A Review on New Frontiers in Drug-Drug Interaction Predictions and Safety Evaluations with In Vitro Cellular Models

Abstract

The characterization of a drug's ADME (absorption, distribution, metabolism, and excretion) profile is crucial for accurately determining its safety and efficacy. The rising prevalence of polypharmacy has significantly increased the risk of drug-drug interactions (DDIs). These interactions can lead to altered drug exposure, potentially compromising efficacy or increasing the risk of adverse drug reactions (ADRs), thereby posing significant clinical and regulatory concerns. Traditional methods for assessing potential DDIs rely heavily on in vitro models, including enzymatic assays and transporter studies. While indispensable, these approaches have inherent limitations in scalability, cost, and ability to predict complex interactions. Recent advancements in analytical technologies, particularly the development of more sophisticated cellular models and computational modeling, have paved the way for more accurate and efficient DDI assessments. Emerging methodologies, such as organoids, physiologically based pharmacokinetic (PBPK) modeling, and artificial intelligence (AI), demonstrate significant potential in this field. A powerful and increasingly adopted approach is the integration of in vitro data with in silico modeling, which can lead to better in vitro-in vivo extrapolation (IVIVE). This review provides a comprehensive overview of both conventional and novel strategies for DDI predictions, highlighting their strengths and limitations. Equipping researchers with a structured framework for selecting optimal methodologies improves safety and efficacy evaluation and regulatory decision-making and deepens the understanding of DDIs.

Keywords: cell cultures; computational modeling; cytochrome P450; drug metabolism; drug-drug interaction; in vitro to in vivo extrapolation; physiologically based pharmacokinetic model.

Figure 1

Isolation and preparation of microsomal, S9, and cytosolic fractions routinely employed in drug metabolism studies.

Figure 2

Different cell model systems. Abbreviations: 2D, two-dimensions; 3D, three-dimensions; PHH, primary human hepatocytes. This figure was partly generated using SMART—Servier Medical Art, licensed under CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). and BioRender. Available online: https://smart.servier.com and https://www.biorender.com (accessed on 22 April 2025).

Figure 3

Organoids generation from ASCs and iPSCs. ASC-derived organoids are generated from healthy or tumor biopsies; the tissue is dissociated into a single-cell suspension and embedded in an ECM; a tissue-specific growth factor-enriched medium is added and refreshed regularly to support organoid expansion. iPSC-derived organoids begin as 2D cultures, which are induced to form aggregates or spheroids; and these structures are then embedded in an ECM and matured using tissue-specific growth factor-enriched medium.