Computational prediction of microRNAs in Histoplasma capsulatum.

MicroRNAs (miRNAs) are small and non-coding RNAs that regulate gene expression through post-transcriptional regulation. Although, the standard miRNA repository, MiRBase, lists more than 200 organisms having miRNA mediated regulation mechanism and thousands of miRNAs, there is not enough information about miRNAs of fungal species. Considering that there are various fungal pathogens causing disease phenotypes, it is important to search for miRNAs of those organisms. The leading cause of endemic mycosis in the USA is a fungal disease known as histoplasmosis, which is resulted by infection with a fungal intracellular parasite, Histoplasma capsulatum (H. capsulatum). In this work, genomes of H. capsulatum strains NAm1 and G217B were explored for potential miRNA like sequences and structures. Through a complex workflow involving miRNA detection and target prediction, several miRNA candidates of H. capsulatum and their possible targets in human were identified. The results presented here indicate that H. capsulatum might be one of the fungal pathogens having a miRNA based post-transcriptional gene regulation mechanism and it might have a miRNA mediated host - parasite interaction with human.

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.

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.

Circular RNA-MicroRNA-MRNA interaction predictions in SARS-CoV-2 infection.

Different types of noncoding RNAs like microRNAs (miRNAs) and circular RNAs (circRNAs) have been shown to take part in various cellular processes including post-transcriptional gene regulation during infection. MiRNAs are expressed by more than 200 organisms ranging from viruses to higher eukaryotes. Since miRNAs seem to be involved in host-pathogen interactions, many studies attempted to identify whether human miRNAs could target severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) mRNAs as an antiviral defence mechanism. In this work, a machine learning based miRNA analysis workflow was developed to predict differential expression patterns of human miRNAs during SARS-CoV-2 infection. In order to obtain the graphical representation of miRNA hairpins, 36 features were defined based on the secondary structures. Moreover, potential targeting interactions between human circRNAs and miRNAs as well as human miRNAs and viral mRNAs were investigated.

Computational analysis of microRNA-mediated interactions in SARS-CoV-2 infection.

MicroRNAs (miRNAs) are post-transcriptional regulators of gene expression found in more than 200 diverse organisms. Although it is still not fully established if RNA viruses could generate miRNAs, there are examples of miRNA like sequences from RNA viruses with regulatory functions. In the case of Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2), there are several mechanisms that would make miRNAs impact the virus, like interfering with viral replication, translation and even modulating the host expression. In this study, we performed a machine learning based miRNA prediction analysis for the SARS-CoV-2 genome to identify miRNA-like hairpins and searched for potential miRNA-based interactions between the viral miRNAs and human genes and human miRNAs and viral genes. Overall, 950 hairpin structured sequences were extracted from the virus genome and based on the prediction results, 29 of them could be precursor miRNAs. Targeting analysis showed that 30 viral mature miRNA-like sequences could target 1,367 different human genes. PANTHER gene function analysis results indicated that viral derived miRNA candidates could target various human genes involved in crucial cellular processes including transcription, metabolism, defense system and several signaling pathways such as Wnt and EGFR signalings. Protein class-based grouping of targeted human genes showed that host transcription might be one of the main targets of the virus since 96 genes involved in transcriptional processes were potential targets of predicted viral miRNAs. For instance, basal transcription machinery elements including several components of human mediator complex (MED1, MED9, MED12L, MED19), basal transcription factors such as TAF4, TAF5, TAF7L and site-specific transcription factors such as STAT1 were found to be targeted. In addition, many known human miRNAs appeared to be able to target viral genes involved in viral life cycle such as S, M, N, E proteins and ORF1ab, ORF3a, ORF8, ORF7a and ORF10. Considering the fact that miRNA-based therapies have been paid attention, based on the findings of this study, comprehending mode of actions of miRNAs and their possible roles during SARS-CoV-2 infections could create new opportunities for the development and improvement of new therapeutics.

MicroRNA prediction based on 3D graphical representation of RNA secondary structures.

