miTAR: a hybrid deep learning-based approach for predicting miRNA targets

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.

Advances in applications of artificial intelligence algorithms for cancer-related miRNA research

MiRNAs are a class of small non-coding RNAs, which regulate gene expression post-transcriptionally by partial complementary base pairing. Aberrant miRNA expressions have been reported in tumor tissues and peripheral blood of cancer patients. In recent years, artificial intelligence algorithms such as machine learning and deep learning have been widely used in bioinformatic research. Compared to traditional bioinformatic tools, miRNA target prediction tools based on artificial intelligence algorithms have higher accuracy, and can successfully predict subcellular localization and redistribution of miRNAs to deepen our understanding. Additionally, the construction of clinical models based on artificial intelligence algorithms could significantly improve the mining efficiency of miRNA used as biomarkers. In this article, we summarize recent development of bioinformatic miRNA tools based on artificial intelligence algorithms, focusing on the potential of machine learning and deep learning in cancer-related miRNA research.

TEC-miTarget: enhancing microRNA target prediction based on deep learning of ribonucleic acid sequences

BACKGROUND

MicroRNAs play a critical role in regulating gene expression by binding to specific target sites within gene transcripts, making the identification of microRNA targets a prominent focus of research. Conventional experimental methods for identifying microRNA targets are both time-consuming and expensive, prompting the development of computational tools for target prediction. However, the existing computational tools exhibit limited performance in meeting the demands of practical applications, highlighting the need to improve the performance of microRNA target prediction models.

RESULTS

In this paper, we utilize the most popular natural language processing and computer vision technologies to propose a novel approach, called TEC-miTarget, for microRNA target prediction based on transformer encoder and convolutional neural networks. TEC-miTarget treats RNA sequences as a natural language and encodes them using a transformer encoder, a widely used encoder in natural language processing. It then combines the representations of a pair of microRNA and its candidate target site sequences into a contact map, which is a three-dimensional array similar to a multi-channel image. Therefore, the contact map's features are extracted using a four-layer convolutional neural network, enabling the prediction of interactions between microRNA and its candidate target sites. We applied a series of comparative experiments to demonstrate that TEC-miTarget significantly improves microRNA target prediction, compared with existing state-of-the-art models. Our approach is the first approach to perform comparisons with other approaches at both sequence and transcript levels. Furthermore, it is the first approach compared with both deep learning-based and seed-match-based methods. We first compared TEC-miTarget's performance with approaches at the sequence level, and our approach delivers substantial improvements in performance using the same datasets and evaluation metrics. Moreover, we utilized TEC-miTarget to predict microRNA targets in long mRNA sequences, which involves two steps: selecting candidate target site sequences and applying sequence-level predictions. We finally showed that TEC-miTarget outperforms other approaches at the transcript level, including the popular seed match methods widely used in previous years.

CONCLUSIONS

We propose a novel approach for predicting microRNA targets at both sequence and transcript levels, and demonstrate that our approach outperforms other methods based on deep learning or seed match. We also provide our approach as an easy-to-use software, TEC-miTarget, at https://github.com/tingpeng17/TEC-miTarget . Our results provide new perspectives for microRNA target prediction.

Identifying Human miRNA Target Sites via Learning the Interaction Patterns between miRNA and mRNA Segments

miRNAs (microRNAs) target specific mRNA (messenger RNA) sites to regulate their translation expression. Although miRNA targeting can rely on seed region base pairing, animal miRNAs, including human miRNAs, typically cooperate with several cofactors, leading to various noncanonical pairing rules. Therefore, identifying the binding sites of animal miRNAs remains challenging. Because experiments for mapping miRNA targets are costly, computational methods are preferred for extracting potential miRNA-mRNA fragment binding pairs first. However, existing prediction tools can have significant false positives due to the prevalent noncanonical miRNA binding behaviors and the information-biased training negative sets that were used while constructing these tools. To overcome these obstacles, we first prepared an information-balanced miRNA binding pair ground-truth data set. A miRNA-mRNA interaction-aware model was then designed to help identify miRNA binding events. On the test set, our model (auROC = 94.4%) outperformed existing models by at least 2.8% in auROC. Furthermore, we showed that this model can suggest potential binding patterns for miRNA-mRNA sequence interacting pairs. Finally, we made the prepared data sets and the designed model available at http://cosbi2.ee.ncku.edu.tw/mirna_binding/download.

