Abstract
As one of the most abundant RNA post-transcriptional modifications, N6-methyladenosine (m6A) involves in a broad spectrum of biological and physiological processes ranging from mRNA splicing and stability to cell differentiation and reprogramming. However, experimental identification of m6A sites is expensive and laborious. Therefore, it is urgent to develop computational methods for reliable prediction of m6A sites from primary RNA sequences. In the current study, a new method called RAM-ESVM was developed for detecting m6A sites from Saccharomyces cerevisiae transcriptome, which employed ensemble support vector machine classifiers and novel sequence features. The jackknife test results show that RAM-ESVM outperforms single support vector machine classifiers and other existing methods, indicating that it would be a useful computational tool for detecting m6A sites in S. cerevisiae. Furthermore, a web server named RAM-ESVM was constructed and could be freely accessible at http://server.malab.cn/RAM-ESVM/.
Highlights
As one of the most abundant RNA post-transcriptional modifications, N6-methyladenosine (m6A) involves in a broad spectrum of biological and physiological processes ranging from mRNA splicing and stability to cell differentiation and reprogramming
In order to demonstrate the effectiveness of pseudo dinucleotide composition (PseDNC) and motif features for m6A sites prediction, we compared the performance of PseDNC and motif features with other RNA sequence features
Wei et al.[19] developed the RNA sequence numeric fingerprints to 98-D, which was proved to be more robust for human microRNA detection
Summary
Zhang et al improved the performance of identifying m6A site in yeast by introducing the heuristic nucleotide physical-chemical property selection algorithm[14]. The performance for identifying m6A site in yeast transcriptome is still not satisfactory and should be improved further Keeping this in mind, in the present study, we proposed an ensemble classifier, called RAM-ESVM, for detecting m6A sites in S. cerevisiae. We employed the SVM to perform the comparisons between the models based on our PseDNC and motif features with that based on the 32D and 98D features. We employed PseDNC features together with SVM, motif features together with SVM, and GkSVM as three basic classifiers A m6A site predictor, called RAM-ESVM, was developed based on the ensemble SVM, where “R” stands for RNA, “A” stands for N6-adenosine, “M” stands for methylation, “E” stands for Ensemble, “SVM” stands for Support Vector Machine
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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.
