Duolin Wang1,2, Shuai Zeng2, Chunhui Xu2, Wangren Qiu2,3, Yanchun Liang1,4, Trupti Joshi2,5, Dong Xu1,2. 1. Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, College of Computer Science and Technology, Jilin University, Changchun 130012, China. 2. Department of Electrical Engineering and Computer Science, Informatics Institute, and Christopher S. Bond Life Sciences Center, University of Missouri, Columbia, MO 65211, USA. 3. Computer Department, Jingdezhen Ceramic Institute, Jingdezhen 333403, China. 4. Department of Computer Science and Technology, Zhuhai College of Jilin University, Zhuhai 519041, China. 5. Department of Health Management and Informatics, School of Medicine, University of Missouri, Columbia, MO 65211, USA.
Abstract
MOTIVATION: Computational methods for phosphorylation site prediction play important roles in protein function studies and experimental design. Most existing methods are based on feature extraction, which may result in incomplete or biased features. Deep learning as the cutting-edge machine learning method has the ability to automatically discover complex representations of phosphorylation patterns from the raw sequences, and hence it provides a powerful tool for improvement of phosphorylation site prediction. RESULTS: We present MusiteDeep, the first deep-learning framework for predicting general and kinase-specific phosphorylation sites. MusiteDeep takes raw sequence data as input and uses convolutional neural networks with a novel two-dimensional attention mechanism. It achieves over a 50% relative improvement in the area under the precision-recall curve in general phosphorylation site prediction and obtains competitive results in kinase-specific prediction compared to other well-known tools on the benchmark data. AVAILABILITY AND IMPLEMENTATION: MusiteDeep is provided as an open-source tool available at https://github.com/duolinwang/MusiteDeep. CONTACT: xudong@missouri.edu. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.
MOTIVATION: Computational methods for phosphorylation site prediction play important roles in protein function studies and experimental design. Most existing methods are based on feature extraction, which may result in incomplete or biased features. Deep learning as the cutting-edge machine learning method has the ability to automatically discover complex representations of phosphorylation patterns from the raw sequences, and hence it provides a powerful tool for improvement of phosphorylation site prediction. RESULTS: We present MusiteDeep, the first deep-learning framework for predicting general and kinase-specific phosphorylation sites. MusiteDeep takes raw sequence data as input and uses convolutional neural networks with a novel two-dimensional attention mechanism. It achieves over a 50% relative improvement in the area under the precision-recall curve in general phosphorylation site prediction and obtains competitive results in kinase-specific prediction compared to other well-known tools on the benchmark data. AVAILABILITY AND IMPLEMENTATION: MusiteDeep is provided as an open-source tool available at https://github.com/duolinwang/MusiteDeep. CONTACT: xudong@missouri.edu. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.
Authors: Lilia M Iakoucheva; Predrag Radivojac; Celeste J Brown; Timothy R O'Connor; Jason G Sikes; Zoran Obradovic; A Keith Dunker Journal: Nucleic Acids Res Date: 2004-02-11 Impact factor: 16.971
Authors: Fuyi Li; Yanan Wang; Chen Li; Tatiana T Marquez-Lago; André Leier; Neil D Rawlings; Gholamreza Haffari; Jerico Revote; Tatsuya Akutsu; Kuo-Chen Chou; Anthony W Purcell; Robert N Pike; Geoffrey I Webb; A Ian Smith; Trevor Lithgow; Roger J Daly; James C Whisstock; Jiangning Song Journal: Brief Bioinform Date: 2019-11-27 Impact factor: 11.622