Tightly integrated genomic and epigenomic data mining using tensor decomposition

Bioinformatics
Jianwen Fang

Abstract

Complex diseases such as cancers often involve multiple types of genomic and/or epigenomic abnormalities. Rapid accumulation of multiple types of omics data demands methods for integrating the multidimensional data in order to elucidate complex relationships among different types of genomic and epigenomic abnormalities. In the present study, we propose a tightly integrated approach based on tensor decomposition. Multiple types of data, including mRNA, methylation, copy number variations and somatic mutations, are merged into a high-order tensor which is used to develop predictive models for overall survival. The weight tensors of the models are constrained using CANDECOMP/PARAFAC (CP) tensor decomposition and learned using support tensor machine regression (STR) and ridge tensor regression (RTR). The results demonstrate that the tensor decomposition based approaches can achieve better performance than the models based individual data type and the concatenation approach. Supplementary data are available at Bioinformatics online.

Citations

Mar 1, 2006·BMC Bioinformatics·Sudhir Varma, Richard Simon
Nov 16, 2007·Proceedings of the National Academy of Sciences of the United States of America·Larsson OmbergOrly Alter
Jul 1, 2009·BMJ : British Medical Journal·Jonathan A C SterneJames R Carpenter
Jan 22, 2010·PLoS Computational Biology·Oron VanunuRoded Sharan
Apr 16, 2010·Nature·Thomas J HudsonHuanming Yang
Sep 15, 2010·Nature Reviews. Genetics·Jeffrey T LeekRafael A Irizarry
Nov 3, 2010·Nucleic Acids Research·Ana Kozomara, Sam Griffiths-Jones
Aug 24, 2011·IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society·Weiwei GuoIoannis Patras
Sep 17, 2013·Nature Methods·Matan HofreeTrey Ideker
Jan 1, 2013·Journal of the American Statistical Association·Hua ZhouHongtu Zhu
Jan 15, 2015·Nature Reviews. Genetics·Marylyn D RitchieDokyoon Kim
Mar 15, 2016·Nature Reviews. Genetics·Andrew P FeinbergAnita Göndör
Dec 28, 2016·Biometrical Journal. Biometrische Zeitschrift·Nathaniel E Helwig
Jan 14, 2017·PloS One·Wong Jee Keen RaymondAb Halim Abu Bakar

Related Concepts

Study
DNA Copy Number Changes
Protein Methylation
Genome
Somatic Mutation
Genomic Stability
Neoplasms
DNA Methylation
Bio-Informatics
Abnormal Pregnancy

Related Feeds

Birth Defects

Birth defects encompass structural and functional alterations that occur during embryonic or fetal development and are present since birth. The cause may be genetic, environmental or unknown and can result in physical and/or mental impairment. Here is the latest research on birth defects.

Bioinformatics in Biomedicine

Bioinformatics in biomedicine incorporates computer science, biology, chemistry, medicine, mathematics and statistics. Discover the latest research on bioinformatics in biomedicine here.

Cancer Genomics (Keystone)

Cancer genomics approaches employ high-throughput technologies to identify the complete catalog of somatic alterations that characterize the genome, transcriptome and epigenome of cohorts of tumor samples. Discover the latest research using such technologies in this feed.

Cancer Genomics

Cancer genomics employ high-throughput technologies to identify the complete catalog of somatic alterations that characterize the genome, transcriptome and epigenome of cohorts of tumor samples. Discover the latest research here.

Related Papers

Omics : a Journal of Integrative Biology
Chenyu LiYan Xu
IEEE Transactions on Neural Networks and Learning Systems
Fujiao JuBaocai Yin
Nihon Jibiinkoka Gakkai kaiho
Keisuke OkuboHirohisa Ssito
© 2020 Meta ULC. All rights reserved