Machine Learning Techniques Applied to the Study of Drug Transporters

Abstract

With the advancement of computer technology, machine learning-based artificial intelligence technology has been increasingly integrated and applied in the fields of medicine, biology, and pharmacy, thereby facilitating their development. Transporters have important roles in influencing drug resistance, drug–drug interactions, and tissue-specific drug targeting. The investigation of drug transporter substrates and inhibitors is a crucial aspect of pharmaceutical development. However, long duration and high expenses pose significant challenges in the investigation of drug transporters. In this review, we discuss the present situation and challenges encountered in applying machine learning techniques to investigate drug transporters. The transporters involved include ABC transporters (P-gp, BCRP, MRPs, and BSEP) and SLC transporters (OAT, OATP, OCT, MATE1,2-K, and NET). The aim is to offer a point of reference for and assistance with the progression of drug transporter research, as well as the advancement of more efficient computer technology. Machine learning methods are valuable and attractive for helping with the study of drug transporter substrates and inhibitors, but continuous efforts are still needed to develop more accurate and reliable predictive models and to apply them in the screening process of drug development to improve efficiency and success rates.

Computational Chemistry in Structure-Based Solute Carrier Transporter Drug Design: Recent Advances and Future Perspectives

“…Along with the development of AI, machine learning plays an increasingly important role in various domains. 214 Machine learning is widely used to predict transporter substrates and inhibitors, which contributes to its ability of identifying complex patterns from vast and complex molecular descriptor data sets. Depending on the type of data, such as whether sample labels are available, the algorithms can be classified as supervised, semisupervised, and unsupervised.…”

“…Along with the development of AI, machine learning plays an increasingly important role in various domains . Machine learning is widely used to predict transporter substrates and inhibitors, which contributes to its ability of identifying complex patterns from vast and complex molecular descriptor data sets.…”

Advances in Modeling Approaches for Oral Drug Delivery: Artificial Intelligence, Physiologically Based Pharmacokinetic, and First-Principal Models

“…In recent years, non-linear QSAR models, based on ML and DL techniques, have become the most popular strategy to develop QSAR models for the prediction of ADME properties of drug candidates [84], and formulation design [85]. Similarly to conventional QSAR, non-linear QSAR models were developed to estimate the permeability [49,82,86], physio-chemical properties [58,59], distribution [49,82], affinity to P-gp [87,88], hepatic clearance [49,82], metabolism by the CYP family [89][90][91][92], and F in fasted [59] and fed states [93]. For reviews on using AI for ADME properties, and other usage in the pharmaceutical industry see Refs.…”