Deep Learning Mechanism Augmented with 16-Hybrid Cellular Automata For Secondary Structure Prediction
Pokkuluri Kiran Sree

Dr P.Kiran Sreee, Professor, Dept of CSE, Shri Vishnu Engineering College for Women, Bhimavaram.

Manuscript received on November 13, 2019. | Revised Manuscript received on 22 November, 2019. | Manuscript published on December 10, 2019. | PP: 490-493 | Volume-9 Issue-2, December 2019. | Retrieval Number: B6458129219/2019©BEIESP | DOI: 10.35940/ijitee.B6458.129219
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: A protein plays various role in our human body like cellular development, reproduction, endurance and regulation of human body. Based on the structure of the genes we can extract lots of information regarding the human body. It is very easy to extract lots of information from a structure than a sequence. Identifying the protein structure helps in drug design. The secondary structure, to some extent tells about the effect of amino acid changes and explains the reason for the disease of an individual. A doctor can suggest medicines without any side effects to a patient based on the protein structure acquired from DNA. We have developed a classifier DL-16-MACA which can predict the secondary structure of an amino acid sequence of different lengths. In this prediction we have considered three classes Helix (H), Strands (E), Coiled(C). For Helix class the sensitivity, percentage accuracy is 0.923 and 90.6% respectively. For Strands class the sensitivity, percentage accuracy is 0.852 and 85.55%respectively. For Coiled class the sensitivity, percentage accuracy is 0.789 and 77.1% respectively. The percentage accuracy when tested with PDB datasets is 85.4% which substantially comparable with existing literature. 
Keywords: Cellular Automata, Deep Learning, Secondary Structure.
Scope of the Article: Deep Learning