Abstract
One of the most common and well studied post-transcription modifications in RNAs is N6-methyladenosine (m6A) which has been involved with a wide range of biological processes. Over the past decades, N6-methyladenosine produced some positive consequences through the high-throughput laboratory techniques but still, these lab processes are time consuming and costly. Diverse computational methods have been proposed to identify m6A sites accurately. In this paper, we proposed a computational model named iMethyl-deep to identify m6A Saccharomyces Cerevisiae on two benchmark datasets M6A2614 and M6A6540 by using single nucleotide resolution to convert RNA sequence into a high quality feature representation. The iMethyl-deep obtained 89.19% and 87.44% of accuracy on M6A2614 and M6A6540 respectively which show that our proposed method outperforms the state-of-the-art predictors, at least 8.44%, 8.96%, 8.69% and 0.173 on M6A2614 and 15.47%, 28.52%, 25.54 and 0.5 on M6A6540 higher in terms of four metrics Sp, Sn, ACC and MCC respectively. Meanwhile, M6A6540 dataset never used to train a model.
Highlights
Many possibilities of methylation as an additional post-transcriptional modification of RNA have been found in sequence RNAs mRNA [1]
The second dataset is called as M6A6540 dataset which was introduced by Xiaolei Zhu et al.’s [20] contains 3270 positive RNA sequences regarded as methylated sites and 3270 negative RNA sequences regarded as non-methylated sites, all steps for preparing the dataset was mentioned in their work
We presented a model based on a convolution neural network (CNN) instead of handcrafted features extraction models as a classifier such as support-vector machine (SVM) [17,35,36,37]
Summary
Many possibilities of methylation as an additional post-transcriptional modification of RNA have been found in sequence RNAs mRNA [1]. The high-throughput laboratory techniques such as two-dimensional thin layer chromatography [14], high performance liquid chromatography [15] and next-generation sequencing techniques (e.g., m6A-seq [16] and MeRIP-Seq [2]) have been developed to identify m6A sites but all of these are time consuming and costly. Because of these restrictions of experimental methods, finding an accurate and fast computational method for m6A sites identification is a significant task
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
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 call
