A Review on Computational Analysis of Big Data in Breast Cancer for Predicting Potential Biomarkers

Breast cancer is the most predominantly occurring cancer in the world. Several genes and proteins have been recently studied to predict biomarkers that enable early disease identification and monitor its recurrence. In the era of high-throughput technology, studies show several applications of big data for identifying potential biomarkers. The review aims to provide a comprehensive overview of big data analysis in breast cancer towards the prediction of biomarkers with emphasis on computational methods like text mining, network analysis, next-generation sequencing technology (NGS), machine learning (ML), deep learning (DL), and precision medicine. Integrating data from various computational approaches enables the stratification of cancer patients and the identification of molecular signatures in cancer and their subtypes. The computational methods and statistical analysis help expedite cancer prognosis and develop precision cancer medicine (PCM). As a part of case study in the present work, we constructed a large gene-drug interaction network to predict new biomarkers genes. The gene-drug network helped us to identify eight genes that could serve as novel potential biomarkers.