Prediction of microRNA targets in Caenorhabditis elegans using a self-organizing map

Machine Learning Strategies in MicroRNA Research: Bridging Genome to Phenome

MicroRNAs (miRNAs) have emerged as a prominent layer of regulation of gene expression. This article offers the salient and current aspects of machine learning (ML) tools and approaches from genome to phenome in miRNA research. First, we underline that the complexity in the analysis of miRNA function ranges from their modes of biogenesis to the target diversity in diverse biological conditions. Therefore, it is imperative to first ascertain the miRNA coding potential of genomes and understand the regulatory mechanisms of their expression. This knowledge enables the efficient classification of miRNA precursors and the identification of their mature forms and respective target genes. Second, and because one miRNA can target multiple mRNAs and vice versa, another challenge is the assessment of the miRNA-mRNA target interaction network. Furthermore, long-noncoding RNA (lncRNA)and circular RNAs (circRNAs) also contribute to this complexity. ML has been used to tackle these challenges at the high-dimensional data level. The present expert review covers more than 100 tools adopting various ML approaches pertaining to, for example, (1) miRNA promoter prediction, (2) precursor classification, (3) mature miRNA prediction, (4) miRNA target prediction, (5) miRNA- lncRNA and miRNA-circRNA interactions, (6) miRNA-mRNA expression profiling, (7) miRNA regulatory module detection, (8) miRNA-disease association, and (9) miRNA essentiality prediction. Taken together, we unpack, critically examine, and highlight the cutting-edge synergy of ML approaches and miRNA research so as to develop a dynamic and microlevel understanding of human health and diseases.

NeRNA: A negative data generation framework for machine learning applications of noncoding RNAs

Many supervised machine learning based noncoding RNA (ncRNA) analysis methods have been developed to classify and identify novel sequences. During such analysis, the positive learning datasets usually consist of known examples of ncRNAs and some of them might even have weak or strong experimental validation. On the contrary, there are neither databases listing the confirmed negative sequences for a specific ncRNA class nor standardized methodologies developed to generate high quality negative examples. To overcome this challenge, a novel negative data generation method, NeRNA (negative RNA), is developed in this work. NeRNA uses known examples of given ncRNA sequences and their calculated structures for octal representation to create negative sequences in a manner similar to frameshift mutations but without deletion or insertion. NeRNA is tested individually with four different ncRNA datasets including microRNA (miRNA), transfer RNA (tRNA), long noncoding RNA (lncRNA), and circular RNA (circRNA). Furthermore, a species-specific case analysis is performed to demonstrate and compare the performance of NeRNA for miRNA prediction. The results of 1000 fold cross-validation on Decision Tree, Naïve Bayes and Random Forest classifiers, and deep learning algorithms such as Multilayer Perceptron, Convolutional Neural Network, and Simple feedforward Neural Networks indicate that models obtained by using NeRNA generated datasets, achieves substantially high prediction performance. NeRNA is released as an easy-to-use, updatable and modifiable KNIME workflow that can be downloaded with example datasets and required extensions. In particular, NeRNA is designed to be a powerful tool for RNA sequence data analysis.

Non-coding RNAs in human health and disease: potential function as biomarkers and therapeutic targets

Human diseases have been a critical threat from the beginning of human history. Knowing the origin, course of action and treatment of any disease state is essential. A microscopic approach to the molecular field is a more coherent and accurate way to explore the mechanism, progression, and therapy with the introduction and evolution of technology than a macroscopic approach. Non-coding RNAs (ncRNAs) play increasingly important roles in detecting, developing, and treating all abnormalities related to physiology, pathology, genetics, epigenetics, cancer, and developmental diseases. Noncoding RNAs are becoming increasingly crucial as powerful, multipurpose regulators of all biological processes. Parallel to this, a rising amount of scientific information has revealed links between abnormal noncoding RNA expression and human disorders. Numerous non-coding transcripts with unknown functions have been found in addition to advancements in RNA-sequencing methods. Non-coding linear RNAs come in a variety of forms, including circular RNAs with a continuous closed loop (circRNA), long non-coding RNAs (lncRNA), and microRNAs (miRNA). This comprises specific information on their biogenesis, mode of action, physiological function, and significance concerning disease (such as cancer or cardiovascular diseases and others). This study review focuses on non-coding RNA as specific biomarkers and novel therapeutic targets.

