Related Experiment Video
Updated: May 10, 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 breast cancer genes with a network based noise-tolerant approach
1National Key Laboratory of Biochemical Engineering, Institute of Process Engineering, Chinese Academy of Sciences, Beijing 100190, China.
BMC Systems Biology
|June 27, 2013
Summary
A new noise-tolerant method effectively identifies breast cancer genes from noisy data, outperforming traditional approaches. This computational method offers a robust way to discover new cancer genes, crucial for advancing breast cancer research.
Area of Science:
- Bioinformatics
- Computational Biology
- Genomics
Background:
- Identifying novel breast cancer genes is critical for research.
- Current methods integrate multiple data sources but struggle with data noise.
- Robust methods are needed for effective data integration in cancer gene discovery.
Purpose of the Study:
- To develop a novel, noise-tolerant computational method for mining breast cancer genes.
- To evaluate the performance and robustness of the proposed method against noise in source data.
- To quantitatively compare the proposed method with established approaches like random walk.
Main Methods:
- Utilized a comprehensive human Protein-Protein Interaction (PPI) network.
- Employed a set of genes with breast cancer-enriched Gene Ontology (GO) annotations as noisy source data.
- Developed a novel noise-tolerant algorithm for ranking candidate breast cancer genes.
- Compared the proposed method with the random walk approach using quantitative evaluations.
Main Results:
- The proposed noise-tolerant method demonstrated superior performance in ranking known breast cancer genes compared to the random walk approach.
- The method exhibited significantly higher robustness against data noise.
- Performance remained relatively stable as noise increased, unlike the random walk method which showed drastic decline.
Conclusions:
- A novel noise-tolerant method for breast cancer gene mining was successfully developed and validated.
- The method outperforms the random walk approach in accuracy and noise robustness.
- This study provides the first quantitative analysis of noise tolerance in breast cancer gene mining methods and offers valuable insights for future data integration efforts.