Introduction to Computational Models in Drug Interaction Prediction

Le résumé fourni par la source

Drug interactions, based on the structures and functions of various treatments, have been predicted using computational techniques. Computational methods are advantageous in correlating the functional similarities between medications and biological components, such as transporters, targets, and enzymes. Identifying drug interactions is an imperative step in both medical investigation and novel drug discovery. Nonetheless, established experimental approaches for identifying medication interactions remain challenging, costly, and inefficient. This chapter will highlight various computational modelling approaches to obtain an efficient pathway for drug interaction prediction. Initially, the basics of pharmacokinetic and pharmacodynamic models related to drug interactions were studied and modelled to predict how medications will interact in biological systems. We have discussed the different aspects of computational methods in detail, emphasizing their use in foreseeing possible adverse drug reactions (ADRs) and drug-drug interactions. These methods include molecular docking, quantitative structure-activity relationship (QSAR) modelling, and machine learning algorithms. The chapter also discusses the shortcomings and difficulties of the modelling techniques used today, including the complexity of biological systems and the need for precise data. It also examines how developments in systems biology, big data, and artificial intelligence (AI) improve the accuracy and scalability of interaction prediction. The potential paths of network-based drug discovery and network-based customized drug discovery can be centered on genome sequencing, tumor clone-based networks, hallmark-based cancer networks, and personalized medicine. This chapter is a useful resource for researchers and clinicians who want to use computational tools for investigating medication interactions, as it provides a thorough review of these methods.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.