miR2Disease: a manually curated database for microRNA deregulation in human disease

Machine learning approaches for predicting the small molecule-miRNA associations: a comprehensive review

MicroRNAs (miRNAs) are evolutionarily conserved small regulatory elements that are ubiquitous in cells and are found to be abnormally expressed during the onset and progression of several human diseases. miRNAs are increasingly recognized as potential diagnostic and therapeutic targets that could be inhibited by small molecules (SMs). The knowledge of SM-miRNA associations (SMAs) is sparse, mainly because of the dynamic and less predictable 3D structures of miRNAs that restrict the high-throughput screening of SMs. Toward augmenting the costly and laborious experiments determining the SM-miRNA interactions, machine learning (ML) has emerged as a cost-effective and efficient platform. In this article, various aspects associated with the ML-guided predictions of SMAs are thoroughly reviewed. Firstly, a detailed account of the SMA data resources useful for algorithms training is provided, followed by an elaboration of various feature extraction methods and similarity measures utilized on SMs and miRNAs. Subsequent to a summary of the ML algorithms basics and a brief description of the performance measures, an exhaustive census of all the 32 ML-based SMA prediction methods developed so far is outlined. Distinctive features of these methods have been described by classifying them into six broad categories, namely, classical ML, deep learning, matrix factorization, network propagation, graph learning, and ensemble learning methods. Trend analyses are performed to investigate the patterns in ML algorithms usage and performance achievement in SMA prediction. Outlining key principles behind the up-to-date methodologies and comparing their accomplishments, this review offers valuable insights into critical areas for future research in ML-based SMA prediction.

Radiosensitization Following Valproic Acid and Gamma Rays in Anaplastic Thyroid Cancer Cells Increases the Expression of hsa-miR-26a-5p

BACKGROUND

Anaplastic thyroid cancer (ATC) is a rare lethal human malignancy with a poor prognosis. Multimodality treatment, including radiotherapy, is recommended to improve local control and survival. Valproic acid (VA) is a clinically available anticonvulsant and histone deacetylase inhibitor with a well-documented side effect profile. Furthermore, VA radiosensitizes various cancer cells, including thyroid cancer. MicroRNAs (miRs) are deregulated in several cancers and may modulate radiation response. Therefore, the aim of this study was to analyze the effect of VA combined with gamma radiation in radioresistant ATC cells at the expression level of miRs.

METHODS

ATC cells (8505c and KTC-2) were VA-treated and gamma-irradiated (2 Gy). The expression profile of miRs in 8505c was evaluated by microarray analysis 4 h after irradiation. Selected miRs were validated by RT-qPCR in both types of ATC cells.

RESULTS

We observed that after combined VA and gamma irradiation treatment, 8505c cells showed 109 differentially expressed miRs as compared to irradiated cells alone. These miRs exhibited a radiosensitization profile highlighted by upregulation of hsa-miR-26a-5p, which is usually downregulated in aggressive thyroid cancers. Moreover, hsa-miR-27a-3p and hsa-miR-486-5p, which are often deregulated in thyroid neoplasms, were downregulated after irradiation and VA treatment, respectively. The expression level of these three miRs was validated in 8505c and KTC-2 cells after treatments.

CONCLUSION

The regulated miRs by VA and gamma irradiation reveal a novel miR expression profile with potential to be further studied in the radio-induced response and radiosensitization of ATC cells.

Enhancing lncRNA-disease associations predictions by optimizing similarity on multiple heterogeneous networks

Focusing on the problem about predicting long non-coding RNA(lncRNA)-disease associations, this article introduces an improved random walk with restart(RWR) model by optimizing similarity on multiple heterogeneous networks, referred to as OS-LDA. Most existing models for constructing heterogeneous networks only consider two types of networks(disease and lncRNA), neglecting the valuable information from other networks. Furthermore the construction of an accurate and reasonable similarity network is crucial to the effectiveness of model. This paper considers four types of networks and focuses on improving and optimizing the similarity framework of network to enhance the prediction capabilities of the model. Firstly, a new approach for measuring disease semantic similarity which combines the advantages of two conventional methods is introduced. Secondly, to overcome the sparsity of disease semantic similarity matrix, this paper proposes an improved measure based on the penalty factor, thereby making it more suitable to measuring similarity between different diseases. In addition, multiple interaction profiles are taken into account for the computation of Gaussian similarity. Finally, this paper constructs precise multilayer heterogeneous similarity networks (lncRNA-gene-miRNA-disease) and the random walk with restart method is implemented on heterogeneous networks to predict disease-related lncRNAs. The average AUC of OS-LDA reaches 0.9876 by ten-fold cross validation, outperforming several other models and indicating the effectiveness of the algorithm.

Integrative analysis of miRNA expression profiles reveals distinct and common molecular mechanisms underlying broad diagnostic groups of severe mental disorders

Micro RNAs (miRNAs) play a crucial role as regulators of various biological processes and have been implicated in the pathogenesis of mental disorders such as schizophrenia and bipolar disorders. In this study, we investigate the expression patterns of miRNAs in the PsyCourse Study (n = 1786), contrasting three broad diagnostic groups: Psychotic (Schizophrenia-spectrum disorders), Affective (Bipolar Disorder I, II and recurrent Depression), and neurotypic healthy individuals. Through comprehensive analyses, including differential miRNA expression, miRNA transcriptome-wide association study (TWAS), and predictive modelling, we identified multiple miRNAs unique to Psychotic and Affective groups as well as shared by both. Furthermore, we performed integrative analysis to identify the target genes of the dysregulated miRNAs and elucidate their potential roles in psychosis. Our findings reveal significant alterations of multiple miRNAs such as miR-584-3p and miR-99b-5p across the studied diagnostic groups, highlighting their role as molecular correlates. Additionally, the miRNA TWAS analysis discovered previously known and novel genetically dysregulated miRNAs confirming the relevance in the etiology of the diagnostic groups. Importantly, novel factors and putative molecular mechanisms underlying these groups were uncovered through the integration of miRNA-target gene interactions. This comprehensive investigation provides valuable insights into the molecular underpinnings of severe mental disorders, shedding light on the complex regulatory networks involving miRNAs.

Comparative analysis of miRNA-mRNA interaction prediction tools based on experimental head and neck cancer data

BACKGROUND

We evaluated the performance of TargetScan, miRDB, and miRWalk for predicting miRNA-mRNA interactions in HNSCC. Based on clinical tumor and cancer-free tissue data, miRWalk emerged as the most comprehensive tool. Validation using NanoString technology and MiRTarBase confirmed key predictions, highlighting the important roles of the PI3K-Akt and Wnt pathways. This study underscores the importance of integrating bioinformatics and experimental data to better understand HNSCC.

BACKGROUND

■ miRWalk had the highest predicted interactions and validated miRNA networks in HNSCC.

BACKGROUND

■ Around 3.3% of interactions overlapped across tools, emphasizing the need for multitool approaches.

BACKGROUND

■ Dysregulated genes and miRNAs were tied to cancerdriving PI3K-Akt and Wnt pathways.

BACKGROUND

■ The validated approach highlights the importance of integrating computational and molecular data.

OBJECTIVE

Head and neck squamous cell carcinoma (HNSCC) has a poor prognosis largely due to late diagnosis and a lack of reliable biomarkers. MicroRNAs (miRNAs), small non-coding RNAs that regulate gene expression, are promising biomarkers for HNSCC. This study evaluated miRNA-mRNA interactions in HNSCC using conventional computational tools and validated the results using molecular data.

METHODS

We compared three miRNA-mRNA interaction prediction tools, TargetScan, miRDB, and miRWalk, using differentially expressed miRNAs and mRNAs from HNSCC and cancer-free tissues. NanoString nCounter was used to measure miRNA and mRNA expression and the miRTarBase database was used to validate the predicted miRNA-mRNA interactions.

RESULTS

TargetScan and miRWalk provide a comprehensive overview of potential interactions, whereas miRDB provides functional insights. Our results identified 77 and 154 differentially expressed miRNAs and mRNAs in HNSCC, respectively. miRWalk predicted the highest number of miRNA-mRNA interactions, followed by miRDB and TargetScan. Only 3.3% of interactions were common among the tools. The MiRTarBase analysis confirmed a small subset of the predictions. Biological pathway analysis highlighted the dysregulation of PI3K-Akt and Wnt signaling; miRWalk was the best for elucidating how miRNAs modulate target mRNAs in these key pathways during HNSCC progression.

CONCLUSION

miRWalk emerged as the most robust tool for predicting miRNA-mRNA interactions. Our findings highlight the importance of integrating bioinformatics predictions with experimental data to better understand the regulatory networks in HNSCC and identify potential biomarkers for diagnosis and therapy.

