Rxivist logo

StackRAM: a cross-species method for identifying RNA N6-methyladenosine sites based on stacked ensemble

By Zhaomin Yu, Baoguang Tian, Yaning Liu, Yaqun Zhang, Qin Ma, Bin Yu

Posted 25 Apr 2020
bioRxiv DOI: 10.1101/2020.04.23.058651

N6-methyladenosine is a prevalent RNA methylation modification, which plays an important role in various biological processes. Accurate identification of the m6A sites is fundamental to deeply understand the biological functions and mechanisms of the modification. However, the experimental methods for detecting m6A sites are usually time-consuming and expensive, and various computational methods have been developed to identify m6A sites in RNA. This paper proposes a novel cross-species computational method StackRAM using machine learning algorithms to identify the m6A sites in S. cerevisiae态H. sapiens and A. thaliana. First, the RNA sequences features are extracted through binary encoding, chemical property, nucleotide frequency, k-mer nucleotide frequency, pseudo dinucleotide composition, and position-specific trinucleotide propensity, and the initial feature set is obtained by feature fusion. Secondly, the Elastic Net is used for the first time to filter redundant and noisy information and retain important features for m6A sites classification. Finally, the base-classifiers output probabilities are combined with the optimal feature subset corresponding to the Elastic Net, and the combination feature input the second-stage meta-classifier SVM. The jackknife test on training dataset S. cerevisiae indicates that the prediction performance of StackRAM is superior to the current state-of-the-art methods. StackRAM prediction accuracy for independent test datasets H. sapiens and A. thaliana reach 92.30% and 87.06%, respectively. Therefore, StackRAM has development potential in cross-species prediction and can be a useful method for identifying m6A sites. ### Competing Interest Statement The authors have declared no competing interest.

Download data

  • Downloaded 146 times
  • Download rankings, all-time:
    • Site-wide: 127,321
    • In bioinformatics: 10,143
  • Year to date:
    • Site-wide: 134,035
  • Since beginning of last month:
    • Site-wide: 120,520

Altmetric data

Downloads over time

Distribution of downloads per paper, site-wide