Artificial neural network-based inference of drug-target interactions

Siyabonga Melamane, Tavonga T. Manadava, Arthur Manda, Nonhlanhla Luphade, Sandile M.M. Khamanga, Pedzisai A. Makoni, Patrick H. Demana, Scott K. Matafwali, Bwalya A. Witika

Research output: Chapter in Book/Report/Conference proceedingChapterpeer-review

Abstract

The emergence of resistant superbugs, as well as new pandemics, has necessitated the need for the development of more efficient processes. Traditionally, the process can be very long and have a very high cost. Some of these costs and time constraints are a direct consequence of the prediction of drug-target interactions (DTI). It is of utmost importance to develop medicines whose interaction with their target can be performed cost-effectively and at breakneck speed. Artificial intelligence (AI) has made this highly possible and effective. One of the more useful aspects of AI is artificial neural networks (ANNs). ANNs make use of a simulated trainable brain capable of performing nonparametric tasks that do not assume an a priori relationship between the variables investigated and the dataset. In this chapter, we discuss the various roles of ANNs in prediction and value in DTI to improve drug discovery and repurposing.

Original languageEnglish
Title of host publicationNanotechnology Principles in Drug Targeting and Diagnosis
PublisherElsevier
Pages35-62
Number of pages28
ISBN (Electronic)9780323917636
ISBN (Print)9780323983488
DOIs
Publication statusPublished - 1 Jan 2023

Keywords

  • Artificial neural networks
  • drug development
  • drug discovery
  • drug repurposing
  • drug-target interactions

Fingerprint

Dive into the research topics of 'Artificial neural network-based inference of drug-target interactions'. Together they form a unique fingerprint.

Cite this