Table 1 Details of each cell line dataset. The enhancers (or promoters) column indicates the number of all known active enhancers (or promoters) for each cell line, which are used for unsupervised feature learning for enhancer (or promoter) sequences
From: Prediction of enhancer-promoter interactions via natural language processing
Dataset | enhancers | promoters | true EPIs | false EPIs |
|---|---|---|---|---|
K562 | 82806 | 8196 | 1977 | 1975 |
IMR90 | 108996 | 5253 | 1254 | 1250 |
GM12878 | 100036 | 8453 | 2113 | 2110 |
HUVEC | 65358 | 8180 | 1524 | 1520 |
HeLa-S3 | 103460 | 7794 | 1740 | 1740 |
NHEK | 144302 | 5254 | 1291 | 1280 |
FANTOM | 43011 | 49620 | 61542 | 61542 |