Multi-Objective Optimization Methods in De Novo Drug Design

Abstract

De-novo drug design (DND) is a complex procedure, requiring the satisfaction of many pharmaceutically important objectives. Several computational methodologies employing various optimization approaches have been developed to search for satisfactory solutions to this multi-objective problem varying from composite methods, which transform the problem to a single objective one to Pareto methods searching for numerous solutions compromising the objectives. In this review we initially focus on the DND problem and the challenges it poses to computational methods, followed by an examination of the reported methodologies and specific applications. Emphasis is placed on the multiobjective nature of the problem, related considerations and the solutions proposed by the drug discovery community.

Advancing drug discovery via GPU-based deep learning

“…Novel, auto-generated molecular representations hold potential to augment our view of bioactive molecules by one-to-one mapping between representations and resulting properties. Multi-criteria optimization for compound generation and selection reflects the reality of pharmaceutical design, where methods such as Pareto curve analysis can identify the set of compounds such that no compound is more superior to another compound in all design objective criteria [18,19]. Deep network models are able to inherently capture multiple design criteria (e.g.…”

Evolutionary algorithms for de novo drug design – A survey

“…In de novo drug design, the drug molecules are constructed in two ways, using either atoms or molecular fragments [6,35]. When the drug is constructed by the atom based method, the chemical search space is huge and it is possible to arrive at a number of novel chemical structures.…”

“…De novo drug design is to generate novel molecular structure with desired biological activity and match the binding pattern of the biological target. Based on the binding pattern, there are two different de novo design techniques: Structure-based and ligand-based methods [6,35]. The overall classification of de novo drug design is shown in Fig.…”

“…This paper surveys the developments in the field of de novo drug design, with particular emphasis on the evolutionary algorithms involved in the design. Though there are few excellent reviews related to CADD [32][33][34], and the application of soft computing techniques in drug discovery process [2], they lack the coverage of all the de novo design tools available to date which utilizes evolutionary algorithms [5,6,35]. The rest of the paper is organized as follows: Section 2 describes the concept of de novo drug design, Sections 3-5 deal with evolutionary algorithm techniques and their types.…”

Development of a New De Novo Design Algorithm for Exploring Chemical Space

“…General de novo design methods deal with only one property: the biological activity for the target. Multi-objective optimization [13] is a valuable approach for solving this problem, and several de novo design methods have been developed to use multi-objective optimization methods. [14,15] Using these methods, we can find new molecules that have desired biological and physical properties, such as both binding affinity and toxicity.…”