Classifying protein segments as transmembrane domains using architecture-altering operations in genetic programming

The biological theory of gene duplication, concerning how new structures and new behaviors are created in living things, is brought to bear on the problem of automated architecture discovery in genetic programming. Using architecture-altering operations patterned after naturally-occurring gene duplication, genetic programming is used to evolve a computer program to classify a given protein segment as being a transmembrane domain or non-transmembrane area of the protein. The out-of-sample error rate for the best genetically-evolved program achieved was slightly better than that of previously-reported human-written algorithms for this problem. This is an instance of an automated machine learning algorithm rivaling a human-written algorithm for a problem. 8.1 Introduction and Overview The goal of automatic programming is to create, in an automated way, a computer program that enables a computer to solve a problem. Ideally, an automatic programming system should require that the user pre-specify as little as possible about the problem environment. In particular, it is desirable that the use