GC\(^2\)NMF: A Novel Matrix Factorization Framework for Gene–Phenotype Association Prediction

  • Yaogong Zhang
  • Jiahui Liu
  • Xiaohu Liu
  • Yuxiang Hong
  • Xin Fan
  • Yalou Huang
  • Yuan Wang
  • Maoqiang XieEmail author
Original Research Article


Gene–phenotype association prediction can be applied to reveal the inherited basis of human diseases and facilitate drug development. Gene–phenotype associations are related to complex biological processes and influenced by various factors, such as relationship between phenotypes and that among genes. While due to sparseness of curated gene–phenotype associations and lack of integrated analysis of the joint effect of multiple factors, existing applications are limited to prediction accuracy and potential gene–phenotype association detection. In this paper, we propose a novel method by exploiting weighted graph constraint learned from hierarchical structures of phenotype data and group prior information among genes by inheriting advantages of Non-negative Matrix Factorization (NMF), called Weighted Graph Constraint and Group Centric Non-negative Matrix Factorization (GC\(^2\)NMF). Specifically, first we introduce the depth of parent–child relationships between two adjacent phenotypes in hierarchical phenotypic data as weighted graph constraint for a better phenotype understanding. Second, we utilize intra-group correlation among genes in a gene group as group constraint for gene understanding. Such information provides us with the intuition that genes in a group probably result in similar phenotypes. The model not only allows us to achieve a high-grade prediction performance, but also helps us to learn interpretable representation of genes and phenotypes simultaneously to facilitate future biological analysis. Experimental results on biological gene–phenotype association datasets of mouse and human demonstrate that GC\(^2\)NMF can obtain superior prediction accuracy and good understandability for biological explanation over other state-of-the-arts methods.


NMF Weighted graph constraint Group centric constraint Gene–phenotype association prediction 



This work is supported by the National Natural Science Foundation of China (nos. 61702367, 61300972). The Research Project of Tianjin Municipal Commission of Education (no. 2017KJ033).


