Update readme
Browse filesFix links
Polish phrasing
README.md
CHANGED
@@ -2,6 +2,8 @@
|
|
2 |
license: mit
|
3 |
tags:
|
4 |
- METL
|
|
|
|
|
5 |
---
|
6 |
|
7 |
# METL
|
@@ -11,19 +13,21 @@ Mutational Effect Transfer Learning (METL) is a framework for pretraining and fi
|
|
11 |
|
12 |
## Model Details
|
13 |
|
14 |
-
This
|
|
|
|
|
15 |
|
16 |
### Model Description
|
17 |
|
18 |
-
METL is discussed in the (
|
|
|
|
|
19 |
|
20 |
-
### Model Sources
|
21 |
|
22 |
-
|
23 |
-
|
24 |
-
- **
|
25 |
-
- **Paper:** [METL bio archrive](https://www.biorxiv.org/content/10.1101/2024.03.15.585128v1)
|
26 |
-
- **Demo:** [Huggingface demo space for METL](https://huggingface.co/spaces/gitter-lab/METL_demo)
|
27 |
|
28 |
## How to Get Started with the Model
|
29 |
|
@@ -38,9 +42,10 @@ scipy>=1.9.1
|
|
38 |
biopandas>=0.2.7
|
39 |
```
|
40 |
|
41 |
-
In order to run the example, a PDB file
|
|
|
42 |
|
43 |
-
After installing those packages and the above file, you may run METL with the following code example (assuming the downloaded file is in the same place as the script):
|
44 |
|
45 |
```python
|
46 |
from transformers import AutoModel
|
@@ -67,10 +72,10 @@ with torch.no_grad():
|
|
67 |
|
68 |
## Citation
|
69 |
|
70 |
-
Biophysics-based protein language models for protein engineering
|
71 |
-
Sam Gelman, Bryce Johnson, Chase Freschlin, Sameer D’Costa, Anthony Gitter, Philip A. Romero
|
72 |
bioRxiv 2024.03.15.585128; doi: https://doi.org/10.1101/2024.03.15.585128
|
73 |
|
74 |
## Model Card Contact
|
75 |
|
76 |
-
For questions and comments about METL, the best way to reach out is through opening a
|
|
|
2 |
license: mit
|
3 |
tags:
|
4 |
- METL
|
5 |
+
- biology
|
6 |
+
- protein
|
7 |
---
|
8 |
|
9 |
# METL
|
|
|
13 |
|
14 |
## Model Details
|
15 |
|
16 |
+
This repository contains a wrapper meant to facilitate the ease of use of METL models.
|
17 |
+
Usage of this wrapper will be provided below.
|
18 |
+
Models are hosted on [Zenodo](https://zenodo.org/doi/10.5281/zenodo.11051644) and will be downloaded by this wrapper when used.
|
19 |
|
20 |
### Model Description
|
21 |
|
22 |
+
METL is discussed in the [paper](https://doi.org/10.1101/2024.03.15.585128) in further detail.
|
23 |
+
The GitHub [repo](https://github.com/gitter-lab/metl) contains more documentation and includes scripts for training and predicting with METL.
|
24 |
+
Google Colab notebooks for finetuning and predicting on publicly available METL models are available as well [here](https://github.com/gitter-lab/metl/tree/main/notebooks).
|
25 |
|
26 |
+
### Model Sources
|
27 |
|
28 |
+
- **Repository:** [METL repo](https://github.com/gitter-lab/metl)
|
29 |
+
- **Paper:** [METL preprint](https://doi.org/10.1101/2024.03.15.585128)
|
30 |
+
- **Demo:** [Hugging Face Spaces demo](https://huggingface.co/spaces/gitter-lab/METL_demo)
|
|
|
|
|
31 |
|
32 |
## How to Get Started with the Model
|
33 |
|
|
|
42 |
biopandas>=0.2.7
|
43 |
```
|
44 |
|
45 |
+
In order to run the example, a PDB file for the GB1 protein structure must be installed.
|
46 |
+
It is provided [here](https://github.com/gitter-lab/metl-pretrained/blob/main/pdbs/2qmt_p.pdb) and in raw format [here](https://raw.githubusercontent.com/gitter-lab/metl-pretrained/main/pdbs/2qmt_p.pdb).
|
47 |
|
48 |
+
After installing those packages and downloading the above file, you may run METL with the following code example (assuming the downloaded file is in the same place as the script):
|
49 |
|
50 |
```python
|
51 |
from transformers import AutoModel
|
|
|
72 |
|
73 |
## Citation
|
74 |
|
75 |
+
Biophysics-based protein language models for protein engineering
|
76 |
+
Sam Gelman, Bryce Johnson, Chase Freschlin, Sameer D’Costa, Anthony Gitter, Philip A. Romero
|
77 |
bioRxiv 2024.03.15.585128; doi: https://doi.org/10.1101/2024.03.15.585128
|
78 |
|
79 |
## Model Card Contact
|
80 |
|
81 |
+
For questions and comments about METL, the best way to reach out is through opening a GitHub issue in the [METL repository](https://github.com/gitter-lab/metl/issues).
|