data

Scikit-Learn (https://scikit-learn.org/stable/datasets/real_world.html), StatLib repository (http://lib.stat.cmu.edu/datasets/)⁠, and the UC Irvine Machine Learning Repository (http://archive.ics.uci.edu/ml/) were the sources of some of the datasets available here. You will also find datasets used to train machine-learning models to predict binding affinity against protein targets. We employ these datasets for teaching and research purposes. The purpose of datasets containing information about protein-ligand interaction is mainly the development of the following machine-learning tools: SAnDReS (https://github.com/azevedolab/sandres) (de Azevedo Jr et al., 2024), Taba (https://github.com/azevedolab/taba) (da Silva et al., 2020), and SFSXplorer (https://github.com/azevedolab/SFSXplorer).