Skip to main content

Table 1 Model learned from the T1D data set. Model learned from the T1D data set using 1-e5 as the p-value threshold, the holdout approach, AdaBoostM1 as the learning algorithm with default configuration (decision stump as the weak learning algorithm and 10 iterations)

From: A comparison of genomic profiles of complex diseases under different models

Chr Chr SNP Allele Allele Weight Genotypes Weight Genotypes
# Pos   1 2 rule 1 rule 1 rule 2 rule 2
1 77051324 SNP_A−1827111 A C 0.0801 {0, missing}   
6 32444658 SNP_A−1934589 A G 0.2326 {0}   
6 30135583 SNP_A−2111335 A G 0.2171 {0} 0.0543 {1}
6 31395153 SNP_A−2079423 C T 0.1525 {0,1}   
6 30390814 SNP_A−2222387 A G 0.0672 {0,1}   
6 31112694 SNP_A−4293786 C T 0.0517 {0,1}   
19 39266932 SNP_A−4281637 A G 0.0904 {0,1}   
  1. Weights and genotypes values are referred to class 1, i.e. absence of disease. Chromosome positions correspond to assembly NCBI dbSNP GRCh38.p2