Molecular representations in AI-driven drug discovery: a review and practical guide

Abstract

The technological advances of the past century, marked by the computer revolution and the advent of high-throughput screening technologies in drug discovery, opened the path to the computational analysis and visualization of bioactive molecules. For this purpose, it became necessary to represent molecules in a syntax that would be readable by computers and understandable by scientists of various fields. A large number of chemical representations have been developed over the years, their numerosity being due to the fast development of computers and the complexity of producing a representation that encompasses all structural and chemical characteristics. We present here some of the most popular electronic molecular and macromolecular representations used in drug discovery, many of which are based on graph representations. Furthermore, we describe applications of these representations in AI-driven drug discovery. Our aim is to provide a brief guide on structural representations that are essential to the practice of AI in drug discovery. This review serves as a guide for researchers who have little experience with the handling of chemical representations and plan to work on applications at the interface of these fields.

Applications of Virtual Screening in Bioprospecting: Facts, Shifts, and Perspectives to Explore the Chemo-Structural Diversity of Natural Products

“…(Lo et al, 2018 ), molecular fingerprints (Zhang et al, 2018 ), functional groups, molecular shape (Bonanno and Ebejer, 2020 ), and pharmacophores (Sato et al, 2010 ); in the case of proteins and peptides, some molecular descriptors include amino acid sequence composition (Wei et al, 2017 ; Manavalan et al, 2018 ; Qiang et al, 2018 ). The choice of the molecular representation and the type of molecular descriptor determine the efficiency and the interpretability of the final results obtained by the ML algorithms (David et al, 2020 ; Jiménez-Luna et al, 2020 ). In structure-based strategies, ML algorithms have been used in scoring the functions of molecular docking methods, seeking rank compound libraries based on their predicted affinity against a molecular target, and discriminating between hits and decoy compounds.…”

Advances in De Novo Drug Design: From Conventional to Machine Learning Methods

“…For the generative model, a multilayer artificial neural network is used. Depending on the type of artificial network, the input layer might consist of SMILES or graphs of molecules [ 84 ]. SMILES represents a molecule as a sequence of characters corresponding to atoms and special characters denoting connectivity [ 85 ].…”

Proposal of the Annotation of Phosphorylated Amino Acids and Peptides Using Biological and Chemical Codes

“…The chemical languages are used to annotate peptides in chemical databases, such as PubChem, ChemSpider, and ChEMBL. Codes used for peptide annotation have been recently discussed by David et al [ 31 ].…”