BioDog, Biomarker Detection for Improving Identification Power of Breast Cancer Histologic Grade in Methylomics

Abstract

Aim: Breast cancer histologic grade (HG) is a well-established prognostic factor. This study aimed to select methylomic biomarkers to predict breast cancer HGs. Materials & methods: The proposed algorithm BioDog firstly used correlation bias reduction strategy to eliminate redundant features. Then incremental feature selection was applied to find the features with a high HG prediction accuracy. The sequential backward feature elimination strategy was employed to further refine the biomarkers. A comparison with existing algorithms were conducted. The HG-specific somatic mutations were investigated. Results & conclusions: BioDog achieved accuracy 0.9973 using 92 methylomic biomarkers for predicting breast cancer HGs. Many of these biomarkers were within the genes and lncRNAs associated with the HG development in breast cancer or other cancer types.

Keywords::

• biomarker detection
• breast cancer
• feature selection
• histologic grade
• methylome

Author contributors

F Zhou and Y Zhang conceived and designed this study. Y Zhang, C Chen and M Duan wrote the programs and carried out the experiments. Y Zhang, M Duan and S Liu drafted the manuscript. Y Zhang and L Huang analyzed the data. F Zhou and Y Zhang polished the manuscript and revised the manuscript according to the reviewers’ comments.

Acknowledgments

The results shown here are in whole or part based upon data generated by the TCGA Research Network: https://www.cancer.gov/tcga. The constructive comments of the anonymous reviewers were greatly appreciated.

Financial & competing interests disclosure

This work was supported by the Jilin Provincial Key Laboratory of Big Data Intelligent Computing (20180622002JC), the Education Department of Jilin Province (JJKH20180145KJ), and the startup grant of the Jilin University. This work was also partially supported by the Bioknow MedAI Institute (BMCPP-2018-001), the High Performance Computing Center of Jilin University and the Fundamental Research Funds for the Central Universities, JLU. The authors have no other relevant affiliations or financial involvement with any organization or entity with a financial interest in or financial conflict with the subject matter or materials discussed in the manuscript apart from those disclosed.

No writing assistance was utilized in the production of this manuscript.

Additional information

Funding

This work was supported by the Jilin Provincial Key Laboratory of Big Data Intelligent Computing (20180622002JC), the Education Department of Jilin Province (JJKH20180145KJ), and the startup grant of the Jilin University. This work was also partially supported by the Bioknow MedAI Institute (BMCPP-2018-001), the High Performance Computing Center of Jilin University and the Fundamental Research Funds for the Central Universities, JLU. The authors have no other relevant affiliations or financial involvement with any organization or entity with a financial interest in or financial conflict with the subject matter or materials discussed in the manuscript apart from those disclosed. No writing assistance was utilized in the production of this manuscript.