Prediction Of Non-coding RNAs Research Articles

Whole-genome sequencing and evolutionary analysis of the wild edible mushroom, Morchella eohespera.

Morels (Morchella, Ascomycota) are an extremely desired group of edible mushrooms with worldwide distribution. Morchella eohespera is a typical black morel species, belonging to the Elata clade of Morchella species. The biological and genetic studies of this mushroom are rare, largely hindering the studies of molecular breeding and evolutionary aspects. In this study, we performed de novo sequencing and assembly of the M. eohespera strain m200 genome using the third-generation nanopore sequencing platform. The whole-genome size of M. eohespera was 53.81 Mb with a contig N50 of 1.93 Mb, and the GC content was 47.70%. A total of 9,189 protein-coding genes were annotated. Molecular dating showed that M. eohespera differentiated from its relative M. conica at ~19.03 Mya (million years ago) in Burdigalian. Evolutionary analysis showed that 657 gene families were contracted and 244 gene families expanded in M. eohespera versus the related morel species. The non-coding RNA prediction results showed that there were 336 tRNAs, 76 rRNAs, and 45 snRNAs in the M. eohespera genome. Interestingly, there was a high degree of repetition (20.93%) in the M. eohespera genome, and the sizes of long interspersed nuclear elements, short interspersed nuclear elements, and long terminal repeats were 0.83 Mb, 0.009 Mb, and 4.56 Mb, respectively. Additionally, selection pressure analysis identified that a total of 492 genes in the M. eohespera genome have undergone signatures of positive selection. The results of this study provide new insights into the genome evolution of M. eohespera and lay the foundation for in-depth research into the molecular biology of the genus Morchella in the future.

Fast and precise prediction of non-coding RNAs (ncRNAs) using sequence alignment and k-mer counting

Fast and precise prediction of non-coding RNAs (ncRNAs) using sequence alignment and k-mer counting

Deep learning tools are top performers in long non-coding RNA prediction.

The increasing amount of transcriptomic data has brought to light vast numbers of potential novel RNA transcripts. Accurately distinguishing novel long non-coding RNAs (lncRNAs) from protein-coding messenger RNAs (mRNAs) has challenged bioinformatic tool developers. Most recently, tools implementing deep learning architectures have been developed for this task, with the potential of discovering sequence features and their interactions still not surfaced in current knowledge. We compared the performance of deep learning tools with other predictive tools that are currently used in lncRNA coding potential prediction. A total of 15 tools representing the variety of available methods were investigated. In addition to known annotated transcripts, we also evaluated the use of the tools in actual studies with real-life data. The robustness and scalability of the tools’ performance was tested with varying sized test sets and test sets with different proportions of lncRNAs and mRNAs. In addition, the ease-of-use for each tested tool was scored. Deep learning tools were top performers in most metrics and labelled transcripts similarly with each other in the real-life dataset. However, the proportion of lncRNAs and mRNAs in the test sets affected the performance of all tools. Computational resources were utilized differently between the top-ranking tools, thus the nature of the study may affect the decision of choosing one well-performing tool over another. Nonetheless, the results suggest favouring the novel deep learning tools over other tools currently in broad use.

MiRPreM and tiRPreM: Improved methodologies for the prediction of miRNAs and tRNA-induced small non-coding RNAs for model and non-model organisms

