Review
Applications of genetic programming in cancer research

https://doi.org/10.1016/j.biocel.2008.09.025Get rights and content

Abstract

The theory of Darwinian evolution is the fundamental keystones of modern biology. Late in the last century, computer scientists began adapting its principles, in particular natural selection, to complex computational challenges, leading to the emergence of evolutionary algorithms. The conceptual model of selective pressure and recombination in evolutionary algorithms allow scientists to efficiently search high dimensional space for solutions to complex problems. In the last decade, genetic programming has been developed and extensively applied for analysis of molecular data to classify cancer subtypes and characterize the mechanisms of cancer pathogenesis and development. This article reviews current successes using genetic programming and discusses its potential impact in cancer research and treatment in the near future.

Section snippets

Background

Darwin's fundamental insight into the nature of evolution has been one of the cornerstones of modern biology. The diversity of species and individuals in the fossil record shows the evolution of complex features, not once, but many times, demonstrating that evolution is a powerful, creative force. Starting in the late 1950s, computer scientists began using the concepts of evolution and natural selection to find creative solutions for computing problems (Fraser, 1957, Barricelli, 1957,

Cancer treatment and research

Genetic programming has been used in a number of areas of cancer research as well as clinical treatment. The advent of modern molecular techniques such as microarrays, proteomics and single nucleotide polymorphism arrays (SNP chips) has provided a large amount of interrelated data that is not easily modeled using conventional data analysis methods. Genetic programming has been used alone, and in combination with other methods to produce useful and informative analyses. Some of these

Other applications

In addition to the cancer-specific papers outlined above, GP has applications in other areas that may have an impact on cancer research and treatment in the future. This includes studies on drug discovery and development (Langdon, 2008a, Archetti et al., 2007) and modeling of dynamic processes such as deducing a metabolic pathway from empirical data (Koza et al., 2001). Reif et al. (2004) demonstrate GP's ability to integrate diverse types of complex molecular data to produce a model based in

Conclusion

Genetic programming has a growing record of success in the analysis of large, complex data sets associated with cancer both from a research perspective and from a clinical context. Its abilities to find useful combinations of features from molecular data set in an unbiased way and to produce human comprehensible non-linear models to describe disease states and characteristics make it particularly useful for such analyses.

Though the development of artificial populations competing within a

Disclosures

W.P.W serves as Genetics Squared's Chief Executive Officer and A.M.C is a member of Scientific Advisory Board for Genetics Squared, Inc.

References (47)

  • N.L. Cramer

    A representation for the adaptive generation of simple sequential programs

  • Digital Database of Screening Mammography....
  • J.A. Driscoll et al.
  • L.J. Fogel et al.

    Artificial intelligence through simulated evolution

    (1966)
  • R. Forsyth

    Beagle: A Darwinian approach to pattern recognition

    Kybernetes

    (1981)
  • A.S. Fraser

    Simulation of genetic systems by automatic digital computers. I. Introduction

    Aust J Biol Sci

    (1957)
  • R.M. Friedberg

    A learning machine. Part 1

    IBM J Res Dev

    (1958)
  • GENICA: Interdisciplinary Study Group on Gene Environment Interaction and Breast Cancer in Germany....
  • R.J. Gilbert et al.

    Genomic computing: explanatory modelling for functional genomics

  • H.F. Gray et al.

    Genetic programming for classification and feature selection: analysis of 1H nuclear magnetic resonance spectra from human brain tumour biopsies

    NMR Biomedicine

    (1998)
  • M. Hinchliffe et al.

    Dynamic chemical process modelling using a multiple basis function genetic programming algorithm

  • J.H. Holland

    Outline for a logical theory of adaptive systems

    J ACM

    (1962)
  • J.H. Hong et al.

    • Cited by (0)

    View full text
    Copyright © 2008 Elsevier Ltd. All rights reserved.