JiecongLin's picture
Document f3 checkpoint layout
394d47b verified
|
Raw
History Blame Contribute Delete
1.16 kB
---
tags:
- biology
- genomics
- gene-expression
---
# EPInformer pipeline checkpoints
This repository provides the 12-fold leave-chromosome-out checkpoints for the
EPInformer pipeline.
## Gene-expression checkpoints
The `expression_models/` directory contains one checkpoint for each of the
12 leave-chromosome-out folds. `f1` uses distance only, `f2` uses distance and
activity, and `f3` uses distance, activity, Hi-C contact, and promoter signal.
Each feature configuration is in its own `f1/`, `f2/`, or `f3/` subdirectory.
| Cell type | Assay | f1 | f2 | f3 |
|---|---|---:|---:|---:|
| K562 | RNA | 0.7528 | 0.8552 | 0.8564 |
| K562 | CAGE | 0.8114 | 0.8709 | 0.8673 |
| GM12878 | RNA | 0.7610 | 0.8268 | 0.8602 |
| GM12878 | CAGE | 0.8270 | 0.8687 | 0.8902 |
| H1 | RNA | 0.6608 | 0.7800 | 0.7811 |
| HepG2 | RNA | 0.6340 | 0.8382 | 0.8447 |
| HUVEC | RNA | 0.6304 | 0.8269 | 0.8390 |
| NHEK | RNA | 0.6053 | 0.8177 | 0.8281 |
Values are pooled Pearson R. Use the matching encoder checkpoints, HDF5 input,
expression labels, and fold split described in the
[EPInformer pipeline README](https://github.com/pinellolab/EPInformer/tree/pipeline).