RT Journal Article
SR Electronic
T1 Predict plant-derived xenomiRs from plant miRNA sequences using random forest and one-dimensional convolutional neural network models
JF bioRxiv
FD Cold Spring Harbor Laboratory
SP 345249
DO 10.1101/345249
A1 Qi Zhao
A1 Qian Mao
A1 Zheng Zhao
A1 Tongyi Dou
A1 Zhiguo Wang
A1 Xiaoyu Cui
A1 Yuanning Liu
A1 Xiaoya Fan
YR 2018
UL http://biorxiv.org/content/early/2018/06/13/345249.abstract
AB Background An increasing number of studies reported that exogenous miRNAs (xenomiRs) can be detected in animal bodies, however, some others reported negative results. Some attributed this divergence to the selective absorption of plant-derived xenomiRs by animals.Results Here, we analyzed 166 plant-derived xenomiRs reported in our previous study and 942 non-xenomiRs extracted from miRNA expression profiles of four species of commonly consumed plants. Employing statistics analysis and cluster analysis, our study revealed the potential sequence specificity of plant-derived xenomiRs. Furthermore, a random forest model and a one-dimensional convolutional neural network model were trained using miRNA sequence features and raw miRNA sequences respectively and then employed to predict unlabeled plant miRNAs in miRBase. A total of 241 possible plant-derived xenomiRs were predicted by both models. Finally, the potential functions of these possible plant-derived xenomiRs along with our previously reported ones in human body were analyzed.Conclusions Our study, for the first time, presents the systematic plant-derived xenomiR sequences analysis and provides evidence for selective absorption of plant miRNA by human body, which could facilitate the future investigation about the mechanisms underlying the transference of plant-derived xenomiR.AadenineACCaccuracyAUCareas under ROC curveCcytosinexenomiRexogenous miRNAFDRfalse discovery rateGIgastrointestinalGguanineLDAlinear discriminant analysisRICSRNA-induced silencing complex1D-CNNone-dimensional convolutional neural networkRFrandom forestROCreceiver operating characteristicSNsensitivitySPspecificityUuracil