MFF-nDA: A Computational Model for ncRNA-Disease Association Prediction Based on Multimodule Fusion

Noncoding RNAs(ncRNAs), including piwi-interacting RNA(piRNA), long noncoding RNA(lncRNA), microRNA(miRNA), small nucleolar RNA(snoRNA), and circular RNA(circRNA), contribute significantly to gene expression regulation and serve as key factors in disease association studies and health-related exploration. Accurate prediction of ncRNA-disease associations is crucial for elucidating disease mechanisms and advancing therapeutic development. Recently, computational models based on a graph neural network have extensively emerged for identifying associations among various ncRNAs and diseases. However, existing computational models have not fully utilized integrative information on ncRNs and diseases, and reliance on GNN-based models alone may be limited in performance due to oversmoothing issues. On the other hand, existing models are mainly targeted at a specific type of ncRNA and may not be applicable to most ncRNAs. Therefore, to overcome these limitations, we propound a computational model MFF-nDA based on multimodule fusion. Specifically, we first introduce five types of similarity network information, including three types of ncRNA and two types of disease similarity information, in order to fully explore and optimize the multisource feature information on these entities. Subsequently, we establish three modules: heterogeneous network representation module based on Transformer, association network representation module based on graph convolutional network (GCN), and topological structure representation module based on graph attention network (GAT), which capture diverse features of nodes in heterogeneous networks and topological structure information reflected in association networks. The complementary effects of the three modules also help relieve the oversmoothing issue to some extent. By leveraging the multimodule fusion learning to comprehensively capture the diverse features of these entities, our model outperforms the available state-of-the-art methods, achieving an AUC greater than 0.9000 for each dataset. This demonstrates the highest predictive performance, making it a valuable tool for identifying potential ncRNA associated with diseases. The code of MFF-nDA can be accessed at https://github.com/Jack-Cxy/MFF-nDA.

PCMR: a comprehensive precancerous molecular resource

Early detection and intervention of precancerous lesions are crucial in reducing cancer morbidity and mortality. Comprehensive analysis of genomic, transcriptomic, proteomic and epigenomic alterations can provide insights into the early stages of carcinogenesis. However, the lacke of an integrated, well-curated data resource of molecular signatures limits our understanding of precancerous processes. Here, we introduce a comprehensive PreCancerous Molecular Resource (PCMR), which compiles 25,828 molecular profiles of precancerous samples paired with normal or malignant counterparts. These profiles cover precancerous lesions of 35 cancer types across 20 organs and tissues, derived from tissue samples, liquid biopsies, cell lines and organoids, with data from transcriptomics, proteomics and epigenomics. PCMR includes 62,566 precancer-gene associations derived from differential analysis and text-mining using the ChatGPT large language model. We examined PCMR dataset reliability and significance by the authoritative precancerous molecular signature, along with its biological and clinical relevance. Overall, PCMR will serve as a valuable resource for advancing precancer research and ultimately improving patient outcomes.

GONNMDA: A Ordered Message Passing GNN Approach for miRNA-Disease Association Prediction

Small non-coding molecules known as microRNAs (miRNAs) play a critical role in disease diagnosis, treatment, and prognosis evaluation. Traditional wet-lab methods for validating miRNA-disease associations are often time-consuming and inefficient. With the advancement of high-throughput sequencing technologies, deep learning methods have become effective tools for uncovering potential patterns in miRNA-disease associations and revealing novel biological insights. Most of the existing approaches focus primarily on individual molecular behavior, overlooking interactions at the multi-molecular level. Conventional graph neural network (GNN) models struggle to generalize to heterogeneous graphs, and as network depth increases, node representations become indistinguishable due to over-smoothing, resulting in reduced predictive performance. GONNMDA first integrates similarity features from multiple data sources and applies noise reduction to obtain a reconstructed, comprehensive similarity representation. It then constructs heterogeneous graphs and applies a root-tree hierarchical alignment, along with an ordered gating message-passing mechanism, effectively addressing the challenges of heterogeneity and over-smoothing. Finally, a multilayer perceptron is employed to produce the final association predictions. To evaluate the effectiveness of GONNMDA, we conducted extensive experiments where the model achieved an AUC of 95.49% and an AUPR of 95.32%. The results demonstrate that GONNMDA outperforms several recent state-of-the-art methods. In addition, case studies and survival analyses on three common human cancers-breast cancer, rectal cancer, and lung cancer-further validate the effectiveness and reliability of GONNMDA in predicting miRNA-disease associations.

IRPCA: An Interpretable Robust Principal Component Analysis Framework for Inferring miRNA-Drug Associations

Recent evidence indicates that microribonucleic acids (miRNAs) are crucial in modulating drug sensitivity by orchestrating the expression of genes involved in drug metabolism and its pharmacological effects. Existing predictive methods struggle to extract features related to miRNAs and drugs, often overlooking the significance of data noise and the limitations of using a single similarity measure. To address these limitations, we propose an interpretable robust principal component analysis framework (IRPCA). IRPCA enhances the robustness of the model by employing a nonconvex low-rank approximation, thereby offering greater flexibility. Interpretability is ensured by analyzing low-rank matrix decomposition, which clarifies how miRNAs interact with drugs. Gaussian interaction profile kernel (GIPK) similarities are introduced to compute integrated similarities between miRNAs and drugs, addressing the issue of the single similarity feature. IRPCA is subsequently utilized to extract pertinent features, and a fully connected neural network is employed to generate the ultimate prediction scores. To assess the efficacy of IRPCA, we implemented 5-fold cross-validation (CV), which outperformed other leading methods, achieving the highest area under the curve (AUC) value of 0.9653. Additionally, case studies provide additional evidence supporting the efficacy of IRPCA.

Understanding the Role of MicroRNAs in Congenital Tooth Agenesis: A Multi-omics Integration

This study employs a comprehensive multi-omics approach to investigate the regulatory roles of specific microRNAs (miRNAs) in Congenital Tooth Agenesis (CTA). A total of 58 miRNAs associated with tooth diseases, cancer, and bone development were initially identified through a literature review and analyzed using bioinformatics. Based on target prediction and network analysis, eight miRNAs with strong connectivity and common target genes were shortlisted for further investigation. Blood samples from 10 CTA patients and 5 healthy controls were analyzed for miRNA expression using stem-loop RT-PCR. Four miRNAs-hsa-miR-218-5p, hsa-miR-15b-5p, hsa-miR-200b-3p, and hsa-let-7a-3p-were identified as significantly differentially expressed, marking their first reported involvement in CTA. Notably, hsa-miR-218-5p and hsa-let-7a-3p emerged as novel regulators with no prior associations with CTA or tooth development. To address the limitations of a small sample size, a multi-omics strategy was employed to validate these findings, integrating miRNA expression data with whole exome sequencing (WES), gene expression panels, and metabolomic profiling. The analysis confirmed the association of these four miRNAs with CTA and highlighted their involvement in critical biological pathways such as Wnt signaling, FGF signaling, and PI3 kinase pathways, which are essential for cellular proliferation, differentiation, and tissue morphogenesis. Importantly, the identification of these miRNAs in blood samples, rather than traditional dental tissues, highlights a minimally invasive approach that could aid in the early detection, therapeutic targeting, and personalized management of dental anomalies.

DeepWalk-Based Graph Embeddings for miRNA-Disease Association Prediction Using Deep Neural Network

Background: In recent years, micro ribonucleic acids (miRNAs) have been recognized as key regulators in numerous biological processes, particularly in the development and progression of diseases. As a result, extensive research has focused on uncovering the critical involvement of miRNAs in disease mechanisms to better comprehend the underlying causes of human diseases. Despite these efforts, relying solely on biological experiments to identify miRNA-disease associations is both time-consuming and costly, making it an impractical approach for large-scale studies. Methods: In this paper, we propose a novel DeepWalk-based graph embedding method for predicting miRNA-disease association (DWMDA). Using DeepWalk, we extracted meaningful low-dimensional vectors from the miRNA and disease networks. Then, we applied a deep neural network to identify miRNA-disease associations using the low-dimensional vectors of miRNAs and diseases extracted via DeepWalk. Results: An ablation study was conducted to assess the proposed graph embedding modules. Furthermore, DWMDA demonstrates exceptional performance in two major cancer case studies (breast and lung), with results based on statistically robust measures, further emphasizing its reliability as a method for identifying associations between miRNAs and diseases. Conclusions: We expect that our model will not only facilitate the accurate prediction of disease-associated miRNAs but also serve as a generalizable framework for exploring interactions among various biological entities.

Association of MiRNA Polymorphisms Involved in the PI3K/ATK/GSK3β Pathway with T2DM in a Chinese Population

Background

Single nucleotide polymorphisms (SNPs) in miRNA genes can influence the expression of miRNAs that modulate the PI3K/AKT/GSK3β pathway and play crucial roles in type 2 diabetes mellitus (T2DM) susceptibility. The purpose of this study was to investigate the association of SNPs in miRNA genes targeting the PI3K/AKT/GSK3β pathway with T2DM.

Methods

This case-control study included 1,416 subjects with T2DM and 1,694 non-diabetics. Eleven SNPs in miRNA genes (rs895819 in miR-27a, rs11888095 in miR-128a, rs2292832 in miR-149, rs6502892 in miR-22, rs13283671 in miR-31, rs1076063 and rs1076064 in miR-378a, rs10061133 in miR-449b, rs3746444 in miR-499a and rs678956 and rs476364 in miR-326) involved in PI3K/AKT/GSK3β pathway were genotyped by TaqMan Genotyping Assay, and the associations of these SNPs with T2DM were analyzed using online SHesis and SNPstats.

