Target Gene Prediction from Microarray Data Using Data Mining Methods

Creative Commons License

Cavdar Z. Y., Ensari T., SERTBAŞ A., AKÇAMAN M. N.

Gazi University Journal of Science, cilt.39, sa.2, ss.1177-1196, 2026 (ESCI, Scopus, TRDizin)

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 39 Sayı: 2
  • Basım Tarihi: 2026
  • Doi Numarası: 10.35378/gujs.1710419
  • Dergi Adı: Gazi University Journal of Science
  • Derginin Tarandığı İndeksler: Emerging Sources Citation Index (ESCI), Scopus, TR DİZİN (ULAKBİM), Academic Search Ultimate (EBSCO), Biomedical Reference Collection: Corporate Edition (EBSCO), Engineering Source (EBSCO)
  • Sayfa Sayıları: ss.1177-1196
  • Anahtar Kelimeler: Data mining, Gene expression analyzing, Microarray analysing, Target gene prediction
  • Açık Arşiv Koleksiyonu: AVESİS Açık Erişim Koleksiyonu
  • Çanakkale Onsekiz Mart Üniversitesi Adresli: Evet

Özet

Many different techniques such as microarray, microrna, RNA sequencing and parallel sequencing are used in biomedical research. Among these biotechnological approaches, microarray is widely used for analysing data such as DNA, RNA or proteins. Microarray technology offers advantages in many areas such as analysing gene expression, mutation analysis, epigenetic studies or biomarker discovery. The use of artificial intelligence methods in the analysis of large amounts of data, such as microarray data, offers a gain in accuracy and speed. In this study, gene expression analysis of microarray data is performed using data mining methods. Freely available datasets are used for the study. The first one is the microarray dataset investigating the effects of chronic hypoxia treatment on the brain of mice. The second is a microarray dataset that examines the changes in mouse neurons exposed to oxidative stress. The method we developed for analysing microarray data is applied separately to both data sets and led to successful results. In this work, after the datasets are made suitable for processing in a computer environment, the prediction process is developed using data mining methods. The study is concluded with the listing of the most affected genes among the result genes.