Overview of Computational and Experimental Methods to Identify Tissue-Specific MicroRNA Targets

As ubiquitous posttranscriptional regulators of gene expression, microRNAs (miRNAs) play key roles in cell physiology and function across taxa. In the last two decades, we have gained a good understanding about miRNA biogenesis pathways, modes of action, and consequences of miRNA-mediated gene regulation. More recently, research has focused on exploring causes for miRNA dysregulation, miRNA-mediated crosstalk between genes and signaling pathways, and the role of miRNAs in disease.This chapter discusses methods for the identification of miRNA-target interactions and causes for tissue-specific miRNA-target regulation. Computational approaches for predicting miRNA target sites and assessing tissue-specific target regulation are discussed. Moreover, there is an emphasis on features that affect miRNA target recognition and how high-throughput sequencing protocols can help in assessing miRNA-mediated gene regulation on a genome-wide scale. In addition, this chapter introduces some experimental approaches for the validation of miRNA targets as well as web-based resources sharing predicted and validated miRNA-target interactions.

Small RNA Targets: Advances in Prediction Tools and High-Throughput Profiling

MicroRNAs (miRNAs) are an abundant class of small non-coding RNAs that regulate gene expression at the post-transcriptional level. They are suggested to be involved in most biological processes of the cell primarily by targeting messenger RNAs (mRNAs) for cleavage or translational repression. Their binding to their target sites is mediated by the Argonaute (AGO) family of proteins. Thus, miRNA target prediction is pivotal for research and clinical applications. Moreover, transfer-RNA-derived fragments (tRFs) and other types of small RNAs have been found to be potent regulators of Ago-mediated gene expression. Their role in mRNA regulation is still to be fully elucidated, and advancements in the computational prediction of their targets are in their infancy. To shed light on these complex RNA-RNA interactions, the availability of good quality high-throughput data and reliable computational methods is of utmost importance. Even though the arsenal of computational approaches in the field has been enriched in the last decade, there is still a degree of discrepancy between the results they yield. This review offers an overview of the relevant advancements in the field of bioinformatics and machine learning and summarizes the key strategies utilized for small RNA target prediction. Furthermore, we report the recent development of high-throughput sequencing technologies, and explore the role of non-miRNA AGO driver sequences.

Recent Deep Learning Methodology Development for RNA–RNA Interaction Prediction

Genetic regulation of organisms involves complicated RNA–RNA interactions (RRIs) among messenger RNA (mRNA), microRNA (miRNA), and long non-coding RNA (lncRNA). Detecting RRIs is beneficial for discovering biological mechanisms as well as designing new drugs. In recent years, with more and more experimentally verified RNA–RNA interactions being deposited into databases, statistical machine learning, especially recent deep-learning-based automatic algorithms, have been widely applied to RRI prediction with remarkable success. This paper first gives a brief introduction to the traditional machine learning methods applied on RRI prediction and benchmark databases for training the models, and then provides a recent methodology overview of deep learning models in the prediction of microRNA (miRNA)–mRNA interactions and long non-coding RNA (lncRNA)–miRNA interactions.

A deep learning method for miRNA/isomiR target detection

Accurate identification of microRNA (miRNA) targets at base-pair resolution has been an open problem for over a decade. The recent discovery of miRNA isoforms (isomiRs) adds more complexity to this problem. Despite the existence of many methods, none considers isomiRs, and their performance is still suboptimal. We hypothesize that by taking the isomiR–mRNA interactions into account and applying a deep learning model to study miRNA–mRNA interaction features, we may improve the accuracy of miRNA target predictions. We developed a deep learning tool called DMISO to capture the intricate features of miRNA/isomiR–mRNA interactions. Based on tenfold cross-validation, DMISO showed high precision (95%) and recall (90%). Evaluated on three independent datasets, DMISO had superior performance to five tools, including three popular conventional tools and two recently developed deep learning-based tools. By applying two popular feature interpretation strategies, we demonstrated the importance of the miRNA regions other than their seeds and the potential contribution of the RNA-binding motifs within miRNAs/isomiRs and mRNAs to the miRNA/isomiR–mRNA interactions.

Antagonistic regulatory effects of a single cis-acting expression quantitative trait locus between transcription and translation of the MRPL43 gene

Background

Heterogeneity of expression quantitative trait locus (eQTL) effects have been shown across gene expression processes. Knowledge on how to produce the heterogeneity is quite limited. This study aims to examine fluctuations in differential gene expression by alleles of sequence variants across expression processes.

