Genetics Research

Research Papers

Prediction of body mass index in mice using dense molecular markers and a regularized neural network

HAYRETTIN OKUTa1a2 c1, DANIEL GIANOLAa2a3a4, GUILHERME J. M. ROSAa3a4 and KENT A. WEIGELa2

a1 Department of Animal Sciences, University of Yuzuncy Yil, Van, 65080, Turkey

a2 Department of Dairy Science, University of Wisconsin, Madison, WI 53706, USA

a3 Department of Animal Sciences, University of Wisconsin, Madison, WI 53706, USA

a4 Department of Biostatistics and Medical Informatics, University of Wisconsin, Madison, WI 53706, USA

Summary

Bayesian regularization of artificial neural networks (BRANNs) were used to predict body mass index (BMI) in mice using single nucleotide polymorphism (SNP) markers. Data from 1896 animals with both phenotypic and genotypic (12 320 loci) information were used for the analysis. Missing genotypes were imputed based on estimated allelic frequencies, with no attempt to reconstruct haplotypes based on family information or linkage disequilibrium between markers. A feed-forward multilayer perceptron network consisting of a single output layer and one hidden layer was used. Training of the neural network was done using the Bayesian regularized backpropagation algorithm. When the number of neurons in the hidden layer was increased, the number of effective parameters, γ, increased up to a point and stabilized thereafter. A model with five neurons in the hidden layer produced a value of γ that saturated the data. In terms of predictive ability, a network with five neurons in the hidden layer attained the smallest error and highest correlation in the test data although differences among networks were negligible. Using inherent weight information of BRANN with different number of neurons in the hidden layer, it was observed that 17 SNPs had a larger impact on the network, indicating their possible relevance in prediction of BMI. It is concluded that BRANN may be at least as useful as other methods for high-dimensional genome-enabled prediction, with the advantage of its potential ability of capturing non-linear relationships, which may be useful in the study of quantitative traits under complex gene action.

(Received October 01 2010)

(Revised November 30 2010)

(Accepted December 06 2010)

(Online publication April 12 2011)

Correspondence:

c1 Corresponding author: University of Wisconsin 1675 Observatory Drive, Madison, WI 53703, USA. Tel: +1 608 772 4922. e-mail: okut@wisc.edu

Metrics