Computational Detection of Pre-microRNAs

MicroRNA (miRNA) studies have been one of the most popular research areas in recent years. Although thousands of miRNAs have been detected in several species, the majority remains unidentified. Thus, finding novel miRNAs is a vital element for investigating miRNA mediated posttranscriptional gene regulation machineries. Furthermore, experimental methods have challenging inadequacies in their capability to detect rare miRNAs, and are also limited to the state of the organism under examination (e.g., tissue type, developmental stage, stress-disease conditions). These issues have initiated the creation of high-level computational methodologies endeavoring to distinguish potential miRNAs in silico. On the other hand, most of these tools suffer from high numbers of false positives and/or false negatives and as a result they do not provide enough confidence for validating all their predictions experimentally. In this chapter, computational difficulties in detection of pre-miRNAs are discussed and a machine learning based approach that has been designed to address these issues is reviewed.

Trends in the development of miRNA bioinformatics tools

MicroRNAs (miRNAs) are small noncoding RNAs that regulate gene expression via recognition of cognate sequences and interference of transcriptional, translational or epigenetic processes. Bioinformatics tools developed for miRNA study include those for miRNA prediction and discovery, structure, analysis and target prediction. We manually curated 95 review papers and ∼1000 miRNA bioinformatics tools published since 2003. We classified and ranked them based on citation number or PageRank score, and then performed network analysis and text mining (TM) to study the miRNA tools development trends. Five key trends were observed: (1) miRNA identification and target prediction have been hot spots in the past decade; (2) manual curation and TM are the main methods for collecting miRNA knowledge from literature; (3) most early tools are well maintained and widely used; (4) classic machine learning methods retain their utility; however, novel ones have begun to emerge; (5) disease-associated miRNA tools are emerging. Our analysis yields significant insight into the past development and future directions of miRNA tools.

The Limitations of Existing Approaches in Improving MicroRNA Target Prediction Accuracy

MicroRNAs (miRNAs) are small (18-24 nt) endogenous RNAs found across diverse phyla involved in posttranscriptional regulation, primarily downregulation of mRNAs. Experimentally determining miRNA-mRNA interactions can be expensive and time-consuming, making the accurate computational prediction of miRNA targets a high priority. Since miRNA-mRNA base pairing in mammals is not perfectly complementary and only a fraction of the identified motifs are real binding sites, accurately predicting miRNA targets remains challenging. The limitations and bottlenecks of existing algorithms and approaches are discussed in this chapter.A new miRNA-mRNA interaction algorithm was implemented in Python (TargetFind) to capture three different modes of association and to maximize detection sensitivity to around 95% for mouse (mm9) and human (hg19) reference data. For human (hg19) data, the prediction accuracy with any one feature among evolutionarily conserved score, multiple targets in a UTR or changes in free energy varied within a close range from 63.5% to 66%. When the results of these features are combined with majority voting, the expected prediction accuracy increases to 69.5%. When all three features are used together, the average best prediction accuracy with tenfold cross validation from the classifiers naïve Bayes, support vector machine, artificial neural network, and decision tree were, respectively, 66.5%, 67.1%, 69%, and 68.4%. The results reveal the advantages and limitations of these approaches.When comparing different sets of features on their strength in predicting true hg19 targets, evolutionarily conserved score slightly outperformed all other features based on thermostability, and target multiplicity. The sophisticated supervised learning algorithms did not improve the prediction accuracy significantly compared to a simple threshold based approach on conservation score or combining the results of each feature with majority agreements. The targets from randomly generated UTRs behaved similar to that of noninteracting pairs with respect to changes in free energy. Availability of additional experimental data describing noninteracting pairs will advance our understanding of the characteristics and the factors positively and negatively influencing these interactions.

MiRNATIP: a SOM-based miRNA-target interactions predictor

Background

MicroRNAs (miRNAs) are small non-coding RNA sequences with regulatory functions to post-transcriptional level for several biological processes, such as cell disease progression and metastasis. MiRNAs interact with target messenger RNA (mRNA) genes by base pairing. Experimental identification of miRNA target is one of the major challenges in cancer biology because miRNAs can act as tumour suppressors or oncogenes by targeting different type of targets. The use of machine learning methods for the prediction of the target genes is considered a valid support to investigate miRNA functions and to guide related wet-lab experiments. In this paper we propose the miRNA Target Interaction Predictor (miRNATIP) algorithm, a Self-Organizing Map (SOM) based method for the miRNA target prediction. SOM is trained with the seed region of the miRNA sequences and then the mRNA sequences are projected into the SOM lattice in order to find putative interactions with miRNAs. These interactions will be filtered considering the remaining part of the miRNA sequences and estimating the free-energy necessary for duplex stability.

Results

We tested the proposed method by predicting the miRNA target interactions of both the Homo sapiens and the Caenorhbditis elegans species; then, taking into account validated target (positive) and non-target (negative) interactions, we compared our results with other target predictors, namely miRanda, PITA, PicTar, mirSOM, TargetScan and DIANA-microT, in terms of the most used statistical measures. We demonstrate that our method produces the greatest number of predictions with respect to the other ones, exhibiting good results for both species, reaching the for example the highest percentage of sensitivity of 31 and 30.5 %, respectively for Homo sapiens and for C. elegans. All the predicted interaction are freely available at the following url: http://tblab.pa.icar.cnr.it/public/miRNATIP/.

