Paper Info
Title
Predictive Meta-Analysis Of Multiple Microarray Datasets: An Application To Classification Of Malignant Gliomas
Abstract
In this study, we conducted a predictive meta-analysis of multiple microarrays to identify a gene signature that can be potentially used to distinguish different grades of malignant gliomas (i.e., Grade III and IV). We showed our developed classification rule achieved an average accuracy and a J index of 75% and 52.6%, respectively, as measured by a dataset cross-validation strategy. Furthermore, we showed that clustering samples on the basis of similarity of expression profiles of the gene signature divides the data across available studies mainly into the two phenotypic groups regardless of the actual study. From the standpoint of data analytics, the results of this study confirm the utility of meta-analysis in integrating raw data from multiple studies into a predictive framework. From a biological perspective, the identified gene signature can be potentially used to shed light on the molecular mechanisms underlying the formation of malignant gliomas.
Year
DOI
Venue
2018
10.1109/BIBM.2018.8621503
PROCEEDINGS 2018 IEEE INTERNATIONAL CONFERENCE ON BIOINFORMATICS AND BIOMEDICINE (BIBM)
Keywords
Field
DocType
Prediction Analysis of Microarrays, Elastic Net, Predictive Meta-analysis, Malignant Gliomas
Classification rule,Microarray,Data analysis,Computer science,Elastic net regularization,Artificial intelligence,Computational biology,Cluster analysis,Gene signature,Meta-analysis,DNA microarray,Machine learning
Conference
ISSN
Citations 
PageRank 
2156-1125
0
0.34
References 
Authors
0
4
Name
Order
Citations
PageRank
Nurislam Tursynbek110.71
Ghazal Ghahramany200.34
Sheida Nabavi3188.68
Amin Zollanvari412519.21