In recent years, microRNAs (miRNAs) and tRNA-derived RNA fragments (tRFs) have been reported extensively following different approaches of identification and analysis. Comprehensively analyzing the present approaches to overcome the existing variations, we developed a benchmarking methodology each for the identification of miRNAs and tRFs, termed as miRNA Prediction Methodology (miRPreM) and tRNA-induced small non-coding RNA Prediction Methodology (tiRPreM), respectively. We emphasized the use of respective genome of organism under study for mapping reads, sample data with at least two biological replicates, normalized read count support and novel miRNA prediction by two standard tools with multiple runs. The performance of these methodologies was evaluated by using Oryza coarctata, a wild rice species as a case study for model and non-model organisms. With organism-specific reference genome approach, 98 miRNAs and 60 tRFs were exclusively found. We observed high accuracy (13 out of 15) when tested these genome-specific miRNAs in support of analyzing the data with respective organism. Such a strong impact of miRPreM, we have predicted more than double number of miRNAs (186) as compared with the traditional approaches (79) and with tiRPreM, we have predicted all known classes of tRFs within the same small RNA data. Moreover, the methodologies presented here are in standard form in order to extend its applicability to different organisms rather than restricting to plants. Hence, miRPreM and tiRPreM can fulfill the need of a comprehensive methodology for miRNA prediction and tRF identification, respectively, for model and non-model organisms.

PlncRNA-HDeep: plant long noncoding RNA prediction using hybrid deep learning based on two encoding styles

BackgroundLong noncoding RNAs (lncRNAs) play an important role in regulating biological activities and their prediction is significant for exploring biological processes. Long short-term memory (LSTM) and convolutional neural network (CNN) can automatically extract and learn the abstract information from the encoded RNA sequences to avoid complex feature engineering. An ensemble model learns the information from multiple perspectives and shows better performance than a single model. It is feasible and interesting that the RNA sequence is considered as sentence and image to train LSTM and CNN respectively, and then the trained models are hybridized to predict lncRNAs. Up to present, there are various predictors for lncRNAs, but few of them are proposed for plant. A reliable and powerful predictor for plant lncRNAs is necessary.ResultsTo boost the performance of predicting lncRNAs, this paper proposes a hybrid deep learning model based on two encoding styles (PlncRNA-HDeep), which does not require prior knowledge and only uses RNA sequences to train the models for predicting plant lncRNAs. It not only learns the diversified information from RNA sequences encoded by p-nucleotide and one-hot encodings, but also takes advantages of lncRNA-LSTM proposed in our previous study and CNN. The parameters are adjusted and three hybrid strategies are tested to maximize its performance. Experiment results show that PlncRNA-HDeep is more effective than lncRNA-LSTM and CNN and obtains 97.9% sensitivity, 95.1% precision, 96.5% accuracy and 96.5% F1 score on Zea mays dataset which are better than those of several shallow machine learning methods (support vector machine, random forest, k-nearest neighbor, decision tree, naive Bayes and logistic regression) and some existing tools (CNCI, PLEK, CPC2, LncADeep and lncRNAnet).ConclusionsPlncRNA-HDeep is feasible and obtains the credible predictive results. It may also provide valuable references for other related research.

Analysis and comprehensive comparison of PacBio and nanopore-based RNA sequencing of the Arabidopsis transcriptome

BackgroundThe number of studies using third-generation sequencing utilising Pacific Biosciences (PacBio) and Oxford Nanopore Technologies (ONT) is rapidly increasing in many different research areas. Among them, plant full-length single-molecule transcriptome studies have mostly used PacBio sequencing, whereas ONT is rarely used. Therefore, in this study, we examined ONT RNA sequencing methods in plants. We performed a detailed evaluation of reads from PacBio, Nanopore direct cDNA (ONT Dc), and Nanopore PCR cDNA (ONT Pc) sequencing including characteristics of raw data and identification of transcripts. In addition, matched Illumina data were generated for comparison.ResultsONT Pc showed overall better raw data quality, whereas PacBio generated longer read lengths. In the transcriptome analysis, PacBio and ONT Pc performed similarly in transcript identification, simple sequence repeat analysis, and long non-coding RNA prediction. PacBio was superior in identifying alternative splicing events, whereas ONT Pc could estimate transcript expression levels.ConclusionsThis paper made a comprehensive comparison of PacBio and nanopore-based RNA sequencing of the Arabidopsis transcriptome, the results indicate that ONT Pc is more cost-effective for generating extremely long reads and can characterise the transcriptome as well as quantify transcript expression. Therefore, ONT Pc is a new cost-effective and worthwhile method for full-length single-molecule transcriptome analysis in plants.

