KATZNCP: a miRNA-disease association prediction model integrating KATZ algorithm and network consistency projection

BACKGROUND

Clinical studies have shown that miRNAs are closely related to human health. The study of potential associations between miRNAs and diseases will contribute to a profound understanding of the mechanism of disease development, as well as human disease prevention and treatment. MiRNA-disease associations predicted by computational methods are the best complement to biological experiments.

RESULTS

In this research, a federated computational model KATZNCP was proposed on the basis of the KATZ algorithm and network consistency projection to infer the potential miRNA-disease associations. In KATZNCP, a heterogeneous network was initially constructed by integrating the known miRNA-disease association, integrated miRNA similarities, and integrated disease similarities; then, the KATZ algorithm was implemented in the heterogeneous network to obtain the estimated miRNA-disease prediction scores. Finally, the precise scores were obtained by the network consistency projection method as the final prediction results. KATZNCP achieved the reliable predictive performance in leave-one-out cross-validation (LOOCV) with an AUC value of 0.9325, which was better than the state-of-the-art comparable algorithms. Furthermore, case studies of lung neoplasms and esophageal neoplasms demonstrated the excellent predictive performance of KATZNCP.

CONCLUSION

A new computational model KATZNCP was proposed for predicting potential miRNA-drug associations based on KATZ and network consistency projections, which can effectively predict the potential miRNA-disease interactions. Therefore, KATZNCP can be used to provide guidance for future experiments.

Integrative analysis of negatively regulated miRNA-mRNA axes for esophageal squamous cell carcinoma

BACKGROUND

MicroRNAs regulating mRNA expression by targeting at mRNAs is known constructive in tumor occurrence, immune escape, and metastasis.

OBJECTIVE

This research aims at finding negatively regulatory miRNA-mRNA pairs in esophageal squamous cell carcinoma (ESCC).

METHODS

GENE expression data of The Cancer Genome Atlas (TCGA) and GEO database were employed in differently expressed RNA and miRNA (DE-miRNAs/DE-mRNAs) screening. Function analysis was conducted with DAVID-mirPath. MiRNA-mRNA axes were identified by MiRTarBase and TarBase and verified in esophageal specimen by real-time reverse transcription polymerase chain reaction (RT-qPCR). Receiver operation characteristic (ROC) curve and Decision Curve Analysis (DCA) were applied in miRNA-mRNA pairs predictive value estimation. Interactions between miRNA-mRNA regulatory pairs and immune features were analyzed using CIBERSORT.

RESULTS

Combining TCGA database, 4 miRNA and 10 mRNA GEO datasets, totally 26 DE-miRNAs (13 up and 13 down) and 114 DE-mRNAs (64 up and 50 down) were considered significant. MiRTarBase and TarBase identified 37 reverse regulation miRNA-mRNA pairs, 14 of which had been observed in esophageal tissue or cell line. Through analysis of RT-qPCR outcome, miR-106b-5p/KIAA0232 signature was chosen as characteristic pair of ESCC. ROC and DCA verified the predictive value of model containing miRNA-mRNA axis in ESCC. Via affecting mast cells, miR-106b-5p/KIAA0232 may contribute to tumor microenvironment.

CONCLUSIONS

The diagnostic model of miRNA-mRNA pair in ESCC was established. Their complex role in ESCC pathogenesis especially tumor immunity was partly disclosed.

GKLOMLI: a link prediction model for inferring miRNA-lncRNA interactions by using Gaussian kernel-based method on network profile and linear optimization algorithm

BACKGROUND

The limited knowledge of miRNA-lncRNA interactions is considered as an obstruction of revealing the regulatory mechanism. Accumulating evidence on Human diseases indicates that the modulation of gene expression has a great relationship with the interactions between miRNAs and lncRNAs. However, such interaction validation via crosslinking-immunoprecipitation and high-throughput sequencing (CLIP-seq) experiments that inevitably costs too much money and time but with unsatisfactory results. Therefore, more and more computational prediction tools have been developed to offer many reliable candidates for a better design of further bio-experiments.

METHODS

In this work, we proposed a novel link prediction model based on Gaussian kernel-based method and linear optimization algorithm for inferring miRNA-lncRNA interactions (GKLOMLI). Given an observed miRNA-lncRNA interaction network, the Gaussian kernel-based method was employed to output two similarity matrixes of miRNAs and lncRNAs. Based on the integrated matrix combined with similarity matrixes and the observed interaction network, a linear optimization-based link prediction model was trained for inferring miRNA-lncRNA interactions.

RESULTS

To evaluate the performance of our proposed method, k-fold cross-validation (CV) and leave-one-out CV were implemented, in which each CV experiment was carried out 100 times on a training set generated randomly. The high area under the curves (AUCs) at 0.8623 ± 0.0027 (2-fold CV), 0.9053 ± 0.0017 (5-fold CV), 0.9151 ± 0.0013 (10-fold CV), and 0.9236 (LOO-CV), illustrated the precision and reliability of our proposed method.

CONCLUSION

GKLOMLI with high performance is anticipated to be used to reveal underlying interactions between miRNA and their target lncRNAs, and deciphers the potential mechanisms of the complex diseases.

