ABSTRACT
Introduction
The implementation of Artificial Intelligence (AI) methodologies to drug discovery (DD) are on the rise. Several applications have been developed for structure-based DD, where AI methods provide an alternative framework for the identification of ligands for validated therapeutic targets, as well as the de novo design of ligands through generative models.
Areas covered
Herein, the authors review the contributions between the 2019 to present period regarding the application of AI methods to structure-based virtual screening (SBVS) which encompasses mainly molecular docking applications – binding pose prediction and binary classification for ligand or hit identification-, as well as de novo drug design driven by machine learning (ML) generative models, and the validation of AI models in structure-based screening. Studies are reviewed in terms of their main objective, used databases, implemented methodology, input and output, and key results .
Expert opinion
More profound analyses regarding the validity and applicability of AI methods in DD have begun to appear. In the near future, we expect to see more structure-based generative models- which are scarce in comparison to ligand-based generative models-, the implementation of standard guidelines for validating the generated structures, and more analyses regarding the validation of AI methods in structure-based DD.
Article highlights
Artificial Intelligence methods, specifically concerning machine learning and deep learning, have been consistently incorporated into the drug discovery pipeline.
Regarding structure-based drug discovery, reported studies show the use of AI for hit or ligand identification, binding pose prediction and de novo drug design.
Within ligand identification, several studies address finding hits in a database comprising more than a hundred million compounds by reducing calculation time with machine learning models rather than calculating docking scores for all molecules.
In comparison with ligand-based generative models, the number of structure-based generative models is low.
Standard available datasets used to validate machine learning methods in virtual screening are not always appropriate. As a consequence, the performance of reported machine learning methods may have suffered from artificial enrichment.
The advent of standard guidelines to validate machine learning methodologies in structure based virtual screening will help the field to score bigger impacts.
Disclosure statement
JI Di Filippo is a fellow and CN Cavasotto a member of CONICET . The authors have no other 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 apart from those disclosed.
Reviewer Disclosures
Peer reviewers on this manuscript have no relevant financial or other relationships to disclose.