Meta-Dimensional Analysis of Phenotypes Using the Analysis Tool for Heritable and Environmental Network Associations (ATHENA): Challenges with Building Large Networks
The search for the underlying heritability ofcomplex traits has led to an explosion of data generation and analysis in the field of human genomics. With these technological advances, we have made some progress in the identification of genes and proteins associated with common, complex human diseases. Still, our understanding of the genetic architecture of complex traits remains limited and additional research is needed to illuminate the genetic and environmental factors important for the disease process, much of which will include looking at variation in DNA, RNA, protein, etc. in ameta-dimensional analysis framework. We have developed amachine learning technique, ATHENA: Analysis Tool for Heritable and Environmental Network Associations, to address this issue of integrating data from multiple “-omics” technologies to identify models that explain or predict the genetic architecture of complex traits. In this chapter, we discuss the challenges in handling meta-dimensional data usinggrammatical evolution neural networks (GENN) which are one modeling component ofATHENA, and a characterization of the models identified in simulation studies to explore the ability of GENN to build complex, meta-dimensional models. Challenges remain to further understand the evolutionary process for GENN, and an explanation of the simplicity of the models. This work highlights potential areas for extension and improvement of the GENN approach within ATHENA.
Key wordsGrammatical evolution Neural networks Data mining Human genetics Systems biology Meta-dimensional data
ERH was supported by NIH/NIGMS training grant T32 GM080178. MDR was supported by NIH grants LM010040 and P-STAR. P-STAR (PGRN Statistical Analysis Resource) is supported by funding from NIGMS and is part of the PGRN (Pharmacogenomics Research Network). P-STAR is a component of HL065962.
- Hamid JS et al (2009a) Data integration in genetics and genomics: methods and challenges. Hum Genomics Proteomics 2009Google Scholar
- Holzinger ER, Buchanan CC, Dudek SM, Torstenson EC, Turner SD, Ritchie MD (2010) Initialization parameter sweep in ATHENA: optimizing neural networks for detecting gene-gene interactions in the presence of small main effects. In: Branke J, Pelikan M, Alba E, Arnold DV, Bongard J, Brabazon A, Branke J, Butz MV, Clune J, Cohen M, Deb K, Engelbrecht AP, Krasnogor N, Miller JF, O’Neill M, Sastry K, Thierens D, van Hemert J, Vanneschi L, Witt C (eds) GECCO ’10: Proceedings of the 12th annual conference on Genetic and evolutionary computation, ACM, Portland, Oregon, USA, pp 203–210, DOI doi:10.1145/1830483.1830519Google Scholar
- Holzinger ER, Dudek SM, Frase AT, Fridley B, Chalise P, Ritchie MD (2012) Comparison of methods for meta-dimensional data analysis using in silico and biological data sets. In: Giacobini M, Vanneschi L, Bush WS (eds) 10th European Conference on Evolutionary Computation, Machine Learning and Data Mining in Bioinformatics, EvoBIO 2012, Springer Verlag, Malaga, Spain, LNCS, vol 7246, pp 134–143, DOI doi:10.1007/ 978-3-642-29066-4-12Google Scholar
- Koza JR, Rice JP (1991) Genetic generation of both the weights and architecture for a neural network. In: International Joint Conference on Neural Networks, IJCNN-91, IEEE Computer Society Press, Washington State Convention and Trade Center, Seattle, WA, USA, vol II, pp 397–404, DOI doi:10.1109/IJCNN.1991.155366, URL http://www.genetic-programming.com/jkpdf/ijcnn1991.pdf
- Motsinger AA, Lee SL, Mellick G, Ritchie MD (2006) GPNN: Power studies and applications of a neural network method for detecting gene-gene interactions in studies of human disease. BMC bioinformatics [electronic resource] 7(1):39–39, DOI doi:10.1186/1471-2105-7-39, URL http://www.biomedcentral.com/1471-2105/7/39
- O’Neill M, Ryan C (2001) Grammatical evolution. IEEE Transactions on Evolutionary Computation 5(4):349–358, DOI doi:10.1109/4235.942529Google Scholar
- O’Neill M, Ryan C (2003) Grammatical Evolution: Evolutionary Automatic Programming in a Arbitrary Language, Genetic programming, vol 4. Kluwer Academic Publishers, URL http://www.wkap.nl/prod/b/1-4020-7444-1
- Skapura D (1995) Building neural networks. ACM Press, New YorkGoogle Scholar
- Turner SD, Dudek SM, Ritchie MD (2010b) Grammatical evolution of neural networks for discovering epistasis among quantitative trait loci. In: Pizzuti C, Ritchie MD, Giacobini M (eds) 8th European Conference on Evolutionary Computation, Machine Learning and Data Mining in Bioinformatics (EvoBIO 2010), Springer, Istanbul, Turkey, Lecture Notes in Computer Science, vol 6023, pp 86–97, DOI doi:10. 1007/978-3-642-12211-8Google Scholar