Machine Learning-Based Annotation of Long Noncoding RNAs Using PLncPRO.

Long noncoding RNAs (lncRNAs) are noncoding RNAs with transcript length more than 200 nucleotides. Although poorly conserved, lncRNAs are expressed across diverse species, including plants and animals, and are known to be involved in regulation of various biological processes. To understand their biological significance, we first need to identify the lncRNAs accurately. However, distinguishing lncRNAs from coding transcripts is still a challenging task. Here, we describe a machine learning-based approach to accurately identify the plant lncRNAs. We describe the usage of plant long noncoding RNA prediction by random forests (PLncPRO), which employs machine learning-based random forest algorithm to recognize the lncRNAs from the set of given transcript sequences. Stepwise instructions have been provided to use PLncPRO to annotate the lncRNA sequences.

Updated Assembly of Phytophthora ramorum pr102 Isolate Incorporating Long Reads from PacBio Sequencing.

The NA1 clonal lineage of Phytophthora ramorum is responsible for sudden oak death, an epidemic that has devastated California coastal forest ecosystems. An NA1 isolate, Pr102, derived from coast live oak in California, was previously sequenced and reported with a 65-Mb assembly containing 12 Mb of gaps in 2,576 scaffolds. Here, we report an improved 70-Mb genome in 1,512 scaffolds with 6,752 bp of gaps after incorporating PacBio P5-C3 long reads. This assembly contains 19,494 gene models (average gene length of 2,515 bp) compared with 16,134 genes (average gene length of 1,673 bp) in the previous version. We predicted 29 new RXLR genes and 76 new paralogs of a total 392 RXLR genes from this assembly. We predicted 35 CRN genes compared with 19 in an earlier version with six paralogs. Our long non-coding RNA prediction identified 255 candidates. This new resource will be invaluable for future evolution studies on the invasive plant pathogen.

Whole genome sequence of moderate halophilic marine bacterium Marinobacter litoralis SW-45: Abundance of non-coding RNAs.

A report on the de novo Whole Genome Sequence (WGS) of Marinobacter litoralis SW-45, a moderately salt-tolerant bacterium isolated from the seawater in Malaysia is presented. The strain has a genome size of 3.45 Mb and is capable of producing halophilic lipase, protease and esterase enzymes. Computational prediction of non-coding RNA (ncRNA) genes in M. litoralis SW-45 was performed using standalone software known as the non-coding RNA characterization (nocoRNAc). In addition, a phylogenetic tree showing the evolutionary relationship between the strain and other members of the genus Marinobacter was constructed using 16SrRNA sequence information. A total of 385 ncRNA transcripts, 1124 terminator region, and 2350 Stress Induced Duplex Destabilization sites were predicted. The current WGS shotgun project has provided the relevant genetic information that may be useful for the strain's improvement studies. This manuscript gives the first description of M. litoralis with a complete genome.

RBind: computational network method to predict RNA binding sites.

Non-coding RNA molecules play essential roles by interacting with other molecules to perform various biological functions. However, it is difficult to determine RNA structures due to their flexibility. At present, the number of experimentally solved RNA-ligand and RNA-protein structures is still insufficient. Therefore, binding sites prediction of non-coding RNA is required to understand their functions. Current RNA binding site prediction algorithms produce many false positive nucleotides that are distance away from the binding sites. Here, we present a network approach, RBind, to predict the RNA binding sites. We benchmarked RBind in RNA-ligand and RNA-protein datasets. The average accuracy of 0.82 in RNA-ligand and 0.63 in RNA-protein testing showed that this network strategy has a reliable accuracy for binding sites prediction. The codes and datasets are available at https://zhaolab.com.cn/RBind. Supplementary data are available at Bioinformatics online.