MicroRNAs (miRNAs) are posttranscriptional regulators of gene expression. While a miRNA can target hundreds of messenger RNA (mRNAs), an mRNA can be targeted by different miRNAs, not to mention that a single miRNA might have various binding sites in an mRNA sequence. Therefore, it is quite involved to investigate miRNAs experimentally. Thus, machine learning (ML) is frequently used to overcome such challenges. The key parts of a ML analysis largely depend on the quality of input data and the capacity of the features describing the data. Previously, more than 1000 features were suggested for miRNAs. Here, it is shown that using 36 features representing the RNA secondary structure and its dynamic 3D graphical representation provides up to 98% accuracy values. In this study, a new approach for ML-based miRNA prediction is proposed. Thousands of models are generated through classification of known human miRNAs and pseudohairpins with 3 classifiers: decision tree, naïve Bayes, and random forest. Although the method is based on human data, the best model was able to correctly assign 96% of nonhuman hairpins from MirGeneDB, suggesting that this approach might be useful for the analysis of miRNAs from other species.

Computational Prediction of Functional MicroRNA-mRNA Interactions.

Proteins have a strong influence on the phenotype and their aberrant expression leads to diseases. MicroRNAs (miRNAs) are short RNA sequences which posttranscriptionally regulate protein expression. This regulation is driven by miRNAs acting as recognition sequences for their target mRNAs within a larger regulatory machinery. A miRNA can have many target mRNAs and an mRNA can be targeted by many miRNAs which makes it difficult to experimentally discover all miRNA-mRNA interactions. Therefore, computational methods have been developed for miRNA detection and miRNA target prediction. An abundance of available computational tools makes selection difficult. Additionally, interactions are not currently the focus of investigation although they more accurately define the regulation than pre-miRNA detection or target prediction could perform alone. We define an interaction including the miRNA source and the mRNA target. We present computational methods allowing the investigation of these interactions as well as how they can be used to extend regulatory pathways. Finally, we present a list of points that should be taken into account when investigating miRNA-mRNA interactions. In the future, this may lead to better understanding of functional interactions which may pave the way for disease marker discovery and design of miRNA-based drugs.

Delineating the impact of machine learning elements in pre-microRNA detection.

Gene regulation modulates RNA expression via transcription factors. Post-transcriptional gene regulation in turn influences the amount of protein product through, for example, microRNAs (miRNAs). Experimental establishment of miRNAs and their effects is complicated and even futile when aiming to establish the entirety of miRNA target interactions. Therefore, computational approaches have been proposed. Many such tools rely on machine learning (ML) which involves example selection, feature extraction, model training, algorithm selection, and parameter optimization. Different ML algorithms have been used for model training on various example sets, more than 1,000 features describing pre-miRNAs have been proposed and different training and testing schemes have been used for model establishment. For pre-miRNA detection, negative examples cannot easily be established causing a problem for two class classification algorithms. There is also no consensus on what ML approach works best and, therefore, we set forth and established the impact of the different parts involved in ML on model performance. Furthermore, we established two new negative datasets and analyzed the impact of using them for training and testing. It was our aim to attach an order of importance to the parts involved in ML for pre-miRNA detection, but instead we found that all parts are intricately connected and their contributions cannot be easily untangled leading us to suggest that when attempting ML-based pre-miRNA detection many scenarios need to be explored.

On the performance of pre-microRNA detection algorithms.

MicroRNAs are crucial for post-transcriptional gene regulation, and their dysregulation has been associated with diseases like cancer and, therefore, their analysis has become popular. The experimental discovery of miRNAs is cumbersome and, thus, many computational tools have been proposed. Here we assess 13 ab initio pre-miRNA detection approaches using all relevant, published, and novel data sets while judging algorithm performance based on ten intrinsic performance measures. We present an extensible framework, izMiR, which allows for the unbiased comparison of existing algorithms, adding new ones, and combining multiple approaches into ensemble methods. In an exhaustive attempt, we condense the results of millions of computations and show that no method is clearly superior; however, we provide a guideline for biomedical researchers to select a tool. Finally, we demonstrate that combining all of the methods into one ensemble approach, for the first time, allows reliable purely computational pre-miRNA detection in large eukaryotic genomes.As the experimental discovery of microRNAs (miRNAs) is cumbersome, computational tools have been developed for the prediction of pre-miRNAs. Here the authors develop a framework to assess the performance of existing and novel pre-miRNA prediction tools and provide guidelines for selecting an appropriate approach for a given data set.

