Abstract
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.
Highlights
DNA N6-methyladenine (6mA) is non-canonical methylation on adenine by attaching a methyl group to the sixth location of the Adenine purine ring [1]
We propose a novel deep learning-based model to classify the DNA N6-methyladenine sites using convolutional neural networks (CNN)
THE PROPOSED MODEL We proposed an efficient deep learning model based on a convolution neural network that identifies the DNA 6mA modification of different species
Summary
DNA N6-methyladenine (6mA) is non-canonical methylation on adenine by attaching a methyl group to the sixth location of the Adenine purine ring [1]. The prediction methods such as iDNA6mA-PseKNC [16] and csDMA [17] are freely available for the identification of DNA 6mA modification in crossspecies, rice genome, and Mus musculus genome. They were based on machine learning algorithms. Deep learning-based bioinformatics predictors such as iDeepS [23], branch point selection [24], Deep Splicing Code [25], iRNA-PseKNC(2methyl) prediction model [26], and DeePromoter [27] have been proposed. A user-friendly web server was made freely accessible at https://home.jbnu.ac.kr/NSCL/iIMCNN.htm
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