Results

The results showed that miR-378a rs1076064 G allele could be a protective factor against T2DM (p<0.001, OR=0.828; 95% CI:0.749-0.916), whereas the miR-31 rs13283671 C allele could increase the risk of developing T2DM (p=0.003, OR=1.193; 95% CI:1.060-1.342). In addition, the miR-378a rs1076063A-rs1076064G haplotype could be a protective against T2DM (p<0.001, OR=0.731; 95% CI:0.649-0.824). According to inheritance mode analysis, compared with the AA-AG genotype, the GG genotype of rs1076064 showed a protective effect in T2DM in the recessive mode (p<0.01, OR=0.71; 95% CI: 0.59-0.84). For rs13283671, compared with the TT genotype, the CT-CC genotype showed a risk effect in T2DM in the dominant inheritance model (p<0.01, OR=1.29; 95% CI: 1.12-1.49). Genotype-Tissue Expression (GTEx) Portal database analysis showed that miR-31 rs13283671 CT and CC genotypes had lower AKT expression than TT genotypes.

Conclusion

In conclusion, rs13283671 in miR-31 and rs1076064 in miR-378a involved in the PI3K/AKT/GSK3β pathway were associated with T2DM susceptibility in a Chinese population.

Exosomal insights into ovarian cancer stem cells: revealing the molecular hubs

Ovarian cancer is a deadly disease, often diagnosed at advanced stages due to a lack of reliable biomarkers. Exosomes, which carry a variety of molecules such as proteins, lipids, DNA, and non-coding RNAs, have recently emerged as promising tools for early cancer detection. While exosomes have been studied in various cancer types, comprehensive network analyses of exosome proteins in ovarian cancer remain limited. In this study, we used a protein-protein interaction (PPI) network. Using the Clustermaker2 app and the MCODE algorithm, we identified six significant clusters within the network, highlighting regions involved in functional pathways. A four-fold algorithmic approach, including MCC, DMNC, Degree, and EPC, identified 12 common hub genes. STRING analysis and visualization techniques provided a detailed understanding of the biological processes associated with these hub genes. Notably, 91.7% of the identified hub genes were involved in translational processes, showing an important role in protein synthesis regulation in ovarian cancer. In addition, we identified the miRNAs and LncRNAs carried by ovarian cancer exosomes. These findings highlight potential biomarkers for early detection and therapeutic targets.

RNA sequence analysis landscape: A comprehensive review of task types, databases, datasets, word embedding methods, and language models

Deciphering information of RNA sequences reveals their diverse roles in living organisms, including gene regulation and protein synthesis. Aberrations in RNA sequence such as dysregulation and mutations can drive a diverse spectrum of diseases including cancers, genetic disorders, and neurodegenerative conditions. Furthermore, researchers are harnessing RNA's therapeutic potential for transforming traditional treatment paradigms into personalized therapies through the development of RNA-based drugs and gene therapies. To gain insights of biological functions and to detect diseases at early stages and develop potent therapeutics, researchers are performing diverse types RNA sequence analysis tasks. RNA sequence analysis through conventional wet-lab methods is expensive, time-consuming and error prone. To enable large-scale RNA sequence analysis, empowerment of wet-lab experimental methods with Artificial Intelligence (AI) applications necessitates scientists to have a comprehensive knowledge of both DNA and AI fields. While molecular biologists encounter challenges in understanding AI methods, computer scientists often lack basic foundations of RNA sequence analysis tasks. Considering the absence of a comprehensive literature that bridges this research gap and promotes the development of AI-driven RNA sequence analysis applications, the contributions of this manuscript are manifold: It equips AI researchers with biological foundations of 47 distinct RNA sequence analysis tasks. It sets a stage for development of benchmark datasets related to 47 distinct RNA sequence analysis tasks by facilitating cruxes of 64 different biological databases. It presents word embeddings and language models applications across 47 distinct RNA sequence analysis tasks. It streamlines the development of new predictors by providing a comprehensive survey of 58 word embeddings and 70 language models based predictive pipelines performance values as well as top performing traditional sequence encoding based predictors and their performances across 47 RNA sequence analysis tasks.

Predicting microRNA target genes using pan-cancer correlation patterns

The interaction relationship between miRNAs and genes is important as miRNAs play a crucial role in regulating gene expression. In the literature, several databases have been constructed to curate known miRNA target genes, which are valuable resources but likely only represent a small fraction of all miRNA-gene interactions. In this study, we constructed machine learning models to predict miRNA target genes that have not been previously reported. Using the miRNA and gene expression data from TCGA, we performed a correlation analysis between all miRNAs and all genes across multiple cancer types. The correlations served as features to describe each miRNA-gene pair. Using the existing databases of curated miRNA targets, we labeled the miRNA-gene pairs, and trained machine learning models to predict novel miRNA-gene interactions. For the miRNA-gene pairs that were consistently predicted across the models, we called them significant miRNA-gene pairs. Using held-out miRNA target databases and a literature survey, we validated 5.5% of the predicted significant miRNA-gene pairs. The remaining predicted miRNA-gene pairs could serve as hypotheses for experimental validation. Additionally, we explored several additional datasets that provided gene expression data before and after a specific miRNA perturbation and observed consistency between the correlation direction of predicted miRNA-gene pairs and their regulatory patterns. Together, this analysis revealed a novel framework for uncovering previously unidentified miRNA-gene relationships, enhancing the collective comprehension of miRNA-mediated gene regulation.

Graph Convolutional Network with Neural Collaborative Filtering for Predicting miRNA-Disease Association

Background: Over the past few decades, micro ribonucleic acids (miRNAs) have been shown to play significant roles in various biological processes, including disease incidence. Therefore, much effort has been devoted to discovering the pivotal roles of miRNAs in disease incidence to understand the underlying pathogenesis of human diseases. However, identifying miRNA-disease associations using biological experiments is inefficient in terms of cost and time. Methods: Here, we discuss a novel machine-learning model that effectively predicts disease-related miRNAs using a graph convolutional neural network with neural collaborative filtering (GCNCF). By applying the graph convolutional neural network, we could effectively capture important miRNAs and disease feature vectors present in the network while preserving the network structure. By exploiting neural collaborative filtering, miRNAs and disease feature vectors were effectively learned through matrix factorization and deep learning, and disease-related miRNAs were identified. Results: Extensive experimental results based on area under the curve (AUC) scores (0.9216 and 0.9018) demonstrated the superiority of our model over previous models. Conclusions: We anticipate that our model could not only serve as an effective tool for predicting disease-related miRNAs but could be employed as a universal computational framework for inferring relationships across biological entities.

CLHGNNMDA: Hypergraph Neural Network Model Enhanced by Contrastive Learning for miRNA-Disease Association Prediction

Numerous biological experiments have demonstrated that microRNA (miRNA) is involved in gene regulation within cells, and mutations and abnormal expression of miRNA can cause a myriad of intricate diseases. Forecasting the association between miRNA and diseases can enhance disease prevention and treatment and accelerate drug research, which holds considerable importance for the development of clinical medicine and drug research. This investigation introduces a contrastive learning-augmented hypergraph neural network model, termed CLHGNNMDA, aimed at predicting associations between miRNAs and diseases. Initially, CLHGNNMDA constructs multiple hypergraphs by leveraging diverse similarity metrics related to miRNAs and diseases. Subsequently, hypergraph convolution is applied to each hypergraph to extract feature representations for nodes and hyperedges. Following this, autoencoders are employed to reconstruct information regarding the feature representations of nodes and hyperedges and to integrate various features of miRNAs and diseases extracted from each hypergraph. Finally, a joint contrastive loss function is utilized to refine the model and optimize its parameters. The CLHGNNMDA framework employs multi-hypergraph contrastive learning for the construction of a contrastive loss function. This approach takes into account inter-view interactions and upholds the principle of consistency, thereby augmenting the model's representational efficacy. The results obtained from fivefold cross-validation substantiate that the CLHGNNMDA algorithm achieves a mean area under the receiver operating characteristic curve of 0.9635 and a mean area under the precision-recall curve of 0.9656. These metrics are notably superior to those attained by contemporary state-of-the-art methodologies.

Modeling ncRNA Synergistic Regulation in Cancer

Cancer seriously threatens human life and health, and the structure and function of genes within cancer cells have changed relative to normal cells. Essentially, cancer is a polygenic disorder, and the core of its occurrence and development is caused by polygenic synergy. Non-coding RNAs (ncRNAs) act as regulators to modulate gene expression levels, and they provide theoretical basis and new technology for the diagnosis and preventive treatment of cancer. However, the study of ncRNA regulation and its role as biomarkers in cancer remain largely unearthed. Driven by multi-omics data, an abundance of computational methods, tools, and databases have been developed for predicting ncRNA-cancer association/causality, inferring ncRNA regulation, and modeling ncRNA synergistic regulation. This chapter aims to provide a comprehensive perspective of modeling ncRNA synergistic regulation. Since the ncRNAs involved in cancer contribute to modeling cancer-associated ncRNA synergistic regulation, we first review the databases and tools of cancer-related ncRNAs. Then we investigate the existing tools or methods for modeling ncRNA-directed and ncRNA-mediated regulation. In addition, we survey the available computational tools or methods for modeling ncRNA synergistic regulation, including synergistic interaction and synergistic competition. Finally, we discuss the future directions and challenges in modeling ncRNA synergistic regulation.