Results

Genome-wide eQTL analyses with transcriptome-wide gene expression data revealed 20 cis-acting eQTLs associated simultaneously with mRNA expression, ribosome occupancy, and protein abundance. A 97 kb-long eQTL signal for mitochondrial ribosomal protein L43 (MRPL43) covered the gene, showing a heterogeneous effect size on gene products across expression stages. One allele of the eQTL was associated with increased mRNA expression and ribosome occupancy but decreased protein abundance. We examined the heterogeneity and found that the eQTL can be attributed to the independent functions of three nucleotide variants, with a strong linkage. NC_000010.11:g.100987606G > T, upstream of MRPL43, may regulate the binding affinity of transcription factors. NC_000010.11:g.100986746C > G, 3 bp from an MRPL43 splice donor site, may alter the splice site. NC_000010.11:g.100978794A > G, in the isoform with a long 3′-UTR, may strengthen the binding affinity of the microRNA. Individuals with the TGG haplotype at these three variants had higher levels of mRNA expression and ribosome occupancy than individuals with the GCA haplotype but lower protein levels, producing the flipped effect throughout the expression process.

Conclusions

These findings suggest that multiple functional variants in a linkage exert their regulatory functions at different points in the gene expression process, producing a complexity of single eQTLs.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12863-022-01057-7.

StackTADB: a stacking-based ensemble learning model for predicting the boundaries of topologically associating domains (TADs) accurately in fruit flies

Chromosome is composed of many distinct chromatin domains, referred to variably as topological domains or topologically associating domains (TADs). The domains are stable across different cell types and highly conserved across species, thus these chromatin domains have been considered as the basic units of chromosome folding and regarded as an important secondary structure in chromosome organization. However, the identification of TAD boundaries is still a great challenge due to the high cost and low resolution of Hi-C data or experiments. In this study, we propose a novel ensemble learning framework, termed as StackTADB, for predicting the boundaries of TADs. StackTADB integrates four base classifiers including Random Forest, Logistic Regression, K-NearestNeighbor and Support Vector Machine. From the analysis of a series of examinations on the data set in the previous study, it is concluded that StackTADB has optimal performance in six metrics, AUC, Accuracy, MCC, Precision, Recall and F1 score, and it is superior to the existing methods. In addition, the comparison of the performance of multiple features shows that Kmers-based features play an essential role in predicting TADs boundaries of fruit flies, and we also apply the SHapley Additive exPlanations (SHAP) framework to interpret the predictions of StackTADB to identify the reason why Kmers-based features are vital. The experimental results show that the subsequences matching the BEAF-32 motif play a crucial role in predicting the boundaries of TADs. The source code is freely available at https://github.com/HaoWuLab-Bioinformatics/StackTADB and the webserver of StackTADB is freely available at http://hwtad.sdu.edu.cn:8002/StackTADB.

Biological features between miRNAs and their targets are unveiled from deep learning models

MicroRNAs (miRNAs) are ~ 22 nucleotide ubiquitous gene regulators. They modulate a broad range of essential cellular processes linked to human health and diseases. Consequently, identifying miRNA targets and understanding how they function are critical for treating miRNA associated diseases. In our earlier work, a hybrid deep learning-based approach (miTAR) was developed for predicting miRNA targets. It performs substantially better than the existing methods. The approach integrates two major types of deep learning algorithms: convolutional neural networks (CNNs) and recurrent neural networks (RNNs). However, the features in miRNA:target interactions learned by miTAR have not been investigated. In the current study, we demonstrated that miTAR captures known features, including the involvement of seed region and the free energy, as well as multiple novel features, in the miRNA:target interactions. Interestingly, the CNN and RNN layers of the model perform differently at capturing the free energy feature: the units in RNN layer is more unique at capturing the feature but collectively the CNN layer is more efficient at capturing the feature. Although deep learning models are commonly thought “black-boxes”, our discoveries support that the biological features in miRNA:target can be unveiled from deep learning models, which will be beneficial to the understanding of the mechanisms in miRNA:target interactions.

Metabolomics and complementary techniques to investigate the plant phytochemical cosmos

Covering: up to 2021Plants and their associated microbial communities are known to produce millions of metabolites, a majority of which are still not characterized and are speculated to possess novel bioactive properties. In addition to their role in plant physiology, these metabolites are also relevant as existing and next-generation medicine candidates. Elucidation of the plant metabolite diversity is thus valuable for the successful exploitation of natural resources for humankind. Herein, we present a comprehensive review on recent metabolomics approaches to illuminate molecular networks in plants, including chemical isolation and enzymatic production as well as the modern metabolomics approaches such as stable isotope labeling, ultrahigh-resolution mass spectrometry, metabolome imaging (spatial metabolomics), single-cell analysis, cheminformatics, and computational mass spectrometry. Mass spectrometry-based strategies to characterize plant metabolomes through metabolite identification and annotation are described in detail. We also highlight the use of phytochemical genomics to mine genes associated with specialized metabolites' biosynthesis. Understanding the metabolic diversity through biotechnological advances is fundamental to elucidate the functions of the plant-derived specialized metabolome.