Classifying kinase conformations using a machine learning approach

Daniel Ian Mcskimming,Natarajan Kannan,Khaled Rasheed

doi:10.1186/s12859-017-1506-2

Daniel Ian Mcskimming, Natarajan Kannan + Show 1 more

Open Access

https://doi.org/10.1186/s12859-017-1506-2

Copy DOI

Journal: BMC bioinformatics	Publication Date: Feb 2, 2017
Citations: 37	License type: open-access

Affiliation: University of Georgia

Abstract

BackgroundSignaling proteins such as protein kinases adopt a diverse array of conformations to respond to regulatory signals in signaling pathways. Perhaps the most fundamental conformational change of a kinase is the transition between active and inactive states, and defining the conformational features associated with kinase activation is critical for selectively targeting abnormally regulated kinases in diseases. While manual examination of crystal structures have led to the identification of key structural features associated with kinase activation, the large number of kinase crystal structures (~3,500) and extensive conformational diversity displayed by the protein kinase superfamily poses unique challenges in fully defining the conformational features associated with kinase activation. Although some computational approaches have been proposed, they are typically based on a small subset of crystal structures using measurements biased towards the active site geometry.ResultsWe utilize an unbiased informatics based machine learning approach to classify all eukaryotic protein kinase conformations deposited in the PDB. We show that the orientation of the activation segment, measured by φ, ψ, χ1, and pseudo-dihedral angles more accurately classify kinase crystal conformations than existing methods. We show that the formation of the K-E salt bridge is statistically dependent upon the activation segment orientation and identify evolutionary differences between the activation segment conformation of tyrosine and serine/threonine kinases. We provide evidence that our method can identify conformational changes associated with the binding of allosteric regulatory proteins, and show that the greatest variation in inactive structures comes from kinase group and family specific side chain orientations.ConclusionWe have provided the first comprehensive machine learning based classification of protein kinase active/inactive conformations, taking into account more structures and measurements than any previous classification effort. Further, our unbiased classification of inactive structures reveals residues associated with kinase functional specificity. To enable classification of new crystal structures, we have made our classifier publicly accessible through a stand-alone program housed at https://github.com/esbg/kinconform [DOI:10.5281/zenodo.249090].

Highlights

Signaling proteins such as protein kinases adopt a diverse array of conformations to respond to regulatory signals in signaling pathways
We find that the orientation of the activation segment alone is sufficient to accurately classify kinase conformations as active or inactive, and identify the relative importance of different regions of the activation segment in classifying protein tyrosine kinase (PTK) and serine/threonine kinase
Kinase conformation is determined by activation segment orientation Previous methods have focused on the active site geometry for conformation classification, using the DFG motif and αC-helix orientations as proxies for the catalytically necessary placement of key residues

Summary

Introduction

Signaling proteins such as protein kinases adopt a diverse array of conformations to respond to regulatory signals in signaling pathways. The enzymatic activity of kinases is regulated through conformational changes in the protein kinase domain, which is shared by diverse members of the protein kinase super-family [1,2,3]. The manual inspection of kinase crystal structures has led to an understanding of the roles key residues play in stabilizing and orienting adenosine tri-phosphate (ATP) for phosphoryl transfer [12, 13], as well as qualitative descriptions of the active site geometry and conformational states. A variety of structural measures have been developed to determine the activation state of a kinase, most of which center on the orientation of two regulatory components: the αC-helix and the activation segment. The activation segment provides two pieces of information: the orientation of the DFG aspartate, which chelates a magnesium ion that coordinates with the β- and γ-phosphates of ATP (Fig. 1b), and whether the C-terminal activation segment is blocking the substrate binding site (Fig. 1c)

Methods

Results

Conclusion