Biomine: predicting links between biological entities using network models of heterogeneous databases

BackgroundBiological databases contain large amounts of data concerning the functions and associations of genes and proteins. Integration of data from several such databases into a single repository can aid the discovery of previously unknown connections spanning multiple types of relationships and databases.ResultsBiomine is a system that integrates cross-references from several biological databases into a graph model with multiple types of edges, such as protein interactions, gene-disease associations and gene ontology annotations. Edges are weighted based on their type, reliability, and informativeness. We present Biomine and evaluate its performance in link prediction, where the goal is to predict pairs of nodes that will be connected in the future, based on current data. In particular, we formulate protein interaction prediction and disease gene prioritization tasks as instances of link prediction. The predictions are based on a proximity measure computed on the integrated graph. We consider and experiment with several such measures, and perform a parameter optimization procedure where different edge types are weighted to optimize link prediction accuracy. We also propose a novel method for disease-gene prioritization, defined as finding a subset of candidate genes that cluster together in the graph. We experimentally evaluate Biomine by predicting future annotations in the source databases and prioritizing lists of putative disease genes.ConclusionsThe experimental results show that Biomine has strong potential for predicting links when a set of selected candidate links is available. The predictions obtained using the entire Biomine dataset are shown to clearly outperform ones obtained using any single source of data alone, when different types of links are suitably weighted. In the gene prioritization task, an established reference set of disease-associated genes is useful, but the results show that under favorable conditions, Biomine can also perform well when no such information is available.The Biomine system is a proof of concept. Its current version contains 1.1 million entities and 8.1 million relations between them, with focus on human genetics. Some of its functionalities are available in a public query interface at http://biomine.cs.helsinki.fi, allowing searching for and visualizing connections between given biological entities.

[1]  D. Swanson.  Fish Oil, Raynaud's Syndrome, and Undiscovered Public Knowledge , 2015, Perspectives in biology and medicine.

[2]  M. Ashburner,et al.  Gene Ontology: tool for the unification of biology , 2000, Nature Genetics.

[3]  C. Deane,et al.  Protein Interactions , 2002, Molecular & Cellular Proteomics.

[4]  Alan F. Scott,et al.  Online Mendelian Inheritance in Man (OMIM), a knowledgebase of human genes and genetic disorders , 2002, Nucleic Acids Res..

[5]  Gregory D. Schuler,et al.  Database resources of the National Center for Biotechnology Information: update , 2004, Nucleic acids research.

[6]  T. Gilliam,et al.  Molecular triangulation: bridging linkage and molecular-network information for identifying candidate genes in Alzheimer's disease. , 2004, Proceedings of the National Academy of Sciences of the United States of America.

[7]  Francis D. Gibbons,et al.  Predicting protein complex membership using probabilistic network reliability. , 2004, Genome research.

[8]  Victoria J. Hodge,et al.  A Survey of Outlier Detection Methodologies , 2004, Artificial Intelligence Review.

[9]  Priyanka Gupta,et al.  BioWarehouse: a bioinformatics database warehouse toolkit , 2006, BMC Bioinformatics.

[10]  Joyce A. Mitchell,et al.  Using literature-based discovery to identify disease candidate genes , 2005, Int. J. Medical Informatics.

[11]  Pablo Tamayo,et al.  Gene set enrichment analysis: A knowledge-based approach for interpreting genome-wide expression profiles , 2005, Proceedings of the National Academy of Sciences of the United States of America.

[12]  Golan Yona,et al.  BIOZON: a system for unification, management and analysis of heterogeneous biological data , 2006, BMC Bioinformatics.

[13]  P. Febbo,et al.  Application of a priori established gene sets to discover biologically important differential expression in microarray data , 2005, Proceedings of the National Academy of Sciences of the United States of America.

[14]  P. Bork,et al.  Literature mining for the biologist: from information retrieval to biological discovery , 2006, Nature Reviews Genetics.

[15]  Jason Y. Liu,et al.  Analysis of protein sequence and interaction data for candidate disease gene prediction , 2006, Nucleic acids research.

[16]  Yehuda Koren,et al.  Measuring and extracting proximity in networks , 2006, KDD '06.

[17]  Hannu Toivonen,et al.  Link Discovery in Graphs Derived from Biological Databases , 2006, DILS.