  1. 1.
    Ali Mashhoori SH (2012) Incorporating hierarchical information into the matrix factorization model for collaborative filtering. Lecture notes in computer science. Springer, Berlin, HeidelbergCrossRefGoogle Scholar
  2. 2.
    Benzi K, Kalofolias V, Bresson X, Vandergheynst P (2016) Song recommendation with non-negative matrix factorization and graph total variationGoogle Scholar
  3. 3.
    Bult CJ, Eppig JT, Kadin JA, Richardson JE, Blake JA (2007) The mouse genome database (MGD): mouse biology and model systems. Nucleic Acids Res 36(Database):D724–D728. CrossRefGoogle Scholar
  4. 4.
    Cai D, He X, Han J, Huang TS (2011) Graph regularized nonnegative matrix factorization for data representation. IEEE Trans Pattern Anal Mach Intell 8:1548–1560. CrossRefGoogle Scholar
  5. 5.
    Chatr-Aryamontri A, Breitkreutz BJ, Heinicke S et al (2013) The BioGRID interaction database: 2013 update. Nucleic Acids Res 41(Database):D816–D823. PubMedCrossRefGoogle Scholar
  6. 6.
    Chen Y, Li L (2015) Phenome-driven disease genetics prediction toward drug discovery. Bioinformatics 12:i276–i283. CrossRefGoogle Scholar
  7. 7.
    Daniel D, Lee HSS (2000) Algorithms for non-negative matrix factorization. In: In NIPS. MIT Press, pp 556–562Google Scholar
  8. 8.
    De Las Rivas J, Fontanillo C (2010) Protein–protein interactions essentials: key concepts to building and analyzing interactome networks. PLoS Comput Biol 6:e1000807. CrossRefGoogle Scholar
  9. 9.
    Eppig JT, Blake JA, Bult CJ, Kadin JA, Richardson JE, Mouse Genome Database Group (2015) The mouse genome database (MGD): facilitating mouse as a model for human biology and disease. Nucleic Acids Res 43(Database issue):D726–D736CrossRefPubMedGoogle Scholar
  10. 10.
    Hwang T, Kuang R (2010) A heterogeneous label propagation algorithm for disease gene discovery. SIAM, p 12Google Scholar
  11. 11.
    Jeribi A (1997) Spectral graph theory. American Mathematical SocietyGoogle Scholar
  12. 12.
    Kanehisa M, Sato Y, Kawashima M, Furumichi M, Tanabe M (2016) KEGG as a reference resource for gene and protein annotation. Nucleic Acids Res 44(D1):D457–D462. CrossRefPubMedGoogle Scholar
  13. 13.
    Köhler S, Bauer S (2008) Walking the interactome for prioritization of candidate disease genes. Am J Human Genetics 4:949–958. CrossRefGoogle Scholar
  14. 14.
    Köhler S, Doelken SC, Mungall CJ et al (2014) The Human Phenotype Ontology project: linking molecular biology and disease through phenotype data. Nucleic Acids Res 42(D1):D966–D974. CrossRefGoogle Scholar
  15. 15.
    Li Y, Patra JC. Genome-wide inferring gene-phenotype relationship by walking on the heterogeneous network (2010) Bioinformatics 9:1219–1224. CrossRefGoogle Scholar
  16. 16.
    Ma H, Yang H, Lyu MR, King I (2008) SoRec: social recommendation using probabilistic matrix factorization. In: Proceeding of the 17th ACM conference on information and knowledge mining—CIKM ’08. ACM Press, New York, New York, USA, p 931.
  17. 17.
    Rajabi R, Khodadadzadeh M, Ghassemian H (2011) Graph regularized nonnegative matrix factorization for hyperspectral data unmixing. In: 2011 7th Iranian conference on machine vision and image processing, pp 1–4. IEEE.
  18. 18.
    Salakhutdinov R, Mnih A (2008) Bayesian probabilistic matrix factorization using Markov chain Monte Carlo. In: Proceedings of the 25th international conference on machine learning—ICML ’08. ACM Press, New York, New York, USA, pp 880–887.
  19. 19.
    Salakhutdinov R, Mnih A (2008) Probabilistic matrix factorization. In: Advances in neural information processing systems, vol 20Google Scholar
  20. 20.
    Shan H, Banerjee A (2010) Generalized probabilistic matrix factorizations for collaborative filtering. In: 2010 IEEE International conference on data mining. IEEE, pp 1025–1030.
  21. 21.
    Smith CL, Eppig JT (2009) The mammalian phenotype ontology: enabling robust annotation and comparative analysis. Wiley interdisciplinary reviews. Syst Biol Med 3:390–399. Google Scholar
  22. 22.
    Vanunu O, Magger O (2010) Associating genes and protein complexes with disease via network propagation. PLoS Comput Biol 1:e1000641. CrossRefGoogle Scholar
  23. 23.
    Wu X, Jiang R (2008) Network-based global inference of human disease genes. Mol Syst Biol 189.
  24. 24.
    Xie M, Xu Y, Zhang Y, Hwang T, Kuang R (2015) Network-based phenome–genome association prediction by bi-random walk. PloS One 5:e0125138. CrossRefGoogle Scholar
  25. 25.
    Zhang S, Wang W, Ford J, Makedon F (2006) Proceedings of the 2006 SIAM International Conference on Data Mining. Society for Industrial and Applied Mathematics, Philadelphia, PA.

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2018

Authors and Affiliations

  • Yaogong Zhang
    • 1
  • Jiahui Liu
    • 1
  • Xiaohu Liu
    • 1
  • Yuxiang Hong
    • 1
  • Xin Fan
    • 1
  • Yalou Huang
    • 1
  • Yuan Wang
    • 2
  • Maoqiang Xie
    • 1
    Email author
  1. 1.College of SoftwareNanKai UniversityTianJinChina
  2. 2.Computer Science and Information EngineeringTianjin University of Science and TechnologyTianJinChina

Personalised recommendations