Spaces:
Sleeping
Sleeping
Update README.md
Browse files
README.md
CHANGED
@@ -18,11 +18,10 @@ short_description: app to generate and view beta-lactam molecules
|
|
18 |
This application demonstrates a drug discovery pipeline that allows users to:
|
19 |
|
20 |
* Generate novel beta-lactam molecules using a generative AI model that was fine-tuned with beta-lactam structures.
|
21 |
-
* View the generated molecules with
|
22 |
-
* Predict ADMET properties for the generated molecules using ADMET-AI.
|
23 |
|
24 |
## Features
|
25 |
-
|
26 |
* Molecule Generation:
|
27 |
* Generates up to 3 beta-lactam molecules at a time.
|
28 |
* Users can adjust the creativity (temperature) of the generation process. Higher number leads to more diverse output.
|
@@ -35,7 +34,6 @@ This application demonstrates a drug discovery pipeline that allows users to:
|
|
35 |
* Displays predicted properties of each molecule.
|
36 |
|
37 |
## How to Use the App
|
38 |
-
|
39 |
1. Set Generation Parameters:
|
40 |
* Use the sidebar to adjust the creativity (temperature) slider.
|
41 |
* Select the number of molecules to generate (maximum of 3).
|
@@ -46,7 +44,6 @@ This application demonstrates a drug discovery pipeline that allows users to:
|
|
46 |
|
47 |
|
48 |
## Technical Details
|
49 |
-
|
50 |
* Generative Model: Uses the model: 'seyonec/PubChem10M_SMILES_BPE_450k' fine-tuned on beta-lactam structures.
|
51 |
* ADMET Predictions: Uses the ADMET-AI library to predict molecular properties.
|
52 |
* Visualization: Employs RDKit and SAFE encoding for molecule rendering.
|
|
|
18 |
This application demonstrates a drug discovery pipeline that allows users to:
|
19 |
|
20 |
* Generate novel beta-lactam molecules using a generative AI model that was fine-tuned with beta-lactam structures.
|
21 |
+
* View the generated molecules with SMILES and SAFE strings.
|
22 |
+
* Predict select ADMET properties for the generated molecules using ADMET-AI.
|
23 |
|
24 |
## Features
|
|
|
25 |
* Molecule Generation:
|
26 |
* Generates up to 3 beta-lactam molecules at a time.
|
27 |
* Users can adjust the creativity (temperature) of the generation process. Higher number leads to more diverse output.
|
|
|
34 |
* Displays predicted properties of each molecule.
|
35 |
|
36 |
## How to Use the App
|
|
|
37 |
1. Set Generation Parameters:
|
38 |
* Use the sidebar to adjust the creativity (temperature) slider.
|
39 |
* Select the number of molecules to generate (maximum of 3).
|
|
|
44 |
|
45 |
|
46 |
## Technical Details
|
|
|
47 |
* Generative Model: Uses the model: 'seyonec/PubChem10M_SMILES_BPE_450k' fine-tuned on beta-lactam structures.
|
48 |
* ADMET Predictions: Uses the ADMET-AI library to predict molecular properties.
|
49 |
* Visualization: Employs RDKit and SAFE encoding for molecule rendering.
|