Flexible and Robust Nonlinear Statistical Modeling Based on High-Dimensional Complex Heterogeneous Data Analysis

2010 Fiscal Year Final Research Report

• Project/Area Number: 20680016
• Research Category: Grant-in-Aid for Young Scientists (A)
• Allocation Type: Single-year Grants
• Research Field: Statistical science
• Research Institution: The University of Tokyo
• Principal Investigator: IMOTO Seiya The University of Tokyo, 医科学研究所, 准教授 (10345027)
• Project Period (FY): 2008 – 2010
• Keywords: 高次元データ解析 / 異種データ統合 / ベイズ統計 / ロバスト

Research Abstract

We developed robust statistical methods for extracting valuable information from various types of high-dimensional heterogeneous data. As the results, when a subset of feature variables is defined a priori, we develop a series of statistical methods that can evaluate whether the subset has a unique distribution by comparing with background variables in the given large dataset. We also proposed a robust estimation method for large gene network from microarray gene expression data and other types of data like transcription binding sites and applied it to the analysis of cancer heterogeneity.

Research Products

• [Journal Article] Comprehensive pharmacogenomic pathway screening by data assimilation (2011)
  • Author(s): T.Hasegawa, R.Yamaguchi, M.Nagasaki, S.Imoto, S.Miyano
  • Journal Title: LNCS (Springer-Verlag) in press.
• [Journal Article] Optimal search on clustered structural constraint for learning Bayesian network structure (2010)
  • Author(s): K.Kojima, E.Perrier, S.Imoto, S.Miyano
  • Journal Title: Journal of Machine Learning Research 11 Pages: 285-310
• [Journal Article] Inferring dynamic gene networks under varying conditions for transcriptomic network comparison. (2010)
  • Author(s): T.Shimamura, S.Imoto, R.Yamaguchi, M.Nagasaki, S.Miyano
  • Journal Title: Bioinformatics 26(8) Pages: 1064-1072
• [Journal Article] Gene set-based module discovery decodes cis-regulatory codes governing diverse gene expression across human multiple tissues (2010)
  • Author(s): A.Niida, S.Imoto, R.Yamaguchi, M.Nagasaki, S.Miyano
  • Journal Title: PLoS One 5(6) Pages: e10910
• [Journal Article] Model-free unsupervised gene set screening based on information enrichment in expression profiles (2010)
  • Author(s): Niida, S.Imoto, R.Yamaguchi, M.Nagasaki, A.Fujita, T.Shimamura, S.Miyano
  • Journal Title: Bioinformatics Pages: 3090-3097
• [Journal Article] Discovering functional gene pathways associated with cancer heterogeneity via sparse supervised learning (2010)
  • Author(s): S.Kawano, T.Shimamura, A.Niida, S.Imoto, R.Yamaguchi, M.Nagasaki, R.Yoshida, C.Print, S.Miyano
  • Journal Title: IEEE Bioinformatics and Biomedicine Pages: 253-258
• [Journal Article] Gene set-based module discovery in the breast cancer transcriptome (2009)
  • Author(s): A.Niida, A.D.Smith, S.Imoto, S.Tsutsumi, H.Aburatani, M.Q.Zhang, T.kiyama
  • Journal Title: BMC Bioinformatics 10 Pages: 71
• [Journal Article] Unraveling dynamic activities of autoacine pathways that control drug-response transcriptome networks (2009)
  • Author(s): Y.Tamada, H.raki, S.Imoto, M.Nagasaki, A.Doi, Y.Nakinishi, Y.Tomiyasu, K.Yasuda, B.Dunmore, D.Sanders, S.Humphries, C.Print, D.S.Charnock-Jones, K.Tashiro, S.Kuhara, S.Miyano
  • Journal Title: Pacific Symposium on Biocomputing 14 Pages: 251-263
• [Journal Article] A novel meta-analysis approach of cancer transcriptomes reveals prevailing transcriptional networks in cancer cells (2009)
  • Author(s): A.Niida, S.Imoto, M.Nagasaki, R.Yamaguchi, S.Miyano
  • Journal Title: Genome Informatics 22 Pages: 121-131
• [Journal Article] Bayesian learning of biological pathways on genomic data assimilation (2008)
  • Author(s): R.Yoshida, M.Nagasaki, R.Yamaguchi, S.Imoto, S.Miyano, T.Higuchi
  • Journal Title: Bioinformatics 24(22) Pages: 2592-2601
• [Presentation] Statistical Modeling of Dynamic Gene Networks in Cancer (2010)
  • Author(s): S.Imoto
  • Organizer: Winter School in Mathematical and Computational Biology (招待講演)
  • Place of Presentation: University of Queensland, Australia
  • Year and Date: 20100700
• [Presentation] Transcriptomic Network Comparison Unravels Key Differences in Gene Regulatory Networks Characterizing Cell Conditions (2010)
  • Author(s): S.Imoto
  • Organizer: Probability and Statistics with Applications in Systems Biology (招待講演)
  • Place of Presentation: Taiwan
  • Year and Date: 20100700
• [Presentation] Statistical inference of gene networks for computational drug-target pathway discovery (2009)
  • Author(s): S.Imoto
  • Organizer: Winter School in Mathematical and Computational Biology (招待講演)
  • Place of Presentation: University of Queensland, Australia
  • Year and Date: 20090700
• [Presentation] Computational Biomarker Identification by Analyzing Time-Course Microarray Gene Expression Data (2009)
  • Author(s): S.Imoto
  • Organizer: International Symposium of Case Studies involving Statistics and Operations Research for Decision Making : Solving Human Problems in Business, Society, and Scientific Areas, Institute of Mathematical Statistics (招待講演)
  • Place of Presentation: Japan
  • Year and Date: 20090300
• [Presentation] Unraveling dynamics of biological networks towards computational drug target discovery (2008)
  • Author(s): S.Imoto
  • Organizer: Statistical Computation and Visualization 2008 (招待講演)
  • Place of Presentation: Academia Sinica, Taiwan
  • Year and Date: 20081200
• [Book] Computational Drug Target Pathway Discovery : A Bayesian Network Approach. (Handbook of Computational Statistics : Statistical Bioinformatics)(in H.Lu, B.Schokop, H.Zhao (Eds.)) (2010)
  • Author(s): S.Imoto, Y.Tamada, H.Araki, S.Miyano
  • Publisher: Springer-Varlag. in press.
• [Remarks] ホームページ等