Conclusions

Results state miRNATIP outperforms or is comparable to the other six state-of-the-art methods, in terms of validated target and non-target interactions, respectively.

mir-233 modulates the unfolded protein response in C. elegans during Pseudomonas aeruginosa infection

The unfolded protein response (UPR), which is activated by perturbations of the endoplasmic reticulum homeostasis, has been shown to play an important role in innate immunity and inflammation. However, little is known about the molecular mechanisms underlying activation of the UPR during immune responses. Using small RNA deep sequencing and reverse genetic analysis, we show that the microRNA mir-233 is required for activation of the UPR in Caenorhabditis elegans exposed to Pseudomonas aeruginosa PA14. P. aeruginosa infection up-regulates the expression of mir-233 in a p38 MAPK-dependent manner. Quantitative proteomic analysis identifies SCA-1, a C. elegans homologue of the sarco/endoplasmic reticulum Ca²⁺-ATPase, as a target of mir-233. During P. aeruginosa PA14 infection, mir-233 represses the protein levels of SCA-1, which in turn leads to activation of the UPR. Whereas mir-233 mutants are more sensitive to P. aeruginosa infection, knockdown of sca-1 leads to enhanced resistance to the killing by P. aeruginosa. Our study indicates that microRNA-dependent pathways may have an impact on innate immunity by activating the UPR.

In the model organism Caenorhabditis elegans, the IRE1–XBP1 pathway, a major branch of the unfolded protein response (UPR), is required for host defense against pathogens. However, how innate immune responses activate the UPR is not fully understood. In this report, we find that Pseudomonas aeruginosa PA14 infection up-regulates the expression of the microRNA mir-233 in C. elegans. The response of mir-233 to P. aeruginosa PA14 infection is dependent on a major pathway of innate immunity, the p38 MAPK signaling cascade. The up-regulation of mir-233 is functionally important since a mutation in mir-233 leads to hypersensitivity of the nematode to the killing by P. aeruginosa PA14. Furthermore, we demonstrate that mir-233 contributes to the activation of the UPR by repressing the protein levels of its target SCA-1, a C. elegans homologue of the sarco/endoplasmic reticulum Ca²⁺-ATPase. Thus, mir-233 is an important regulator of the UPR during the innate immune response.

Nicotine exposure and transgenerational impact: a prospective study on small regulatory microRNAs

Early developmental stages are highly sensitive to stress and it has been reported that pre-conditioning with tobacco smoking during adolescence predisposes those youngsters to become smokers as adults. However, the molecular mechanisms of nicotine-induced transgenerational consequences are unknown. In this study, we genome-widely investigated the impact of nicotine exposure on small regulatory microRNAs (miRNAs) and its implication on health disorders at a transgenerational aspect. Our results demonstrate that nicotine exposure, even at the low dose, affected the global expression profiles of miRNAs not only in the treated worms (F0 parent generation) but also in two subsequent generations (F1 and F2, children and grandchildren). Some miRNAs were commonly affected by nicotine across two or more generations while others were specific to one. The general miRNA patterns followed a “two-hit” model as a function of nicotine exposure and abstinence. Target prediction and pathway enrichment analyses showed daf-4, daf-1, fos-1, cmk-1, and unc-30 to be potential effectors of nicotine addiction. These genes are involved in physiological states and phenotypes that paralleled previously published nicotine induced behavior. Our study offered new insights and further awareness on the transgenerational effects of nicotine exposed during the vulnerable post-embryonic stages, and identified new biomarkers for nicotine addiction.

Computational developments in microRNA-regulated protein-protein interactions

Protein-protein interaction (PPI) is one of the most important functional components of a living cell. Recently, researchers have been interested in investigating the correlation between PPI and microRNA, which has been found to be a regulator at the post-transcriptional level. Studies on miRNA-regulated PPI networks will not only facilitate an understanding of the fine tuning role that miRNAs play in PPI networks, but will also provide potential candidates for tumor diagnosis. This review describes basic studies on the miRNA-regulated PPI network in the way of bioinformatics which includes constructing a miRNA-target protein network, describing the features of miRNA-regulated PPI networks and overviewing previous findings based on analysing miRNA-regulated PPI network features.

