Corpus ID: 8969100

Opleiding Informatica An evolutionary algorithm for finding diverse sets of molecules with user-defined properties

  title={Opleiding Informatica An evolutionary algorithm for finding diverse sets of molecules with user-defined properties},
  author={Benjamin van der Burgh},
The multidisciplinary field of drug discovery deals with the discovery and synthesis of novel medications. For over half a century, Computer Science has aided chemists in exploring the extremely large chemistry space that comprises the set of all drug-like molecules. But only in recent years, the technological advances in computational power and the development of novel algorithms have enabled researchers to start experimenting with in silico screening of promising compounds. While many classes… Expand
Indicator-Based Evolutionary Level Set Approximation: Mixed Mutation Strategy and Extended Analysis
The results are promising and show that even for difficult problems in moderate dimension the proposed evolutionary level set approximation algorithm (ELSA) can serve as a versatile and robust meta-heuristic. Expand
Indicator-Based Evolutionary Level Set Approximation: Foundations and Empirical Studies
The aim of the Black Box Level Set Approximation Problem is to find an approximation of the set of inputs of a function that give rise to a targeted output below a threshold. The motivation forExpand


The Molecule Evoluator. An Interactive Evolutionary Algorithm for the Design of Drug-Like Molecules
A software tool to design drug-like molecules, the Molecule Evoluator, is developed, which brings a human being's creativity, implicit knowledge, and imagination into the design process, next to the more standard chemical rules. Expand
A knowledge-based approach in designing combinatorial or medicinal chemistry libraries for drug discovery. 1. A qualitative and quantitative characterization of known drug databases.
The effective range of physicochemical properties presented here can be used in the design of drug-like combinatorial libraries as well as in developing a more efficient corporate medicinal chemistry library. Expand
Molecular optimization using computational multi-objective methods.
This paper first presents a brief introduction to issues related to MOOP and then surveys the application of MOOP methods in the field of chemoinformatics. Expand
Beyond mere diversity: tailoring combinatorial libraries for drug discovery.
Library design requires a synergistic effort between computational and synthetic medicinal chemists, so specialized interactive software has been developed to integrate substructure searching, display, and statistical experimental design to facilitate this interaction for the effective design of well-tailored libraries. Expand
Computer-based de novo design of drug-like molecules
This review outlines the various design concepts and highlights current developments in computer-based de novo design of hit and lead structure candidates for drug discovery projects. Expand
Chemoinformatics—an introduction for computer scientists
The emphasis is placed on describing the general methods that are routinely applied in molecular discovery and in a context that provides for an easily accessible article for computer scientists as well as scientists from other numerate disciplines. Expand
Combining Aggregation with Pareto Optimization: A Case Study in Evolutionary Molecular Design
It is proposed to reduce a many objective problem to a multi-objective optimization problem with a low number of objectives, for which the visualization of the Pareto front is still possible and the size of a high-resolution approximation set is affordable. Expand
A Modification of the Jaccard–Tanimoto Similarity Index for Diverse Selection of Chemical Compounds Using Binary Strings
A new association coefficient is developed that overcomes an intrinsic bias toward smaller compounds when used to select compounds for an optimal spread design and contrasts the two coefficients for selecting diverse sets of compounds from a large collection. Expand
Experimental and computational approaches to estimate solubility and permeability in drug discovery and development settings.
Experimental and computational approaches to estimate solubility and permeability in discovery and development settings are described and useful predictions are possible in closely related analog series when coupled with experimental thermodynamicsolubility measurements. Expand
Maximizing population diversity in single-objective optimization
NoAH is proposed, an evolutionary algorithm which solves a mixed multi-objective problem by iteratively switching between objective value and set-diversity optimization while automatically adapting a constraint on the objective value until it reaches the barrier. Expand