Page 139 - 49A Field Guide to Genetic Programming

12.7 Medicine, Biology and Bioinformatics 125

control laws to apply). For example, Fleming’s group in Sheffield used multi-
objective GP (Hinchliffe and Willis, 2003; Rodriguez-Vazquez, Fonseca, and
Fleming, 2004) to reduce the cost of running aircraft jet engines (Arkov,
Evans, Fleming, Hill, Norton, Pratt, Rees, and Rodriguez-Vazquez, 2000;
Evans, Fleming, Hill, Norton, Pratt, Rees, and Rodriguez-Vazquez, 2001).
Alves da Silva and Abrao (2002) surveyed GP and other AI techniques
applied in the electrical power industry.

12.7 Medicine, Biology and Bioinformatics

GP has long been applied to medicine, biology and bioinformatics. Early
work by Handley (1993) and Koza and Andre (1996) used GP to make pre-
dictions about the behaviour and properties of biological systems, principally
proteins. Oakley, a practising medical doctor, used GP to model blood flow
in toes (Oakley, 1994) as part of his long term interests in frostbite.
In 2002 Banzhaf and Foster organised BioGEC: the first GECCO work-
shop on biological applications of genetic and evolutionary computation.
BioGEC has become a bi-annual feature of the annual GECCO conference.
Half a year later Marchiori and Corne organised EvoBio: the European con-
ference on evolutionary computation, machine learning and data mining in
bioinformatics. EvoBio is held every year alongside EuroGP. GP figures
heavily in both BioGEC and EvoBIO.
GP is often used in biomedical data mining. Of particular medical in-
terest are very wide data sets, with many inputs per sample (Lavington,
Dewhurst, Wilkins, and Freitas, 1999). Examples include infrared spectra
(Ellis, Broadhurst, and Goodacre, 2004; Ellis, Broadhurst, Kell, Rowland,
and Goodacre, 2002; Goodacre, 2003; Goodacre, Shann, Gilbert, Timmins,
McGovern, Alsberg, Kell, and Logan, 2000; Harrigan, LaPlante, Cosma,
Cockerell, Goodacre, Maddox, Luyendyk, Ganey, and Roth, 2004; John-
son, Gilbert, Winson, Goodacre, Smith, Rowland, Hall, and Kell, 2000;
McGovern, Broadhurst, Taylor, Kaderbhai, Winson, Small, Rowland, Kell,
and Goodacre, 2002; Taylor, Goodacre, Wade, Rowland, and Kell, 1998;
Vaidyanathan, Broadhurst, Kell, and Goodacre, 2003), single nuclear poly-
morphisms (Barrett, 2003; Reif, White, and Moore, 2004; Shah and Kusiak,
2004), chest pain (Bojarczuk, Lopes, and Freitas, 2000), and Affymetrix
GeneChip microarray data (de Sousa, de C. T. Gomes, Bezerra, de Castro,
and Von Zuben, 2004; Eriksson and Olsson, 2004; Heidema, Boer, Nagelk-
erke, Mariman, van der A, and Feskens, 2006; Ho, Hsieh, Chen, and Huang,
2006; Hong and Cho, 2006; Langdon and Buxton, 2004; Li, Jiang, Li, Moser,
Guo, Du, Wang, Topol, Wang, and Rao, 2005; Linden and Bhaya, 2007; Yu,
Yu, Almal, Dhanasekaran, Ghosh, Worzel, and Chinnaiyan, 2007).