Effective Data Mining Technique for Classification Cancers via Mutations in Gene using Neural Network

TL;DR

This paper presents a neural network-based data mining technique that improves the classification and diagnosis of cancers caused by TP53 gene mutations using large datasets and bioinformatics tools.

Contribution

It introduces a novel neural network approach combined with bioinformatics techniques for accurate cancer classification from big gene mutation datasets.

Findings

High accuracy in classifying cancer types

Effective mutation prediction using neural networks

Integration of bioinformatics tools enhances diagnosis

Abstract

The prediction plays the important role in detecting efficient protection and therapy of cancer. The prediction of mutations in gene needs a diagnostic and classification, which is based on the whole database (big dataset), to reach sufficient accuracy results. Since the tumor suppressor P53 is approximately about fifty percentage of all human tumors because mutations that occur in the TP53 gene into the cells. So, this paper is applied on tumor p53, where the problem is there are several primitive databases (excel database) contain datasets of TP53 gene with its tumor protein p53, these databases are rich datasets that cover all mutations and cause diseases (cancers). But these Data Bases cannot reach to predict and diagnosis cancers, i.e. the big datasets have not efficient Data Mining method, which can predict, diagnosis the mutation, and classify the cancer of patient. The goal of this paper to reach a Data Mining technique, that employs neural network, which bases on the big datasets. Also, offers friendly predictions, flexible, and effective classified cancers, in order to overcome the previous techniques drawbacks. This proposed technique is done by using two approaches, first, bioinformatics techniques by using BLAST, CLUSTALW, etc, in order to know if there are malignant mutations or not. The second, data mining by using neural network; it is selected (12) out of (53) TP53 gene database fields. To clarify, one of these 12 fields (gene location field) did not exists in TP53 gene database; therefore, it is added to the database of TP53 gene in training and testing back propagation algorithm, in order to classify specifically the types of cancers. Feed Forward Back Propagation supports this Data Mining method with data training rate (1) and Mean Square Error (MSE) (0.00000000000001). This effective technique allows in a quick, accurate and easy way to classify the type of cancer.