Protein domain recurrence and order can enhance prediction of protein functions

被引:19
|
作者
Messih, Mario Abdel [4 ,5 ]
Chitale, Meghana [1 ]
Bajic, Vladimir B. [5 ]
Kihara, Daisuke [1 ,2 ,3 ]
Gao, Xin [4 ,5 ]
机构
[1] Purdue Univ, Dept Comp Sci, W Lafayette, IN 47907 USA
[2] Purdue Univ, Dept Biol Sci, Coll Sci, W Lafayette, IN 47907 USA
[3] Purdue Univ, Markey Ctr Struct Biol, W Lafayette, IN 47907 USA
[4] KAUST, Math & Comp Sci & Engn Div, Thuwal 239556900, Saudi Arabia
[5] KAUST, Computat Biosci Res Ctr, Thuwal 239556900, Saudi Arabia
关键词
ADAPTER PROTEIN; DATABASE; SEVENLESS; ANNOTATION; INTERACTS; FAMILIES; RESOURCE;
D O I
10.1093/bioinformatics/bts398
中图分类号
Q5 [生物化学];
学科分类号
071010 ; 081704 ;
摘要
Motivation: Burgeoning sequencing technologies have generated massive amounts of genomic and proteomic data. Annotating the functions of proteins identified in this data has become a big and crucial problem. Various computational methods have been developed to infer the protein functions based on either the sequences or domains of proteins. The existing methods, however, ignore the recurrence and the order of the protein domains in this function inference. Results: We developed two new methods to infer protein functions based on protein domain recurrence and domain order. Our first method, DRDO, calculates the posterior probability of the Gene Ontology terms based on domain recurrence and domain order information, whereas our second method, DRDO-NB, relies on the naive Bayes methodology using the same domain architecture information. Our large-scale benchmark comparisons show strong improvements in the accuracy of the protein function inference achieved by our new methods, demonstrating that domain recurrence and order can provide important information for inference of protein functions.
引用
收藏
页码:I444 / I450
页数:7
相关论文
共 50 条
  • [41] Prediction of Protein Functions from Protein Interaction Networks: A Naive Bayes Approach
    Nguyen, Cao D.
    Gardiner, Katheleen J.
    Nguyen, Duong
    Cios, Krzysztof J.
    PRICAI 2008: TRENDS IN ARTIFICIAL INTELLIGENCE, 2008, 5351 : 788 - +
  • [42] An improved protein decoy set for testing energy functions for protein structure prediction
    Tsai, J
    Bonneau, R
    Morozov, AV
    Kuhlman, B
    Rohl, CA
    Baker, D
    PROTEINS-STRUCTURE FUNCTION AND BIOINFORMATICS, 2003, 53 (01) : 76 - 87
  • [43] Prediction of human protein functions with protein mapping techniques and deep learning model
    Alaku, Talha Burak
    Turkoglu, Ibrahim
    PAMUKKALE UNIVERSITY JOURNAL OF ENGINEERING SCIENCES-PAMUKKALE UNIVERSITESI MUHENDISLIK BILIMLERI DERGISI, 2022, 28 (02): : 255 - 265
  • [44] A Protein-Protein Interaction Prediction Method Embracing Intra-Protein Domain Cohesion Information
    Jang, Woo-Hyuk
    Jung, Suk Hoon
    Hyun, Bo-ra
    Han, Dong-Soo
    2009 IEEE INTERNATIONAL CONFERENCE ON BIOINFORMATICS AND BIOMEDICINE, 2009, : 371 - 374
  • [45] Protein Scaffolds Can Enhance the Bistability of Multisite Phosphorylation Systems
    Chan, Carlo
    Liu, Xinfeng
    Wang, Liming
    Bardwell, Lee
    Nie, Qing
    Enciso, German
    PLOS COMPUTATIONAL BIOLOGY, 2012, 8 (06)
  • [46] A Study of Network-based Kernel Methods on Protein-Protein Interaction for Protein Functions Prediction
    Ching, Wai-Ki
    Li, Limin
    Chan, Yat-Ming
    Mamitsuka, Hiroshi
    OPTIMIZATION AND SYSTEMS BIOLOGY, 2009, 11 : 25 - +
  • [47] On network-based kernel methods for protein-protein interactions with applications in protein functions prediction
    Limin Li
    Waiki Ching
    Yatming Chan
    Hiroshi Mamitsuka
    Journal of Systems Science and Complexity, 2010, 23 : 917 - 930
  • [48] On network-based kernel methods for protein-protein interactions with applications in protein functions prediction
    Li, Limin
    Ching, Waiki
    Chan, Yatming
    Mamitsuka, Hiroshi
    JOURNAL OF SYSTEMS SCIENCE & COMPLEXITY, 2010, 23 (05) : 917 - 930
  • [49] Prediction of protein functions based on protein-protein interaction networks: A min-cut approach
    Altaf-Ul-Amin, Md. (amin-m@is.naist.jp), The IEEE Computer Society; The Database Society of Japan, DBSJ; Information Processing Society of Japan, IPSJ; The Inst. of Elec., Info. and Com. Engineers, IEICE (Inst. of Elec. and Elec. Eng. Computer Society, 445 Hoes Lane - P.O.Box 1331, Piscataway, NJ 08855-1331, United States):
  • [50] Mutual information and variants for protein domain-domain contact prediction
    Mireille Gomes
    Rebecca Hamer
    Gesine Reinert
    Charlotte M Deane
    BMC Research Notes, 5 (1)