A Machine Learning Approach for MicroRNA Precursor Prediction in Retro-transcribing Virus Genomes.

Identification of microRNA (miRNA) precursors has seen increased efforts in recent years. The difficulty in experimental detection of pre-miRNAs increased the usage of computational approaches. Most of these approaches rely on machine learning especially classification. In order to achieve successful classification, many parameters need to be considered such as data quality, choice of classifier settings, and feature selection. For the latter one, we developed a distributed genetic algorithm on HTCondor to perform feature selection. Moreover, we employed two widely used classification algorithms libSVM and random forest with different settings to analyze the influence on the overall classification performance. In this study we analyzed 5 human retro virus genomes; Human endogenous retrovirus K113, Hepatitis B virus (strain ayw), Human T lymphotropic virus 1, Human T lymphotropic virus 2, Human immunodeficiency virus 2, and Human immunodeficiency virus 1. We then predicted pre-miRNAs by using the information from known virus and human pre-miRNAs. Our results indicate that these viruses produce novel unknown miRNA precursors which warrant further experimental validation.

Feature Selection Has a Large Impact on One-Class Classification Accuracy for MicroRNAs in Plants.

MicroRNAs (miRNAs) are short RNA sequences involved in posttranscriptional gene regulation. Their experimental analysis is complicated and, therefore, needs to be supplemented with computational miRNA detection. Currently computational miRNA detection is mainly performed using machine learning and in particular two-class classification. For machine learning, the miRNAs need to be parametrized and more than 700 features have been described. Positive training examples for machine learning are readily available, but negative data is hard to come by. Therefore, it seems prerogative to use one-class classification instead of two-class classification. Previously, we were able to almost reach two-class classification accuracy using one-class classifiers. In this work, we employ feature selection procedures in conjunction with one-class classification and show that there is up to 36% difference in accuracy among these feature selection methods. The best feature set allowed the training of a one-class classifier which achieved an average accuracy of ~95.6% thereby outperforming previous two-class-based plant miRNA detection approaches by about 0.5%. We believe that this can be improved upon in the future by rigorous filtering of the positive training examples and by improving current feature clustering algorithms to better target pre-miRNA feature selection.

The impact of feature selection on one and two-class classification performance for plant microRNAs.

MicroRNAs (miRNAs) are short nucleotide sequences that form a typical hairpin structure which is recognized by a complex enzyme machinery. It ultimately leads to the incorporation of 18-24 nt long mature miRNAs into RISC where they act as recognition keys to aid in regulation of target mRNAs. It is involved to determine miRNAs experimentally and, therefore, machine learning is used to complement such endeavors. The success of machine learning mostly depends on proper input data and appropriate features for parameterization of the data. Although, in general, two-class classification (TCC) is used in the field; because negative examples are hard to come by, one-class classification (OCC) has been tried for pre-miRNA detection. Since both positive and negative examples are currently somewhat limited, feature selection can prove to be vital for furthering the field of pre-miRNA detection. In this study, we compare the performance of OCC and TCC using eight feature selection methods and seven different plant species providing positive pre-miRNA examples. Feature selection was very successful for OCC where the best feature selection method achieved an average accuracy of 95.6%, thereby being ∼29% better than the worst method which achieved 66.9% accuracy. While the performance is comparable to TCC, which performs up to 3% better than OCC, TCC is much less affected by feature selection and its largest performance gap is ∼13% which only occurs for two of the feature selection methodologies. We conclude that feature selection is crucially important for OCC and that it can perform on par with TCC given the proper set of features.