Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:

---

Today, machine-learning approaches are widely used in the analysis of massive data. Due to new technology and the production of high-throughput data in biology (such as next-generation sequencing data), the use of machine learning methods on large biological data can help to understand the mechanism of complex diseases such as cancer. Extraction of candida genes as a therapeutic target or biomarkers from high-throughput biological data such as gene expression data considered as the first step in cancer treatment. Therefore, developing an efficient approach to analyzing such data plays a key role in bioinformatics and computational biology. In this paper, we try to identify lung cancer-related genes as potential biomarkers by applying the WCC algorithm and SVM to lung cancer gene expression data. The data from RNA-Seq technology used for lung cancer samples as well as healthy tissue samples obtained from the TCGA database. These data include the expression of mRNA genes in cancerous and healthy tissue samples. The results of the study led to important findings such as CASZ1 and ASNS, which according to previously published articles have an important role in the formation of cancer and their role in the formation of lung cancer can be examined in future studies. In addition, the validation results of the proposed method show the power of machine learning-based methods in analyzing gene expression data.

Keywords: Lung Cancer, WCC Algorithm, Support Vector Machine, Biomarker, Machine Learning, Gene Expression Data

Full-Text [PDF 417 kb]   (373 Downloads)    

Add your comments about this article : Your username or Email:

---

---