Update README.md
Browse files
README.md
CHANGED
|
@@ -350,6 +350,16 @@ if __name__ == '__main__':
|
|
| 350 |
print(f"An error occurred while writing to JSON: {e}")
|
| 351 |
```
|
| 352 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 353 |
## **A word of caution**
|
| 354 |
|
| 355 |
- We have not yet fully tested the ability of the model for the generation of new-to-nature enzymes, i.e.,
|
|
|
|
| 350 |
print(f"An error occurred while writing to JSON: {e}")
|
| 351 |
```
|
| 352 |
|
| 353 |
+
- As a reference, the bash script should look something like this:
|
| 354 |
+
```python
|
| 355 |
+
INFERENCE_FOLDER=output_folder # change to the name of the output folder you want
|
| 356 |
+
MODEL=checkpoint-90000 # path to the model
|
| 357 |
+
INFERENCE_TXT=reaction.txt # text file containing the reactions (in SMILE format) wanting to generate for.
|
| 358 |
+
|
| 359 |
+
source .environment/bin/activate # load an environment containing the required dependencies (transformers, torch, datasets)
|
| 360 |
+
python inference.py --input_file "$INFERENCE_TXT" --model_path "$MODEL" --output_folder "$INFERENCE_FOLDER" --tokenizer_mol tokenizer_ABPE_rexzyme_offset --tokenizer_aa tokenizer_aa
|
| 361 |
+
```
|
| 362 |
+
|
| 363 |
## **A word of caution**
|
| 364 |
|
| 365 |
- We have not yet fully tested the ability of the model for the generation of new-to-nature enzymes, i.e.,
|