Data-Driven and Artificial Intelligence Approaches for System-Wide Prediction of the Drugable Proteome to Drug Discovery in Farm Animals

A druggable proteome is of global interest for the drug development process. Growing livestock for food relies strongly on pharmacologically active chemicals, or medicines, in modern agricultural practice. The use of medications in food animals is critical for the welfare and well-being of the animals and the industry’s economics. Drug consumption, on the other hand, is linked to adverse impacts on public well-being. Therefore it is crucial to test the drug comprehensively before its use in agricultural practice. The identification of druggable proteome requires a non-trivial amount of resources and time, therefore, artificial intelligence and machine learning have emerged as invaluable tools for drawing meaningful perspectives and improving decision making in drug research. In this respect, the overall drug discovery process necessitates a long-term transition and lowers production costs. Artificial intelligence is a promising alternative for dysfunctional drug discovery and development. This chapter outlines the applications of artificial intelligence and machine learning innovations to many other techniques in drug development, such as target recognition, compound screening, lead generation and optimization, drug reaction and synergy prediction, de novo drug design, and drug repurposing.