Related Experiment Video
Updated: Jun 3, 2026
07:41
Performing Data Mining And Integrative Analysis Of Biomarker in Breast Cancer Using Multiple Publicly Accessible Databases
Published on: May 17, 2019
Mining microarray data to predict the histological grade of a breast cancer.
Mickael Fabregue1, Sandra Bringay2, Pascal Poncelet1
1LIRMM UM2 CNRS, UMR 5506 - CC 477, 161 rue Ada, 34095 Montpellier Cedex 5, France.
Journal of Biomedical Informatics
|March 15, 2011
Summary
This study introduces a new method using sequential patterns for molecular biomarker discovery in breast cancer classification. The approach shows promise for prognostic and predictive tools, particularly for distinct tumor grades.
Area of Science:
- Bioinformatics
- Genomics
- Cancer Research
Background:
- Developing novel methods for identifying molecular biomarkers is crucial for cancer prognostics.
- Gene sequences hold potential as predictive tools for disease classification.
Purpose of the Study:
- To develop an original method for extracting relevant molecular biomarkers (gene sequences).
- To enable class prediction and establish prognostic and predictive tools.
Main Methods:
- Utilized sequential patterns as features for machine learning-based class prediction.
- Applied the developed method to classify breast cancer tumors based on histological grade.
Main Results:
- Achieved high accuracy (recall and precision) in classifying breast cancer grades 1 and 3.
- Encountered challenges in achieving satisfactory results for grade 2 tumors, consistent with existing literature.
Conclusions:
- Sequential patterns are effective for class prediction in microarray data.
- The developed method provides a foundation for future prognostic and predictive applications in cancer research.
