首页|Identification of DNA N4-methylcytosine sites via fuzzy model on self representation
Identification of DNA N4-methylcytosine sites via fuzzy model on self representation
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NSTL
Elsevier
N4-methylcytosine (4mC) has a significant effect on altering protein interactions, DNA conformation, gene expression and genomic imprinting. Accurate recognition of the 4mC sites is helpful for indepth study of biomedical research. Although there are experimental methods for detecting 4mC sites, these techniques are time-consuming and laborious, and cannot be applied to large-scale genome scanning. Therefore, supplementation with an efficient computational method is absolutely necessary. In this study, we propose a prediction tool, 4mCPred-FSVM, to solve the above problems. We use position-specific trinucleotide propensity (PSTNP) to construct feature vectors. Subsequently, the feature vector was used as the input of the fuzzy support vector machine (FSVM) and the final predictor was developed. We measure the performance of the model on six datasets. In comparison to the state-of-the-art predictor, our predictor has achieved much higher accuracies in predicting 4mC sites. (C)& nbsp;2022 Elsevier B.V. All rights reserved.
N4-methylcytosineMachine learningFuzzy support vector machineMembership functionKernelized representationMETHYLATION
NSTL
Elsevier
