Abstract
MicroRNAs (miRNAs) are one kind of non-coding RNA, play vital role in regulating several physiological and developmental processes. Subcellular localization of miRNAs and their abundance in the native cell are central for maintaining physiological homeostasis. Besides, RNA silencing activity of miRNAs is also influenced by their localization and stability. Thus, development of computational method for subcellular localization prediction of miRNAs is desired. In this work, we have proposed a computational method for predicting subcellular localizations of miRNAs based on principal component scores of thermodynamic, structural properties and pseudo compositions of di-nucleotides. Prediction accuracy was analyzed following fivefold cross validation, where ~ 63–71% of AUC-ROC and ~ 69–76% of AUC-PR were observed. While evaluated with independent test set, > 50% localizations were found to be correctly predicted. Besides, the developed computational model achieved higher accuracy than the existing methods. A user-friendly prediction server “miRNALoc” is freely accessible at http://cabgrid.res.in:8080/mirnaloc/, by which the user can predict localizations of miRNAs.
Highlights
It has been established that the non-coding RNAs are important regulator rather than the junk sequences[1]
The pseudodinucleotide compositions along with the physico-chemical and thermodynamic properties of miRNAs were utilized as features, where the support vector machine (SVM)[36] along with other machine learning methods were employed as predictor
From the heat map of the AUC-ROC (Fig. 1D), it can be seen that the radial basis function (RBF) kernel yielded higher accuracy for all the eight localizations predictors across all the four different kind of feature sets
Summary
It has been established that the non-coding RNAs (ncRNAs) are important regulator rather than the junk sequences[1]. From the heat map of the AUC-ROC (Fig. 1D), it can be seen that the radial basis function (RBF) kernel yielded higher accuracy for all the eight localizations predictors across all the four different kind of feature sets. With the default parameters setting of RBF kernel, prediction accuracies were further evaluated for all the four different feature sets i.e., PseDNC, DiPro, PseDNC + DiPro and PrinComp using same sample dataset as used in analyzing the kernel functions.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: 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.