A comparative study of different classification algorithms on RNA-Seq cancer data


Şimşek N. Y. , Haznedar B. , Kuzudişli C.

New Trends and Issues Proceedings on Advances in Pure and Applied Sciences, cilt.12, ss.24-35, 2020 (Düzenli olarak gerçekleştirilen hakemli kongrenin bildiri kitabı)

  • Cilt numarası: 12
  • Basım Tarihi: 2020
  • Doi Numarası: 10.18844/gjpaas.v0i12.4983
  • Dergi Adı: New Trends and Issues Proceedings on Advances in Pure and Applied Sciences
  • Sayfa Sayıları: ss.24-35

Özet

Gene mutations are the most important reason of cancer diseases, and there are different kind of causing genes across these diseases. RNA-Seq technology enables us to allow for gathering information about many genes simultaneously; hence, RNA-Seq data can be used for cancer diagnosis and classification. In this study, RNA-Seq dataset for renal cell cancer is analysed using three different developed classification methods: random forest (RF), artificial neural network (ANN) and deep learning (DL). The genes in our dataset are related to the following cancer types: kidney renal papillary cell, kidney renal clear cell and kidney chromophore carcinomas. It suggests that the DL method gives the highest accuracy rate compared to RF and ANN for 95.15%, 91.83% and 89.22%, respectively. We believe that the results acquired in this study will make a contribution to the classification of cancer types and support doctors in their processes of decision making.