This Python program predicts compound properties such as molecular formula and exact mass using a Deep Neural Network (DNN) algorithm. The program retrieves data from a MySQL database, preprocesses it, trains a DNN model, and then uses the trained model to make predictions on new data.
Article Explanation: https://medium.com/@opemipo404/identifying-metabolites-with-deep-neural-networks-556e8c61ebb8
- Python 3.x
- pandas
- scikit-learn
- tensorflow (or any other deep learning framework of your choice)
- mysql-connector-python
- Clone the repository to your local machine:
git clone https://github.com/yourusername/compound-property-prediction.git
- Install the required libraries using pip:
pip install pandas scikit-learn tensorflow mysql-connector-python
- Set up a MySQL database with the required data. Update the database connection details (e.g.,
user
,password
,host
,database
) in thecnx
object in themain.py
file. - Run the
main.py
file to run the program.
You can customize the model architecture, hyperparameters, and other settings by modifying the code in the main.py
file. You can also update the preprocessing steps in the main.py
file according to your specific requirements.
If you would like to contribute to this project, please follow the standard GitHub fork and pull request workflow.
This project is licensed under the MIT License.
If you have any questions, suggestions, or issues, please feel fre to contact me at opethepope@gmail.com.