Commit
·
1aa9ce8
1
Parent(s):
0b807b0
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,9 +1,8 @@
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
---
|
| 4 |
-
|
| 5 |
**PepMLM: Target Sequence-Conditioned Generation of Peptide Binders via Masked Language Modeling**
|
| 6 |
-
|
| 7 |
In this work, we introduce **PepMLM**, a purely target sequence-conditioned *de novo* generator of linear peptide binders.
|
| 8 |
By employing a novel masking strategy that uniquely positions cognate peptide sequences at the terminus of target protein sequences,
|
| 9 |
PepMLM tasks the state-of-the-art ESM-2 pLM to fully reconstruct the binder region,
|
|
@@ -15,13 +14,11 @@ In total, PepMLM enables the generative design of candidate binders to any targe
|
|
| 15 |
- Colab Notebook: [Link](https://colab.research.google.com/drive/1u0i-LBog_lvQ5YRKs7QLKh_RtI-tV8qM?usp=sharing)
|
| 16 |
- Preprint: [Link](https://arxiv.org/abs/2310.03842)
|
| 17 |
|
| 18 |
-
**Graphical Summary**:
|
| 19 |
-
|
| 20 |
-
|
| 21 |
```
|
| 22 |
# Load model directly
|
| 23 |
from transformers import AutoTokenizer, AutoModelForMaskedLM
|
| 24 |
|
| 25 |
tokenizer = AutoTokenizer.from_pretrained("TianlaiChen/PepMLM-650M")
|
| 26 |
model = AutoModelForMaskedLM.from_pretrained("TianlaiChen/PepMLM-650M")
|
| 27 |
-
```
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
---
|
|
|
|
| 4 |
**PepMLM: Target Sequence-Conditioned Generation of Peptide Binders via Masked Language Modeling**
|
| 5 |
+
|
| 6 |
In this work, we introduce **PepMLM**, a purely target sequence-conditioned *de novo* generator of linear peptide binders.
|
| 7 |
By employing a novel masking strategy that uniquely positions cognate peptide sequences at the terminus of target protein sequences,
|
| 8 |
PepMLM tasks the state-of-the-art ESM-2 pLM to fully reconstruct the binder region,
|
|
|
|
| 14 |
- Colab Notebook: [Link](https://colab.research.google.com/drive/1u0i-LBog_lvQ5YRKs7QLKh_RtI-tV8qM?usp=sharing)
|
| 15 |
- Preprint: [Link](https://arxiv.org/abs/2310.03842)
|
| 16 |
|
|
|
|
|
|
|
|
|
|
| 17 |
```
|
| 18 |
# Load model directly
|
| 19 |
from transformers import AutoTokenizer, AutoModelForMaskedLM
|
| 20 |
|
| 21 |
tokenizer = AutoTokenizer.from_pretrained("TianlaiChen/PepMLM-650M")
|
| 22 |
model = AutoModelForMaskedLM.from_pretrained("TianlaiChen/PepMLM-650M")
|
| 23 |
+
```
|
| 24 |
+
|