AlphaSpace is for fragment-centric pocket detection at the protein surface and can be used to characterize PPI interfaces as a set of dynamic, localized, fragment-targetable interaction regions.
Website: https://yzhang.hpc.nyu.edu/AlphaSpace/
Website: https://yzhang.hpc.nyu.edu/AlphaSpace2/
D. W. Rooklin, C. Wang, J. Katigbak, P. S. Arora, and Y. Zhang,
J. Chem. Inf. Model., 55, 1585-1599
(2015).
AlphaSpace: Fragment-Centric Topographical Mapping to Target Protein-Protein Interaction Interfaces
J. Katigbak, H. Li, D. W. Rooklin and Y. Zhang,
J. Chem. Inf. Model., 60, 1494-1508
(2020).
AlphaSpace 2.0: Representing Concave Biomolecular Surfaces using Beta-Clusters
• • •
A new scoring function incorporates explicit water molecules and ligand stability has been developed using the Delta-Vina XGBoost (ΔvinaXGB) algorithm. It has achieved superior performance in all power tests of CASF-2016 benchmark and two rescoring tests (LocalOpt and FlexDock).
Jianing Lu, Xuben Hou, Cheng, Wang, and Yingkai Zhang,
J. Chem. Inf. Model.,
59, 4540 - 4549 (2019)
Incorporating Explicit Water Molecules and Ligand Conformation Stability in Machine-Learning Scoring Functions
A scoring function employs twenty descriptors in addition to the AutoDock Vina score, and has been developed using the Delta Random Forest (ΔRF) algorithm. It has achieved superior performance in all power tests of both CASF-2013 and CASF-2007 benchmarks.
C. Wang, and Y. Zhang,
J. Comput. Chem.,
38 , 169-177 (2017).
Improving Scoring-Docking-Screening Powers of Protein–Ligand Scoring Functions using Random Forest