Duolin Wang1,2, Yanchun Liang2,3, Dong Xu1,2. 1. Department of Electrical Engineering and Computer Science, and Christopher S. Bond Life Sciences Center, University of Missouri, Columbia, MO, USA. 2. Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, College of Computer Science and Technology, Jilin University, Changchun, China. 3. Department of Computer Science and Technology, Zhuhai College of Jilin University, Zhuhai, China.
Abstract
MOTIVATION: Computational methods for protein post-translational modification (PTM) site prediction provide a useful approach for studying protein functions. The prediction accuracy of the existing methods has significant room for improvement. A recent deep-learning architecture, Capsule Network (CapsNet), which can characterize the internal hierarchical representation of input data, presents a great opportunity to solve this problem, especially using small training data. RESULTS: We proposed a CapsNet for predicting protein PTM sites, including phosphorylation, N-linked glycosylation, N6-acetyllysine, methyl-arginine, S-palmitoyl-cysteine, pyrrolidone-carboxylic-acid and SUMOylation sites. The CapsNet outperformed the baseline convolutional neural network architecture MusiteDeep and other well-known tools in most cases and provided promising results for practical use, especially in learning from small training data. The capsule length also gives an accurate estimate for the confidence of the PTM prediction. We further demonstrated that the internal capsule features could be trained as a motif detector of phosphorylation sites when no kinase-specific phosphorylation labels were provided. In addition, CapsNet generates robust representations that have strong discriminant power in distinguishing kinase substrates from different kinase families. Our study sheds some light on the recognition mechanism of PTMs and applications of CapsNet on other bioinformatic problems. AVAILABILITY AND IMPLEMENTATION: The codes are free to download from https://github.com/duolinwang/CapsNet_PTM. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.
MOTIVATION: Computational methods for protein post-translational modification (PTM) site prediction provide a useful approach for studying protein functions. The prediction accuracy of the existing methods has significant room for improvement. A recent deep-learning architecture, Capsule Network (CapsNet), which can characterize the internal hierarchical representation of input data, presents a great opportunity to solve this problem, especially using small training data. RESULTS: We proposed a CapsNet for predicting protein PTM sites, including phosphorylation, N-linked glycosylation, N6-acetyllysine, methyl-arginine, S-palmitoyl-cysteine, pyrrolidone-carboxylic-acid and SUMOylation sites. The CapsNet outperformed the baseline convolutional neural network architecture MusiteDeep and other well-known tools in most cases and provided promising results for practical use, especially in learning from small training data. The capsule length also gives an accurate estimate for the confidence of the PTM prediction. We further demonstrated that the internal capsule features could be trained as a motif detector of phosphorylation sites when no kinase-specific phosphorylation labels were provided. In addition, CapsNet generates robust representations that have strong discriminant power in distinguishing kinase substrates from different kinase families. Our study sheds some light on the recognition mechanism of PTMs and applications of CapsNet on other bioinformatic problems. AVAILABILITY AND IMPLEMENTATION: The codes are free to download from https://github.com/duolinwang/CapsNet_PTM. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.
Authors: David L Wheeler; Tanya Barrett; Dennis A Benson; Stephen H Bryant; Kathi Canese; Vyacheslav Chetvernin; Deanna M Church; Michael Dicuccio; Ron Edgar; Scott Federhen; Michael Feolo; Lewis Y Geer; Wolfgang Helmberg; Yuri Kapustin; Oleg Khovayko; David Landsman; David J Lipman; Thomas L Madden; Donna R Maglott; Vadim Miller; James Ostell; Kim D Pruitt; Gregory D Schuler; Martin Shumway; Edwin Sequeira; Steven T Sherry; Karl Sirotkin; Alexandre Souvorov; Grigory Starchenko; Roman L Tatusov; Tatiana A Tatusova; Lukas Wagner; Eugene Yaschenko Journal: Nucleic Acids Res Date: 2007-11-27 Impact factor: 16.971