Update README.md
Browse files
README.md
CHANGED
|
@@ -49,7 +49,7 @@ running the model in zero-shot is that it doesn't require any further training.
|
|
| 49 |
### **Example 1: Generating nitrilases (EC 3.5.5.1)**
|
| 50 |
|
| 51 |
The script below will be used for the generation of any BRENDA class in a zero-shot fashion,
|
| 52 |
-
here we showcase the generation of novel
|
| 53 |
|
| 54 |
To run this script, you should download ZymCTRL to a local folder in your workstation.
|
| 55 |
Then replace the placeholders in the script with your actual folder path.
|
|
@@ -62,8 +62,8 @@ it will store the sequence's computed perplexity value. Perplexity is a measure
|
|
| 62 |
in that generation, with lower values being better. The sequences are ordered by perplexity before writing them out,
|
| 63 |
so those that finish in *_0.fasta and *_1.fasta will be the best ones per batch.
|
| 64 |
|
| 65 |
-
**Given that generation runs so fast, we recommend generating hundreds or thousands and then only picking the best 5%.
|
| 66 |
-
With the script below, that would mean picking only those that finish in '_0.fasta'**
|
| 67 |
|
| 68 |
```
|
| 69 |
import torch
|
|
|
|
| 49 |
### **Example 1: Generating nitrilases (EC 3.5.5.1)**
|
| 50 |
|
| 51 |
The script below will be used for the generation of any BRENDA class in a zero-shot fashion,
|
| 52 |
+
here we showcase the generation of novel nitrilases.
|
| 53 |
|
| 54 |
To run this script, you should download ZymCTRL to a local folder in your workstation.
|
| 55 |
Then replace the placeholders in the script with your actual folder path.
|
|
|
|
| 62 |
in that generation, with lower values being better. The sequences are ordered by perplexity before writing them out,
|
| 63 |
so those that finish in *_0.fasta and *_1.fasta will be the best ones per batch.
|
| 64 |
|
| 65 |
+
**Given that generation runs so fast, we recommend generating hundreds or thousands and then only picking the best 5% or less.
|
| 66 |
+
With the script below, that would mean picking only those that finish in '_0.fasta'. Good perplexity values for this model so be below 1.75-1.5.**
|
| 67 |
|
| 68 |
```
|
| 69 |
import torch
|