Prediction of miRNA-disease associations based on PCA and cascade forest

BACKGROUND

As a key non-coding RNA molecule, miRNA profoundly affects gene expression regulation and connects to the pathological processes of several kinds of human diseases. However, conventional experimental methods for validating miRNA-disease associations are laborious. Consequently, the development of efficient and reliable computational prediction models is crucial for the identification and validation of these associations.

RESULTS

In this research, we developed the PCACFMDA method to predict the potential associations between miRNAs and diseases. To construct a multidimensional feature matrix, we consider the fusion similarities of miRNA and disease and miRNA-disease pairs. We then use principal component analysis(PCA) to reduce data complexity and extract low-dimensional features. Subsequently, a tuned cascade forest is used to mine the features and output prediction scores deeply. The results of the 5-fold cross-validation using the HMDD v2.0 database indicate that the PCACFMDA algorithm achieved an AUC of 98.56%. Additionally, we perform case studies on breast, esophageal and lung neoplasms. The findings revealed that the top 50 miRNAs most strongly linked to each disease have been validated.

CONCLUSIONS

Based on PCA and optimized cascade forests, we propose the PCACFMDA model for predicting undiscovered miRNA-disease associations. The experimental results demonstrate superior prediction performance and commendable stability. Consequently, the PCACFMDA is a potent instrument for in-depth exploration of miRNA-disease associations.

Pivotal Role of miRNA-lncRNA Interactions in Human Diseases

New technologies have shown that most of the genome comprises transcripts that cannot code for proteins and are referred to as non-coding RNAs (ncRNAs). Some ncRNAs, like long non-coding RNAs (lncRNAs) and microRNAs (miRNAs), are of substantial interest because of their critical function in controlling genes and numerous biological activities. The expression levels and function of miRNAs and lncRNAs are rigorously monitored throughout developmental processes and the maintenance of physiological homeostasis. Due to their critical roles, any dysregulation or changes in their expression can significantly influence the pathogenesis of various human diseases. The interactions between miRNAs and lncRNAs have been found to influence gene expression in various ways. These interactions significantly influence the understanding of disease etiology, cellular processes, and potential therapeutic targets. Different experimental and in silico methods can be used to investigate miRNA-lncRNA interactions. By aiding the elucidation of miRNA-lncRNA interactions and deepening the understanding of post-transcriptional gene regulation, researchers can open a new window for designing hypotheses, conducting experiments, and discovering methods for diagnosing and treating complex human diseases. This review briefly summarizes miRNA and lncRNA functions, discusses their interaction mechanisms, and examines the experimental and computational methods used to study these interactions. Additionally, we highlight significant studies on lncRNA and miRNA interactions in various diseases from 2000 to 2024, using the academic research databases such as PubMed, Google Scholar, ScienceDirect, and Scopus.

The 2024 Nobel Prize in Physiology or Medicine: microRNA Takes Center Stage

The Non-coding Journal Editorial Board Members would like to congratulate Victor Ambros and Gary Ruvkun, who were jointly awarded the 2024 Nobel Prize in Physiology or Medicine for their groundbreaking discovery of microRNAs and the role of microRNAs in post-transcriptional gene regulation, uncovering a previously unknown layer of gene control in eukaryotes [...].

miRNA genetic variations associated with the predisposition of oral squamous cell carcinoma in central Indian population

The disease burden of Oral Squamous Cell Carcinoma (OSCC) is rising day-by-day and is expected to rise 62 % through 2035. The chewing of tobacco, areca nut, and betel leaf, poor oral hygiene, and chronic infection are common risk factors of OSCC, but genetic and epigenetic factors also contribute equally. MicroRNAs (miRNAs) are comprised of small, non-coding endogenous RNA that regulate a plethora of biological activities by targeting messenger RNA through degradation or inhibition. Single Nucleotide Polymorphisms (SNPs) in miRNA genes can regulate the development and progression of OSCC. The present study aimed to determine the association between SNPs in miRNA genes (miRSNPs) with the risk of OSCC. A case-control study involving 225 histo-pathologically confirmed OSCC cases and 225 healthy controls was conducted, where 25 miRSNPs were analyzed by iPLEX MassArray analysis. A SNP rs12220909 in MIR4293 showed a highly protective effect (CC vs GG, OR = 0.0431, 95%CI = 0.005-0.323, p = 3e-6). Whereas three SNPs, namely, rs4705342 in MIR143 (CC vs TT, OR = 2.25, 95%CI = 2.00-2.53, p = 0.0008), rs531564 in MIR124 (CC vs GG, OR = 24.18, 95%CI = 3.22-181.37, p = 3e-6), and rs3746444 in MIR499 (AA vs GG, OR = 2.01, 95%CI = 1.32-3.05, p = 0.001) were significantly associated with a higher risk of OSCC. Additionally, NanoString-based nCounter miRNA expression profiling revealed that miR-499a (Log2FC = -1.07), and miR-143 (Log2FC = -1.56) were aberrantly expressed in OSCC tissue. Taken together, the above miSNPs may contribute to the high incidence of OSCC in central India. However, further studies with large cohorts and ethnic stratification are required to validate our findings.

Predicting miRNA-Disease Associations Based on Spectral Graph Transformer With Dynamic Attention and Regularization

Extensive research indicates that microRNAs (miRNAs) play a crucial role in the analysis of complex human diseases. Recently, numerous methods utilizing graph neural networks have been developed to investigate the complex relationships between miRNAs and diseases. However, these methods often face challenges in terms of overall effectiveness and are sensitive to node positioning. To address these issues, the researchers introduce DARSFormer, an advanced deep learning model that integrates dynamic attention mechanisms with a spectral graph Transformer effectively. In the DARSFormer model, a miRNA-disease heterogeneous network is constructed initially. This network undergoes spectral decomposition into eigenvalues and eigenvectors, with the eigenvalue scalars being mapped into a vector space subsequently. An orthogonal graph neural network is employed to refine the parameter matrix. The enhanced features are then input into a graph Transformer, which utilizes a dynamic attention mechanism to amalgamate features by aggregating the enhanced neighbor features of miRNA and disease nodes. A projection layer is subsequently utilized to derive the association scores between miRNAs and diseases. The performance of DARSFormer in predicting miRNA-disease associations (MDAs) is exemplary. It achieves an AUC of 94.18% in a five-fold cross-validation on the HMDD v2.0 database. Similarly, on HMDD v3.2, it records an AUC of 95.27%. Case studies involving colorectal, esophageal, and prostate tumors confirm 27, 28, and 26 of the top 30 associated miRNAs against the dbDEMC and miR2Disease databases, respectively.

Investigating gene expression datasets of hippocampus tissue to discover Alzheimer's disease-associated molecular markers

BACKGROUND

Alzheimer's disease (AD) is an advancing neurodegenerative disorder distinguished by the formation of amyloid plaques and neurofibrillary tangles in the human brain. Nevertheless, the lack of peripheral biomarkers that can detect the development of AD remains a significant limitation.

OBJECTIVE

The main aim of this work was to discover the molecular markers associated with AD.

METHODS

We conducted a comprehensive microarray analysis of gene expression data from hippocampus tissue in AD patients and control samples using three microarray datasets (GSE1297, GSE28146, and GSE29378) collected from Gene Expression Omnibus (GEO). The datasets were pre-processed and normalized, revealing 346 significant genes, 103 of which were upregulated and 243 downregulated. The PPI network of significant genes was constructed to detect the top 50 hub genes, which were then further analyzed using Gene Ontology (GO) terms, Kyoto Encyclopedia of Genes and Genomes pathway (KEGG), and GSEA, revealing 47 key genes involved in AD-related pathways. These key genes were then subjected to feed forward loop (FFL) motif analysis for the prediction of transcriptional factors (TFs) and microRNAs (miRNAs) mediated gene regulatory networks.

RESULTS

The interaction of AD-associated TFs HNF4A, SPI1, EGR1, STAT3, and MYC and miRNAs hsa-miR-155-5p and hsa-miR-16-5p in the transcriptional and post-transcriptional events of 3 upregulated and 10 downregulated genes: H2AFZ, MCM3, MYO1C, AXIN1, CCND1, ETS2, MYH9, RELA, RHEB, SOCS3, TBL1X, TBP, TXNIP, and YWHAZ, respectively, has been identified. The miRNA/TF-mediated three types of the FFL motifs, i.e., miRNA-FFL, TF-FFL, and composite-FFL, were constructed, and seven common genes among these FFL were identified: CCND1, MYH9, SOCS3, RHEB, MYO1C, TXNIP, AXIN1, and TXNIP.

CONCLUSIONS

These findings may provide insights into the development of potential molecular markers for therapeutic management of AD.

MicroRNA Nobel Prize: Timely Recognition and High Anticipation of Future Products-A Prospective Analysis

MicroRNAs (miRNAs) maintain cellular homeostasis by blocking mRNAs by binding with them to fine-tune the expression of genes across numerous biological pathways. The 2024 Nobel Prize in Medicine and Physiology for discovering miRNAs was long overdue. We anticipate a deluge of research work involving miRNAs to repeat the history of prizes awarded for research on other RNAs. Although miRNA therapies are included for several complex diseases, the realization that miRNAs regulate genes and their roles in addressing therapies for hundreds of diseases are expected; but with advancement in drug discovery tools, we anticipate even faster entry of new drugs. To promote this, we provide details of the current science, logic, intellectual property, formulations, and regulatory process with anticipation that many more researchers will introduce novel therapies based on the discussion and advice provided in this paper.

