To search, Click below search items. |
| All Published Papers Search Service |
|
|
|
Title |
Statistically Weighted Voting Analysis of Microarrays for Molecular Pattern Selection and Discovery Cancer Genotypes |
|
Author |
Vladimir A. Kuznetsov, Oleg V. Senko, Lance D. Miller, Anna V. Ivshina |
| Citation |
Vol. 6 No. 12 pp. 73-83 |
|
Abstract |
We developed a methodological approach to genetic class discovery using gene expression microarray data, which is based a on statistically-oriented class-prediction method called Statistically Weighted Voting (SWV) analysis integrating with clinical risk factor and survival analyses, and statistics of Gene Ontology annotation terms which we use to validate candidate biomarker selection. Our approach provides a ""voting"" class prediction function constructed using the most informative and robust discrete segments (sub-regions) of all covariate ranges and their gradated pairs, which thus allows to model the interactions of variables (genes). We show here that the SWV-based methodology can be adapted for microarray data and profitably used to biomarker selection and discovered two genetic classes associated with essentially improvement of classical histological grade II of human breast cancer. Our findings show that small and reliable genetic grade signatures could improve an individual prognosis for patients with histologic grated II and, thus after further biomedical validation, be used in therapeutic planning for breast cancer patients. |
|
Keywords |
Voting Algorithms, Biomarker Selection, Prediction, Microarray, Histologic Grades, Cancer Classification. |
|
URL |