A DNAzyme-enhanced nonlinear hybridization chain reaction for sensitive detection of microRNA

As a typical biomarker, the expression of microRNA is closely related to the occurrence of cancer. However, in recent years, the detection methods have had some limitations in the research and application of microRNAs. In this paper, an autocatalytic platform was constructed through the combination of a nonlinear hybridization chain reaction and DNAzyme to achieve efficient detection of microRNA-21. Fluorescently labeled fuel probes can form branched nanostructures and new DNAzyme under the action of the target, and the newly formed DNAzyme can trigger a new round of reactions, resulting in enhanced fluorescence signals. This platform is a simple, efficient, fast, low-cost, and selective method for the detection of microRNA-21, which can detect microRNA-21 at concentrations as low as 0.004 nM and can distinguish sequence differences by single-base differences. In tissue samples from liver cancer patients, the platform shows the same detection accuracy as real-time PCR but with better reproducibility. In addition, through the flexible design of the trigger chain, our method could be adapted to detect other nucleic acids biomarkers.

BMPMDA: Prediction of MiRNA-Disease Associations Using a Space Projection Model Based on Block Matrix

With the high-quality development of bioinformatics technology, miRNA-disease associations (MDAs) are gradually being uncovered. At present, convenient and efficient prediction methods, which solve the problem of resource-consuming in traditional wet experiments, need to be further put forward. In this study, a space projection model based on block matrix is presented for predicting MDAs (BMPMDA). Specifically, two block matrices are first composed of the known association matrix and similarity to increase comprehensiveness. For the integrity of information in the heterogeneous network, matrix completion (MC) is utilized to mine potential MDAs. Considering the neighborhood information of data points, linear neighborhood similarity (LNS) is regarded as a measure of similarity. Next, LNS is projected onto the corresponding completed association matrix to derive the projection score. Finally, the AUC and AUPR values for BMPMDA reach 0.9691 and 0.6231, respectively. Additionally, the majority of novel MDAs in three disease cases are identified in existing databases and literature. It suggests that BMPMDA can serve as a reliable prediction model for biological research.

Improving miRNA Disease Association Prediction Accuracy Using Integrated Similarity Information and Deep Autoencoders

MicroRNAs (miRNAs) are short endogenous non-encoding RNA molecules (22nt) that have a vital role in many biological and molecular processes inside the human body. Abnormal and dysregulated expressions of miRNAs are correlated with many complex disorders. Time-consuming wet-lab biological experiments are costly and labour-intensive. So, the situation demands feasible and efficient computational approaches for predicting promising miRNAs associated with diseases. Here a two-stage feature pruning approach based on miRNA feature similarity fusion that uses deep attention autoencoder and recursive feature elimination with cross-validation (RFECV) is proposed for predicting unknown miRNA-disease associations. In the first stage, an attention autoencoder captures highly influential features from the fused feature vector. For further pruning of features, RFECV is applied. The resultant features were given to a Random Forest classifier for association prediction. The Highest AUC of 94.41% is attained when all miRNA similarity measures are merged with disease similarities. Case studies were done on two diseases-lymphoma and leukaemia, to examine the reliability of the approach. Comparative analysis shows that the proposed approach outperforms recent methodologies for predicting miRNA-disease associations.

Bioinformatics and cheminformatics approaches to identify pathways, molecular mechanisms and drug substances related to genetic basis of cervical cancer

Cervical cancer (CC) is a global threat to women and our knowledge is frighteningly little about its underlying genomic contributors. Our research aimed to understand the underlying molecular and genetic mechanisms of CC by integrating bioinformatics and network-based study. Transcriptomic analyses of three microarray datasets identified 218 common differentially expressed genes (DEGs) within control samples and CC specimens. KEGG pathway analysis revealed pathways in cell cycle, drug metabolism, DNA replication and the significant GO terms were cornification, proteolysis, cell division and DNA replication. Protein-protein interaction (PPI) network analysis identified 20 hub genes and survival analyses validated CDC45, MCM2, PCNA and TOP2A as CC biomarkers. Subsequently, 10 transcriptional factors (TFs) and 10 post-transcriptional regulators were detected through TFs-DEGs and miRNAs-DEGs regulatory network assessment. Finally, the CC biomarkers were subjected to a drug-gene relationship analysis to find the best target inhibitors. Standard cheminformatics method including in silico ADMET and molecular docking study substantiated PD0325901 and Selumetinib as the most potent candidate-drug for CC treatment. Overall, this meticulous study holds promises for further in vitro and in vivo research on CC diagnosis, prognosis and therapies. Communicated by Ramaswamy H. Sarma.

