Commit
•
1769e3c
1
Parent(s):
7659554
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,27 @@
|
|
| 1 |
-
---
|
| 2 |
-
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
+
metrics:
|
| 5 |
+
- accuracy
|
| 6 |
+
- AUC ROC
|
| 7 |
+
- precision
|
| 8 |
+
- recall
|
| 9 |
+
tags:
|
| 10 |
+
- biology
|
| 11 |
+
- chemistry
|
| 12 |
+
- therapeutic science
|
| 13 |
+
- drug design
|
| 14 |
+
- drug development
|
| 15 |
+
- therapeutics
|
| 16 |
+
library_name: tdc
|
| 17 |
+
license: bsd-2-clause
|
| 18 |
+
---
|
| 19 |
+
The TDC Transformers APi is still under development. You may download PINNACLE pre-trained weights and hyperparameters from the files included.
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
We introduce PINNACLE, a flexible geometric deep-learning approach that is trained on contextualized protein interaction networks to generate context-PINNACLE protein representations. Leveraging a human multi-organ single-cell transcriptomic atlas, PINNACLE provides 394,760 protein representations split across 156 cell type contexts from 24 tissues and organs.
|
| 23 |
+
To load the pre-trained model, use the Files and Versions tab files.
|
| 24 |
+
|
| 25 |
+
## References
|
| 26 |
+
* Dataset entry in Therapeutics Data Commons, https://tdcommons.ai/multi_pred_tasks/scdti/
|
| 27 |
+
* Li, Michelle, et al. “Contextualizing Protein Representations Using Deep Learning on Protein Networks and Single-Cell Data” bioRxiv (2023)
|