SPICE, A Dataset of Drug-like Molecules and Peptides for Training Machine Learning Potentials.
Peter K. EastmanPavan Kumar BeharaDavid L. DotsonRaimondas GalvelisJohn E. HerrJosh T. HortonYuezhi MaoJohn D. ChoderaBenjamin P. PritchardYuanqing WangGianni De FabritiisThomas E. MarklandPublished in: CoRR (2022)
Keyphrases
- machine learning
- training dataset
- supervised learning
- ligand docking
- pattern recognition
- learning algorithm
- support vector machine
- training process
- machine learning methods
- training set
- decision trees
- pharmaceutical industry
- drug discovery
- benchmark datasets
- computer vision
- training examples
- training samples
- information extraction
- knowledge discovery
- feature selection
- data mining
- high order
- amino acids
- computational biology
- active learning
- chemical compounds
- feature space