Matrix reconstruction with reliable neighbors for predicting potential MiRNA-disease associations

Numerous experimental studies have indicated that alteration and dysregulation in mircroRNAs (miRNAs) are associated with serious diseases. Identifying disease-related miRNAs is therefore an essential and challenging task in bioinformatics research. Computational methods are an efficient and economical alternative to conventional biomedical studies and can reveal underlying miRNA-disease associations for subsequent experimental confirmation with reasonable confidence. Despite the success of existing computational approaches, most of them only rely on the known miRNA-disease associations to predict associations without adding other data to increase the prediction accuracy, and they are affected by issues of data sparsity. In this paper, we present MRRN, a model that combines matrix reconstruction with node reliability to predict probable miRNA-disease associations. In MRRN, the most reliable neighbors of miRNA and disease are used to update the original miRNA-disease association matrix, which significantly reduces data sparsity. Unknown miRNA-disease associations are reconstructed by aggregating the most reliable first-order neighbors to increase prediction accuracy by representing the local and global structure of the heterogeneous network. Five-fold cross-validation of MRRN produced an area under the curve (AUC) of 0.9355 and area under the precision-recall curve (AUPR) of 0.2646, values that were greater than those produced by comparable models. Two different types of case studies using three diseases were conducted to demonstrate the accuracy of MRRN, and all top 30 predicted miRNAs were verified.

DeepsmirUD: Prediction of Regulatory Effects on microRNA Expression Mediated by Small Molecules Using Deep Learning

Aberrant miRNA expression has been associated with a large number of human diseases. Therefore, targeting miRNAs to regulate their expression levels has become an important therapy against diseases that stem from the dysfunction of pathways regulated by miRNAs. In recent years, small molecules have demonstrated enormous potential as drugs to regulate miRNA expression (i.e., SM-miR). A clear understanding of the mechanism of action of small molecules on the upregulation and downregulation of miRNA expression allows precise diagnosis and treatment of oncogenic pathways. However, outside of a slow and costly process of experimental determination, computational strategies to assist this on an ad hoc basis have yet to be formulated. In this work, we developed, to the best of our knowledge, the first cross-platform prediction tool, DeepsmirUD, to infer small-molecule-mediated regulatory effects on miRNA expression (i.e., upregulation or downregulation). This method is powered by 12 cutting-edge deep-learning frameworks and achieved AUC values of 0.843/0.984 and AUCPR values of 0.866/0.992 on two independent test datasets. With a complementarily constructed network inference approach based on similarity, we report a significantly improved accuracy of 0.813 in determining the regulatory effects of nearly 650 associated SM-miR relations, each formed with either novel small molecule or novel miRNA. By further integrating miRNA-cancer relationships, we established a database of potential pharmaceutical drugs from 1343 small molecules for 107 cancer diseases to understand the drug mechanisms of action and offer novel insight into drug repositioning. Furthermore, we have employed DeepsmirUD to predict the regulatory effects of a large number of high-confidence associated SM-miR relations. Taken together, our method shows promise to accelerate the development of potential miRNA targets and small molecule drugs.

miRdisNET: Discovering microRNA biomarkers that are associated with diseases utilizing biological knowledge-based machine learning

During recent years, biological experiments and increasing evidence have shown that microRNAs play an important role in the diagnosis and treatment of human complex diseases. Therefore, to diagnose and treat human complex diseases, it is necessary to reveal the associations between a specific disease and related miRNAs. Although current computational models based on machine learning attempt to determine miRNA-disease associations, the accuracy of these models need to be improved, and candidate miRNA-disease relations need to be evaluated from a biological perspective. In this paper, we propose a computational model named miRdisNET to predict potential miRNA-disease associations. Specifically, miRdisNET requires two types of data, i.e., miRNA expression profiles and known disease-miRNA associations as input files. First, we generate subsets of specific diseases by applying the grouping component. These subsets contain miRNA expressions with class labels associated with each specific disease. Then, we assign an importance score to each group by using a machine learning method for classification. Finally, we apply a modeling component and obtain outputs. One of the most important outputs of miRdisNET is the performance of miRNA-disease prediction. Compared with the existing methods, miRdisNET obtained the highest AUC value of .9998. Another output of miRdisNET is a list of significant miRNAs for disease under study. The miRNAs identified by miRdisNET are validated via referring to the gold-standard databases which hold information on experimentally verified microRNA-disease associations. miRdisNET has been developed to predict candidate miRNAs for new diseases, where miRNA-disease relation is not yet known. In addition, miRdisNET presents candidate disease-disease associations based on shared miRNA knowledge. The miRdisNET tool and other supplementary files are publicly available at: https://github.com/malikyousef/miRdisNET.

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

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

MicroRNA-Mediated Mitochondrial Dysfunction Is Involved in the Anti-triple-Negative Breast Cancer Cell Activity of Phytosesquiterpene Lactones

