Update README.md
Browse files
README.md
CHANGED
@@ -9,9 +9,12 @@ tags:
|
|
9 |
metrics:
|
10 |
- accuracy
|
11 |
---
|
|
|
12 |
|
13 |
# CELL-E 2
|
14 |
|
|
|
|
|
15 |
## Model description
|
16 |
|
17 |
CELL-E 2 is the second iteration of the original [CELL-E](https://www.biorxiv.org/content/10.1101/2022.05.27.493774v1) model which utilizes an amino acid sequence and nucleus image to make predictions of subcellular protein localization with respect to the nucleus.
|
@@ -21,7 +24,7 @@ CELL-E 2 not only captures the spatial complexity of protein localization and pr
|
|
21 |
We trained on the [Human Protein Atlas](https://www.proteinatlas.org) (HPA) and the [OpenCell](https://opencell.czbiohub.org) datasets.
|
22 |
|
23 |
CELL-E 2 utilizes pretrained amino acid embeddings from [ESM-2](https://github.com/facebookresearch/esm).
|
24 |
-
|
25 |
|
26 |
## Model variations
|
27 |
|
|
|
9 |
metrics:
|
10 |
- accuracy
|
11 |
---
|
12 |
+
[![Huang Lab](images/huanglogo.jpeg)](huanglab.ucsf.edu)
|
13 |
|
14 |
# CELL-E 2
|
15 |
|
16 |
+
[![CELL-E_2](images/architecture.png)](https://github.com/BoHuangLab/CELL-E_2)
|
17 |
+
|
18 |
## Model description
|
19 |
|
20 |
CELL-E 2 is the second iteration of the original [CELL-E](https://www.biorxiv.org/content/10.1101/2022.05.27.493774v1) model which utilizes an amino acid sequence and nucleus image to make predictions of subcellular protein localization with respect to the nucleus.
|
|
|
24 |
We trained on the [Human Protein Atlas](https://www.proteinatlas.org) (HPA) and the [OpenCell](https://opencell.czbiohub.org) datasets.
|
25 |
|
26 |
CELL-E 2 utilizes pretrained amino acid embeddings from [ESM-2](https://github.com/facebookresearch/esm).
|
27 |
+
Localization is predicted as a binary image atop the provided nucleus. The logit values are weighted against these binary images to produce a heatmap of expected localization.
|
28 |
|
29 |
## Model variations
|
30 |
|