Group Contribution Method-based Multi-objective Evolutionary Molecular Design

Abstract

The search for compounds exhibiting desired physical and chemical properties is an essential, yet complex problem in the chemical, petrochemical, and pharmaceutical industries. During the formulation of this optimization-based design problem two tasks must be taken into consideration: the automated generation of feasible molecular structures and the estimation of macroscopic properties based on the resultant structures. For this structural characteristic-based property prediction task numerous methods are available. However, the inverse problem, the design of a chemical compound exhibiting a set of desired properties from a given set of fragments is not so well studied. Since in general design problems molecular structures exhibiting several and sometimes conflicting properties should be optimized, we proposed a methodology based on the modification of the multi-objective Non-dominated Sorting Genetic Algorithm-II (NSGA-II). The originally huge chemical search space is conveniently described by the Joback estimation method. The efficiency of the algorithm was enhanced by soft and hard structural constraints, which expedite the search for feasible molecules. These constraints are related to the number of available groups (fragments), the octet rule and the validity of the branches in the molecule. These constraints are also used to introduce a special genetic operator that improves the individuals of the populations to ensure the estimation of the properties is based on only reliable structures. The applicability of the proposed method is tested on several benchmark problems.

Hierarchical Representation Based Constrained Multi-objective Evolutionary Optimisation of Molecular Structures

“…With the multiple candidate molecules of the resultant Pareto front, several further targets can be taken into consideration: financial aspects, toxicity, availability, taste, aroma, colour, etc., thus the designer can consider personal insights during the design task. The presented algorithms have a wider application range compared to the previously published material in [32]. The defined methods worked with varying degrees of effectivity in the test problems.…”

“…The application of multi-objective genetic algorithms is a promising approach to generate the Pareto set of solutions which represent different design aspects. We demonstrated that the well-established multi-objective Non-dominated Sorting Genetic Algorithm-II (NSGA-II) is ideal tool to handle this problem [32]. There is a need to further improve this approach by increasing the efficiency of the search in the huge chemical search space represented by group contribution methods [33].…”

Building a Reusable Data Model to Support Systematic Layout Planning with Discrete Event Simulation of Flexible Manufacturing Systems

“…The depth of formation of the digital twin is determined in each case by the development goal [8]. Process development in the digital model is typically cheaper, providing more what-if analysis possibilities than an analysis or trial of a real-life production system [9].…”