, which showed no significant difference between patients and healthy subjects. Dose adjustment of gilteritinib co-administered with rifampicin required a 3-fold increase of the initial dose, while other substrates were further tuned to achieve the desired drug exposure. CONCLUSIONS: The pharmacokinetic parameters AUCR and CmaxR of drugs metabolized by CYP3A4, when influenced by Rifampicin, were predicted by the semi-mechanistic model to be approximately twice the empirically observed values, which suggests that the semi-mechanistic model was able to reasonably simulate the effect. The doses of four drugs adjusted via simulation to reduce rifampicin interaction.