Redefining the Protein Kinase Conformational Space with Machine Learning. Issue 7 (19th July 2018)

• Record Type: Journal Article
• Authors: Ung, Peter Man-Un; Rahman, Rayees; Schlessinger, Avner
• Is Part Of: Cell chemical biology. Volume 25:Issue 7(2018)
• Page Start: 916
• Page End: 924.e2
• Publication Date: 2018-07-19
• Subjects: protein kinase -- structure -- conformation -- random forest -- classification -- inhibitor -- selectivity -- drug discovery -- cheminformatics; Biochemistry -- Periodicals; 572.05
• DOI: 10.1016/j.chembiol.2018.05.002
• Languages: English
• ISSNs: 2451-9456

Abstract

Summary: Protein kinases are dynamic, adopting different conformational states that are critical for their catalytic activity. We assess a range of structural features derived from the conserved αC helix and DFG motif to define the conformational space of the catalytic domain of protein kinases. We then construct Kinformation, a random forest classifier, to annotate the conformation of 3, 708 kinase structures in the PDB. Our classification scheme captures known active and inactive kinase conformations and defines an additional conformational state, thereby refining the current understanding of the kinase conformational space. Furthermore, network analysis of the small molecules recognized by each conformation captures chemical substructures that are associated with each conformation type. Our description of the kinase conformational space is expected to improve modeling of protein kinase structures, as well as guide the development of conformation-specific kinase inhibitors with optimal pharmacological profiles. Graphical Abstract: Highlights: DFG motif and αC helix structural features define protein kinases conformations Random forest classifier annotates the kinase conformations in the PDB Current classification refines the description of kinase conformational space A number of chemical substructures of kinase inhibitors are conformation specific Abstract : Ung and Rahman et al . constructed a machine-learning-based algorithm to refine the current classification of protein kinase structures into active and inactive conformations. Analysis of the small molecules recognized by each conformation captures conformation-specific chemical substructures.