Prediction of Non-coding RNAs as Drug Targets.

MiRNA is a class of small non-coding RNA molecule that regulates gene expression at post-transcriptional level. Increasing evidences show aberrant expression of miRNAs in a variety of diseases. Targeting the dysregulated miRNAs with small molecule drugs has become a novel therapeutics for many human diseases, especially cancers. In this chapter, we introduced a series of computational studies for prediction of small molecule and miRNA associations. Based on different hypotheses, such as transcriptional response similarity, functional consistence or network closeness, the small molecule-miRNA networks were constructed and further analyzed. In addition, several resources that collected experimentally validated relationships or computational predicted associations between small molecules and miRNAs were provided. Collectively, these computational frameworks and databases pave a new way for miRNA-targeted therapy and drug repositioning.

3D Structure Prediction of Noncoding RNA and Single Stranded DNA

3D Structure Prediction of Noncoding RNA and Single Stranded DNA

MiRNAFold: a web server for fast miRNA precursor prediction in genomes.

Computational methods are required for prediction of non-coding RNAs (ncRNAs), which are involved in many biological processes, especially at post-transcriptional level. Among these ncRNAs, miRNAs have been largely studied and biologists need efficient and fast tools for their identification. In particular, ab initio methods are usually required when predicting novel miRNAs. Here we present a web server dedicated for miRNA precursors identification at a large scale in genomes. It is based on an algorithm called miRNAFold that allows predicting miRNA hairpin structures quickly with high sensitivity. miRNAFold is implemented as a web server with an intuitive and user-friendly interface, as well as a standalone version. The web server is freely available at: http://EvryRNA.ibisc.univ-evry.fr/miRNAFold.

Enhanced Prediction of Small Non-coding RNA in Bacterial Genomes Based on Improved Inter-Nucleotide Distances of Genomes

Small non-coding RNA genes have been concerned as an important field of life sciences in recent years. It plays important regulatory roles in cellular processes. However, the prediction of noncoding RNA genes is a great challenge, because non-coding RNAs have a small size, are not translated into proteins and show variable stability. In this paper, we propose an improved inter-nucleotide distances model as sequence characteristics, and combine with support vector machines (SVM) to predict small non-coding RNA in bacterial genomes. The prediction result of the mixed bacterial ncRNA is 95.38%, which shows that our method can effectively predict bacterial ncRNAs. Keywords: Small non-coding RNA, inter-nucleotide distances, prediction, support vector machines, machine learning.

In silico prediction of long intergenic non-coding RNAs in sheep.

Long non-coding RNAs (lncRNAs) are transcribed RNA molecules >200 nucleotides in length that do not encode proteins and serve as key regulators of diverse biological processes. Recently, thousands of long intergenic non-coding RNAs (lincRNAs), a type of lncRNAs, have been identified in mammalians using massive parallel large sequencing technologies. The availability of the genome sequence of sheep (Ovis aries) has allowed us genomic prediction of non-coding RNAs. This is the first study to identify lincRNAs using RNA-seq data of eight different tissues of sheep, including brain, heart, kidney, liver, lung, ovary, skin, and white adipose. A computational pipeline was employed to characterize 325 putative lincRNAs with high confidence from eight important tissues of sheep using different criteria such as GC content, exon number, gene length, co-expression analysis, stability, and tissue-specific scores. Sixty-four putative lincRNAs displayed tissues-specific expression. The highest number of tissues-specific lincRNAs was found in skin and brain. All novel lincRNAs that aligned to the human and mouse lincRNAs had conserved synteny. These closest protein-coding genes were enriched in 11 significant GO terms such as limb development, appendage development, striated muscle tissue development, and multicellular organismal development. The findings reported here have important implications for the study of sheep genome.