TIWMFLP: Two-Tier Interactive Weighted Matrix Factorization and Label Propagation Based on Similarity Matrix Fusion for Drug-Disease Association Prediction

Accurately identifying new therapeutic uses for drugs is crucial for advancing pharmaceutical research and development. Matrix factorization is often used in association prediction due to its simplicity and high interpretability. However, existing matrix factorization models do not enable real-time interaction between molecular feature matrices and similarity matrices, nor do they consider the geometric structure of the matrices. Additionally, efficiently integrating multisource data remains a significant challenge. To address these issues, we propose a two-tier interactive weighted matrix factorization and label propagation model based on similarity matrix fusion (TIWMFLP) to assist in personalized treatment. First, we calculate the Gaussian and Laplace kernel similarities for drugs and diseases using known drug-disease associations. We then introduce a new multisource similarity fusion method, called similarity matrix fusion (SMF), to integrate these drug/disease similarities. SMF not only considers the different contributions represented by each neighbor but also incorporates drug-disease association information to enhance the contextual topological relationships and potential features of each drug/disease node in the network. Second, we innovatively developed a two-tier interactive weighted matrix factorization (TIWMF) method to process three biological networks. This method realizes for the first time the real-time interaction between the drug/disease feature matrix and its similarity matrix, allowing for a better capture of the complex relationships between drugs and diseases. Additionally, the weighted matrix of the drug/disease similarity matrix is introduced to preserve the underlying structure of the similarity matrix. Finally, the label propagation algorithm makes predictions based on the three updated biological networks. Experimental outcomes reveal that TIWMFLP consistently surpasses state-of-the-art models on four drug-disease data sets, two small molecule-miRNA data sets, and one miRNA-disease data set.

Decreased Serum Insulin Receptor Messenger RNA Level in H. pylori IgG Seropositive Type 2 Diabetic Patients

Background

Helicobacter pylori (H. pylori) is a known gastro-intestinal pathogen but implicated in extra-gastric diseases. The relationship between H. pylori infection and type 2 diabetes (T2DM) remains insufficiently elucidated, particularly in terms of molecular mediators such as microRNAs (miRNAs) and messenger RNAs (mRNAs).

Objective

We aimed to characterize expression pattern of insulin signalling mRNAs and targeted miRNAs in T2DM patients exposed to H. pylori infection.

Methods

We conducted a cross-sectional study among patients diagnosed with type 2 diabetes mellitus and were aged 18 to 60 years. Overnight fasting blood samples were collected and processed for plasma and serum. The plasma samples were used for glucose estimation and the serum used for H. pylori IgG screening. Total RNA was extracted from the serum with commercial kit, and mRNAs and miRNAs quantified by RT-qPCR with specific primers and under predetermined amplification conditions. Clinical data were obtained from medical records of patients.

Results

Among 351 patients enrolled, 267 (76.1%) were females, 224 (63.8%) were married, and 79 (22.5%) had tertiary education. Expression level of insulin receptor mRNA was significantly lower in H. pylori positive T2DM patients compared to H. pylori negative (P < .05). There was no evidence of a difference in insulin receptor substrate 1 mRNA level (P > .05). Although not statistically significant, the expression levels of miRNA-222 and miRNA-155 in the patients exposed to H. pylori were higher than that of the unexposed group (P > .05).

Conclusions

We found a significantly reduced serum insulin receptor messenger RNA level and higher levels of miRNA-222 and miRNA-155 in H. pylori exposed T2DM patients. The findings suggest a possible role of the infection in insulin signalling alteration in the patients.

Prediction of Potential miRNA-Disease Associations Based on a Masked Graph Autoencoder

Biomedical evidence has demonstrated the relevance of microRNA (miRNA) dysregulation in complex human diseases, and determining the relationship between miRNAs and diseases can aid in the early detection and prevention of diseases. Traditional biological experimental methods have the disadvantages of high cost and low efficiency, which are well compensated by computational methods. However, many computational methods have the challenge of excessively focusing on the neighbor relationship, ignoring the structural information of the graph, and belittling the redundant information of the graph structure. This study proposed a computational model based on a graph-masking autoencoder named MGAEMDA. MGAEMDA is an asymmetric framework in which the encoder maps partially observed graphs into latent representations. The decoder reconstructs the masked structural information based on the edge and node levels and combines it with linear matrices to obtain the result. The empirical results on the two datasets reveal that the MGAEMDA model performs better than its counterparts. We also demonstrated the predictive performance of MGAEMDA using a case study of four diseases, and all the top 30 predicted miRNAs were validated in the database, providing further evidence of the excellent performance of the model.

miRNA in Machine-Learning-Based Diagnostics of Oral Cancer

BACKGROUND

MicroRNAs (miRNAs) are crucial regulators of gene expression, playing significant roles in various cellular processes, including cancer pathogenesis. Traditional cancer diagnostic methods, such as biopsies and histopathological analyses, while effective, are invasive, costly, and require specialized skills. With the rising global incidence of cancer, there is a pressing need for more accessible and less invasive diagnostic alternatives.

OBJECTIVE

This research investigates the potential of machine-learning (ML) models based on miRNA attributes as non-invasive diagnostic tools for oral cancer. Methods and Tools: We utilized a comprehensive methodological framework involving the generation of miRNA attributes, including sequence characteristics, target gene associations, and cancer-specific signaling pathways.

RESULTS

The miRNAs were classified using various ML algorithms, with the BayesNet classifier demonstrating superior performance, achieving an accuracy of 95% and an area under receiver operating characteristic curve (AUC) of 0.98 during cross-validation. The model's effectiveness was further validated using independent datasets, confirming its potential clinical utility.

DISCUSSION

Our findings highlight the promise of miRNA-based ML models in enhancing early cancer detection, reducing healthcare burdens, and potentially saving lives.

CONCLUSIONS

This study paves the way for future research into miRNA biomarkers, offering a scalable and adaptable diagnostic approach for various cancers.

A Controllability Reinforcement Learning Method for Pancreatic Cancer Biomarker Identification

Pancreatic cancer is one of the most malignant cancers with rapid progression and poor prognosis. The use of transcriptional data can be effective in finding new biomarkers for pancreatic cancer. Many network-based methods used to identify cancer biomarkers are proposed, among which the combination of network controllability appears. However, most of the existing methods do not study RNA, rely on priori and mutations information, or can only achieve classification tasks. In this study, we propose a method combined Relational Graph Convolutional Network and Deep Q-Network called RDDriver to identify pancreatic cancer biomarkers based on multi-layer heterogeneous transcriptional regulation network. Firstly, we construct a regulation network containing long non-coding RNA, microRNA, and messenger RNA. Secondly, Relational Graph Convolutional Network is used to learn the node representation. Finally, we use the idea of Deep Q-Network to build a model, which score and prioritize each RNA with the Popov-Belevitch-Hautus criterion. We train RDDriver on three small simulated networks, and calculate the average score after applying the model parameters to the regulation networks separately. To demonstrate the effectiveness of the method, we perform experiments for comparison between RDDriver and other eight methods based on the approximate benchmark of three types cancer drivers RNAs.

MicroRNA and Rare Human Diseases

BACKGROUND

The role of microRNAs (miRNAs) in the pathogenesis of rare genetic disorders has been gradually discovered. MiRNAs, a class of small non-coding RNAs, regulate gene expression by silencing target messenger RNAs (mRNAs). Their biogenesis involves transcription into primary miRNA (pri-miRNA), processing by the DROSHA-DGCR8 (DiGeorge syndrome critical region 8) complex, exportation to the cytoplasm, and further processing by DICER to generate mature miRNAs. These mature miRNAs are incorporated into the RNA-induced silencing complex (RISC), where they modulate gene expression.

METHODS/RESULTS

The dysregulation of miRNAs is implicated in various Mendelian disorders and familial diseases, including DICER1 syndrome, neurodevelopmental disorders (NDDs), and conditions linked to mutations in miRNA-binding sites. We summarized a few mechanisms how miRNA processing and regulation abnormalities lead to rare genetic disorders. Examples of such genetic diseases include hearing loss associated with MIR96 mutations, eye disorders linked to MIR184 mutations, and skeletal dysplasia involving MIR140 mutations.

CONCLUSIONS

Understanding these molecular mechanisms is crucial, as miRNA dysregulation is a key factor in the pathogenesis of these conditions, offering significant potential for the diagnosis and potential therapeutic intervention.

