AUTHOR=Ramakrishnan Gayatri , Baakman Coos , Heijl Stephan , Vroling Bas , van Horck Ragna , Hiraki Jeffrey , Xue Li C. , Huynen Martijn A. 

TITLE=Understanding structure-guided variant effect predictions using 3D convolutional neural networks

JOURNAL=Frontiers in Molecular Biosciences

VOLUME=Volume 10 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/molecular-biosciences/articles/10.3389/fmolb.2023.1204157

DOI=10.3389/fmolb.2023.1204157

ISSN=2296-889X

ABSTRACT=Predicting pathogenicity of missense variants in molecular diagnostics remains a challenge despite the available wealth of data that include evolutionary sequence conservation and of tools to integrate those data. We describe DeepRank-Mut, a configurable framework designed to extract and learn from physicochemically relevant features of amino acids surrounding missense variants in 3D space. For each variant, various atomic and residue-level features are extracted from its structural environment, including sequence conservation scores of the surrounding amino acids, and stored in multi-channel 3D voxel grids which are then used to train a 3D convolutional neural network (3D-CNN). The resultant model gives a probabilistic estimate of whether a given input variant is disease-causing or benign. The performance of our approach is comparable to other widely used resources which also combine sequence and structural features. Based on our 10-fold cross-validation experiments, we achieve an average accuracy of 0.77 on independent test datasets. We discuss the contribution of the variant neighborhood in the model's predictive power, in addition to the impact of individual features on the model's performance. We also highlight how predictions are influenced by the underlying disease mechanisms of missense mutations and offer insights into understanding these to improve pathogenicity predictions. Our study presents aspects to take into consideration when adopting deep learning approaches for protein structure-guided pathogenicity predictions.