Table 2 Comparison of the prediction rule between the empirical Bayes and other classifiers
From: Large-scale risk prediction applied to Genetic Analysis Workshop 17 mini-exome sequence data
Feature | Empirical Bayes method | Random forest classifier | Logistic regression | ||||||
|---|---|---|---|---|---|---|---|---|---|
Genes | #SNP | MAF | Genes | #SNP | MAF | Genes | #SNP | MAF | |
1 | Age | Age | Age | ||||||
2 | Smoke | Smoke | Smoke | ||||||
3 | ATP11A | 1 | 0.29 | FLT1 | 25 | <0.01 | SUSD2 | 36 | <0.01 |
7 | 0.01–0.05 | 6 | 0.01–0.05 | ||||||
3 | ≥0.05 | 3 | ≥0.05 | ||||||
4 | FLT1 | 25 | <0.01 | SUSD2 | 36 | <0.01 | ATP11A | 1 | 0.29 |
7 | 0.01–0.05 | 6 | 0.01–0.05 | ||||||
3 | ≥0.05 | 3 | ≥0.05 | ||||||
5 | SUSD2 | 36 | SHD | 10 | < 0.01 | BUD13 | 1 | 0.11 | |
6 | 1 | 0.01–0.05 | |||||||
3 | 2 | ≥0.05 | |||||||
6 | BUD13 | 1 | 0.11 | RIPK3 | 17 | <0.01 | RIPK3 | 17 | <0.01 |
2 | 0.01–0.05 | 2 | 0.01–0.05 | ||||||
2 | ≥0.05 | 2 | ≥0.05 | ||||||
7 | RIPK3 | 17 | <0.01 | ADAMTS4 | 23 | <0.01 | FLT1 | 25 | <0.01 |
2 | 0.01–0.05 | 4 | 0.01–0.05 | 7 | 0.01–0.05 | ||||
2 | ≥0.05 | 3 | ≥0.05 | 3 | ≥0.05 | ||||
8 | C10ORF107 | 1 | 0.13 | CECR1 | 8 | <0.01 | MAP3K12 | 14 | <0.01 |
0.01–0.05 | 3 | 0.01–0.05 | |||||||
4 | ≥0.05 | ≥0.05 | |||||||
9 | ADAMTS4 | 33 | <0.01 | GOLGA1 | 1 | <0.01 | ADAMTS4 | 33 | <0.01 |
4 | 0.01–0.05 | 1 | 0.01–0.05 | 4 | 0.01–0.05 | ||||
3 | ≥0.05 | 1 | ≥0.05 | 3 | ≥0.05 | ||||
10 | MAP3K12 | 14 | <0.01 | C14orf108 | 16 | <0.01 | C10ORF107 | 1 | 0.13 |
3 | 0.01–0.05 | 1 | 0.01–0.05 | ||||||
2 | ≥0.05 | ||||||||