Application of Machine Learning and Mechanistic Modeling to Predict Intravenous Pharmacokinetic Profiles in Humans
Xuelian Jia1,2, Donato Teutonico3, Saroj Dhakal4
1Center for Biomedical Informatics and Genomics, Tulane University, New Orleans, Louisiana 70112, United States.
Journal of Medicinal Chemistry
|March 27, 2025
Summary
Machine learning models predict human pharmacokinetics (PK) for drug discovery. These data-driven approaches offer accurate predictions, improving early drug screening and design.
Area of Science:
- Pharmacology
- Computational Chemistry
- Drug Discovery
Background:
- Accurate prediction of human pharmacokinetics (PK) is vital for efficient drug discovery.
- Traditional PK prediction methods (allometric scaling, mechanistic modeling) are resource-intensive and raise ethical concerns due to reliance on in vitro/in vivo data.
- Machine learning (ML) offers a data-driven alternative to overcome these limitations.
Purpose of the Study:
- To develop and validate novel machine learning frameworks for predicting human pharmacokinetic profiles.
- To leverage a comprehensive dataset of small molecules' physicochemical and PK properties, including digitized human plasma concentration-time profiles.
- To enhance early molecular screening and design in the drug discovery pipeline.
Main Methods:
- Compiled a large dataset of small molecule physicochemical and PK properties from public sources.
- Digitized human plasma concentration-time profiles for approximately 800 compounds.
- Developed and applied a hybrid modeling framework combining ML with physiologically based pharmacokinetic modeling.
- Utilized a hierarchical ML framework with two learning steps for direct PK profile estimation.
Main Results:
- The developed ML frameworks achieved prediction accuracies within 2-fold error for 40-60% of compounds and 5-fold error for 80-90% of compounds for both AUC and Cmax.
- The models were validated on a set of 106 drugs.
- Demonstrated the capability of data-driven models to accurately predict key PK parameters.
Conclusions:
- The proposed hybrid and hierarchical ML frameworks provide accurate and efficient methods for predicting human pharmacokinetic profiles.
- These data-driven approaches can significantly enhance early-stage molecular screening and design in drug discovery.
- The study advances computational capabilities for drug development, potentially reducing costs and timelines.
Related Concept Videos
01:20Pharmacokinetic Models: Overview
526
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...
There are three primary types of models: empirical, compartment, and physiological. Empirical models, with minimal...
526
01:21Mechanistic Models: Overview of Compartment Models
52
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...
52
01:26Pharmacokinetic Models: Comparison and Selection Criterion
31
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.
31
01:06Model Approaches for Pharmacokinetic Data: Distributed Parameter Models
54
Pharmacokinetic models are mathematical constructs that represent and predict the time course of drug concentrations in the body, providing meaningful pharmacokinetic parameters. These models are categorized into compartment, physiological, and distributed parameter models.
The distributed parameter models are specifically designed to account for variations and differences in some drug classes. This model is particularly useful for assessing regional concentrations of anticancer or...
The distributed parameter models are specifically designed to account for variations and differences in some drug classes. This model is particularly useful for assessing regional concentrations of anticancer or...
54
01:14Analysis Methods of Pharmacokinetic Data: Model and Model-Independent Approaches
74
Drug disposition in the body is a complex process and can be studied using two major approaches: the model and the model-independent approaches.
The model approach uses mathematical models to describe changes in drug concentration over time. Pharmacokinetic models help characterize drug behavior in patients, predict drug concentration in the body fluids, calculate optimum dosage regimens, and evaluate the risk of toxicity. However, ensuring that the model fits the experimental data accurately...
The model approach uses mathematical models to describe changes in drug concentration over time. Pharmacokinetic models help characterize drug behavior in patients, predict drug concentration in the body fluids, calculate optimum dosage regimens, and evaluate the risk of toxicity. However, ensuring that the model fits the experimental data accurately...
74
01:14Model Approaches for Pharmacokinetic Data: Compartment Models
64
Compartmental analysis is a widely adopted approach to characterizing drug pharmacokinetics. It uses compartment models that conceptualize the body as a collection of reversibly communicating compartments, each representing a group of tissues exhibiting similar drug distribution characteristics. The movement rate of the drug between these compartments is typically described by first-order kinetics.
Two primary types of compartment models are recognized: mammillary and catenary. The more...
Two primary types of compartment models are recognized: mammillary and catenary. The more...
64