File size: 1,185 Bytes
3d081c2
 
 
ec80ad6
 
1cdca32
ec80ad6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
---
license: mit
---
We provide both huggingface version and 
[esm version](https://github.com/facebookresearch/esm) of
 SaProt (see our github <https://github.com/SaProt/SaProt>). Users can choose either one to use.

### Huggingface model
The following code shows how to load the model.
```
from transformers import EsmTokenizer, EsmForMaskedLM

model_path = "/your/path/to/SaProt_650M_AF2"
tokenizer = EsmTokenizer.from_pretrained(model_path)
model = EsmForMaskedLM.from_pretrained(model_path)

#################### Example ####################
device = "cuda"
model.to(device)

seq = "MdEvVpQpLrVyQdYaKv"
tokens = tokenizer.tokenize(seq)
print(tokens)

inputs = tokenizer(seq, return_tensors="pt")
inputs = {k: v.to(device) for k, v in inputs.items()}

outputs = model(**inputs)
print(outputs.logits.shape)

"""
['Md', 'Ev', 'Vp', 'Qp', 'Lr', 'Vy', 'Qd', 'Ya', 'Kv']
torch.Size([1, 11, 446])
"""
```

### esm model
The esm version is also stored in the same folder, named `SaProt_650M_AF2.pt`. We provide a function to load the model.
```
from utils.esm_loader import load_esm_saprot

model_path = "/your/path/to/SaProt_650M_AF2.pt"
model, alphabet = load_esm_saprot(model_path)
```