MUBD-DecoyMaker 2.0: A Python GUI Application to Generate Maximal Unbiased Benchmarking Data Sets for Virtual Drug
1State Key Laboratory of Bioactive Substance and Function of Natural Medicines, Department of New Drug Research and Development, Institute of Materia Medica, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, 100050, China.
Molecular Informatics
|December 13, 2019
Summary
A new Python application, MUBD-DecoyMaker 2.0, simplifies the creation of high-quality benchmarking datasets for drug discovery. This tool aids in selecting optimal methods for mining drug-like molecules and identifying potential biases.
Area of Science:
- Computational chemistry
- cheminformatics
- Drug discovery
Background:
- Benchmarking datasets are crucial for evaluating ligand enrichment methods in drug discovery.
- Existing datasets, like MUBD-HDACs, have demonstrated effectiveness but accessibility can be a barrier.
- The need for user-friendly tools to generate reliable benchmarking data is increasing.
Purpose of the Study:
- To develop a more accessible and user-friendly tool for generating benchmarking datasets.
- To enhance the capabilities of existing decoy generation algorithms.
- To facilitate the rational selection of data mining approaches in drug discovery.
Main Methods:
- Development of a Python Graphical User Interface (GUI) application named MUBD-DecoyMaker 2.0.
- Incorporation of two new modules: "Detect 2D Bias" and "Quality Control".
- Utilizing unique de-biasing algorithms for dataset generation.
Main Results:
- MUBD-DecoyMaker 2.0 provides an easy-to-use interface for generating high-quality benchmarking datasets.
- The new version maintains the quality of datasets generated by previous methods.
- The application includes novel modules for bias detection and quality control.
Conclusions:
- MUBD-DecoyMaker 2.0 enhances the accessibility of advanced benchmarking tools for drug discovery researchers.
- The software supports more effective ligand enrichment assessment and data mining.
- This tool is expected to contribute significantly to modern drug discovery efforts.
