AGGNM Vis: Allosteric pocket prediction based on multidimensional feature comparison visual analysis

Abstract

Accurate identification of allosteric pockets is key to the development of allosteric drugs. Pockets within the same protein often have certain topological connections, and traditional methods that rely on static features to predict allosteric pockets may ignore the topological relationships between pockets. To address this issue, this paper proposes a new visual analysis method called AGGNM Vis. Firstly, to address the weakness in model prediction due to the lack of dynamic pocket features, static and dynamic features of pockets are calculatedand integrated as multidimensional features of pockets. Then, an allosteric pocket prediction method named AGGNM is constructed based on AutoGluon. Secondly, to solve the problem of missing potential allosteric pockets due to the lack of topological relationship analysis between pockets, AGGNM Vis conducts multi-scale comparative visual analysis on the allosteric pockets predicted by AGGNM and other pockets. The analysis compares spatial correlations, feature values, and spatial structures between pockets, assisting users in identifying potential allosteric pockets. This provides a new research perspective for allosteric pocket prediction. The experimental results show that AGGNM Vis can effectively predict the allosteric pocket, which is helpful for the development of allosteric drugs.