Aims: Emerging evidence suggests that modulating redox homeostasis through targeting mitochondrial functions may be a useful strategy for suppressing triple-negative breast cancer (TNBC) activities. However, whether there are specific microRNAs (miRNAs) involved in regulating oxidative stress-associated mitochondrial functions that can act as therapeutic targets to suppress TNBC activities remains unclear. Here, we aimed to identify the role of redox-associated miRNAs in TNBC and investigated their potential as therapeutic targets. Results: We identified oxidative stress-responsive differentially expressed miRNAs (DEMs) regulated by phytosesquiterpene lactone deoxyelephantopin (DET) and its novel derivative DETD-35, which are known to inhibit TNBC growth and metastasis in vitro and in vivo, using comparative miRNA microarray analysis and reactive oxygen species (ROS) scavenging approaches. Mitochondrial dysfunction was identified as a major biological function regulated by a few specific DEMs. In particular, miR-4284 was identified to play a role in DET- and DETD-35-mediated ROS production, mitochondrial basal proton leak, and antiproliferation activity in TNBC cells. Moreover, DET- and DETD-35-induced mitochondrial DNA damage was observed in TNBC cells and xenograft tumors. miR-4284 was also identified to play a role in oxidative DNA damage in TNBC tumors. Innovation: We identified a novel role for miR-4284 in regulating mitochondrial basal proton leak in TNBC cells, and highlighted its significance in TNBC tumor oxidative DNA damage, and its direct correlation with TNBC patient survival. Conclusion: We used DET and DETD-35 as proof of concept to demonstrate that activities of anticancer agents can involve regulation of multiple miRNAs playing different roles in cancer progression. Antioxid. Redox Signal. 38, 198-214.

Microfluidics for Profiling miRNA Biomarker Panels in AI-Assisted Cancer Diagnosis and Prognosis

Early detection of cancers and their precise subtyping are essential to patient stratification and effective cancer management. Data-driven identification of expression biomarkers coupled with microfluidics-based detection shows promise to revolutionize cancer diagnosis and prognosis. MicroRNAs play key roles in cancers and afford detection in tissue and liquid biopsies. In this review, we focus on the microfluidics-based detection of miRNA biomarkers in AI-based models for early-stage cancer subtyping and prognosis. We describe various subclasses of miRNA biomarkers that could be useful in machine-based predictive modeling of cancer staging and progression. Strategies for optimizing the feature space of miRNA biomarkers are necessary to obtain a robust signature panel. This is followed by a discussion of the issues in model construction and validation towards producing Software-as-Medical-Devices (SaMDs). Microfluidic devices could facilitate the multiplexed detection of miRNA biomarker panels, and an overview of the different strategies for designing such microfluidic systems is presented here, with an outline of the detection principles used and the corresponding performance measures. Microfluidics-based profiling of miRNAs coupled with SaMD represent high-performance point-of-care solutions that would aid clinical decision-making and pave the way for accessible precision personalized medicine.

Epigenetic adaptations in drug-tolerant tumor cells

Traditional chemotherapy against cancer is often severely hampered by acquired resistance to the drug. Epigenetic alterations and other mechanisms like drug efflux, drug metabolism, and engagement of survival pathways are crucial in evading drug pressure. Herein, growing evidence suggests that a subpopulation of tumor cells can often tolerate drug onslaught by entering a "persister" state with minimal proliferation. The molecular features of these persister cells are gradually unraveling. Notably, the "persisters" act as a cache of cells that can eventually re-populate the tumor post-withdrawal drug pressure and contribute to acquiring stable drug-resistant features. This underlines the clinical significance of the tolerant cells. Accumulating evidence highlights the importance of modulation of the epigenome as a critical adaptive strategy for evading drug pressure. Chromatin remodeling, altered DNA methylation, and de-regulation of non-coding RNA expression and function contribute significantly to this persister state. No wonder targeting adaptive epigenetic modifications is increasingly recognized as an appropriate therapeutic strategy to sensitize them and restore drug sensitivity. Furthermore, manipulating the tumor microenvironment and "drug holiday" is also explored to maneuver the epigenome. However, heterogeneity in adaptive strategies and lack of targeted therapies have significantly hindered the translation of epigenetic therapy to the clinics. In this review, we comprehensively analyze the epigenetic alterations adapted by the drug-tolerant cells, the therapeutic strategies employed to date, and their limitations and future prospects.

Splicing signature database development to delineate cancer pathways using literature mining and transcriptome machine learning

Alternative splicing (AS) events modulate certain pathways and phenotypic plasticity in cancer. Although previous studies have computationally analyzed splicing events, it is still a challenge to uncover biological functions induced by reliable AS events from tremendous candidates. To provide essential splicing event signatures to assess pathway regulation, we developed a database by collecting two datasets: (i) reported literature and (ii) cancer transcriptome profile. The former includes knowledge-based splicing signatures collected from 63,229 PubMed abstracts using natural language processing, extracted for 202 pathways. The latter is the machine learning-based splicing signatures identified from pan-cancer transcriptome for 16 cancer types and 42 pathways. We established six different learning models to classify pathway activities from splicing profiles as a learning dataset. Top-ranked AS events by learning model feature importance became the signature for each pathway. To validate our learning results, we performed evaluations by (i) performance metrics, (ii) differential AS sets acquired from external datasets, and (iii) our knowledge-based signatures. The area under the receiver operating characteristic values of the learning models did not exhibit any drastic difference. However, random-forest distinctly presented the best performance to compare with the AS sets identified from external datasets and our knowledge-based signatures. Therefore, we used the signatures obtained from the random-forest model. Our database provided the clinical characteristics of the AS signatures, including survival test, molecular subtype, and tumor microenvironment. The regulation by splicing factors was additionally investigated. Our database for developed signatures supported retrieval and visualization system.