Cancer pharmacoinformatics: Databases and analytical tools

Cancer is a subject of extensive investigation, and the utilization of omics technology has resulted in the generation of substantial volumes of big data in cancer research. Numerous databases are being developed to manage and organize this data effectively. These databases encompass various domains such as genomics, transcriptomics, proteomics, metabolomics, immunology, and drug discovery. The application of computational tools into various core components of pharmaceutical sciences constitutes "Pharmacoinformatics", an emerging paradigm in rational drug discovery. The three major features of pharmacoinformatics include (i) Structure modelling of putative drugs and targets, (ii) Compilation of databases and analysis using statistical approaches, and (iii) Employing artificial intelligence/machine learning algorithms for the discovery of novel therapeutic molecules. The development, updating, and analysis of databases using statistical approaches play a pivotal role in pharmacoinformatics. Multiple software tools are associated with oncoinformatics research. This review catalogs the databases and computational tools related to cancer drug discovery and highlights their potential implications in the pharmacoinformatics of cancer.

Microparticle Mediated Delivery of Apelin Improves Heart Function in Post Myocardial Infarction Mice

BACKGROUND

Apelin is an endogenous prepropeptide that regulates cardiac homeostasis and various physiological processes. Intravenous injection has been shown to improve cardiac contractility in patients with heart failure. However, its short half-life prevents studying its impact on left ventricular remodeling in the long term. Here, we aim to study whether microparticle-mediated slow release of apelin improves heart function and left ventricular remodeling in mice with myocardial infarction (MI).

METHODS

A cardiac patch was fabricated by embedding apelin-containing microparticles in a fibrin gel scaffold. MI was induced via permanent ligation of the left anterior descending coronary artery in adult C57BL/6J mice followed by epicardial patch placement immediately after (acute MI) or 28 days (chronic MI) post-MI. Four groups were included in this study, namely sham, MI, MI plus empty microparticle-embedded patch treatment, and MI plus apelin-containing microparticle-embedded patch treatment. Cardiac function was assessed by transthoracic echocardiography. Cardiomyocyte morphology, apoptosis, and cardiac fibrosis were evaluated by histology. Cardioprotective pathways were determined by RNA sequencing, quantitative polymerase chain reaction, and Western blot.

RESULTS

The level of endogenous apelin was largely reduced in the first 7 days after MI induction and it was normalized by day 28. Apelin-13 encapsulated in poly(lactic-co-glycolic acid) microparticles displayed a sustained release pattern for up to 28 days. Treatment with apelin-containing microparticle-embedded patch inhibited cardiac hypertrophy and reduced scar size in both acute and chronic MI models, which is associated with improved cardiac function. Data from cellular and molecular analyses showed that apelin inhibits the activation and proliferation of cardiac fibroblasts by preventing transforming growth factor-β-mediated activation of Smad2/3 (supporessor of mothers against decapentaplegic 2/3) and downstream profibrotic gene expression.

CONCLUSIONS

Poly(lactic-co-glycolic acid) microparticles prolonged the apelin release time in the mouse hearts. Epicardial delivery of the apelin-containing microparticle-embedded patch protects mice from both acute and chronic MI-induced cardiac dysfunction, inhibits cardiac fibrosis, and improves left ventricular remodeling.

Characterization of residual microRNAs in AAV vector batches produced in HEK293 mammalian cells and Sf9 insect cells

With more than 130 clinical trials and 8 approved gene therapy products, adeno-associated virus (AAV) stands as one of the most popular vehicles to deliver therapeutic DNA in vivo. One critical quality attribute analyzed in AAV batches is the presence of residual DNA, as it could pose genotoxic risks or induce immune responses. Surprisingly, the presence of small cell-derived RNAs, such as microRNAs (miRNAs), has not been investigated previously. In this study, we examined the presence of miRNAs in purified AAV batches produced in mammalian or in insect cells. Our findings revealed that miRNAs were present in all batches, regardless of the production cell line or capsid serotype (2 and 8). Quantitative assays indicated that miRNAs were co-purified with the recombinant AAV particles in a proportion correlated with their abundance in the production cells. The level of residual miRNAs was reduced via an immunoaffinity chromatography purification process including a tangential flow filtration step or by RNase treatment, suggesting that most miRNA contaminants are likely non-encapsidated. In summary, we demonstrate, for the first time, that miRNAs are co-purified with AAV particles. Further investigations are required to determine whether these miRNAs could interfere with the safety or efficacy of AAV-mediated gene therapy.

Computational identification and molecular dynamics simulation of potential circularRNA derived peptide from gene expression profile of Rheumatoid arthritis, Alzheimer's disease, and Atrial fibrillation

The two most serious global health challenges confronting human society today are autoimmune disorders (AIDs) and neurological diseases (NDs), both of which shorten people's lives and worsen the situation. Despite their extensive impact, statistics show that AIDs is associated with a higher risk of ND. Circular RNAs (circRNAs) are critical in several illnesses and disorders, especially AID and ND. Therefore, the present study focused on understanding the underlying causes of the pathophysiology of diseases such as AID and ND through in silico-based research. In order to determine how circRNAs are related to various disease pathways, this study examined the gene expression data sets for Rheumatoid arthritis (RA), Alzheimer's disease (AD), and atrial fibrillation (AF). Our study identified and analyzed two circRNAs, their respective host genes (DHTKD1 and RAN) and their related miRNAs, which could serve as potential markers for treating disorders like myotonic dystrophy type 1, spinocerebellar ataxia and fragile X syndrome. Further, the circRNA-derived peptide was identified and analysed with the molecular dynamics simulation (MDS) followed by a principal component (PC) based free energy landscape (FEL) profile. The computational results obtained here provide a basis for the development of therapeutics against AD, RA and AF. Moreover, further functional studies are needed to validate their role in disease aetiology and to provide a detailed understanding of their association with AID and ND.Communicated by Ramaswamy H. Sarma.

EVPsort: An Atlas of Small ncRNA Profiling and Sorting in Extracellular Vesicles and Particles

Extracellular vesicles and particles (EVPs) play a crucial role in mediating cell-to-cell communication by transporting various molecular cargos, with small non-coding RNAs (ncRNAs) holding particular significance. A thorough investigation into the abundance and sorting mechanisms of ncRNA within EVPs is imperative for advancing their clinical applications. We have developed EVPsort, which not only provides an extensive overview of ncRNA profiling in 3,162 samples across various biofluids, cell lines, and disease contexts but also seamlessly integrates 19 external databases and tools. This integration encompasses information on associations between ncRNAs and RNA-binding proteins (RBPs), motifs, targets, pathways, diseases, and drugs. With its rich resources and powerful analysis tools, EVPsort extends its profiling capabilities to investigate ncRNA sorting, identify relevant RBPs and motifs, and assess functional implications. EVPsort stands as a pioneering database dedicated to comprehensively addressing both the abundance and sorting of ncRNA within EVPs. It is freely accessible at https://bioinfo.vanderbilt.edu/evpsort/.

PGCNMDA: Learning node representations along paths with graph convolutional network for predicting miRNA-disease associations

Identifying miRNA-disease associations (MDAs) is crucial for improving the diagnosis and treatment of various diseases. However, biological experiments can be time-consuming and expensive. To overcome these challenges, computational approaches have been developed, with Graph Convolutional Network (GCN) showing promising results in MDA prediction. The success of GCN-based methods relies on learning a meaningful spatial operator to extract effective node feature representations. To enhance the inference of MDAs, we propose a novel method called PGCNMDA, which employs graph convolutional networks with a learning graph spatial operator from paths. This approach enables the generation of meaningful spatial convolutions from paths in GCN, leading to improved prediction performance. On HMDD v2.0, PGCNMDA obtains a mean AUC of 0.9229 and an AUPRC of 0.9206 under 5-fold cross-validation (5-CV), and a mean AUC of 0.9235 and an AUPRC of 0.9212 under 10-fold cross-validation (10-CV), respectively. Additionally, the AUC of PGCNMDA also reaches 0.9238 under global leave-one-out cross-validation (GLOOCV). On HMDD v3.2, PGCNMDA obtains a mean AUC of 0.9413 and an AUPRC of 0.9417 under 5-CV, and a mean AUC of 0.9419 and an AUPRC of 0.9425 under 10-CV, respectively. Furthermore, the AUC of PGCNMDA also reaches 0.9415 under GLOOCV. The results show that PGCNMDA is superior to other compared methods. In addition, the case studies on pancreatic neoplasms, thyroid neoplasms and leukemia show that 50, 50 and 48 of the top 50 predicted miRNAs linked to these diseases are confirmed, respectively. It further validates the effectiveness and feasibility of PGCNMDA in practical applications.

Synchronous Mutual Learning Network and Asynchronous Multi-Scale Embedding Network for miRNA-Disease Association Prediction

MicroRNA (miRNA) serves as a pivotal regulator of numerous cellular processes, and the identification of miRNA-disease associations (MDAs) is crucial for comprehending complex diseases. Recently, graph neural networks (GNN) have made significant advancements in MDA prediction. However, these methods tend to learn one type of node representation from a single heterogeneous network, ignoring the importance of multiple network topologies and node attributes. Here, we propose SMDAP (Sequence hierarchical modeling-based Mirna-Disease Association Prediction framework), a novel GNN-based framework that incorporates multiple network topologies and various node attributes including miRNA seed and full-length sequences to predict potential MDAs. Specifically, SMDAP consists of two types of MDA representation: following a heterogeneous pattern, we construct a transfer learning-like synchronous mutual learning network to learn the first MDA representation in conjunction with the miRNA seed sequence. Meanwhile, following a homogeneous pattern, we design a subgraph-inspired asynchronous multi-scale embedding network to obtain the second MDA representation based on the miRNA full-length sequence. Subsequently, an adaptive fusion approach is designed to combine the two branches such that we can score the MDAs by the downstream classifier and infer novel MDAs. Comprehensive experiments demonstrate that SMDAP integrates the advantages of multiple network topologies and node attributes into two branch representations. Moreover, the area under the receiver operating characteristic curve is 0.9622 on DB1, which is a 5.06% increase from the baselines. The area under the precision-recall curve is 0.9777, which is a 7.33% increase from the baselines. In addition, case studies on three human cancers validated the predictive performance of SMDAP. Overall, SMDAP represents a powerful tool for MDA prediction.

