%0 Book Section %1 koza:1996:adpmECTA %A Koza, John R. %A Andre, David %B Evolutionary Computation: Theory and Applications %C Singapore %D 1996 %E Yao, Xin %I World Scientific %K DEAD PROSITE SWISSPROT, algorithms, box, genetic programming, %T Automatic discovery of protein motifs using genetic programming %U http://www.genetic-programming.com/jkpdf/ecta1999.pdf %X Automated methods of machine learning may prove to be useful in discovering biologically meaningful information hidden in the rapidly growing databases of DNA sequences and protein sequences. Genetic programming is an extension of the genetic algorithm in which a population of computer programs is bred, over a series of generations, in order to solve a problem. Genetic programming is capable of evolving complicated problem-solving expressions of unspecified size and shape. Moreover, when automatically defined functions are added to genetic programming, genetic programming becomes capable of efficiently capturing and exploiting recurring sub-patterns. This chapter describes how genetic programming with automatically defined functions successfully evolved motifs for detecting the D-E-A-D box family of proteins and for detecting the manganese superoxide dismutase family. Both motifs were evolved without prespecifying their length. Both evolved motifs employed automatically defined functions to capture the repeated use of common subexpressions. When tested against the SWISS-PROT database of proteins, the two genetically evolved consensus motifs detect the two families either as well, or slightly better than, the comparable human-written motifs found in the PROSITE database.

@incollection{koza:1996:adpmECTA, abstract = {Automated methods of machine learning may prove to be useful in discovering biologically meaningful information hidden in the rapidly growing databases of DNA sequences and protein sequences. Genetic programming is an extension of the genetic algorithm in which a population of computer programs is bred, over a series of generations, in order to solve a problem. Genetic programming is capable of evolving complicated problem-solving expressions of unspecified size and shape. Moreover, when automatically defined functions are added to genetic programming, genetic programming becomes capable of efficiently capturing and exploiting recurring sub-patterns. This chapter describes how genetic programming with automatically defined functions successfully evolved motifs for detecting the D-E-A-D box family of proteins and for detecting the manganese superoxide dismutase family. Both motifs were evolved without prespecifying their length. Both evolved motifs employed automatically defined functions to capture the repeated use of common subexpressions. When tested against the SWISS-PROT database of proteins, the two genetically evolved consensus motifs detect the two families either as well, or slightly better than, the comparable human-written motifs found in the PROSITE database.}, added-at = {2008-06-19T17:35:00.000+0200}, address = {Singapore}, author = {Koza, John R. and Andre, David}, biburl = {https://www.bibsonomy.org/bibtex/23664c50a77e541a206522cae6e513d09/brazovayeye}, booktitle = {Evolutionary Computation: Theory and Applications}, editor = {Yao, Xin}, interhash = {7606f2fbcaa1cd016ff82b1871c70acb}, intrahash = {3664c50a77e541a206522cae6e513d09}, keywords = {DEAD PROSITE SWISSPROT, algorithms, box, genetic programming,}, note = {In Press 1997?}, notes = {ECTA, two ADFs each has OR in function set (ie combination of 2 alternative amino acids at this point). Result producing branch has AND (ie two adjacent (along backbone) amino-acids (or sets of aacids)). Covariance fitness, formula in terms of number true positives etc. Jury method: 12 motives evolved by separate GP runs combined into one by requiring unanimous jury decision. (Combined by hand or automatically?) Parallel GP system, 64 transputer nodes.}, publisher = {World Scientific}, timestamp = {2008-06-19T17:44:03.000+0200}, title = {Automatic discovery of protein motifs using genetic programming}, url = {http://www.genetic-programming.com/jkpdf/ecta1999.pdf}, year = 1996 }