Automatic molecular design using evolutionary techniques

by

Globus, A., Lawtonb, J. and Wipkeb, T.

Literature search on Evolutionary ComputationBBase ©1999-2013, Rasmus K. Ursem
     Home · Search · Adv. search · Authors · Login · Add entries   Webmaster
Note to authors: Please submit your bibliography and contact information - online papers are more frequently cited.

Info: The Sixth Foresight Conference on Molecular Nanotechnology (Conference proceedings), 1998
Keywords:genetic algorithms, genetic programming, ring crossover, graphs, drugs
Abstract:
Molecular nanotechnology is the precise, three-dimensional control of materials and devices at the atomic scale. An important part of nanotechnology is the design of molecules for specific purposes. This paper describes early results using genetic software techniques to automatically design molecules under the control of a fitness function. [FF] The fitness function [FF] must be capable of determining which of two arbitrary molecules is better for a specific task. The software begins by generating a population of random molecules. The population is then evolved towards greater fitness by randomly combining parts of the better individuals to create new molecules. These new molecules then replace some of the worst molecules in the population. The unique aspect of our approach is that we apply genetic crossover to molecules represented by graphs, i.e., sets of atoms and the bonds that connect them. We present evidence suggesting that crossover alone, operating on graphs, can evolve any possible molecule given an appropriate fitness function [FF] and a population containing both rings and chains. Prior work evolved strings or trees that were subsequently processed to generate molecular graphs. In principle, genetic graph software should be able to evolve other graph representable systems such as circuits, transportation networks, metabolic pathways, computer networks, [MP] etc.
Notes:
http://www.foresight.org/Conferences/MNT6/index.html
URL(s):(G)zipped postscript
HTML

Review item:

Mark as doublet (will be reviewed)

Print entry



BibTex:
@InProceedings{globus:1998:amduet,
  author =       "Al Globus and John Lawtonb and Todd Wipkeb",
  title =        "Automatic molecular design using evolutionary
                 techniques",
  booktitle =    "The Sixth Foresight Conference on Molecular
                 Nanotechnology",
  year =         "1998",
  editor =       "Al Globus and Deepak Srivastava",
  address =      "Westin Hotel in Santa Clara, CA, USA",
  month =        nov # " 12-15, 1998",
  organisation = "Foresight Institute",
  keywords =     "genetic algorithms, genetic programming, ring
                 crossover, graphs, drugs",
  URL =          "http://www.foresight.org/Conferences/MNT6/Papers/Globus/index.html",
  abstract =     "Molecular nanotechnology is the precise,
                 three-dimensional control of materials and devices at
                 the atomic scale. An important part of nanotechnology
                 is the design of molecules for specific purposes. This
                 paper describes early results using genetic software
                 techniques to automatically design molecules under the
                 control of a fitness function. The fitness function
                 must be capable of determining which of two arbitrary
                 molecules is better for a specific task. The software
                 begins by generating a population of random molecules.
                 The population is then evolved towards greater fitness
                 by randomly combining parts of the better individuals
                 to create new molecules. These new molecules then
                 replace some of the worst molecules in the population.
                 The unique aspect of our approach is that we apply
                 genetic crossover to molecules represented by graphs,
                 i.e., sets of atoms and the bonds that connect them. We
                 present evidence suggesting that crossover alone,
                 operating on graphs, can evolve any possible molecule
                 given an appropriate fitness function and a population
                 containing both rings and chains. Prior work evolved
                 strings or trees that were subsequently processed to
                 generate molecular graphs. In principle, genetic graph
                 software should be able to evolve other graph
                 representable systems such as circuits, transportation
                 networks, metabolic pathways, computer networks, etc.",
  notes =        "http://www.foresight.org/Conferences/MNT6/index.html",
}