Analysis of aberrant miRNA-mRNA interaction networks in prostate cancer to conjecture its molecular mechanisms

BACKGROUND

MicroRNAs (miRNAs) capable of post-transcriptionally regulating mRNA expression are essential to tumor occurrence and progression.

OBJECTIVE

This study aims to find negatively regulatory miRNA-mRNA pairs in prostate adenocarcinoma (PRAD).

METHODS

Combining The Cancer Genome Atlas (TCGA) RNA-Seq data with Gene Expression Omnibus (GEO) mRNA/miRNA expression profiles, differently expressed miRNA/mRNA (DE-miRNAs/DE-mRNAs) were identified. MiRNA-mRNA pairs were screened by miRTarBase and TarBase, databases collecting experimentally confirmed miRNA-mRNA pairs, and verified in 30 paired prostate specimens by real-time reverse transcription polymerase chain reaction (RT-qPCR). The diagnostic values of miRNA-mRNA pairs were measured by receiver operation characteristic (ROC) curve and Decision Curve Analysis (DCA). DAVID-mirPath database and Connectivity Map were employed in GO/KEGG analysis and compounds research. Interactions between miRNA-mRNA pairs and phenotypic features were analyzed with correlation heatmap in hiplot.

RESULTS

Based on TCGA RNA-Seq data, 22 miRNA and 14 mRNA GEO datasets, 67 (20 down and 47 up) miRNAs and 351 (139 up and 212 down) mRNAs were selected. After screening from 2 databases, 8 miRNA (up)-mRNA (down) and 7 miRNA (down)-mRNA (up) pairs were identified with Pearson's correlation in TCGA. By external validation, miR-221-3p (down)/GALNT3 (up) and miR-20a-5p (up)/FRMD6 (down) were chosen. The model combing 4 signatures possessed better diagnostic value. These two miRNA-mRNA pairs were significantly connected with immune cells fraction and tumor immune microenvironment.

CONCLUSIONS

The diagnostic model containing 2 negatively regulatory miRNA-mRNA pairs was established to distinguish PRADs from normal controls.

In Silico and In Vivo Evaluation of microRNA-181c-5p's Role in Hepatocellular Carcinoma

Hepatocellular carcinoma (HCC) is a fatal disease, accounting for 75-85% of primary liver cancers. The conclusive research on miR-181c-5p's role in hepatocarcinogenesis, whether it has oncogenic effects or acts as a tumor repressor, is limited and fluctuating. Therefore, the current study aimed to elucidate the role of miR-181c-5p in HCC in silico and in vivo. The bioinformatics analysis of miR-181c-5p expression data in HCC using several databases strongly shed light on its involvement in HCC development, but also confirmed the fluctuating data around its role. miR-181c-5p was proven here to have an oncogenic role by increasing HepG2 cells' viability as confirmed by MTT analysis. In addition, miR-181c-5p was upregulated in the HCC positive control group and progressed the HCC development and malignant features by its forced expression in an HCC mouse model by targeted delivery using a LA-PAMAM polyplex. This is indicated by the cancerous gross and histological features, and the significant increase in liver function biomarkers. The functional enrichment bioinformatics analyses of miR-181c-5p-downregulated targets in HCC indicated that miR-181c-5p targets were significantly enriched in multiple pathways and biological processes involved in HCC development. Fbxl3, an example for miR-181c-5p potential targets, downregulation and its correlation with miR-181c-5p were validated by qPCR. In conclusion, miR-181c-5p is upregulated in HCC and has an oncogenic role enhancing HCC progression.

SGAEMDA: Predicting miRNA-Disease Associations Based on Stacked Graph Autoencoder

MicroRNA (miRNA)-disease association (MDA) prediction is critical for disease prevention, diagnosis, and treatment. Traditional MDA wet experiments, on the other hand, are inefficient and costly.Therefore, we proposed a multi-layer collaborative unsupervised training base model called SGAEMDA (Stacked Graph Autoencoder-Based Prediction of Potential miRNA-Disease Associations). First, from the original miRNA and disease data, we defined two types of initial features: similarity features and association features. Second, stacked graph autoencoder is then used to learn unsupervised low-dimensional representations of meaningful higher-order similarity features, and we concatenate the association features with the learned low-dimensional representations to obtain the final miRNA-disease pair features. Finally, we used a multilayer perceptron (MLP) to predict scores for unknown miRNA-disease associations. SGAEMDA achieved a mean area under the ROC curve of 0.9585 and 0.9516 in 5-fold and 10-fold cross-validation, which is significantly higher than the other baseline methods. Furthermore, case studies have shown that SGAEMDA can accurately predict candidate miRNAs for brain, breast, colon, and kidney neoplasms.

