www.gp-field-guide.org.uk
Contents Top Previous Next

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 predictions about the behaviour and properties of biological systems, principally proteins. Oakley, a practising medical doctor, used GP to model blood flow in toes (Oakley1994) as part of his long term interests in frostbite.

In 2002 Banzhaf and Foster organised BioGEC: the first GECCO workshop 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 conference 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 interest are very wide data sets, with many inputs per sample (Lavington, Dewhurst, Wilkins, and Freitas1999). Examples include infrared spectra (Ellis, Broadhurst, and Goodacre2004Ellis, Broadhurst, Kell, Rowland, and Goodacre2002Goodacre2003Goodacre, Shann, Gilbert, Timmins, McGovern, Alsberg, Kell, and Logan2000Harrigan, LaPlante, Cosma, Cockerell, Goodacre, Maddox, Luyendyk, Ganey, and Roth2004Johnson, Gilbert, Winson, Goodacre, Smith, Rowland, Hall, and Kell2000McGovern, Broadhurst, Taylor, Kaderbhai, Winson, Small, Rowland, Kell, and Goodacre2002Taylor, Goodacre, Wade, Rowland, and Kell1998?), single nuclear polymorphisms (Barrett2003Reif, White, and Moore2004Shah and Kusiak2004), chest pain (Bojarczuk, Lopes, and Freitas2000), and Affymetrix GeneChip microarray data (de Sousa, de C. T. Gomes, Bezerra, de Castro, and Von Zuben2004Eriksson and Olsson2004Heidema, Boer, Nagelkerke, Mariman, van der A, and Feskens2006Ho, Hsieh, Chen, and Huang2006Hong and Cho2006Langdon and Buxton2004Li, Jiang, Li, Moser, Guo, Du, Wang, Topol, Wang, and Rao2005Linden and Bhaya2007?).

Kell and his colleagues in Aberystwyth have had great success in applying GP widely in bioinformatics (see infrared spectra above and (Allen, Davey, Broadhurst, Heald, Rowland, Oliver, and Kell2003Day, Kell, and Griffith2002Gilbert, Goodacre, Woodward, and Kell1997Goodacre and Gilbert1999Jones, Young, Taylor, Kell, and Rowland1998Kell2002a, b,cKell, Darby, and Draper2001Shaw, Winson, Woodward, McGovern, Davey, Kaderbhai, Broadhurst, Gilbert, Taylor, Timmins, Goodacre, Kell, Alsberg, and Rowland2000?)). Another very active group is that of Moore and his colleagues (Moore, Parker, Olsen, and Aune2002Motsinger, Lee, Mellick, and Ritchie2006Ritchie, Motsinger, Bush, Coffey, and Moore2007Ritchie, White, Parker, Hahn, and Moore2003).

Computational chemistry is widely used in the drug industry. The properties of simple molecules can be calculated. However, the interactions between chemicals which might be used as drugs and medicinal targets within the body are beyond exact calculation. Therefore, there is great interest in the pharmaceutical industry in approximate in silico models which attempt to predict either favourable or adverse interactions between proto-drugs and biochemical molecules. Since these are computational models, they can be applied very cheaply in advance of the manufacturing of chemicals, to decide which of the myriad of chemicals might be worth further study. Potentially, such models can make a huge impact both in terms of money and time without being anywhere near 100% correct. Machine learning and GP have both been tried. GP approaches include (Bains, Gilbert, Sviridenko, Gascon, Scoffin, Birchall, Harvey, and Caldwell2002Barrett and Langdon2006Buxton, Langdon, and Barrett2001Felton2000Globus, Lawton, and Wipke1998Goodacre, Vaidyanathan, Dunn, Harrigan, and Kell2004Harrigan et al.2004Hasan, Daugelat, Rao, and Schreiber2006Krasnogor2004Si, Wang, Zhang, Hu, and Fan2006??).


www.gp-field-guide.org.uk
Contents Top Previous Next