Related Experiment Video
Updated: Aug 5, 2026
14:34
A Bilingual Computational Workflow for Identifying Potential PLK1 Inhibitors in American Sign Language and English
Published on: April 3, 2026
Machine Learning Enables Rapid Prediction of Acid-Reducing Agent Drug Interactions: A Streamlined Complement to PBPK
Yuanfang Qin1,2, Lehua Yu2, Tao Chen3
1Department of Pharmacy, The Third Xiangya Hospital, Central South University, Changsha, China.
CPT: Pharmacometrics & Systems Pharmacology
|August 1, 2026
Summary
A new machine learning model predicts pH-dependent drug-drug interactions (DDIs) between acid-reducing agents and basic drugs. This PBPK-informed tool aids early drug development by efficiently assessing DDI risk.
Area of Science:
- Pharmacokinetics and Drug Metabolism
- Computational Chemistry and Cheminformatics
- Drug Development and Pharmacology
Background:
- pH-dependent drug-drug interactions (DDIs) frequently occur when acid-reducing agents (ARAs) are administered with weakly basic drugs.
- Physiologically based pharmacokinetic (PBPK) modeling is effective for evaluating these DDIs but is often limited by costly commercial software.
- Early assessment of DDI risk is crucial in drug development to ensure safety and efficacy.
Purpose of the Study:
- To develop a PBPK-informed machine learning (ML) model for the early assessment of pH-dependent DDI risk in drug development.
- To create a cost-effective and efficient alternative to traditional PBPK modeling for screening potential DDIs.
- To provide a practical tool for researchers and developers to predict DDI outcomes.
Main Methods:
- PBPK models were constructed for 14 weakly basic drugs using literature data to identify key determinants of pH-dependent DDIs.
- A virtual drug population (4339 compounds) was generated and simulated under various gastric pH conditions.
- An extreme gradient boosting (XGBoost) algorithm was employed to build the ML model, validated with clinical data from eight additional drugs.
Main Results:
- The XGBoost model demonstrated high internal performance (R²=1.00, MAPE=0.99 for training; R²=0.98, MAPE=2.64 for testing).
- External validation showed 100% of predictions within the 0.5-2.0-fold range of observed clinical values for eight drugs.
- The model achieved 87.5% accuracy in classifying DDI AUC risk, correctly identifying 7 out of 8 cases.
Conclusions:
- The PBPK-informed ML framework provides an efficient method for screening pH-dependent DDI risk involving ARAs and weakly basic drugs.
- The developed model serves as a valuable complement to conventional PBPK modeling in early drug development.
- A freely accessible web tool integrating this model is available for practical application in drug development.
Related Concept Videos
01:26Pharmacokinetic Models: Comparison and Selection Criterion
Physiological and compartmental models are valuable tools used in studying biological systems. These models rely on differential equations to maintain mass balance within the system, ensuring an accurate representation of the dynamic processes at play.
Physiological models take a detailed approach by considering specific molecular processes. They can predict drug distribution, metabolism, and elimination changes, providing a comprehensive understanding of how drugs interact with the body.
Physiological models take a detailed approach by considering specific molecular processes. They can predict drug distribution, metabolism, and elimination changes, providing a comprehensive understanding of how drugs interact with the body.
01:15Impact of Pharmacokinetic–Pharmacodynamic Models: Regulatory Decisions
PK–PD modeling has significantly influenced FDA regulatory decisions, particularly drug approval, dosage optimization, and labeling. These models integrate pharmacokinetics (PK) and pharmacodynamics (PD) to predict drug behavior and effects, aiding in optimizing dosing regimens and enhancing the probability of clinical trial success.One notable example is Nesiritide (Natrecor®), a recombinant human brain natriuretic peptide for treating acute decompensated congestive heart failure (CHF).
01:21Mechanistic Models: Overview of Compartment Models
Mechanistic models, a category encompassing both physiological and compartmental modeling, differ from empirical models' approaches to incorporating known factors about the systems being modeled. Empirical models describe data with minimal assumptions, while mechanistic models aim to provide a robust description of available data by specifying assumptions and integrating known factors about the system. Compartmental analysis is a key example of a mechanistic model in pharmacokinetics and...
01:14Pharmacokinetic–Pharmacodynamic Relationship: Model Components
Pharmacokinetic-pharmacodynamic (PK–PD) modeling is essential in drug development and clinical pharmacology. It provides a quantitative framework to predict drug behavior and response over time. This approach integrates pharmacokinetics (PK), which describes the drug's absorption, distribution, metabolism, and excretion, with pharmacodynamics (PD), which characterizes the drug’s biological effects and mechanisms of action.The disposition kinetics of a drug determine its plasma...
01:20Pharmacokinetic Models: Overview
Pharmacokinetic models utilize mathematical analysis to achieve a detailed quantitative understanding of a drug's life cycle within the body. They are instrumental in simulating a drug's pharmacokinetic parameters, predicting drug concentrations over time, optimizing dosage regimens, linking concentrations with pharmacologic activity, and estimating potential toxicity.
There are three primary types of models: empirical, compartment, and physiological. Empirical models, with minimal assumptions,...
There are three primary types of models: empirical, compartment, and physiological. Empirical models, with minimal assumptions,...
01:24Pharmacokinetic–Pharmacodynamic Relationship: Problems
The empirical approach to drug therapy optimization relies on correlating pharmacological response with administered dosage. Such an approach can be costly, time-consuming, and often yields poor correlation due to variables like formulation factors and drug elimination characteristics. A more precise approach correlates response with plasma drug concentration or the amount of drug in the body, rather than dosage. This is achieved through pharmacokinetic-pharmacodynamic (PK/PD) modeling, which...