Classifying protein structures into folds by convolutional neural networks, distance maps, and persistent homology
Yechan Hong, Yongyu Deng, Haofan Cui, Jan Segert, Jianlin Jack Cheng
This paper develops a 2D-convolutional neural network to classify protein 3D structures into predefined folds using distance matrices and persistent homology images, achieving high accuracy on SCOP and SCOPe datasets.
bioRxiv · Apr 15, 2020 · PreprintBioinformatics