Metadata-Version: 2.2
Name: DrugAutoML
Version: 0.0.1
Summary: DrugAutoML: An Open-Source Automated Machine Learning and Statistical Evaluation Tool for Bioactivity Prediction in Drug Discovery
Home-page: https://github.com/aycapmkcu/DrugAutoML
Author: Ayça Beyhan & Aslı Suner
Author-email: aycapamukcu9@gmail.com
License: MIT
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Requires-Python: >=3.6
Description-Content-Type: text/markdown
Requires-Dist: pandas
Requires-Dist: numpy
Requires-Dist: scikit-learn
Requires-Dist: matplotlib
Requires-Dist: rdkit
Requires-Dist: shap
Requires-Dist: xgboost
Requires-Dist: lightgbm
Requires-Dist: hyperopt
Dynamic: author
Dynamic: author-email
Dynamic: classifier
Dynamic: description
Dynamic: description-content-type
Dynamic: home-page
Dynamic: license
Dynamic: requires-dist
Dynamic: requires-python
Dynamic: summary

# DrugAutoML

**DrugAutoML** is an open-source automated machine learning (AutoML) and statistical evaluation tool designed for bioactivity prediction in drug discovery. It provides data preprocessing, fingerprint generation, model selection, and result analysis pipelines to streamline the machine learning workflow.

## Key Features

- **Data Preprocessing**  
  Cleans and validates SMILES, classifies compounds as active/inactive based on IC50 thresholds.

- **Fingerprint Calculation**  
  Generates Morgan (ECFP) fingerprints for molecular representation.

- **AutoML Pipeline**  
  Automates model training with hyperparameter optimization for multiple ML algorithms.

- **Model Selection & Analysis**  
  Provides cross-validation metrics, ROC/PRC curves, confusion matrices, and SHAP explanations.