Chronic nicotine exposure systemically alters microRNA expression profiles during post-embryonic stages in Caenorhabditis elegans

Tobacco smoking is associated with many diseases. Addiction is of the most notorious tobacco-related syndrome and is mainly attributed to nicotine. In this study, we employed Caenorhabditis elegans as a biological model to systemically investigate the effect of chronic nicotine exposure on microRNA (miRNA) expression profile and their regulated biochemical pathways. Nicotine treatment (20 µM and 20 mM) was limited to the post-embryonic stage from L1 to L4 (∼31 h) period after which worms were collected for genome-wide miRNA profiling. Our results show that nicotine significantly altered the expression patterns of 40 miRNAs. The effect was proportional to the nicotine dose and was expected to have an additive, more robust response. Based on pathway enrichment analyses coupled with nicotine-induced miRNA patterns, we inferred that miRNAs as a system mediates "regulatory hormesis", manifested in biphasic behavioral and physiological phenotypes. We proposed a model where nicotine addiction is mediated by miRNAs' regulation of fos-1 and is maintained by epigenetic factors. Thus, our study offers new insights for a better understanding of the sensitivity of early developmental stages to nicotine.

Analysis of microRNA expression using machine learning

The systematic analysis of miRNA expression and its potential mRNA targets constitutes a basal objective in miRNA research in addition to miRNA gene detection and miRNA target prediction. In this chapter we address methodical issues of miRNA expression analysis using self-organizing maps (SOM), a neural network machine learning algorithm with strong visualization and second-level analysis capabilities widely used to categorize large-scale, high-dimensional data. We shortly review selected experimental and theoretical aspects of miRNA expression analysis. Then, the protocol of our SOM method is outlined with special emphasis on miRNA/mRNA coexpression. The method allows extracting differentially expressed RNA transcripts, their functional context, and also characterization of global properties of expression states and profiles. In addition to the separate study of miRNA and mRNA expression landscapes, we propose the combined analysis of both entities using a covariance SOM.

Methylmercury exposure increases lipocalin related (lpr) and decreases activated in blocked unfolded protein response (abu) genes and specific miRNAs in Caenorhabditis elegans

Methylmercury (MeHg) is a persistent environmental and dietary contaminant that causes serious adverse developmental and physiologic effects at multiple cellular levels. In order to understand more fully the consequences of MeHg exposure at the molecular level, we profiled gene and miRNA transcripts from the model organism Caenorhabditis elegans. Animals were exposed to MeHg (10 μM) from embryo to larval 4 (L4) stage and RNAs were isolated. RNA-seq analysis on the Illumina platform revealed 541 genes up- and 261 genes down-regulated at a cutoff of 2-fold change and false discovery rate-corrected significance q < 0.05. Among the up-regulated genes were those previously shown to increase under oxidative stress conditions including hsp-16.11 (2.5-fold), gst-35 (10.1-fold), and fmo-2 (58.5-fold). In addition, we observed up-regulation of 6 out of 7 lipocalin related (lpr) family genes and down regulation of 7 out of 15 activated in blocked unfolded protein response (abu) genes. Gene Ontology enrichment analysis highlighted the effect of genes related to development and organism growth. miRNA-seq analysis revealed 6-8 fold down regulation of mir-37-3p, mir-41-5p, mir-70-3p, and mir-75-3p. Our results demonstrate the effects of MeHg on specific transcripts encoding proteins in oxidative stress responses and in ER stress pathways. Pending confirmation of these transcript changes at protein levels, their association and dissociation characteristics with interaction partners, and integration of these signals, these findings indicate broad and dynamic mechanisms by which MeHg exerts its harmful effects.

miRNAs and their putative roles in the development and progression of Parkinson's disease

Small regulatory RNAs, such as miRNAs, are increasingly being recognized not only as regulators of developmental processes but contributors to pathological states. The number of miRNAs determined experimentally to be involved in Parkinson's disease (PD) development and progression is small and includes regulators of pathologic proteins, neurotrophic factors, and xenobiotic metabolizing enzymes. PD gene-association studies have also indicated miRNAs in the pathology. In this review, we present known miRNAs and their validated targets that contribute to PD development and progression. We also incorporate data mining methods to link additional miRNAs with non-experimentally validated targets and propose additional roles of miRNAs in neurodegenerative processes. Furthermore, we present the potential contribution of next-generation-sequencing approaches to elucidate mechanisms and etiology of PD through discovery of novel miRNAs and other non-coding RNA classes.

Uncovering new functions for microRNAs in Caenorhabditis elegans

In the nematode Caenorhabditis elegans, microRNA (miRNA) regulation of development was first observed in the striking abnormalities of lin-4 and let-7 loss of function mutants. However, after these first two miRNA mutant phenotypes were described, progress on the identification of miRNA functions in worms slowed considerably. Recent advances reveal new functions for miRNAs in embryonic and larval development as well as in the regulation of lifespan and stress response. Results from a combination of computational, biochemical, and genetic approaches have deepened our understanding of miRNA regulation of target mRNAs and support the hypothesis that miRNAs have an important role in ensuring the robustness of developmental and physiological pathways.