skip to main content
Ngôn ngữ:
Giới hạn tìm kiếm: Giới hạn tìm kiếm: Dạng tài nguyên Hiển thị kết quả với: Hiển thị kết quả với: Chỉ mục

Protein complex identification through Markov clustering with firefly algorithm on dynamic protein--protein interaction networks.(Report)

Lei, Xiujuan ; Wang, Fei ; Wu, Fang-Xiang ; Zhang, Aidong ; Pedrycz, Witold

Information Sciences, Feb 1, 2016, Vol.329, p.303 [Tạp chí có phản biện]

ISSN: 0020-0255 ; DOI: 10.1016/j.ins.2015.09.028

Toàn văn sẵn có

Trích dẫn Trích dẫn bởi
  • Nhan đề:
    Protein complex identification through Markov clustering with firefly algorithm on dynamic protein--protein interaction networks.(Report)
  • Tác giả: Lei, Xiujuan ; Wang, Fei ; Wu, Fang-Xiang ; Zhang, Aidong ; Pedrycz, Witold
  • Chủ đề: Computer Science – Analysis ; Biomedical Engineering – Analysis ; Algorithms – Analysis ; Optimization Theory – Analysis
  • Là 1 phần của: Information Sciences, Feb 1, 2016, Vol.329, p.303
  • Mô tả: To access, purchase, authenticate, or subscribe to the full-text of this article, please visit this link: http://dx.doi.org/10.1016/j.ins.2015.09.028 Byline: Xiujuan Lei [xjlei@snnu.edu.cn] (a,*), Fei Wang (a), Fang-Xiang Wu (b), Aidong Zhang (c), Witold Pedrycz [wpedrycz@ualberta.ca] (d,e,f) Keywords Dynamic protein--protein interaction network (DPIN); Markov clustering (MCL) algorithm; Firefly algorithm (FA); Protein complex Abstract Markov clustering (MCL) is a commonly used algorithm for clustering networks in bioinformatics. It shows good performance in clustering dynamic protein--protein interaction networks (DPINs). However, a limitation of MCL and its variants (e.g, regularized MCL and soft regularized MCL) is that the clustering results are mostly dependent on the parameters whose values are user-specified. In this study, we propose a new MCL method based on the firefly algorithm (FA) to identify protein complexes from DPIN. Based on three-sigma principle, we construct the DPIN and discuss an overall modeling process. In order to optimize parameters, we exploit a number of population-based optimization methods. A thorough comparison completed for different swarm optimization algorithms such as particle swarm optimization (PSO) and firefly algorithm (FA) has been carried out. The identified protein complexes on the DIP dataset show that the new algorithm outperforms the state-of-the-art approaches in terms of accuracy of protein complex identification. Author Affiliation: (a) School of Computer Science, Shaanxi Normal University, Xi'an, Shaanxi 710062, China (b) Division of Biomedical Engineering, University of Saskatchewan, Saskatoon SK S7N 5A9, Canada (c) Department of Computer Science and Engineering, State University of New York at Buffalo, NY 14260-2000, USA (d) Department of Electrical & Computer Engineering, University of Alberta, Edmonton T6R 2V4 AB, Canada (e) Department of Electrical and Computer Engineering Faculty of Engineering, King Abdulaziz University, Jeddah 21589, Saudi Arabia (f) Systems Research Institute, Polish Academy of Sciences Warsaw, Poland * Corresponding author. Tel.: +86 29 85310161. Article History: Received 31 December 2014; Revised 8 September 2015; Accepted 12 September 2015
  • Ngôn ngữ: English
  • Số nhận dạng: ISSN: 0020-0255 ; DOI: 10.1016/j.ins.2015.09.028

Đang tìm Cơ sở dữ liệu bên ngoài...