ML Approach for Breast Cancer Detection using DNA Sequence Recognition
P. Sabitha1, Kartik Gupta2, Tejas Sharma3, Ravi Kumar Singh4, Jugnu Kumar5

1Kartik Gupta, Department of CSE, SRM University, Chennai (Tamil Nadu), India.
2Tejas Sharma, Department of CSE, SRM University, Chennai (Tamil Nadu), India.
3Ravi Kumar Singh, Department of CSE, SRM University, Chennai (Tamil Nadu), India.
4Jugnu Kumar, Department of CSE, SRM University, Chennai (Tamil Nadu), India.
5Mrs P. Sabitha, Department of CSE,AP,ME, SRM University, Chennai (Tamil Nadu), India.

Manuscript received on 18 June 2019 | Revised Manuscript received on 25 June 2019 | Manuscript published on 30 June 2019 | PP: 285-290 | Volume-8 Issue-5, June 2019 | Retrieval Number: E6897068519/19©BEIESP
Open Access | Ethics and 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 (

Abstract: Current approaches for DNA pattern recognition rely on traditional methods and algorithms of machine learning. Machine learning is a process that makes a computer or a program learn from experience. When this DNA sequence gets recognized, it can be utilized to scrutinize numerous applications in the field of bioinformatics and biomedical informatics. In this paper, we solve the problem of pattern recognition by the use of probability method and metric, then we put forward the concept of neural networks in place of some sequence alignment algorithms which intensifies the performance on time complexity. The use of neural networks will assist to recognize the sequences without any ambiguities. This result will serve as a utility for detecting breast cancer in the DNA by matching number of DNA’s (sequences) which possess cancer and DNA’s with no cancer cells, to diagnose whether cancer cells possess the human body or not. This method of prior detection of the disease using DNA overcomes the problem of complex techniques for diagnosis. This matching will involve another machine learning algorithm which will comprise of logistic regression, random forests. This method to recognize and match the DNA sequence to put forward as a application to detect cancer is just a sample model which has a lower accuracy rate, and does not solely depend on computer technologies. Medical research in deep levels is necessary to implement in daily life.
Keywords: Bioinformatics; Dnasequencing, Classification, Machine Learning ; Neural Networks; Probability Method And Metric, Logistic Regression, DNA Matching; Cancer Detection Index Terms: About Four Key Words Or Phrases In Alphabetical Order, Separated By Commas.

Scope of the Article: Classification