PlantRNA_Sniffer: A SVM-Based Workflow to Predict Long Intergenic Non-Coding RNAs in Plants

Abstract

Non-coding RNAs (ncRNAs) constitute an important set of transcripts produced in the cells of organisms. Among them, there is a large amount of a particular class of long ncRNAs that are difficult to predict, the so-called long intergenic ncRNAs (lincRNAs), which might play essential roles in gene regulation and other cellular processes. Despite the importance of these lincRNAs, there is still a lack of biological knowledge and, currently, the few computational methods considered are so specific that they cannot be successfully applied to other species different from those that they have been originally designed to. Prediction of lncRNAs have been performed with machine learning techniques. Particularly, for lincRNA prediction, supervised learning methods have been explored in recent literature. As far as we know, there are no methods nor workflows specially designed to predict lincRNAs in plants. In this context, this work proposes a workflow to predict lincRNAs on plants, considering a workflow that includes known bioinformatics tools together with machine learning techniques, here a support vector machine (SVM). We discuss two case studies that allowed to identify novel lincRNAs, in sugarcane (Saccharum spp.) and in maize (Zea mays). From the results, we also could identify differentially-expressed lincRNAs in sugarcane and maize plants submitted to pathogenic and beneficial microorganisms.

Analysis of Soybean Long Non-Coding RNAs Reveals a Subset of Small Peptide-Coding Transcripts

“…Various tools are available to evaluate the coding potential of transcripts and distinguish noncoding RNAs from protein-coding ones using machine learning approaches. These methods have used a variety of models, such as support vector machine (Liu et al, 2006;Kong et al, 2007;Sun et al, 2013aSun et al, , 2013bLi et al, 2014;Kang et al, 2017;Vieira et al, 2017), random forest (Hu et al, 2017;Singh et al, 2017;Wucher et al, 2017), logistic regression (Wang et al, 2013), and REPTree (Negri et al, 2018). The features used by these machine learning approaches are usually extracted directly from nucleotide sequences.…”

Roles of Non-Coding RNA in Sugarcane-Microbe Interaction

“…To train the model, positive and negative datasets of 1000 transcripts each were built. From 2432 sugarcane transcripts mapped on intergenic regions, 1689 were classified as lincRNAs by the SVM model and 97 by BLAST [ 32 ]. Finally, a total of 67 transcripts were classified as lincRNAs by both BLAST and the SVM model.…”

“…Using data from sugarcane transcriptome datasets [ 30 ], lincRNAs of sugarcane were identified with a pipeline available in Figure S1 , including a specific designed SVM (Support Vector Machine) model [ 32 ]. The pipeline was constructed using data from Sorghum bicolor , a plant evolutionarily close to sugarcane for which the full genome sequence is known.…”

LncRNAs: genetic and epigenetic effects in plants

“…CONC performs slowly on analyzing large ncRNA datasets, while CPC is suitable for known protein-coding transcripts. However, CPC may tend to classify novel PCTs into ncRNAs not recorded in the protein databases [111,118]. The most common methods use pairwise comparisons (CPC [116] and PORTRAIT [117]) or multiple alignments (PhyloCSF [119] and RNAcode [120]).…”