Genetic diversity: applications of evolutionary algorithms to combinatorial library design

Rd, Brown; Clark, DE

doi:10.1517/13543776.8.11.1447

Cited by 19 publications

(4 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The algorithm terminates when satisfying solutions are found. Recently, EAs have been applied for problems such as lead structure discovery and optimization and computer-assisted molecule design (see refs [9][10][11][12][13][14][15]. Most of these applications involve the chemical structure search in a conformational space.…”

Section: Evolutionary Algorithmsmentioning

confidence: 99%

Evolutionary-Algorithm-Based Strategy for Computer-Assisted Structure Elucidation

Han

Steinbeck

2004

J. Chem. Inf. Comput. Sci.

View full text Add to dashboard Cite

An evolutionary algorithm (EA) using a graph-based data structure to explore the molecular constitution space is presented. The EA implementation proves to be a promising alternative to deterministic approaches to the problem of computer-assisted structure elucidation (CASE). While not relying on any external database, the EA-guided CASE program SENECA is able to find correct solutions within calculation times comparable to that of other CASE expert systems. The implementation presented here significantly expands the size limit of constitutional optimization problems treatable with evolutionary algorithms by introducing novel efficient graph-based genetic operators. The new EA-based search strategy is discussed including the underlying data structures, component design, parameter optimization, and evolution process control. Typical structure elucidation examples are given to demonstrate the algorithm's performance.

show abstract

Section: Evolutionary Algorithmsmentioning

confidence: 99%

Evolutionary-Algorithm-Based Strategy for Computer-Assisted Structure Elucidation

Han

Steinbeck

2004

J. Chem. Inf. Comput. Sci.

View full text Add to dashboard Cite

show abstract

“…Already then it was observed that genetic algorithms in general do not find the best solutions compared to specialized algorithms. Nevertheless, they were successively used in several other articles about denovo design of diverse libraries. , However, the evolved individuals are not molecules by themselves but rather several building blocks that are later on synthesized to molecules. In the latter publication, diversity selection has even been combined with other objectives rendering it a multiobjective optimization problem.…”

Section: Related Workmentioning

confidence: 99%

Maximum-Score Diversity Selection for Early Drug Discovery

Meinl

Ostermann

Berthold

2011

J. Chem. Inf. Model.

View full text Add to dashboard Cite

Diversity selection is a common task in early drug discovery. One drawback of current approaches is that usually only the structural diversity is taken into account, therefore, activity information is ignored. In this article, we present a modified version of diversity selection, which we term Maximum-Score Diversity Selection, that additionally takes the estimated or predicted activities of the molecules into account. We show that finding an optimal solution to this problem is computationally very expensive (it is NP-hard), and therefore, heuristic approaches are needed. After a discussion of existing approaches, we present our new method, which is computationally far more efficient but at the same time produces comparable results. We conclude by validating these theoretical differences on several data sets.

show abstract

“…Novel structures are generated through the elements of mutation and crossover of bits from the strings of structures with desired properties, thus mimicking the processes found in biological evolution. Genetic algorithms find widespread use for the virtual design of compound collections -probing against in silico parameters and thus working in a self-consistent system [28][29][30], but only few evolution experiments have been based on the biochemical selection of compounds. Searching for optimum substrates of stromelysin, Singh et al searched the space of the 64,000,000 hexapeptides that can be generated from the 20 naturally occurring amino acids.…”

Section: Chemical Evolution and Dynamic Com-binatorial Chemistrymentioning

confidence: 99%

Combinatorial Chemistry and Fragment Screening - Two Unlike Siblings?

Nestler¹

2005

CDDT

View full text Add to dashboard Cite

Efficiently scouting the chemical space is one of the major challenges for lead discovery for drug development. In recent times some shifts have been made away from HTS and combinatorial chemistry to more focused approaches. Combinatorial chemistry was the starting point for the development of synthesis concepts that were intended to cover and explore the chemical space without having to prepare every individual compound. In this review, these lead finding approaches will be discussed comparing virtual and synthesized libraries. In addition we discuss the concepts and relationships of evolutionary libraries using genetic algorithms and dynamic combinatorial chemistries, as well as templated fragment ligation concepts. Taking a more abstract view of all approaches, the concepts may loop back into Combinatorial Chemistry allowing a more educated choice of building blocks and chemistries.

show abstract

Genetic diversity: applications of evolutionary algorithms to combinatorial library design

Cited by 19 publications

References 39 publications

Evolutionary-Algorithm-Based Strategy for Computer-Assisted Structure Elucidation

Evolutionary-Algorithm-Based Strategy for Computer-Assisted Structure Elucidation

Maximum-Score Diversity Selection for Early Drug Discovery

Combinatorial Chemistry and Fragment Screening - Two Unlike Siblings?

Contact Info

Product

Resources

About