Table 1.
Cross-validation performance for each definition of ALS-linked genes. Precision, recall, and fold-change enrichment are given as the mean (standard deviation) for five folds. The numbers of genes are minimum-maximum. The fold-change enrichment is based on the expected precision of random guessing. Each of the five folds is considered significantly enriched if the p-value for predicting at least as many genes correctly is < 0.05 under the hypergeometric distribution.
| Training | Validation | |||||||
|---|---|---|---|---|---|---|---|---|
| # of Genes | Precision | Recall | # of Genes | Precision | Recall | Fold-Change Enrichment | Number of Significantly Enriched Folds | |
| ALSoD | 60–61 | 0.23 (0.16) | 0.55 (0.09) | 15–16 | 0.07 (0.08) | 0.45 (0.17) | 23.33 (23.53) | 5/5 |
| ClinVar | 29–30 | 0.16 (0.09) | 0.86 (0.04) | 7–8 | 0.05 (0.02) | 0.82 (0.17) | 30.05 (15.64) | 5/5 |
| DisGeNet | 54–55 | 0.44 (0.33) | 0.23 (0.16) | 13–14 | 0.15 (0.22) | 0.09 (0.08) | 55.90 (81.66) | 2/5 |
| Manual | 21–22 | 0.27 (0.01) | 0.85 (0.04) | 5–6 | 0.09 (0.01) | 0.86 (0.14) | 84.54 (13.27) | 5/5 |
| Union | 96 | 0.16 (0.04) | 0.73 (0.05) | 24 | 0.04 (0.02) | 0.67 (0.07) | 8.92 (4.28) | 5/5 |