Cis-regulatory mutations associate with transcriptional and post-transcriptional deregulation of gene regulatory programs in cancers

Most cancer alterations occur in the noncoding portion of the human genome, where regulatory regions control gene expression. The discovery of noncoding mutations altering the cells' regulatory programs has been limited to few examples with high recurrence or high functional impact. Here, we show that transcription factor binding sites (TFBSs) have similar mutation loads to those in protein-coding exons. By combining cancer somatic mutations in TFBSs and expression data for protein-coding and miRNA genes, we evaluate the combined effects of transcriptional and post-transcriptional alterations on the regulatory programs in cancers. The analysis of seven TCGA cohorts culminates with the identification of protein-coding and miRNA genes linked to mutations at TFBSs that are associated with a cascading trans-effect deregulation on the cells' regulatory programs. Our analyses of cis-regulatory mutations associated with miRNAs recurrently predict 12 mature miRNAs (derived from 7 precursors) associated with the deregulation of their target gene networks. The predictions are enriched for cancer-associated protein-coding and miRNA genes and highlight cis-regulatory mutations associated with the dysregulation of key pathways associated with carcinogenesis. By combining transcriptional and post-transcriptional regulation of gene expression, our method predicts cis-regulatory mutations related to the dysregulation of key gene regulatory networks in cancer patients.

Updated review of advances in microRNAs and complex diseases: experimental results, databases, webservers and data fusion

MicroRNAs (miRNAs) are gene regulators involved in the pathogenesis of complex diseases such as cancers, and thus serve as potential diagnostic markers and therapeutic targets. The prerequisite for designing effective miRNA therapies is accurate discovery of miRNA-disease associations (MDAs), which has attracted substantial research interests during the last 15 years, as reflected by more than 55 000 related entries available on PubMed. Abundant experimental data gathered from the wealth of literature could effectively support the development of computational models for predicting novel associations. In 2017, Chen et al. published the first-ever comprehensive review on MDA prediction, presenting various relevant databases, 20 representative computational models, and suggestions for building more powerful ones. In the current review, as the continuation of the previous study, we revisit miRNA biogenesis, detection techniques and functions; summarize recent experimental findings related to common miRNA-associated diseases; introduce recent updates of miRNA-relevant databases and novel database releases since 2017, present mainstream webservers and new webserver releases since 2017 and finally elaborate on how fusion of diverse data sources has contributed to accurate MDA prediction.

Updated review of advances in microRNAs and complex diseases: towards systematic evaluation of computational models

Currently, there exist no generally accepted strategies of evaluating computational models for microRNA-disease associations (MDAs). Though K-fold cross validations and case studies seem to be must-have procedures, the value of K, the evaluation metrics, and the choice of query diseases as well as the inclusion of other procedures (such as parameter sensitivity tests, ablation studies and computational cost reports) are all determined on a case-by-case basis and depending on the researchers' choices. In the current review, we include a comprehensive analysis on how 29 state-of-the-art models for predicting MDAs were evaluated. Based on the analytical results, we recommend a feasible evaluation workflow that would suit any future model to facilitate fair and systematic assessment of predictive performance.

PMMS: Predicting essential miRNAs based on multi-head self-attention mechanism and sequences

Increasing evidence has proved that miRNA plays a significant role in biological progress. In order to understand the etiology and mechanisms of various diseases, it is necessary to identify the essential miRNAs. However, it is time-consuming and expensive to identify essential miRNAs by using traditional biological experiments. It is critical to develop computational methods to predict potential essential miRNAs. In this study, we provided a new computational method (called PMMS) to identify essential miRNAs by using multi-head self-attention and sequences. First, PMMS computes the statistic and structure features and extracts the static feature by concatenating them. Second, PMMS extracts the deep learning original feature (BiLSTM-based feature) by using bi-directional long short-term memory (BiLSTM) and pre-miRNA sequences. In addition, we further obtained the multi-head self-attention feature (MS-based feature) based on BiLSTM-based feature and multi-head self-attention mechanism. By considering the importance of the subsequence of pre-miRNA to the static feature of miRNA, we obtained the deep learning final feature (WA-based feature) based on the weighted attention mechanism. Finally, we concatenated WA-based feature and static feature as an input to the multilayer perceptron) model to predict essential miRNAs. We conducted five-fold cross-validation to evaluate the prediction performance of PMMS. The areas under the ROC curves (AUC), the F1-score, and accuracy (ACC) are used as performance metrics. From the experimental results, PMMS obtained best prediction performances (AUC: 0.9556, F1-score: 0.9030, and ACC: 0.9097). It also outperformed other compared methods. The experimental results also illustrated that PMMS is an effective method to identify essential miRNA.

MicroRNAs in Cancer and Cardiovascular Disease

Although cardiac tumor formation is rare, accumulating evidence suggests that the two leading causes of deaths, cancers, and cardiovascular diseases are similar in terms of pathogenesis, including angiogenesis, immune responses, and fibrosis. These similarities have led to the creation of new exciting field of study called cardio-oncology. Here, we review the similarities between cancer and cardiovascular disease from the perspective of microRNAs (miRNAs). As miRNAs are well-known regulators of translation by binding to the 3'-untranslated regions (UTRs) of messenger RNAs (mRNAs), we carefully dissect how a specific set of miRNAs are both oncomiRs (miRNAs in cancer) and myomiRs (muscle-related miRNAs). Furthermore, from the standpoint of similar pathogenesis, miRNAs categories related to the similar pathogenesis are discussed; namely, angiomiRs, Immune-miRs, and fibromiRs.

