Related Experiment Video
Updated: Apr 16, 2026
09:40
Characterization of Functionally Associated miRNAs in Glioblastoma and their Engineering into Artificial Clusters for Gene Therapy
Published on: October 4, 2019
6.1K
Classification and Clustering on Microarray Data for Gene Functional Prediction Using R
Liliana López-Kleine, Liliana López Kleine1, Rosa Montaño2
1Departamento de Estadística, Universidad Nacional de Colombia, Edificio 404, Oficina 342, Carreara 45 No 26-28, Bogotá, DC, Colombia. llopezk@unal.edu.co.
Methods in Molecular Biology (Clifton, N.J.)
|March 13, 2015
Summary
Unlock insights from genomic data using multivariate clustering and classification. These powerful, accessible methods predict gene product functions, enhancing biological study outcomes.
Area of Science:
- Genomics
- Bioinformatics
- Computational Biology
Background:
- Publicly available genomic datasets, including gene expression data (microarrays, RNA-sequencing), offer vast potential for biological discovery.
- Multivariate statistical methods are increasingly vital for analyzing complex genomic information.
Purpose of the Study:
- To demonstrate the application of multivariate cluster and classification methods on gene expression data.
- To highlight the utility of these methods for predicting gene product functions within specific biological categories.
Main Methods:
- Utilizing freely available software for implementing multivariate cluster and classification analyses.
- Focusing on nonlinear kernel classification methods for enhanced predictive power.
Main Results:
- Gene expression data analysis using these methods can accurately predict the functional roles of gene products.
- The application of these techniques leads to a deeper understanding of studied organisms and functional categories.
Conclusions:
- Every biological study should leverage available genomic data and multivariate methods for knowledge discovery.
- Nonlinear kernel classification offers a powerful approach for functional genomics research.
