Imbalance learning for the prediction of N6-Methylation sites in mRNAs

Abstract

BackgroundN6-methyladenosine (m6A) is an important epigenetic modification which plays various roles in mRNA metabolism and embryogenesis directly related to human diseases. To identify m6A in a large scale, machine learning methods have been developed to make predictions on m6A sites. However, there are two main drawbacks of these methods. The first is the inadequate learning of the imbalanced m6A samples which are much less than the non-m6A samples, by their balanced learning approaches. Second, the features used by these methods are not outstanding to represent m6A sequence characteristics.ResultsWe propose to use cost-sensitive learning ideas to resolve the imbalance data issues in the human mRNA m6A prediction problem. This cost-sensitive approach applies to the entire imbalanced dataset, without random equal-size selection of negative samples, for an adequate learning. Along with site location and entropy features, top-ranked positions with the highest single nucleotide polymorphism specificity in the window sequences are taken as new features in our imbalance learning. On an independent dataset, our overall prediction performance is much superior to the existing predictors. Our method shows stronger robustness against the imbalance changes in the tests on 9 datasets whose imbalance ratios range from 1:1 to 9:1. Our method also outperforms the existing predictors on 1226 individual transcripts. It is found that the new types of features are indeed of high significance in the m6A prediction. The case studies on gene c-Jun and CBFB demonstrate the detailed prediction capacity to improve the prediction performance.ConclusionThe proposed cost-sensitive model and the new features are useful in human mRNA m6A prediction. Our method achieves better correctness and robustness than the existing predictors in independent test and case studies. The results suggest that imbalance learning is promising to improve the performance of m6A prediction.Electronic supplementary materialThe online version of this article (10.1186/s12864-018-4928-y) contains supplementary material, which is available to authorized users.

Deep and accurate detection of m6A RNA modifications using miCLIP2 and m6Aboost machine learning

“…Third, we trained a machine learning model, termed m6Aboost, to accurately extract Mettl3-dependent m 6 A sites from any miCLIP2 dataset. Several machine learning approaches have been developed to predict m 6 A sites from the primary RNA sequences [43][44][45]. However, most existing models were trained on data of limited resolution and size, and consequently perform poorly for single-nucleotide predictions.…”

Predicting Active NBA Players Most Likely to Be Inducted into the Basketball Hall of Famers Using Artificial Neural Networks in Microsoft Excel: Development and Usability Study

“…After variables selected (i.e., Type I error less than 0.05) in 2.2.1, the ANN and the CNN models were built for comparing their model accuracies (e.g., sensitivity(SENS), specificity(SPEC), and area under the receiver operating characteristic curve (AUC) [ 22 , 23 ].…”

LITHOPHONE: Improving lncRNA Methylation Site Prediction Using an Ensemble Predictor

“…Deep-m6A (Zhang Sy et al, 2019) took the product of a onehot encoding of the sequence characteristics and the sites' reads count in the IP samples as an input to predict m 6 A sites using a CNN. In addition, PRNAm-PC (Liu et al, 2016), RAM-ESVM (Wei et al, 2017a), AthMethPre (Xiang et al, 2016), and other methods (Chen et al, 2015c;Li et al, 2016;Zhao et al, 2018;Liu et al, 2020) can also be used to predict m 6 A methylation sites. Although all these methods can predict RNA methylation sites, they are entirely based on the sequence context information.…”