Genetic Programming for Predicting Protein Networks

Created by W.Langdon from gp-bibliography.bib Revision:1.8051

@InProceedings{DBLP:conf/iberamia/GarciaALS08,

• author = "Beatriz Garcia and Ricardo Aler and Agapito Ledezma and Araceli Sanchis",
• title = "Genetic Programming for Predicting Protein Networks",
• booktitle = "Proceedings of the 11th Ibero-American Conference on AI, IBERAMIA 2008",
• year = "2008",
• editor = "Hector Geffner and Rui Prada and Isabel Machado Alexandre and Nuno David",
• volume = "5290",
• series = "Lecture Notes in Computer Science",
• pages = "432--441",
• address = "Lisbon, Portugal",
• month = oct # " 14-17",
• publisher = "Springer",
• note = "Advances in Artificial Intelligence",
• keywords = "genetic algorithms, genetic programming, Protein interaction prediction, data integration, bioinformatics, evolutionary computation, machine learning, classification, control bloat",
• isbn13 = "978-3-540-88308-1",
• URL = "http://www.caos.inf.uc3m.es/~beatriz/papers/garcia_et.al._iberamia08-paper_InPress.pdf",
• DOI = "doi:10.1007/978-3-540-88309-8_44",
• size = "10 pages",
• bibsource = "DBLP, http://dblp.uni-trier.de",
• abstract = "One of the definitely unsolved main problems in molecular biology is the protein-protein functional association prediction problem. Genetic Programming (GP) is applied to this domain. GP evolves an expression, equivalent to a binary classifier, which predicts if a given pair of proteins interacts. We take advantages of GP flexibility, particularly, the possibility of defining new operations. In this paper, the missing values problem benefits from the definition of if-unknown, a new operation which is more appropriate to the domain data semantics. Besides, in order to improve the solution size and the computational time, we use the Tarpeian method which controls the bloat effect of GP. According to the obtained results, we have verified the feasibility of using GP in this domain, and the enhancement in the search efficiency and interpretability of solutions due to the Tarpeian method.",
• notes = "lilgp. BIND, DIP, Butland, IntAct, EcoCyc, KEGG, iHoP. P436 Training 'instances is reduced to 264,752' Actually 10000 used for training. Function set: +, -, * and protected division, if, if_?. FS 'closed always returning the unknown value ? if any of their input values is ?'. Comparison with WEKA.",

}

Genetic Programming entries for Beatriz Garcia Ricardo Aler Mur Agapito Ledezma Araceli Sanchis

Citations