The PyBioMed Documentation¶
The python package PyBioMed is designed by CBDD Group (Computational Biology & Drug Design Group), Xiangya School of Pharmaceutical Sciences, Central South University. To develop a powerful model for prediction tasks by machine learning algorithms such as sckit-learn, one of the most important things to consider is how to effectively represent the molecules under investigation such as small molecules, proteins, DNA and even complex interactions, by a descriptor. PyBioMed is a feature-rich package used for the characterization of various complex biological molecules and interaction samples, such as chemicals, proteins, DNA, and their interactions. PyBioMed calculates nine types of features including chemical descriptors or molecular fingerprints, structural and physicochemical features of proteins and peptides from amino acid sequence, composition and physicochemical features of DNA from their primary sequences, chemical-chemical interaction features, chemical-protein interaction features, chemical-DNA interaction features, protein-protein interaction features, protein-DNA interaction features, and DNA-DNA interaction features. We hope that the package can be used for exploring questions concerning structures, functions and interactions of various molecular data in the context of chemoinformatics, bioinformatics, and systems biology.
- Overview
- Getting Started with PyBioMed
- Application
- Application 1 Prediction of Caco-2 Cell Permeability
- Application 2 Prediction of aqueous solubility
- Application 3 Prediction of drug–target interaction from the integration of chemical and protein spaces
- Application 4 Prediction of protein subcellular location
- Application 5 Predicting nucleosome positioning in genomes with dinucleotide-based auto covariance