Reach Us +44 3308 085114
Data Integration for Cancer Clinical Outcome Prediction | OMICS International
ISSN: 2157-7420
Journal of Health & Medical Informatics

Like us on:

Make the best use of Scientific Research and information from our 700+ peer reviewed, Open Access Journals that operates with the help of 50,000+ Editorial Board Members and esteemed reviewers and 1000+ Scientific associations in Medical, Clinical, Pharmaceutical, Engineering, Technology and Management Fields.
Meet Inspiring Speakers and Experts at our 3000+ Global Conferenceseries Events with over 600+ Conferences, 1200+ Symposiums and 1200+ Workshops on Medical, Pharma, Engineering, Science, Technology and Business
All submissions of the EM system will be redirected to Online Manuscript Submission System. Authors are requested to submit articles directly to Online Manuscript Submission System of respective journal.

Data Integration for Cancer Clinical Outcome Prediction

Dokyoon Kim and Marylyn D Ritchie*
Center for Systems Genomics, Department of Biochemistry and Molecular Biology, Pennsylvania State University, University Park, Pennsylvania, USA
*Corresponding Author : Marylyn D Ritchie
Center for Systems Genomics
Department of Biochemistry and Molecular Biology
Pennsylvania State University
University Park, Pennsylvania, USA
Tel: +1 814 8634467
E-mail: [email protected]
Received January 16, 2014; Accepted January 18, 2014; Published January 24, 2014
Citation: Kim D, Ritchie MD (2014) Data Integration for Cancer Clinical Outcome Prediction. J Health Med Informat. 5:e122. doi:10.4172/2157-7420.1000e122
Copyright: © 2014 Kim D, et al. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

Visit for more related articles at Journal of Health & Medical Informatics

Cancer clinical outcome prediction based on the molecular information has received increasing interest for better diagnostics, prognostics, and further therapeutics. Accurate molecular-based predictors of outcome can be used clinically to choose the best of several available therapies for a cancer patient. In the past decade, gene expression profiles have been most widely used to predict clinical outcomes in several cancers [1,2]. There have been also many attempts at cancer clinical outcome prediction using a set of copy number alterations (CNA), miRNA, DNA methylation, and protein expression [3-6].
However, it is still difficult to accurately predict clinical outcome since the cancer genome is neither simple nor independent but rather complicated and dysregulated by multiple levels of the biological system through genome, epigenome, transcriptome, proteome, metabolome, interactome, etc. [7]. For instance, cancer is mainly caused by somatic driver mutations in coding and non-coding sequences or epigenetic changes of methylation, acetylation, and histone. Collectively, these genetic and epigenetic changes can lead to many alternative forms of cause-and-result effect in transcription, translation, and post-translational modification, which are all involved in cancer pathophysiology. Therefore, no single type of genomic data will be sufficient to elucidate the phenotypic end-point of events accumulated through multiple levels of biological systems involved in cancer, and hence, a consideration of incorporating the multi-layered processes in biological systems might provide much more reasonable prediction of cancer clinical outcome.
Recently, emerging multi-omics data and clinical information from cancer patients have been providing unprecedented opportunities to investigate the multi-layered processes involved in cancer development and progression for improving the ability to diagnose, treat, and prevent cancer. The Cancer Genome Atlas (TCGA) is a large-scale collaborative initiative to improve our understanding of multi-layered of molecular basis of cancer and has been generating multi-omics data for 25 cancer types [8]. In addition, the International Cancer Genome Consortium (ICGC) is another comprehensive collaborative initiative to obtain a multidisciplinary description of genomic, epigenomic, and transcriptomic changes in 50 different cancer types [9]. Before exploding multi-omics data in cancer from TCGA or ICGC, there have been many integrative studies for two types of genomic data such as association, regression, or correlation-based methods [10]. However, as multi-scale genomic data have become more available, it is hard to directly use existing integrative methods, which are mainly for two types of genomic data. Thus, the development of multi-scale integrative approaches is more required in order to integrate multiple types of genomic data at hand and investigate an enhanced global view on interplays between different types of genomic data.
In order to solve the current problems for data integration in cancer research, many multi-scale integrative approaches have been recently proposed. Kim et al. proposed a graph-based integration framework for predicting cancer clinical outcomes using CNA, methylation, miRNA, and gene expression data [11]. Sohn et al. [12] proposed an integrative statistical framework based on a sparse regression to model the impact of multi-layered genomic features including CNA, miRNA, and methylation on gene expression traits. Kim et al. [13] also investigated an integrative framework in order to identify interactions between different types of genomic data associated with clinical outcome. In addition, Mankoo et al. [14] predicted time to recurrence and survival in ovarian cancer using CNA, methylation, miRNA, and gene expression data using multivariate Cox Lass model.
While the TCGA and ICGC provide many opportunities to uncover the novel knowledge of the molecular basis of cancer, it is crucial to address the issue of development of an appropriate methodological framework for data integration to better understand different cancer phenotypes, further providing an enhanced global view on the interplays between different genomic features. With an abundance in of multi-omics data and clinical data from cancer patients, relevant integration frameworks will be valuable for explaining the molecular pathogenesis and underlying biology in cancer, eventually leading to more effective screening strategies and therapeutic targets in many types of cancer.
This work was funded by NIH grant 5R01 LM010040 and NHLBI grant 2U01 HL065962.
Select your language of interest to view the total content in your interested language
Post your comment

Share This Article

Article Usage

  • Total views: 12938
  • [From(publication date):
    March-2014 - Nov 21, 2019]
  • Breakdown by view type
  • HTML page views : 9093
  • PDF downloads : 3845