Automatic molecular design using evolutionary techniques

Globus, Al; Lawton, John G.; Wipke, Todd

doi:10.1088/0957-4484/10/3/312

Cited by 70 publications

(60 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1) Similarity to a target molecule [8,10] 2) QSAR-functions [14] 3) Docking [15,19] 4) Experiment [11] For drug design, each of these methods has its advantages and disadvantages. Similarity to a target molecule results in molecules very similar to the target molecule, in many cases even the target molecule itself, which is not useful for designing new molecules.…”

Section: Fitnessmentioning

confidence: 99%

“…Atom-based algorithms work by mutating atoms, and can therefore fine-tune each structure optimally. This approach has been chosen in many articles [4,8,10,14]. On the other hand, several investigators construct molecules using larger fragments [17,19].…”

Section: The Molecule Representationmentioning

confidence: 99%

“…There have been several experiments in de novo drug design using evolutionary algorithms [8,9,10,14,15,17,19]. However, reviewing these experiments leads to the conclusion that despite the power inherent to global optimization methods, evolutionary algorithms are still difficult to apply to molecule design.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

The Molecule Evoluator. An Interactive Evolutionary Algorithm for the Design of Drug-Like Molecules

Lameijer

Kok

Bäck

et al. 2006

J. Chem. Inf. Model.

View full text Add to dashboard Cite

To help chemists design new drugs, we created a tool that uses interactive evolution to design drug molecules, the "Molecule Evoluator". In contrast to most other evolutionary de novo design programs, the molecule representation and the set of mutations enable it to both search the chemical space of all drug like molecules extensively and to fine-tune molecular structures to the problem at hand. Additionally, we use interaction with the user as a fitness function, which is new in evolutionary algorithms in drug design. This interactivity allows the Molecule Evoluator to use the domain knowledge of the chemist to estimate the ease of synthesis and the biological activity of the compound. This knowledge can guide the optimization process and thereby improve its results. Chemists of our department using the Molecule Evoluator were able to find six novel and synthesizable druglike core structures, indicating that the Molecule Evoluator can be used as a tool to enhance the chemist's creativity.

show abstract

Section: Fitnessmentioning

confidence: 99%

Section: The Molecule Representationmentioning

confidence: 99%

See 1 more Smart Citation

The Molecule Evoluator. An Interactive Evolutionary Algorithm for the Design of Drug-Like Molecules

Lameijer

Kok

Bäck

et al. 2006

J. Chem. Inf. Model.

View full text Add to dashboard Cite

show abstract

“…A quasi-natural approach for the finding of optimal peptide sequences is the use of evolutionary algorithms, and there have been a number of reports on the successful optimization of nonpeptidic drugs (Globus et al, 1999;Goh and Foster, 2000) and peptides with respect to a single objective using such methods (Jones, 1994;Campbell et al, 2002). Here we show that it is possible to generalize the evolutionary approach to the systematic solution of the multiobjective problem described above, with the three objectives being maximization of similarity to an epitope, maximization of stability, and minimization of peptide chain length.…”

Section: Introductionmentioning

confidence: 99%

A Multiobjective Evolutionary Method for the Design of Peptidic Mimotopes

Hohm

Limbourg

Hoffmann

2006

Journal of Computational Biology

View full text Add to dashboard Cite

Peptides that mimic protein epitopes are interesting drug candidates. However, the design of effective peptidic drugs is difficult for several reasons, such as the fast degradation of peptides, their high flexibility, and thus high entropy loss on binding to the target. We therefore propose an in silico method for the automated design of peptides that are optimal with respect to several objectives. We present a Pareto-based multiobjective evolutionary algorithm for in silico peptide design. Using a simple molecular model, we apply the method to the design of peptides that (a) mimic antibody epitopes of the proteins thrombin and blood coagulation factor VIII, respectively, that (b) are short, and (c) are conformationally stable.

show abstract

“…Several attempts to generate graphs using evolutionary approaches have also been done. Methods have been proposed in the fields of molecular design [10] and electrical circuit design [11], using a direct encoding of the evolving graph. It is worth noting that these methods define evolutionary operators tailored for the considered problem.…”

Section: Introductionmentioning

confidence: 99%

EvoGeneS, a New Evolutionary Approach to Graph Generation

Cordella

Stefano

Fontanella

et al. 2005

Evolutionary Computation in Combinatorial Optimization

View full text Add to dashboard Cite

Abstract. Graphs are powerful and versatile data structures, useful to represent complex and structured information of interest in various fields of science and engineering. We present a system, called EvoGeneS, based on an evolutionary approach, for generating undirected graphs whose number of nodes is not a priori known. The method is based on a special data structure, called multilist, which encodes undirected attributed relational graphs. Two novel crossover and mutation operators are defined in order to evolve such structure. The developed system has been tested on a wireless network configuration and the results compared with those obtained by a genetic programming based approach recently proposed in the literature.

show abstract

Automatic molecular design using evolutionary techniques

Abstract: Abstract

Cited by 70 publications

References 8 publications

The Molecule Evoluator. An Interactive Evolutionary Algorithm for the Design of Drug-Like Molecules

The Molecule Evoluator. An Interactive Evolutionary Algorithm for the Design of Drug-Like Molecules

A Multiobjective Evolutionary Method for the Design of Peptidic Mimotopes

EvoGeneS, a New Evolutionary Approach to Graph Generation

Contact Info

Product

Resources

About