Comparison of artificial neural network analysis with other multimarker methods for detecting genetic association

BMC Genomic Data

Table 1 Relative power of heterogeneity tests, logistic regression, UNPHASED analyses and ANN analysis to detect association at p < 0.01 in a case control study using different disease models

Chromosome	Penetrance values	Power of heterogeneity test of haplotype frequencies	Power of heterogeneity test using permutation testing	Power of logistic regression analysis	Power of UNPHASED analysis using haplotype effects	Power of UNPHASED analysis using allele effects	Power of ANN analysis
7	0.01, 0.02, 0.02	0.48	0.50	0.50	0.54	0.48	0.52
7	0.01, 0.03, 0.03	0.58	0.60	0.61	0.60	0.59	0.68
17	0.01, 0.02, 0.02	0.29	0.30	0.31	0.31	0.29	0.34
17	0.01, 0.03, 0.03	0.36	0.37	0.36	0.37	0.36	0.44
7	0.01, 0.01, 0.02	0.37	0.43	0.38	0.42	0.40	0.46
7	0.01, 0.01, 0.03	0.48	0.48	0.48	0.52	0.51	0.60
17	0.01, 0.01, 0.02	0.31	0.33	0.34	0.37	0.35	0.34
17	0.01, 0.01, 0.03	0.54	0.54	0.57	0.58	0.58	0.58
All combined		0.42	0.44	0.44	0.45	0.44	0.48

ISSN: 2730-6844