Deep convolution neural networks for variant classification

摘要

The technique disclosed relates to constructing a convolutional neural network based classifier for variant classification. Specifically, the disclosed technique is a convolutional neural network for training data using a backpropagation-based gradient update technique that progressively matches the output of a convolutional neural network-based classifier with the corresponding ground truth label. Regarding training the base classifier. A convolutional neural network-based classifier comprises groups of residual blocks, with each group of residual blocks being the number of convolution filters in the residual block, the convolution window size of the residual block, and the expansion of the residual block. Parameterized by the convolution rate, the size of the convolution window varies between groups of residual blocks, and the expansion convolution rate varies between groups of residual blocks. Training data includes benign and pathogenic training examples of translated sequence pairs generated from benign and pathogenic variants.