HTFSMMA: Higher-Order Topological Guided Small Molecule-MicroRNA Associations Prediction

Small molecules (SMs) play a pivotal role in regulating microRNAs (miRNAs). Existing prediction methods for associations between SM-miRNA have overlooked crucial aspects: the incorporation of local topological features between nodes, which represent either SMs or miRNAs, and the effective fusion of node features with topological features. This study introduces a novel approach, termed high-order topological features for SM-miRNA association prediction (HTFSMMA), which specifically addresses these limitations. Initially, an association graph is formed by integrating SM-miRNA association data, SM similarity, and miRNA similarity. Subsequently, we focus on the local information of links and propose target neighborhood graph convolutional network for extracting local topological features. Then, HTFSMMA employs graph attention networks to amalgamate these local features, thereby establishing a platform for the acquisition of high-order features through random walks. Finally, the extracted features are integrated into the multilayer perceptron to derive the association prediction scores. To demonstrate the performance of HTFSMMA, we conducted comprehensive evaluations including five-fold cross-validation, leave-one-out cross-validation (LOOCV), SM-fixed local LOOCV, and miRNA-fixed local LOOCV. The area under receiver operating characteristic curve values were 0.9958 ± 0.0024 (0.8722 ± 0.0021), 0.9986 (0.9504), 0.9974 (0.9111), and 0.9977 (0.9074), respectively. Our findings demonstrate the superior performance of HTFSMMA over existing approaches. In addition, three case studies and the DeLong test have confirmed the effectiveness of the proposed method. These results collectively underscore the significance of HTFSMMA in facilitating the inference of associations between SMs and miRNAs.

An ontology-based knowledge graph for representing interactions involving RNA molecules

The "RNA world" represents a novel frontier for the study of fundamental biological processes and human diseases and is paving the way for the development of new drugs tailored to each patient's biomolecular characteristics. Although scientific data about coding and non-coding RNA molecules are constantly produced and available from public repositories, they are scattered across different databases and a centralized, uniform, and semantically consistent representation of the "RNA world" is still lacking. We propose RNA-KG, a knowledge graph (KG) encompassing biological knowledge about RNAs gathered from more than 60 public databases, integrating functional relationships with genes, proteins, and chemicals and ontologically grounded biomedical concepts. To develop RNA-KG, we first identified, pre-processed, and characterized each data source; next, we built a meta-graph that provides an ontological description of the KG by representing all the bio-molecular entities and medical concepts of interest in this domain, as well as the types of interactions connecting them. Finally, we leveraged an instance-based semantically abstracted knowledge model to specify the ontological alignment according to which RNA-KG was generated. RNA-KG can be downloaded in different formats and also queried by a SPARQL endpoint. A thorough topological analysis of the resulting heterogeneous graph provides further insights into the characteristics of the "RNA world". RNA-KG can be both directly explored and visualized, and/or analyzed by applying computational methods to infer bio-medical knowledge from its heterogeneous nodes and edges. The resource can be easily updated with new experimental data, and specific views of the overall KG can be extracted according to the bio-medical problem to be studied.

Dataset of miRNA-disease relations extracted from textual data using transformer-based neural networks

MicroRNAs (miRNAs) play important roles in post-transcriptional processes and regulate major cellular functions. The abnormal regulation of expression of miRNAs has been linked to numerous human diseases such as respiratory diseases, cancer, and neurodegenerative diseases. Latest miRNA-disease associations are predominantly found in unstructured biomedical literature. Retrieving these associations manually can be cumbersome and time-consuming due to the continuously expanding number of publications. We propose a deep learning-based text mining approach that extracts normalized miRNA-disease associations from biomedical literature. To train the deep learning models, we build a new training corpus that is extended by distant supervision utilizing multiple external databases. A quantitative evaluation shows that the workflow achieves an area under receiver operator characteristic curve of 98% on a holdout test set for the detection of miRNA-disease associations. We demonstrate the applicability of the approach by extracting new miRNA-disease associations from biomedical literature (PubMed and PubMed Central). We have shown through quantitative analysis and evaluation on three different neurodegenerative diseases that our approach can effectively extract miRNA-disease associations not yet available in public databases. Database URL: https://zenodo.org/records/10523046.

miRNA-protein-metabolite interaction network reveals the regulatory network and players of pregnancy regulation in dairy cows

Pregnancy is a complex process involving complex molecular interaction networks, such as between miRNA-protein, protein-protein, metabolite-metabolite, and protein-metabolite interactions. Advances in technology have led to the identification of many pregnancy-associated microRNA (miRNA), protein, and metabolite fingerprints in dairy cows. An array of miRNA, protein, and metabolite fingerprints produced during the early pregnancy of dairy cows were described. We have found the in silico interaction networks between miRNA-protein, protein-protein, metabolite-metabolite, and protein-metabolite. We have manually constructed miRNA-protein-metabolite interaction networks such as bta-miR-423-3p-IGFBP2-PGF2α interactomes. This interactome is obtained by manually combining the interaction network formed between bta-miR-423-3p-IGFBP2 and the interaction network between IGFBP2-PGF2α with IGFBP2 as a common interactor with bta-miR-423-3p and PGF2α with the provided sources of evidence. The interaction between bta-miR-423-3p and IGFBP2 has many sources of evidence including a high miRanda score of 169, minimum free energy (MFE) score of -25.14, binding probability (p) of 1, and energy of -25.5. The interaction between IGFBP2 and PGF2α occurs at high confidence scores (≥0.7 or 70%). Interestingly, PGF2α is also found to interact with different metabolites, such as PGF2α-PGD2, PGF2α-thromboxane B2, PGF2α-PGE2, and PGF2α-6-keto-PGF1α at high confidence scores (≥0.7 or 70%). Furthermore, the interactions between C3-PGE2, C3-PGD2, PGE2-PGD2, PGD2-thromboxane B2, PGE2-thromboxane B2, 6-keto-PGF1α-thromboxane B2, and PGE2-6-keto-PGF1α were also obtained at high confidence scores (≥0.7 or 70%). Therefore, we propose that miRNA-protein-metabolite interactomes involving miRNA, protein, and metabolite fingerprints of early pregnancy of dairy cows such as bta-miR-423-3p, IGFBP2, PGF2α, PGD2, C3, PGE2, 6-keto-PGF1 alpha, and thromboxane B2 may form the key regulatory networks and players of pregnancy regulation in dairy cows. This is the first study involving miRNA-protein-metabolite interactomes obtained in the early pregnancy stage of dairy cows.

HHOMR: a hybrid high-order moment residual model for miRNA-disease association prediction

Numerous studies have demonstrated that microRNAs (miRNAs) are critically important for the prediction, diagnosis, and characterization of diseases. However, identifying miRNA-disease associations through traditional biological experiments is both costly and time-consuming. To further explore these associations, we proposed a model based on hybrid high-order moments combined with element-level attention mechanisms (HHOMR). This model innovatively fused hybrid higher-order statistical information along with structural and community information. Specifically, we first constructed a heterogeneous graph based on existing associations between miRNAs and diseases. HHOMR employs a structural fusion layer to capture structure-level embeddings and leverages a hybrid high-order moments encoder layer to enhance features. Element-level attention mechanisms are then used to adaptively integrate the features of these hybrid moments. Finally, a multi-layer perceptron is utilized to calculate the association scores between miRNAs and diseases. Through five-fold cross-validation on HMDD v2.0, we achieved a mean AUC of 93.28%. Compared with four state-of-the-art models, HHOMR exhibited superior performance. Additionally, case studies on three diseases-esophageal neoplasms, lymphoma, and prostate neoplasms-were conducted. Among the top 50 miRNAs with high disease association scores, 46, 47, and 45 associated with these diseases were confirmed by the dbDEMC and miR2Disease databases, respectively. Our results demonstrate that HHOMR not only outperforms existing models but also shows significant potential in predicting miRNA-disease associations.

