A Combination of Machine Learning and PBPK Modeling Approach for Pharmacokinetics Prediction of Small Molecules in Humans

Abstract

Recently, there has been rapid development in model-induced drug development, which has the potential to reduce animal experiments and accelerate drug discovery. Physiologically based pharmacokinetic (PBPK) and machine learning (ML) models are commonly used in early drug discovery to predict drug properties. However, basic PBPK models require a large number of molecule-specific inputs from in vitro experiments, which hinders the efficiency and accuracy of these models. To address this issue, this paper introduces a new computational platform that combines ML and PBPK models. The platform predicts molecule PK profiles with high accuracy and without the need for experimental data. This study developed a whole-body PBPK model and ML models of plasma protein unbinding (fup), Caco-2 cell permeability, and total plasma clearance to predict the PK of small molecules. Pharmacokinetic profiles were simulated using a "bottom-up" PBPK modeling approach with ML inputs. Additionally, 40 compounds were used to evaluate the platform's accuracy. Results showed that the ML-PBPK model predicted the area under the concentration-time curve (AUC) with 62.5% accuracy within a 2-fold range, which was higher than using in vitro inputs with 47.5% accuracy. The ML-PBPK model platform provides high accuracy in prediction and reduces the number of experiments and time required compared to traditional PBPK approaches. The platform successfully predicts human PK parameters without in vitro and in vivo experiments and can potentially guide early drug discovery and development.

Systematic Evaluation of High-Throughput PBK Modelling Strategies for the Prediction of Intravenous and Oral Pharmacokinetics in Humans

“…Others did perform predictions for humans but relied in their validation of prediction quality on summary PK parameters, like Cmax or AUC values (Punt et al 2022a;Miljković et al 2021;Li et al 2023). The problem with such approaches is that they do not consider the full information about the quality of the predicted concentration-time curve as a whole.…”

“…ML and AI technologies are now increasingly being explored to provide rapid PK predictions without the need for new animal data. Sometimes, this is pursued by using AI/ML methods to directly predict summary PK/TK parameters, like maximum concentration (Cmax) or area under the curve (AUC) values (Miljković et al 2021;Fagerholm et al 2021;Li et al 2023). Other times, it is done by predicting mechanistically relevant compound properties, like the lipophilicity, solubility or clearance of compounds, which can then be used as inputs for making PK predictions using mechanistic models (Danishuddin et al 2022;Pillai et al 2022;Fagerholm et al 2023;Mavroudis et al 2023;Führer et al 2024).…”

“…While valuable, the ultimate goal in pharmacology and toxicology is to yield human-relevant conclusions. In those instances where such approaches were developed for predicting human data, evaluations were usually performed against relatively small datasets, typically not exceeding a few dozen compounds (Punt et al 2022a;Li et al 2023;Fagerholm et al 2023). Moreover, PK prediction validations frequently relied on summary PK parameters, like Cmax or AUC values (Miljković et al 2021).…”

Machine Learning Models for Predicting Personalized Tacrolimus Stable Dosages in Pediatric Renal Transplant Patients

“…Because of the numerous issues that PM and ML encounter, research in this field remains in its exploratory phase, underscoring the need for further investigation and validation. The fusion of PK and ML holds the potential to yield precise estimations of drug exposure by simulating rich concentration-versus-time profiles, by exploring and learning the relationships within all the patient covariates [62] or by using faster models and performing faster analyses [63]. For instance, the ML approach has been shown to confer advantages over traditional approaches, including increased accuracy and reduced variance [64].…”

Advancing Drug Safety in Drug Development: Bridging Computational Predictions for Enhanced Toxicity Prediction

“…A significant obstacle in constructing these models is the scarcity of the necessary drug/chemical-specific parameters, for which measurements often remain unavailable, a gap that AI has begun to fill. ,, AI models can be developed by utilizing the available PK data, and their incorporation into PBPK models facilitates the prediction of PK parameters . The inclusion of ML in PBPK models has improved their performance, offering a sophisticated approach for understanding drug kinetics and safety . This integration represents a promising framework to overcome the limitations of extrapolating data, particularly for predicting complex biological interactions and individual variability in drug responses.…”