This project focuses on querying the PubChem database to retrieve as many descriptors as possible for various chemical subtituents in aromatic corganic compounds. Additionally, it includes several engineered features to enhance the dataset. The project is organized into 12 Jupyter notebooks, each addressing different aspects of the analysis and machine learning processes:
- 00_chem_comp_basic.ipynb: Introduction to basic computational chemistry concepts.
- 01_EDA_data.ipynb: Exploratory Data Analysis (EDA) of the retrieved data.
- 02_get_properties_per_name.ipynb: Script to get properties based on chemical names.
- 03_get_the_properties_per_line.ipynb: Script to get properties based on line input.
- 04_Vanilla_ML_approach.ipynb: Initial machine learning approach to predict properties.
- 05_ML_search_for_best_algorithm.ipynb: Search for the best regression algorithm.
- 06_HPO_for_best_model.ipynb: Hyperparameter optimization for the best model obtained from NB 05.
- 07_prototype_for_serial_HPO.ipynb: Prototype for hyperparameter optimization for a series of regression algorithm.
- 08_ML_search_best_algortim_multiple_cols.ipynb: Search for the best algorithm for that predicts multiple values.
- 09_serial_HPO_for_selected_algos_predic_delta_VC_m: Serial HPO for selected algorithms to predict a single output.
- 10_serial_HPO_for_selected_algos_predic_delta_VC_m_VC_p: Serial HPO for selected algorithms to predict multiple outputs.
- 11_Vanilla_ML_multipred_cols.ipynb: Vanilla machine learning approach for prediction of a substituents multiple systems (Benzene, Pyrene, Pyridine, Butadiene, Butadiyne) columns .
- 12_Vanilla_ML_multipred_multisubs.ipynb: Vanilla machine learning approach for multiple substituents on multiple systems.
This comprehensive project leverages both standard and advanced machine learning techniques to analyze and predict properties from small substituents, providing a robust material for computational chemistry research.
├── LICENSE
│
├── README.md <- The top-level README for developers using this project.
│
├── data <- A folder for the expected csv files for input and destinations for output
│ └── search_dataframes_result <- CSV files from the HPO for the models
│
├── models <- selected models after HPO
│
├── notebook <- Jupyter notebooks from the projecs
│
├── environment.yml <- The requirements file for reproducing the analysis environment, e.g.
│ generated with `conda env export --no-builds | head -n -1 > environment.yml`
│
├── figures <- A folder for the expected figures for diverse results
│
├── src <- source code for use in this project.
Contributions are welcome! Please follow these steps to contribute:
- Fork the repository.
- Create a new branch (
git checkout -b feature/your-feature-name). - Commit your changes (
git commit -m 'Add some feature'). - Push to the branch (
git push origin feature/your-feature-name). - Open a pull request.
This project is licensed under the MIT License - see the LICENSE file for details.
- PubChem for the chemical data.
- cookiecutter data science project template
KAUST Vizualization Core Lab :
Project based on the cookiecutter data science project template. #cookiecutterdatascience