Machine Learning approaches to improve prediction of target-drug interactions

BALATTI, GALO E; BARLETTA, PATRICIO G.; PEREZ, ANDRES, D.; GIUDICESSI, SILVANA L.; MARTÍNEZCERON, MARÍA C.

Design of New Drugs Using Machine Learning

Scrivener Publisher, Wiley

Lugar: Beverly, MA; Año: 2022; p. 1 - 77

In the initial steps of early drug discovery, the traditional techniques like docking, QSAR orMolecular Dynamics have been used for decades identifying targets, ranking molecule candidatesand optimizing the lead compounds chemically to decrease toxicity and improve drug ADME(absorption, distribution, metabolism, and excretion) properties. Nowadays, computational tools areincreasingly used not only in the drug discovery process, but also in drug development. Informationtechnologies like Artificial Intelligence (AI) and Machine Learning (ML) participate in practicallyevery step in the pharma value chain, improving and accelerating the overall drug development anddesign.Besides the rise of new methodologies, the improving of relative old computational techniques likedocking, QSAR or cavity search with new ML-based algorithms like Random Forest, Support VectorMachines or Neural Networks are being developing and promises to reduce times and operationalcosts mainly in the drug design process.In this chapter, we review some of these approaches, briefly introducing the most used ML techniques in study drug-target interactions. Also, an especial section about peptide-based drugs and its advantages over small organic molecules is discussed.