(59ak) Structure-Based Prediction of Kinase Activation amidst a Varied Mutational Landscape Using Privileged Learning

Post-translational modifications such as phosphorylation catalyzed by kinases are essential for cell signaling. The activation of mutated kinase in a cancer cell can profoundly impact disease progression and drug efficacy. However, numerous clinical mutations in the human kinome impose challenges in defining the quantitative structure-activity relationship. Previous work (Patil K. et al. PNAS 2021, 118(10), e2019132118.) shows that perturbation of structural properties such as hydrogen-bonding occupancy in the áC-helix and the activation loop domains computed from molecular dynamics (MD) simulation is a good indicator of the activation status of anaplastic ymphoma kinase (ALK) mutants with 2/3rd of the mutants utilizing this mechanism of activation.

Here we develop a neural network-based privileged learning algorithm that utilizes structural features computed from MD simulation for a small fraction of kinase mutants as privileged information to improve the binary classification performance of kinase activation. For 223 mutants with privileged information, the weights W and bias factors B of output hidden nodes are obtained from the neural network (Net1) using all 135 features. The values F of output hidden nodes are obtained from Net2 using only 59 mutational features. The adjusted hidden features W*F+B and the activation status are used as inputs and outputs for Net3, respectively. For 690 mutants without privileged information, W′ and B′ are estimated from a weighted linear combination of W and B obtained from Net1, where the similarity coefficients are calculated using the radial basis function kernel.

We show that the privileged learning method achieves about 72.4% balanced accuracy against ~900 mutations across ~20 kinase classes which outperforms other neural network and tree-based ML methods which are trained without privileged information, or trained using K nearest neighbor imputation methods for estimating the missing structural features for the rest 690 mutants. Our approach paves way for interpretable prediction of cancer-driving kinase mutations and guiding precision medicine treatment.