Journal
IEEE ACCESS
Volume 7, Issue -, Pages 178577-178583Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/ACCESS.2019.2958618
Keywords
DNA N6-methyladenine; sequence analysis; cross-species; deep learning; convolution neural network
Categories
Funding
- Brain Research Program of the National Research Foundation (NRF) - Korean Government (MSIT) [NRF-2017M3C7A1044815]
Ask authors/readers for more resources
DNA N6-methyladenine (6mA) is related to a vast range of biological progress like transcription, replication, and repair of DNA. The precise discrimination of the 6mA sites plays a vital role in the understanding of its biological functions. Even though biochemical experiments produced positive results, they were inefficient in terms of cost and time. Therefore, to facilitate the identification of 6mA sites it is important to develop a robust computational model. In this regard, we develop a deep learning-based computational model named as iIM-CNN for the identification of N6-methyladenine sites from DNA sequences. The iIM-CNN is capable of extracting important features using a convolution neural network (CNN). The proposed model achieves the Mathew correlation coefficient (MCC) of 0.651, 0.752 and 0.941 for cross-species, Rice, and M. musculus genome respectively. The comparison of the outcomes depicts that the proposed model outperforms the existing computational tools for the prediction of the 6mA sites. Finally, a publically available user-friendly web server is available at https://home.jbnu.ac.kr/NSCL/iIMCNN.htm
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available