Home About Login Current Archives Announcements Editorial Board
Submit Now For Authors Call for Submissions Statistics Contact
Home > Archives > Volume 20, No 7 (2022) > Article

DOI: 10.14704/nq.2022.20.7.NQ33081

Applying and an Assessment for Machine Learning Techniques for Classifying Cancer Via TP53 Gene Mutations

Dina Yousif Mikhail, Dr. Firas Husham Almukhtar, Ali Hussein Yousif, Dr. Shahab Wahab Kareem


Prognosis of mutations plays a vital role in the detection and effective prevention of cancers. Due to mutations in the TP53 gene Database, the tumor suppressor P53 is responsible for a substantial number of human malignancies. It is so hard the ability to accurately predict and diagnose cancer from elementary data (in excel file), therefor this research proposes a functional model of Machin learning and an Artificial Neural Network for classifying cancer caused by a codon mutation in the tumor protein P53. The bagging classifier and K-nearest neighbor’s classifier mechanisms have been used for learning and testing the Neural Network to obtain the best accuracy of the proposed architecture. By picking (12) of the (53) TP53 gene database fields, machine learning algorithms are used to build two classification models for the bagging and K-nearest neighbor’s classifier . To be clear, it is discovered that one of these 12 fields (gene location field) is missing from the UMD TP53 Mutation Database2010; as a result, it is added to the TP53 gene database for training and testing the neural network algorithms, as a way to classify cancer types. The proposed architecture's learning and testing results demonstrate that the bagging classifier algorithm outperforms K nearest neighbors in terms of accuracy and error rates


Artificial Neural Network, Mutation, TP53 gene, Bagging Classifier, K nearest neighbors

Full Text