Evolution of a Computer Program for Classifying Protein Segments as Transmembrane Domains Using Genetic Programming

The recently-developedgenetic programming paradigmisused to evoIve a computer program to classify a given protein segment as being a transmembrane domainor non-uansmembranearea of the protein. Genetic programming starts with a primordial ooze of randomly generated computer programs composed of available programmatic ingredients and then genetically breeds the . population of programs using the Darwinian principle of survival of the fittest and an analog of the nalurally occurring genetic operationof crossover (sexualrecombination).Automatic function definitionenables genetic programmingto dynamically create subrourines dynamically during the run. Geneticprogrammingis given a trainingset of differently-sized protein segments and their u > m t classificafion (butno biochemical knowledge. such as hydrophobicity values). Correlation is used as the fitness measure to drive the evolutionary process. The best genetically-evolved program achieves an out-of-sample correlationof 0.968 and

• Type: Conference
• Year: 1994
• Where: ISMB
• Authors: John R. Koza
• Keywords: Computational Biology, Genetic Operationof Crossover, ISMB 1994, Protein Segments, Transmembrane Domainor Non-uansmembranearea