Improved Classification of Somatic Mutations Using AdaBoost With Feture Se-lection
Anuradha Chokka1, K Sandhya Rani2
1A Anuradha Chokka, Research Scholar, Department of Computer Science, Sri Padmavathi Mahila Visvavidyalayam, Tirupati (A.P), India
2Dr. K Sandhya Rani, Professor, Department of Computer Science, Sri Padmavathi Mahila Visvavidyalayam, Tirupati (A.P), India
Manuscript received on 22 April 2019 | Revised Manuscript received on 01 May 2019 | Manuscript Published on 05 May 2019 | PP: 382-386 | Volume-8 Issue-2S2, May 2019 | Retrieval Number: B10800182S219/19©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: The normal cells in human are transformed to cancer cells due to sequence of abnormal genetic events and cancer can be considered genetic changes of somatic mutations. To find the somatic mutations in accurate manner is the major challenge in cancer research. The main difficulty in cancer prediction analysis lies on tumor samples with the contamination and normal data samples. Identifying somatic mutations in cancer genes is a complex process. Feature extraction techniques retrieve significant features from the data and the classifiers which are developed based on these features improve the performance of the classifier. In this paper, to maximize the precision AdaBoost technique with feature selection is applied to detect the gene changes among the normal and tumor cells which are the causes of somatic mutations. The experimental results proved that AdaBoost with the feature selection method improves the performance of classifier in terms of precision, accuracy, and recall.
Keywords: Cancer Prediction, Somatic Mutations, AdaBoost T Echnique, Feature Selection.
Scope of the Article: Classification