CmirC: an integrated database of clustered miRNAs co-localized with copy number variations in cancer

Genomic rearrangements and copy number variations (CNVs) are the major regulators of clustered microRNAs (miRNAs) expression. Several clustered miRNAs are harbored in and around chromosome fragile sites (CFSs) and cancer-associated genomic hotspots. Aberrant expression of such clusters can lead to oncogenic or tumor suppressor activities. Here, we developed CmirC (Clustered miRNAs co-localized with CNVs), a comprehensive database of clustered miRNAs co-localized with CNV regions. The database consists of 481 clustered miRNAs co-localized with CNVs and their expression patterns in 35 cancer types of the TCGA. The portal also provides information on CFSs, miRNA cluster candidates, genomic coordinates, target gene networks, and gene functionality. The web portal is integrated with advanced tools such as JBrowse, NCBI-BLAST, GeneSCF, visNetwork, and NetworkD3 to help the researchers in data analysis, visualization, and browsing. This portal provides a promising avenue for integrated data analytics and offers additional evidence for the complex regulation of clustered miRNAs in cancer. The web portal is freely accessible at http://slsdb.manipal.edu/cmirclust to explore clinically significant miRNAs.

An Exosomal miRNA Biomarker for the Detection of Pancreatic Ductal Adenocarcinoma

Pancreatic ductal adenocarcinoma (PDAC) remains a difficult tumor to diagnose and treat. To date, PDAC lacks routine screening with no markers available for early detection. Exosomes are 40-150 nm-sized extracellular vesicles that contain DNA, RNA, and proteins. These exosomes are released by all cell types into circulation and thus can be harvested from patient body fluids, thereby facilitating a non-invasive method for PDAC detection. A bioinformatics analysis was conducted utilizing publicly available miRNA pancreatic cancer expression and genome databases. Through this analysis, we identified 18 miRNA with strong potential for PDAC detection. From this analysis, 10 (MIR31, MIR93, MIR133A1, MIR210, MIR330, MIR339, MIR425, MIR429, MIR1208, and MIR3620) were chosen due to high copy number variation as well as their potential to differentiate patients with chronic pancreatitis, neoplasms, and PDAC. These 10 were examined for their mature miRNA expression patterns, giving rise to 18 mature miRs for further analysis. Exosomal RNA from cell culture media was analyzed via RTqPCR and seven mature miRs exhibited statistical significance (miR-31-5p, miR-31-3p, miR-210-3p, miR-339-5p, miR-425-5p, miR-425-3p, and miR-429). These identified biomarkers can potentially be used for early detection of PDAC.

Identification of neoplasm-specific signatures of miRNA interactions by employing a systems biology approach

MicroRNAs represent major regulatory components of the disease epigenome and they constitute powerful biomarkers for the accurate diagnosis and prognosis of various diseases, including cancers. The advent of high-throughput technologies facilitated the generation of a vast amount of miRNA-cancer association data. Computational approaches have been utilized widely to effectively analyze and interpret these data towards the identification of miRNA signatures for diverse types of cancers. Herein, a novel computational workflow was applied to discover core sets of miRNA interactions for the major groups of neoplastic diseases by employing network-based methods. To this end, miRNA-cancer association data from four comprehensive publicly available resources were utilized for constructing miRNA-centered networks for each major group of neoplasms. The corresponding miRNA-miRNA interactions were inferred based on shared functionally related target genes. The topological attributes of the generated networks were investigated in order to detect clusters of highly interconnected miRNAs that form core modules in each network. Those modules that exhibited the highest degree of mutual exclusivity were selected from each graph. In this way, neoplasm-specific miRNA modules were identified that could represent potential signatures for the corresponding diseases.

A Survey on Computational Methods for Investigation on ncRNA-Disease Association through the Mode of Action Perspective

Molecular and sequencing technologies have been successfully used in decoding biological mechanisms of various diseases. As revealed by many novel discoveries, the role of non-coding RNAs (ncRNAs) in understanding disease mechanisms is becoming increasingly important. Since ncRNAs primarily act as regulators of transcription, associating ncRNAs with diseases involves multiple inference steps. Leveraging the fast-accumulating high-throughput screening results, a number of computational models predicting ncRNA-disease associations have been developed. These tools suggest novel disease-related biomarkers or therapeutic targetable ncRNAs, contributing to the realization of precision medicine. In this survey, we first introduce the biological roles of different ncRNAs and summarize the databases containing ncRNA-disease associations. Then, we suggest a new trend in recent computational prediction of ncRNA-disease association, which is the mode of action (MoA) network perspective. This perspective includes integrating ncRNAs with mRNA, pathway and phenotype information. In the next section, we describe computational methodologies widely used in this research domain. Existing computational studies are then summarized in terms of their coverage of the MoA network. Lastly, we discuss the potential applications and future roles of the MoA network in terms of integrating biological mechanisms for ncRNA-disease associations.

