44
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      Integrating multi-platform genomic data using hierarchical Bayesian relevance vector machines

      research-article

      Read this article at

      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          Background

          Recent advances in genome technologies and the subsequent collection of genomic information at various molecular resolutions hold promise to accelerate the discovery of new therapeutic targets. A critical step in achieving these goals is to develop efficient clinical prediction models that integrate these diverse sources of high-throughput data. This step is challenging due to the presence of high-dimensionality and complex interactions in the data. For predicting relevant clinical outcomes, we propose a flexible statistical machine learning approach that acknowledges and models the interaction between platform-specific measurements through nonlinear kernel machines and borrows information within and between platforms through a hierarchical Bayesian framework. Our model has parameters with direct interpretations in terms of the effects of platforms and data interactions within and across platforms. The parameter estimation algorithm in our model uses a computationally efficient variational Bayes approach that scales well to large high-throughput datasets.

          Results

          We apply our methods of integrating gene/mRNA expression and microRNA profiles for predicting patient survival times to The Cancer Genome Atlas (TCGA) based glioblastoma multiforme (GBM) dataset. In terms of prediction accuracy, we show that our non-linear and interaction-based integrative methods perform better than linear alternatives and non-integrative methods that do not account for interactions between the platforms. We also find several prognostic mRNAs and microRNAs that are related to tumor invasion and are known to drive tumor metastasis and severe inflammatory response in GBM. In addition, our analysis reveals several interesting mRNA and microRNA interactions that have known implications in the etiology of GBM.

          Conclusions

          Our approach gains its flexibility and power by modeling the non-linear interaction structures between and within the platforms. Our framework is a useful tool for biomedical researchers, since clinical prediction using multi-platform genomic information is an important step towards personalized treatment of many cancers. We have a freely available software at: http://odin.mdacc.tmc.edu/~vbaladan.

          Related collections

          Most cited references14

          • Record: found
          • Abstract: found
          • Article: not found

          MicroRNA-21 targets a network of key tumor-suppressive pathways in glioblastoma cells.

          MicroRNA dysregulation is observed in different types of cancer. MiR-21 up-regulation has been reported for the majority of cancers profiled to date; however, knowledge is limited on the mechanism of action of miR-21, including identification of functionally important targets that contribute to its proproliferative and antiapoptotic actions. In this study, we show for the first time that miR-21 targets multiple important components of the p53, transforming growth factor-beta (TGF-beta), and mitochondrial apoptosis tumor-suppressive pathways. Down-regulation of miR-21 in glioblastoma cells leads to derepression of these pathways, causing repression of growth, increased apoptosis, and cell cycle arrest. These phenotypes are dependent on two of the miR-21 targets validated in this study, HNRPK and TAp63. These findings establish miR-21 as an important oncogene that targets a network of p53, TGF-beta, and mitochondrial apoptosis tumor suppressor genes in glioblastoma cells.
            Bookmark
            • Record: found
            • Abstract: found
            • Article: not found

            High-mobility group box 1 and cancer.

            High-mobility group box 1 protein (HMGB1), a chromatin associated nuclear protein and extracellular damage associated molecular pattern molecule (DAMP), is an evolutionarily ancient and critical regulator of cell death and survival. Overexpression of HMGB1 is associated with each of the hallmarks of cancer including unlimited replicative potential, ability to develop blood vessels (angiogenesis), evasion of programmed cell death (apoptosis), self-sufficiency in growth signals, insensitivity to inhibitors of growth, inflammation, tissue invasion and metastasis. Our studies and those of our colleagues suggest that HMGB1 is central to cancer (abnormal wound healing) and many of the findings in normal wound healing as well. Here, we focus on the role of HMGB1 in cancer, the mechanisms by which it contributes to carcinogenesis, and therapeutic strategies based on targeting HMGB1. Copyright 2009 Elsevier B.V. All rights reserved.
              Bookmark
              • Record: found
              • Abstract: found
              • Article: not found

              A framework for feature selection in clustering.

              We consider the problem of clustering observations using a potentially large set of features. One might expect that the true underlying clusters present in the data differ only with respect to a small fraction of the features, and will be missed if one clusters the observations using the full set of features. We propose a novel framework for sparse clustering, in which one clusters the observations using an adaptively chosen subset of the features. The method uses a lasso-type penalty to select the features. We use this framework to develop simple methods for sparse K-means and sparse hierarchical clustering. A single criterion governs both the selection of the features and the resulting clusters. These approaches are demonstrated on simulated data and on genomic data sets.
                Bookmark

                Author and article information

                Contributors
                Journal
                EURASIP J Bioinform Syst Biol
                EURASIP J Bioinform Syst Biol
                EURASIP Journal on Bioinformatics and Systems Biology
                BioMed Central
                1687-4145
                1687-4153
                2013
                28 June 2013
                : 2013
                : 1
                : 9
                Affiliations
                [1 ]Department of Statistics, Purdue University, 250 N. University Street, West Lafayette, IN 47907, USA
                [2 ]Department of Bioinformatics and Computational Biology, Division of Quantitative Sciences, The University of Texas MD Anderson Cancer Center, 1515 Holcombe Blvd, Unit 1411, Houston, Texas, USA
                [3 ]Department of Computer Science, University of Houston, 4800 Calhoun, Houston, Texas, USA
                [4 ]Department of Biostatistics, Division of Quantitative Sciences, The University of Texas MD Anderson Cancer Center, 1515 Holcombe Blvd, Unit 1411, Houston, Texas, USA
                Article
                1687-4153-2013-9
                10.1186/1687-4153-2013-9
                3726335
                23809014
                80cb80f6-ea63-49f2-85c9-3518b485344f
                Copyright © 2013 Srivastava et al.; licensee Springer.

                This is an Open Access article distributed under the terms of the Creative Commons Attribution License ( http://creativecommons.org/licenses/by/2.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

                History
                : 7 March 2013
                : 10 June 2013
                Categories
                Research

                Bioinformatics & Computational biology
                bayesian modeling; multiple kernel learning; genomics; high-dimensional data analysis; prediction; variational inference

                Comments

                Comment on this article