Update README.md
Browse files
README.md
CHANGED
@@ -8,4 +8,65 @@ tags:
|
|
8 |
- transformers
|
9 |
metrics:
|
10 |
- accuracy
|
11 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
8 |
- transformers
|
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.
|
18 |
+
|
19 |
+
CELL-E 2 is novel bidirectional transformer that can generate images depicting protein subcellular localization from the amino acid sequences (and *vice versa*).
|
20 |
+
CELL-E 2 not only captures the spatial complexity of protein localization and produce probability estimates of localization atop a nucleus image, but also being able to generate sequences from images, enabling *de novo* protein design.
|
21 |
+
We trained on the [Human Protein Atlas](https://www.proteinatlas.org) 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 |
+
|
28 |
+
We have made several versions of CELL-E 2 available. The naming scheme follows the structure ```training set_hidden size``` where the hidden size is set to the embedding dimension of the pretrained ESM-2 model.
|
29 |
+
|
30 |
+
### HPA Models:
|
31 |
+
|
32 |
+
| Model | #params | Language |
|
33 |
+
|------------------------|--------------------------------|-------|
|
34 |
+
| [`bert-base-uncased`](https://huggingface.co/bert-base-uncased) | 110M | English |
|
35 |
+
| [`bert-large-uncased`](https://huggingface.co/bert-large-uncased) | 340M | English | sub
|
36 |
+
| [`bert-base-cased`](https://huggingface.co/bert-base-cased) | 110M | English |
|
37 |
+
| [`bert-large-cased`](https://huggingface.co/bert-large-cased) | 340M | English |
|
38 |
+
|
39 |
+
## Intended uses & limitations
|
40 |
+
|
41 |
+
You can use the raw model for either masked language modeling or next sentence prediction, but it's mostly intended to
|
42 |
+
be fine-tuned on a downstream task. See the [model hub](https://huggingface.co/models?filter=bert) to look for
|
43 |
+
fine-tuned versions of a task that interests you.
|
44 |
+
|
45 |
+
Note that this model is primarily aimed at being fine-tuned on tasks that use the whole sentence (potentially masked)
|
46 |
+
to make decisions, such as sequence classification, token classification or question answering. For tasks such as text
|
47 |
+
generation you should look at model like GPT2.
|
48 |
+
|
49 |
+
### How to use
|
50 |
+
|
51 |
+
```
|
52 |
+
|
53 |
+
Here is how to use this model to get the features of a given text in PyTorch:
|
54 |
+
|
55 |
+
```python
|
56 |
+
configs = OmegaConf.load(configs/config.yaml);
|
57 |
+
model = instantiate_from_config(configs.model).to(device);
|
58 |
+
model.sample(text=sequence, condition=nucleus)
|
59 |
+
```
|
60 |
+
|
61 |
+
|
62 |
+
### BibTeX entry and citation info
|
63 |
+
|
64 |
+
```bibtex
|
65 |
+
@article{,
|
66 |
+
author = {Emaad Khwaja and
|
67 |
+
Yun S Song and
|
68 |
+
Aaron Agarunov and
|
69 |
+
Bo Huang},
|
70 |
+
title = {{CELL-E 2:} Translating Proteins to Pictures and Back with a Bidirectional Text-to-Image Transforme},
|
71 |
+
}
|
72 |
+
```
|