Metadata-Version: 2.1
Name: antibacterial-model
Version: 1.0.8
Summary: A model for predicting antibacterial activity from SMILES strings
Author: Chonthicha Arbsuwan, Jiratchaya Nakbang
Author-email: chon7599@gmail.com, jiratchaya2356@gmail.com
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.6
Classifier: Programming Language :: Python :: 3.7
Classifier: Programming Language :: Python :: 3.8
Classifier: Programming Language :: Python :: 3.9
Requires-Python: >=3.6
Description-Content-Type: text/markdown

# Machine Learning model for identification of antibacterial compounds

A python package developed from a machine learning model for identifying antibacterial compounds from the SMILES format.

## Getting Started

These instructions will inform you how to use and run our developed package on your local machine for development and testing purposes. Read below on how to deploy the project on a live system.

## Installing
You can install the package using pip:

```bash 
pip install antibacterial-model 
```
## Usage
How to use the prediction package is as follows:
1. Import Antibacterial model package.
2. Create an instance of Antibacterial model.
3. Use the model to predict antibacterial activity from a text file containing SMILES structures.

```python
# import package  
from antibacterial_model import AntibacterialModel

# Create an instance of AntibacterialModel
model = AntibacterialModel()

# Use the model to make predictions
model.predict('Your_SMILES_file.txt', 'Your_Prediction_output.txt')
```
Finally, the output will be saved as a text file after prediction using the model.


### Input and output file example
The **input file** must be a text file containing isomeric SMILES structures as shown in the example below:

```bash
# in input_file.txt
C1=CC=C(C(=C1)C(=O)O)O 
C1CCNC(C1)C2COC(O2)(C3=CC=CC=C3)C4=CC=CC=C4
C(C(C(C(C(CO)O)O)O)O)O
C1CC(CNC1)C(=O)NNC(=O)C2CCC3CN2C(=O)N3OS(=O)(=O)O
C1=CN=CC=C1N
```
The **output file** will be a text file containing SMILES structures and the prediction results as shown in the example:

```bash
# in output_file.txt
C1=CC=C(C(=C1)C(=O)O)O - Prediction : Active
C1CCNC(C1)C2COC(O2)(C3=CC=CC=C3)C4=CC=CC=C4 - Prediction : Inactive
C(C(C(C(C(CO)O)O)O)O)O - Prediction : Active
C1CC(CNC1)C(=O)NNC(=O)C2CCC3CN2C(=O)N3OS(=O)(=O)O - Prediction : Inactive
C1=CN=CC=C1N - Prediction : Inactive
```
## Prediction result
The prediction output consists of 2 values:
- **Active:** a substance **with** antibacterial properties
- **Inactive:** a substance **without** antibacterial properties

## Limitation
The developed model is suitable only for Python language and must install libraries to match the version used by the researchers to run the code through the model for prediction results

## Credits
- Author: Chonthicha Arbsuwan, Jiratchaya  Nakbang 
- Email: chon7599@gmail.com, jiratchaya2356@gmail.com
- Project URL: [GitHub](https://github.com/Chon26/Antibacterial-model) 