Predicting Long Non-coding RNAs Based on Genomic Sequence Information

The binary classification of coding and non-coding genes is simplified near to 50 years. Genome-wide transcriptome studies have revealed that there exist tens of thousands of long non-coding RNAs (lncRNAs), while the functions are being uncovered slowly. Accurate identification of lncRNAs is the initial step to the systematic characterization of lncRNAs. The diversity of transcription patterns for lncRNAs challenges the available non-coding RNA prediction algorithms. Until now, prediction of lncRNAs mostly relies on genomic sequence and cross-species alignment information. Here, we introduce the main strategies that can discriminate lncRNA from protein-coding transcripts. Especially, recently available machine learning algorithms are shown efficient to the rapid and accurate identification of lncRNAs from a large number of putative lncRNAs based on transcriptome assembled transcripts, which would provide the basis of understanding of lncRNA biology.

Prediction of tRNA Based on LS-SVM Algorithm with Principal Component Analysis

Recently, non-coding RNA prediction is the one of the most important researches in bioinformatics. In this paper, on the basis of principal component analysis, we present a tRNA prediction strategy by using least squares support vector machine (LS-SVM). Appearance frequencies of single nucleotide, 2 – nucleotides and (G-C) %, (A-T) % were chosen as characteristics inputs. Results from tests showed that the prediction accuracy was 90.51% on prokaryotic tRNA dataset. Experimental results indicate that the method is effective for prokaryotic ncRNA prediction.

In silico prediction of noncoding RNAs using supervised learning and feature ranking methods

We propose here a new approach for ncRNA prediction. Our approach selects features derived from RNA folding programs and ranks these features using a class separation method that measures the ability of the features to differentiate between positive and negative classes. The target feature set comprising top-ranked features is then used to construct several classifiers with different supervised learning algorithms. These classifiers are compared to the same supervised learning algorithms with the baseline feature set employed in a state-of-the-art method. Experimental results based on ncRNA families taken from the Rfam database demonstrate the good performance of the proposed approach.

Robust and accurate prediction of noncoding RNAs from aligned sequences

BackgroundComputational prediction of noncoding RNAs (ncRNAs) is an important task in the post-genomic era. One common approach is to utilize the profile information contained in alignment data rather than single sequences. However, this strategy involves the possibility that the quality of input alignments can influence the performance of prediction methods. Therefore, the evaluation of the robustness against alignment errors is necessary as well as the development of accurate prediction methods.ResultsWe describe a new method, called Profile BPLA kernel, which predicts ncRNAs from alignment data in combination with support vector machines (SVMs). Profile BPLA kernel is an extension of base-pairing profile local alignment (BPLA) kernel which we previously developed for the prediction from single sequences. By utilizing the profile information of alignment data, the proposed kernel can achieve better accuracy than the original BPLA kernel. We show that Profile BPLA kernel outperforms the existing prediction methods which also utilize the profile information using the high-quality structural alignment dataset. In addition to these standard benchmark tests, we extensively evaluate the robustness of Profile BPLA kernel against errors in input alignments. We consider two different types of error: first, that all sequences in an alignment are actually ncRNAs but are aligned ignoring their secondary structures; second, that an alignment contains unrelated sequences which are not ncRNAs but still aligned. In both cases, the effects on the performance of Profile BPLA kernel are surprisingly small. Especially for the latter case, we demonstrate that Profile BPLA kernel is more robust compared to the existing prediction methods.ConclusionsProfile BPLA kernel provides a promising way for identifying ncRNAs from alignment data. It is more accurate than the existing prediction methods, and can keep its performance under the practical situations in which the quality of input alignments is not necessarily high.

Computational RNomics: Structure identification and functional prediction of non-coding RNAs in silico

The eukaryotic genome contains varying numbers of non-coding RNA (ncRNA) genes. "Computational RNomics" takes a multidisciplinary approach, like information science, to resolve the structure and function of ncRNAs. Here, we review the main issues in "Computational RNomics" of data storage and management, ncRNA gene identification and characterization, ncRNA target identification and functional prediction, and we summarize the main methods and current content of "computational RNomics".