Incorporating network structure in integrative analysis of cancer prognosis data.
نویسندگان
چکیده
In high-throughput cancer genomic studies, markers identified from the analysis of single datasets may have unsatisfactory properties because of low sample sizes. Integrative analysis pools and analyzes raw data from multiple studies, and can effectively increase sample size and lead to improved marker identification results. In this study, we consider the integrative analysis of multiple high-throughput cancer prognosis studies. In the existing integrative analysis studies, the interplay among genes, which can be described using the network structure, has not been effectively accounted for. In network analysis, tightly connected nodes (genes) are more likely to have related biological functions and similar regression coefficients. The goal of this study is to develop an analysis approach that can incorporate the gene network structure in integrative analysis. To this end, we adopt an AFT (accelerated failure time) model to describe survival. A weighted least squares approach, which has low computational cost, is adopted for estimation. For marker selection, we propose a new penalization approach. The proposed penalty is composed of two parts. The first part is a group MCP penalty, and conducts gene selection. The second part is a Laplacian penalty, and smoothes the differences of coefficients for tightly connected genes. A group coordinate descent approach is developed to compute the proposed estimate. Simulation study shows satisfactory performance of the proposed approach when there exist moderate-to-strong correlations among genes. We analyze three lung cancer prognosis datasets, and demonstrate that incorporating the network structure can lead to the identification of important genes and improved prediction performance.
منابع مشابه
Patterns Prediction of Chemotherapy Sensitivity in Cancer Cell lines Using FTIR Spectrum, Neural Network and Principal Components Analysis
Drug resistance enables cancer cells to break away from cytotoxic effect of anticancer drugs. Identification of resistant phenotype is very important because it can lead to effective treatment plan. There is an interest in developing classifying models of resistance phenotype based on the multivariate data. We have investigated a vibrational spectroscopic approach in order to characterize a...
متن کاملComparison of the Childhood Trauma, Mindfulness Attention Awareness and Integrative Self Knowledge in Cancer Patients and General Population
Background: This study organized in purpose of comparing childhood trauma, integrative self knowledge and mindfulness attention awareness ic patients with cancer and typical cases. Methods: This descriptive analytical study was conducted on 139 patients with cancer and 139 typical cases referred to Firoozgar hospital and Samar NGO who were selected by convenience samoling method. Contributers...
متن کاملAn evidence based care package to improve motor skills of infants living in foster care according to integrative review approach
Background: Infancy is the most important extra uterine period of brain development. And it requires environmental stimulation for expression of the developmental capabilities. Meanwhile, due to repeated environmental disparities foster care children are at risk for developmental delay. Aim: designing evidence based care package to improve motor skills of orphan living infants according to inte...
متن کاملPatterns Prediction of Chemotherapy Sensitivity in Cancer Cell lines Using FTIR Spectrum, Neural Network and Principal Components Analysis
Drug resistance enables cancer cells to break away from cytotoxic effect of anticancer drugs. Identification of resistant phenotype is very important because it can lead to effective treatment plan. There is an interest in developing classifying models of resistance phenotype based on the multivariate data. We have investigated a vibrational spectroscopic approach in order to characterize a...
متن کاملIdentification of specific gene expression after exposure to low dose ionizing radiation revealed through integrative analysis of cDNA microarray data and the interactome
Background: Accumulating reports suggest that the biological effects of low- and high- dose ionizing radiation (LDIR and HDIR) are qualitatively different and might cause different effects in human skin. Materials and Methods: To better understand the potential risks of LDIR, we analyzed three cDNA microarray datasets from the Gene Expression Omnibus database. Results: A pathway analysis showed...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- Genetic epidemiology
دوره 37 2 شماره
صفحات -
تاریخ انتشار 2013