Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,19 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: agpl-3.0
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: agpl-3.0
|
| 3 |
+
tags:
|
| 4 |
+
- EpiATLAS
|
| 5 |
+
- IHEC
|
| 6 |
+
- epigenetics
|
| 7 |
+
- EpiClass
|
| 8 |
+
- pytorch
|
| 9 |
+
---
|
| 10 |
+
Epigenome Assay/Target classifier trained on the EpiATLAS dataset. The classes are IHEC reference epigenome assays:
|
| 11 |
+
- Seven (7) ChIP-Seq assays: H3k27ac, H3k27me3, H3k36me3, H3k4me1, H3k4me3, H3k9me3, input
|
| 12 |
+
- Two (2) RNA-Seq protocols (total/mrna)
|
| 13 |
+
- Two (2) WGBS protocols (pbat/standard)
|
| 14 |
+
|
| 15 |
+
The model is a simple fense feedforward neural network, with one hidden layer of 3000 nodes.The model was trained using PyTorch Lightning. See Github repository [rabyj/epi_ml](https://github.com/rabyj/epi_ml/blob/master/src/python/epi_ml/core/model_pytorch.py) for model code.
|
| 16 |
+
|
| 17 |
+
See the .o and .e files for training details. More information is also available on Comet ML, in the rabyj/epiclass project. The ID of this training run is [0f8e5eb996114868a17057bebe64f87c](https://www.comet.com/rabyj/epiclass/0f8e5eb996114868a17057bebe64f87c)
|
| 18 |
+
|
| 19 |
+
For more context, like the associated publication, see the EpiClass collection details.
|