plantMirP: an efficient computational program for the prediction of plant pre-miRNA by incorporating knowledge-based energy features

Abstract

We developed a promising SVM-based program, plantMirP, for predicting plant pre-miRNAs by incorporating a set of novel knowledge-based energy features.

Computational methods for the ab initio identification of novel microRNA in plants: a systematic review

“…Different studies have been conducted to show the impact of different sets of features. Some methods show that thermodynamic features (Yao et al, 2016) are better while another reports that sequential features (Yousef et al, 2016) are better. However, there is no concrete answer or common theme since there aren't many studies comparing different feature types for plant miRNA prediction.…”

“…Of the papers discussed here all used either miRBase or its precursor the microRNA registry database, of which seven used miRBase version 20 or 21. Of these papers; (Yao et al, 2016;Yousef, Allmer & Khalifa, 2015;Yousef et al, 2016;Vitsios et al, 2017;Douglass et al, 2016;Tseng et al, 2018;Koh & Kim, 2017), only (Douglass et al, 2016) makes reference to the confidence of the sequences used. Whilst they do not explicitly say they used ''high confidence'' sequences, they specify they required either one or two types of experimental evidence dependant upon species and available evidence (Douglass et al, 2016).…”

“…Also, as mentioned before, many authors use features proven to be most effective for animals on models developed for plants without comprehensive evaluation. This likely impacts the performance due to the noticeable differences between plant and animal miRNA sequences (Yao et al, 2016;Douglass et al, 2016). On top of this, some models have not considered feature selection at all (Silla, De O Camargo-Brunetto & Binneck, 2010;Williams, Eyles & Weiller, 2012;Xiao et al, 2011 etc.…”

PlantMirP-Rice: An Efficient Program for Rice Pre-miRNA Prediction

“…The character strings and structure strings of real and pseudo pre-miRNAs are reversed to obtain the corresponding reversed strings ( Figure 1 ). As previously mentioned, in the predicted secondary structure, paired or unpaired nucleotides indicated by “(“ in 5′ end and “)” in 3′ end are indistinguishably represented by “(“ [ 20 , 28 , 29 ]. Then, the Needleman–Wunsch algorithm is used to align structure strings and the corresponding reversed structure strings.…”

New 3D graphical representation for RNA structure analysis and its application in the pre-miRNA identification of plants

“…7 ML-based methods have been widely applied to identify plant miRNAs. 1,[8][9][10][11][12][13][14][15] ML-based methods have treated pre-miRNA iden-tication as a binary classication task to discriminate between real and pseudo-pre-miRNAs. However, the performance of MLbased predictors mainly depends on ML algorithms or operation engines.…”