SalZa2004 commited on
Commit
2fd9be7
·
verified ·
1 Parent(s): 7aedd72

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +53 -4
README.md CHANGED
@@ -11,9 +11,58 @@ pinned: false
11
  short_description: Predict Cetane Number from SMILES
12
  ---
13
 
14
- # Welcome to Streamlit!
15
 
16
- Edit `/src/streamlit_app.py` to customize this app to your heart's desire. :heart:
17
 
18
- If you have any questions, checkout our [documentation](https://docs.streamlit.io) and [community
19
- forums](https://discuss.streamlit.io).
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
11
  short_description: Predict Cetane Number from SMILES
12
  ---
13
 
14
+ # Cetane Number Predictor ⛽
15
 
16
+ Predict cetane numbers from SMILES strings using machine learning.
17
 
18
+ ## Features
19
+
20
+ - 🔬 **Single Prediction**: Enter one SMILES string to get instant cetane number prediction
21
+ - 📊 **Batch Prediction**: Upload CSV files with multiple SMILES for bulk predictions
22
+ - 📈 **Visual Analysis**: View molecular structures and prediction distributions
23
+ - 📥 **Export Results**: Download predictions as CSV
24
+
25
+ ## How to Use
26
+
27
+ ### Single Prediction
28
+ 1. Go to the "Single Prediction" tab
29
+ 2. Enter a SMILES string (e.g., `CCCCCCCCCCCCCCCC`)
30
+ 3. Click "Predict"
31
+ 4. View your cetane number prediction!
32
+
33
+ ### Batch Prediction
34
+ 1. Go to the "Batch Prediction" tab
35
+ 2. Upload a CSV file with a `SMILES` column
36
+ 3. Click "Predict All"
37
+ 4. Download results with predictions
38
+
39
+ ## Model Details
40
+
41
+ - **Input**: SMILES strings (molecular structure representation)
42
+ - **Output**: Cetane number (0-150 scale)
43
+ - **Features**:
44
+ - Morgan fingerprints (2048 bits, radius=2)
45
+ - 208 RDKit molecular descriptors
46
+ - Feature selection (top 300 important features)
47
+ - **Training**: Experimental cetane number data from fuel database
48
+
49
+ ## Example SMILES
50
+
51
+ | SMILES | Name | Typical CN |
52
+ |--------|------|-----------|
53
+ | `CCCCCCCCCCCCCCCC` | Hexadecane | ~100 |
54
+ | `CC(C)CCCCC` | Isoheptane | ~30 |
55
+ | `CCCCCCCC` | Octane | ~65 |
56
+
57
+ ## Citation
58
+
59
+ If you use this model in your research, please cite:
60
+
61
+ ```bibtex
62
+ @misc{cn_predictor_2025,
63
+ author = {Salvina Zahir},
64
+ title = {Cetane Number Predictor},
65
+ year = {2025},
66
+ publisher = {HuggingFace},
67
+ url = {https://huggingface.co/spaces/SalZa2004/cn-predictor}
68
+ }