[18]  C. Wijmenga,et al.  Reconstruction of a functional human gene network, with an application for prioritizing positional candidate genes. , 2006, American journal of human genetics.

[19]  Christopher J. Rawlings,et al.  Graph-based analysis and visualization of experimental results with ONDEX , 2006, Bioinform..

[20]  B. Snel,et al.  Predicting disease genes using protein–protein interactions , 2006, Journal of Medical Genetics.

[21]  Tom Fawcett,et al.  An introduction to ROC analysis , 2006, Pattern Recognit. Lett..

[22]  K. N. Chandrika,et al.  Analysis of the human protein interactome and comparison with yeast, worm and fly interaction datasets , 2006, Nature Genetics.

[23]  Kai Wang,et al.  Pathway-based approaches for analysis of genomewide association studies. , 2007, American journal of human genetics.

[24]  Yehuda Koren,et al.  Measuring and extracting proximity graphs in networks , 2007, TKDD.

[25]  Francisco Melo,et al.  StAR: a simple tool for the statistical comparison of ROC curves , 2008, BMC Bioinformatics.

[26]  R. Sharan,et al.  Network-based prediction of protein function , 2007, Molecular systems biology.

[27]  Jon M. Kleinberg,et al.  The link-prediction problem for social networks , 2007, J. Assoc. Inf. Sci. Technol..

[28]  Tatiana A. Tatusova,et al.  Entrez Gene: gene-centered information at NCBI , 2004, Nucleic Acids Res..

[29]  Fred W. Glover,et al.  Solving the maximum edge weight clique problem via unconstrained quadratic programming , 2007, Eur. J. Oper. Res..

[30]  M. McCarthy,et al.  Genome-wide association studies for complex traits: consensus, uncertainty and challenges , 2008, Nature Reviews Genetics.

[31]  P. Robinson,et al.  Walking the interactome for prioritization of candidate disease genes. , 2008, American journal of human genetics.

[32]  Andrew D. Johnson,et al.  Bmc Medical Genetics an Open Access Database of Genome-wide Association Results , 2009 .

[33]  R. Sharan,et al.  Protein networks in disease. , 2008, Genome research.

[34]  D. Chasman.  On the utility of gene set methods in genomewide association studies of quantitative traits , 2008, Genetic epidemiology.

[35]  Hannu Toivonen,et al.  Finding reliable subgraphs from large probabilistic graphs , 2008, Data Mining and Knowledge Discovery.

[36]  Damian Smedley,et al.  BioMart – biological queries made easy , 2009, BMC Genomics.

[37]  Robert D. Finn,et al.  InterPro: the integrative protein signature database , 2008, Nucleic Acids Res..

[38]  E. Snitkin,et al.  Genome-wide prioritization of disease genes and identification of disease-disease associations from an integrated human functional linkage network , 2009, Genome Biology.

[39]  Mei Liu,et al.  Assessing reliability of protein-protein interactions by integrative analysis of data in model organisms , 2009, BMC Bioinformatics.

[40]  Christian von Mering,et al.  STRING 8—a global view on proteins and their functional interactions in 630 organisms , 2008, Nucleic Acids Res..

[41]  Oliver P. T. Barrett,et al.  Evolved orthogonal ribosome purification for in vitro characterization , 2010, Nucleic acids research.

[42]  María Martín,et al.  The Universal Protein Resource (UniProt) in 2010 , 2010 .

[43]  TaeHyun Hwang,et al.  A Heterogeneous Label Propagation Algorithm for Disease Gene Discovery , 2010, SDM.

[44]  George Kollios,et al.  k-nearest neighbors in uncertain graphs , 2010, Proc. VLDB Endow..

[45]  Baris E. Suzek,et al.  The Universal Protein Resource (UniProt) in 2010 , 2009, Nucleic Acids Res..

[46]  A. Barabasi,et al.  Network medicine : a network-based approach to human disease , 2010 .

[47]  Roded Sharan,et al.  Associating Genes and Protein Complexes with Disease via Network Propagation , 2010, PLoS Comput. Biol..

[48]  Carl Kingsford,et al.  The power of protein interaction networks for associating genes with diseases , 2010, Bioinform..

[49]  Susumu Goto,et al.  KEGG for representation and analysis of molecular networks involving diseases and drugs , 2009, Nucleic Acids Res..

[50]  Bart De Moor,et al.  A guide to web tools to prioritize candidate genes , 2011, Briefings Bioinform..