ABSTRACT
Introduction
Although significant development has been made in high-throughput screening of oral drug absorption and oral bioavailability, in silico prediction continues to play an important role in prediction of oral bioavailability and assisting in the proper selection of potential drug candidates.
Areas covered
This review describes the improvements and latest modeling methods and algorithms available for the prediction of this important parameter. We performed a PubMed database search with a focus on the literature published in the last 15 years.
Expert opinion
A tremendous efforts have been done in the past several years to develop reliable prediction tools that can provide accurate prediction for oral bioavailability. Several studies demonstrated new methodologies and techniques to develop either web-based in silico predictive tools or integrated PBPK models to predict oral bioavailability for new molecules. Improvements in the databases and the computational power will enhance the in silico prediction accuracy and reliability. Finally, introducing artificial intelligence to the drug development process will help improve the prediction tools.
Article highlights
In silico oral bioavailability prediction continues to play an important role in facilitating the appropriate selection of new drug candidates.
Early assessment of oral bioavailability can minimize the time and cost of screening and testing.
Physiologically Based Pharmacokinetic (PBPK) Modeling integrates all kinetic processes in addition to drug-related data to predict the main pharmacokinetic parameters, including oral bioavailability.
Artificial intelligence (AI) will increase the efficiency and speed of the drug development process.
Declaration of interest
The author has no relevant affiliations or financial involvement with any organization or entity with a financial interest in or financial conflict with the subject matter or materials discussed in the manuscript. This includes employment, consultancies, honoraria, stock ownership or options, expert testimony, grants or patents received or pending, or royalties.
Reviewer disclosures
Peer reviewers on this manuscript have no relevant financial or other relationships to disclose.