Genetic programming for combining neural networks for drug discovery

We have previously shown [Langdon and Buxton, 2001b] on a range of benchmarks genetic programming (GP) can automatically fuse given classifiers of diverse types to produce a combined classifier whose Receiver Operating Characteristics (ROC) are better than [Scott et al., 1998]’s “Maximum Realisable Receiver Operating Characteristics” (MRROC). i.e. better than their convex hull. Here our technique is used in a blind trial where artificial neural networks are trained by Clementine on P450 pharmaceutical data. Using just the networks, GP automatically evolves a composite classifier.

[1]  Nitesh V. Chawla,et al.  SMOTE: Synthetic Minority Over-sampling Technique , 2002, J. Artif. Intell. Res..

[2]  William B. Langdon,et al.  Genetic programming for combining classifiers , 2001 .

[3]  J A Swets,et al.  Better decisions through science. , 2000, Scientific American.

[4]  William B. Langdon,et al.  Combining Decision Trees and Neural Networks for Drug Discovery , 2002, EuroGP.

[5]  William B. Langdon,et al.  Genetic Programming for Improved Receiver Operating Characteristics , 2001, Multiple Classifier Systems.

[6]  Mahesan Niranjan,et al.  Realisable Classifiers: Improving Operating Performance on Variable Cost Problems , 1998, BMVC.

[7]  Riccardo Poli,et al.  The evolution of size and shape , 1999 .

[8]  Sean Luke,et al.  A survey and comparison of tree generation algorithms , 2001 .

[9]  John R. Koza,et al.  Genetic programming - on the programming of computers by means of natural selection , 1993, Complex adaptive systems.

[10]  Brian A. Baertlein,et al.  Feature-Level and Decision-Level Fusion of Noncoincidently Sampled Sensors for Land Mine Detection , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  Peter D. Turney.  Cost-Sensitive Classification: Empirical Evaluation of a Hybrid Genetic Decision Tree Induction Algorithm , 1994, J. Artif. Intell. Res..

[12]  William B. Langdon.  Data structures and genetic programming , 1995 .

[13]  Matthew A. Kupinski,et al.  Multiobjective Genetic Optimization of Diagnostic Classifiers with Implications for Generating ROC Curves , 1999, IEEE Trans. Medical Imaging.

[14]  Geoffrey E. Hinton,et al.  Adaptive Mixtures of Local Experts , 1991, Neural Computation.

[15]  Riccardo Poli,et al.  Foundations of Genetic Programming , 1999, Springer Berlin Heidelberg.

[16]  Arthur K. Kordon,et al.  Soft sensor development using genetic programming , 2001 .

[17]  William J. Christmas,et al.  Combining multiple experts for classifying shot changes in video sequences , 1999, Proceedings IEEE International Conference on Multimedia Computing and Systems.

[18]  Peter J. Angeline,et al.  Multiple Interacting Programs: a Representation for Evolving Complex Behavior , 1998, Cybern. Syst..

[19]  William B. Langdon,et al.  Size fair and homologous tree genetic programming crossovers , 1999 .

[20]  Matthew A. Kupinski,et al.  Multiobjective genetic optimization of diagnostic classifiers used in the computerized detection of mass lesions in mammography , 2000, Medical Imaging: Image Processing.

[21]  William B. Langdon,et al.  Evolving Receiver Operating Characteristics for Data Fusion , 2001, EuroGP.

[22]  William B. Langdon,et al.  Size Fair and Homologous Tree Crossovers for Tree Genetic Programming , 2000, Genetic Programming and Evolvable Machines.

[23]  Terence Soule,et al.  Voting teams: a cooperative approach to non-typical problems using genetic programming , 1999 .