A Robust Gene Finding Classifier for Variable Length DNA Sequences
Keywords:
.Abstract
Deep Learning algorithm has two phases, learning or training phase and testing phase. In the training phase, the algorithm is trained with some available patterns. Subsequent to the training, the model performs the task of prediction in the testing phase. Based upon the nature of the training, there are two broad categories of Deep Learning. The first category of training is named as supervised learning, where the algorithm is trained with a set of examples. This algorithm analyzes the input data and produces an inferred function, which can predict the unseen or untrained instances. The second category is unsupervised learning, where the classes are surmised from the input patterns based on some likeness measure. The user can define the number of classes in the training phase. We have used a versatile algorithm with deep learning to find a gene in different length DNA sequences. This proposed algorithm is versatile and results prove the efficiency when compared with the existing methods.
References
2. Sree PK, Babu IR, Devi NU. A Novel Protein Coding Region Identifying Tool using Cellular Automata Classifier with Trust-Region Method and Parallel Scan Algorithm (NPCRITCACA). International Journal of Biotechnology and Biochemistry 2008; 4(2): 177-89.
3. Sree PK, Babu IR, Devi NU. HMACA: Towards proposing cellular automata based tool for protein coding, promoter region identification and protein structure prediction. International Journal of Research in Computer Applications and Information Technology 2013; 1(1): 26-31.
4. Sree PK, Babu IR, Devi NU. PRMACA: A promoter region identification using Multiple Attractor Cellular Automata (MACA) in the proceedings CT and critical infrastructure. Advances in Intelligent Systems and Computing 2014; 248: 393-9.
5. Sree PK, Babu IR, Devi NU. AIS-PSMACA: Towards proposing an artificial immune system for strengthening PSMACA: an automated protein structure prediction using multiple attractor cellular automata. Global Journal of Computer Science and Technology 2013; 13(4).
6. Sree PK, Babu IR, Devi NU. Multiple Attractor Cellular Automata (MACA) for addressing major problems in bioinformatics. Review of Bioinformatics and Biometrics. 2013; 2(3): 70-6.
7. Sree PK, Babu IR, Devi NU. Protein coding region identification. International Conference on Proteomics Bioinformatics, Embassy Suites Las Vegas, USA. Special Issue of Journal of Proteomics and Bioinformatics 2012; 5(6): 123.
8. Sree PK, Babu IR, Devi NU. Hybrid attractor cellular automata for addressing major problems in bioinformatics in research and reviews. Journal of Engineering and Technology 2013; 2(4): 42-8.
9. Sree PK, Babu IR, Devi NU. AIS-PRMACA: artificial immune system based multiple attractor cellular automata for strengthening PRMACA, Promoter Region Identification. The Standard International Journals 2013; 1(4): 124-7.
10. Sree PK, Babu IR, Devi NU. A novel AIS-MACAX classifier in bioinformatics. World Congress on Biotechnology, Valencia Conference Centre, Valencia, Spain. 2014.