THGNCDA: circRNA-disease association prediction based on triple heterogeneous graph network

Circular RNAs (circRNAs) are a class of noncoding RNA molecules featuring a closed circular structure. They have been proved to play a significant role in the reduction of many diseases. Besides, many researches in clinical diagnosis and treatment of disease have revealed that circRNA can be considered as a potential biomarker. Therefore, understanding the association of circRNA and diseases can help to forecast some disorders of life activities. However, traditional biological experimental methods are time-consuming. The most common method for circRNA-disease association prediction on the basis of machine learning can avoid this, which relies on diverse data. Nevertheless, topological information of circRNA and disease usually is not involved in these methods. Moreover, circRNAs can be associated with diseases through miRNAs. With these considerations, we proposed a novel method, named THGNCDA, to predict the association between circRNAs and diseases. Specifically, for a certain pair of circRNA and disease, we employ a graph neural network with attention to learn the importance of its each neighbor. In addition, we use a multilayer convolutional neural network to explore the relationship of a circRNA-disease pair based on their attributes. When calculating embeddings, we introduce the information of miRNAs. The results of experiments show that THGNCDA outperformed the SOTA methods. In addition, it can be observed that our method gives a better recall rate. To confirm the significance of attention, we conducted extensive ablation studies. Case studies on Urinary Bladder and Prostatic Neoplasms further show THGNCDA's ability in discovering known relationships between circRNA candidates and diseases.

Motif-Aware miRNA-Disease Association Prediction via Hierarchical Attention Network

As post-transcriptional regulators of gene expression, micro-ribonucleic acids (miRNAs) are regarded as potential biomarkers for a variety of diseases. Hence, the prediction of miRNA-disease associations (MDAs) is of great significance for an in-depth understanding of disease pathogenesis and progression. Existing prediction models are mainly concentrated on incorporating different sources of biological information to perform the MDA prediction task while failing to consider the fully potential utility of MDA network information at the motif-level. To overcome this problem, we propose a novel motif-aware MDA prediction model, namely MotifMDA, by fusing a variety of high- and low-order structural information. In particular, we first design several motifs of interest considering their ability to characterize how miRNAs are associated with diseases through different network structural patterns. Then, MotifMDA adopts a two-layer hierarchical attention to identify novel MDAs. Specifically, the first attention layer learns high-order motif preferences based on their occurrences in the given MDA network, while the second one learns the final embeddings of miRNAs and diseases through coupling high- and low-order preferences. Experimental results on two benchmark datasets have demonstrated the superior performance of MotifMDA over several state-of-the-art prediction models. This strongly indicates that accurate MDA prediction can be achieved by relying solely on MDA network information. Furthermore, our case studies indicate that the incorporation of motif-level structure information allows MotifMDA to discover novel MDAs from different perspectives.

Three-layer heterogeneous network based on the integration of CircRNA information for MiRNA-disease association prediction

Increasing research has shown that the abnormal expression of microRNA (miRNA) is associated with many complex diseases. However, biological experiments have many limitations in identifying the potential disease-miRNA associations. Therefore, we developed a computational model of Three-Layer Heterogeneous Network based on the Integration of CircRNA information for MiRNA-Disease Association prediction (TLHNICMDA). In the model, a disease-miRNA-circRNA heterogeneous network is built by known disease-miRNA associations, known miRNA-circRNA interactions, disease similarity, miRNA similarity, and circRNA similarity. Then, the potential disease-miRNA associations are identified by an update algorithm based on the global network. Finally, based on global and local leave-one-out cross validation (LOOCV), the values of AUCs in TLHNICMDA are 0.8795 and 0.7774. Moreover, the mean and standard deviation of AUC in 5-fold cross-validations is 0.8777+/-0.0010. Especially, the two types of case studies illustrated the usefulness of TLHNICMDA in predicting disease-miRNA interactions.

AE-RW: Predicting miRNA-disease associations by using autoencoder and random walk on miRNA-gene-disease heterogeneous network

Since scientific investigations have demonstrated that aberrant expression of miRNAs brings about the incidence of numerous intricate diseases, precise determination of miRNA-disease relationships greatly contributes to the advancement of human medical progress. To tackle the issue of inefficient conventional experimental approaches, numerous computational methods have been proposed to predict miRNA-disease association with enhanced accuracy. However, constructing miRNA-gene-disease heterogeneous network by incorporating gene information has been relatively under-explored in existing computational techniques. Accordingly, this paper puts forward a technique to predict miRNA-disease association by applying autoencoder and implementing random walk on miRNA-gene-disease heterogeneous network(AE-RW). Firstly, we integrate association information and similarities between miRNAs, genes, and diseases to construct a miRNA-gene-disease heterogeneous network. Subsequently, we consolidate two network feature representations extracted independently via an autoencoder and a random walk procedure. Finally, deep neural network(DNN) are utilized to conduct association prediction. The experimental results demonstrate that the AE-RW model achieved an AUC of 0.9478 through 5-fold CV on the HMDD v3.2 dataset, outperforming the five most advanced existing models. Additionally, case studies were implemented for breast and lung cancer, further validated the superior predictive capabilities of our model.

Heterogeneous graph inference with range constrainted L2,1-collaborative matrix factorization for small molecule-miRNA association prediction

MicroRNAs (miRNAs) play a vital role in regulating gene expression and various biological processes. As a result, they have been identified as effective targets for small molecule (SM) drugs in disease treatment. Heterogeneous graph inference stands as a classical approach for predicting SM-miRNA associations, showcasing commendable convergence accuracy and speed. However, most existing methods do not adequately address the inherent sparsity in SM-miRNA association networks, and imprecise SM/miRNA similarity metrics reduce the accuracy of predicting SM-miRNA associations. In this research, we proposed a heterogeneous graph inference with range constrained L2,1-collaborative matrix factorization (HGIRCLMF) method to predict potential SM-miRNA associations. First, we computed the multi-source similarities of SM/miRNA and integrated these similarity information into a comprehensive SM/miRNA similarity. This step improved the accuracy of SM and miRNA similarity, ensuring reliability for the subsequent inference of the heterogeneity map. Second, we used a range constrained L2,1-collaborative matrix factorization (RCLMF) model to pre-populate the SM-miRNA association matrix with missing values. In this step, we developed a novel matrix decomposition method that enhances the robustness and formative nature of SM-miRNA edges between SM networks and miRNA networks. Next, we built a well-established SM-miRNA heterogeneous network utilizing the processed biological information. Finally, HGIRCLMF used this network data to infer unknown association pair scores. We implemented four cross-validation experiments on two distinct datasets, and HGIRCLMF acquired the highest areas under the curve, surpassing six state-of-the-art computational approaches. Furthermore, we performed three case studies to validate the predictive power of our method in practical application.

IDMIR: identification of dysregulated miRNAs associated with disease based on a miRNA-miRNA interaction network constructed through gene expression data

Micro ribonucleic acids (miRNAs) play a pivotal role in governing the human transcriptome in various biological phenomena. Hence, the accumulation of miRNA expression dysregulation frequently assumes a noteworthy role in the initiation and progression of complex diseases. However, accurate identification of dysregulated miRNAs still faces challenges at the current stage. Several bioinformatics tools have recently emerged for forecasting the associations between miRNAs and diseases. Nonetheless, the existing reference tools mainly identify the miRNA-disease associations in a general state and fall short of pinpointing dysregulated miRNAs within a specific disease state. Additionally, no studies adequately consider miRNA-miRNA interactions (MMIs) when analyzing the miRNA-disease associations. Here, we introduced a systematic approach, called IDMIR, which enabled the identification of expression dysregulated miRNAs through an MMI network under the gene expression context, where the network's architecture was designed to implicitly connect miRNAs based on their shared biological functions within a particular disease context. The advantage of IDMIR is that it uses gene expression data for the identification of dysregulated miRNAs by analyzing variations in MMIs. We illustrated the excellent predictive power for dysregulated miRNAs of the IDMIR approach through data analysis on breast cancer and bladder urothelial cancer. IDMIR could surpass several existing miRNA-disease association prediction approaches through comparison. We believe the approach complements the deficiencies in predicting miRNA-disease association and may provide new insights and possibilities for diagnosing and treating diseases. The IDMIR approach is now available as a free R package on CRAN (https://CRAN.R-project.org/package=IDMIR).

Integrative experimental validation of concomitant miRNAs and transcription factors with differentially expressed genes in acute myocardial infarction

Identification of concomitant miRNAs and transcription factors (TFs) with differential expression (DEGs) in MI is crucial for understanding holistic gene regulation, identifying key regulators, and precision in biomarker and therapeutic target discovery. We performed a comprehensive analysis using Affymetrix microarray data, advanced bioinformatic tools, and experimental validation to explore potential biomarkers associated with human pathology. The search strategy includes the identification of the GSE83500 dataset, comprising gene expression profiles from aortic wall punch biopsies of MI and non-MI patients, which were used in the present study. The analysis identified nine distinct genes exhibiting DEGs within the realm of MI. miRNA-gene/TF and TF-gene/miRNA regulatory relations were mapped to retrieve interacting hub genes to acquire an MI miRNA-TF co-regulatory network. Furthermore, an animal model of I/R-induced MI confirmed the involved gene based on quantitative RT-PCR and Western blot analysis. The consequences of the bioinformatic tool substantiate the inference regarding the presence of three key hub genes (UBE2N, TMEM106B, and CXADR), a central miRNA (hsa-miR-124-3p), and sixteen TFs. Animal studies support the involvement of predicted genes in the I/R-induced myocardial infarction assessed by RT-PCR and Western blotting. Thus, the final consequences suggest the involvement of promising molecular pathways regulated by TF (p53/NF-κB1), miRNA (hsa-miR-124-3p), and hub gene (UBE2N), which may play a key role in the pathogenesis of MI.