A critical review of datasets and computational suites for improving cancer theranostics and biomarker discovery

Cancer has been constantly evolving and so is the research pertaining to cancer diagnosis and therapeutic regimens. Early detection and specific therapeutics are the key features of modern cancer therapy. These requirements can only be fulfilled with the integration of diverse high-throughput technologies. Integration of advanced omics methodology involving genomics, epigenomics, proteomics, and transcriptomics provide a clear understanding of multi-faceted cancer. In the past few years, tremendous high-throughput data have been generated from cancer genomics and epigenomic analyses, which on further methodological analyses can yield better biological insights. The major epigenetic alterations reported in cancer are DNA methylation levels, histone post-translational modifications, and epi-miRNA regulating the oncogenes and tumor suppressor genes. While the genomic analyses like gene expression profiling, cancer gene prediction, and genome annotation divulge the genetic alterations in oncogenes or tumor suppressor genes. Also, systems biology approach using biological networks is being extensively used to identify novel cancer biomarkers. Therefore, integration of these multi-dimensional approaches will help to identify potential diagnostic and therapeutic biomarkers. Here, we reviewed the critical databases and tools dedicated to various epigenomic and genomic alterations in cancer. The review further focuses on the multi-omics resources available for further validating the identified cancer biomarkers. We also highlighted the tools for cancer biomarker discovery using a systems biology approach utilizing genomic and epigenomic data. Biomarkers predicted using such integrative approaches are shown to be more clinically relevant.

RNADisease v4.0: an updated resource of RNA-associated diseases, providing RNA-disease analysis, enrichment and prediction

Numerous studies have shown that RNA plays an important role in the occurrence and development of diseases, and RNA-disease associations are not limited to noncoding RNAs in mammals but also exist for protein-coding RNAs. Furthermore, RNA-associated diseases are found across species including plants and nonmammals. To better analyze diseases at the RNA level and facilitate researchers in exploring the pathogenic mechanism of diseases, we decided to update and change MNDR v3.0 to RNADisease v4.0, a repository for RNA-disease association (http://www.rnadisease.org/ or http://www.rna-society.org/mndr/). Compared to the previous version, new features include: (i) expanded data sources and categories of species, RNA types, and diseases; (ii) the addition of a comprehensive analysis of RNAs from thousands of high-throughput sequencing data of cancer samples and normal samples; (iii) the addition of an RNA-disease enrichment tool and (iv) the addition of four RNA-disease prediction tools. In summary, RNADisease v4.0 provides a comprehensive and concise data resource of RNA-disease associations which contains a total of 3 428 058 RNA-disease entries covering 18 RNA types, 117 species and 4090 diseases to meet the needs of biological research and lay the foundation for future therapeutic applications of diseases.

AntiVIRmiR: A repository of host antiviral miRNAs and their expression along with experimentally validated viral miRNAs and their targets

miRNAs play an essential role in promoting viral infections as well as modulating the antiviral defense. Several miRNA repositories have been developed for different species, e.g., human, mouse, and plant. However, 'VIRmiRNA' is the only existing resource for experimentally validated viral miRNAs and their targets. We have developed a 'AntiVIRmiR' resource encompassing data on host/virus miRNA expression during viral infection. This resource with 22,741 entries is divided into four sub-databases viz., 'DEmiRVIR', 'AntiVmiR', 'VIRmiRNA2' and 'VIRmiRTar2'. 'DEmiRVIR' has 10,033 differentially expressed host-viral miRNAs for 21 viruses. 'AntiVmiR' incorporates 1,642 entries for host miRNAs showing antiviral activity for 34 viruses. Additionally, 'VIRmiRNA2' includes 3,340 entries for experimentally validated viral miRNAs from 50 viruses along with 650 viral isomeric sequences for 14 viruses. Further, 'VIRmiRTar2' has 7,726 experimentally validated targets for viral miRNAs against 21 viruses. Furthermore, we have also performed network analysis for three sub-databases. Interactions between up/down-regulated human miRNAs and viruses are displayed for 'AntiVmiR' as well as 'DEmiRVIR'. Moreover, 'VIRmiRTar2' interactions are shown among different viruses, miRNAs, and their targets. We have provided browse, search, external hyperlinks, data statistics, and useful analysis tools. The database available at https://bioinfo.imtech.res.in/manojk/antivirmir would be beneficial for understanding the host-virus interactions as well as viral pathogenesis.

Inferring human miRNA–disease associations via multiple kernel fusion on GCNII

Increasing evidence shows that the occurrence of human complex diseases is closely related to the mutation and abnormal expression of microRNAs(miRNAs). MiRNAs have complex and fine regulatory mechanisms, which makes it a promising target for drug discovery and disease diagnosis. Therefore, predicting the potential miRNA-disease associations has practical significance. In this paper, we proposed an miRNA–disease association predicting method based on multiple kernel fusion on Graph Convolutional Network via Initial residual and Identity mapping (GCNII), called MKFGCNII. Firstly, we built a heterogeneous network of miRNAs and diseases to extract multi-layer features via GCNII. Secondly, multiple kernel fusion method was applied to weight fusion of embeddings at each layer. Finally, Dual Laplacian Regularized Least Squares was used to predict new miRNA–disease associations by the combined kernel in miRNA and disease spaces. Compared with the other methods, MKFGCNII obtained the highest AUC value of 0.9631. Code is available at https://github.com/cuntjx/bioInfo.

Exploration of shared TF-miRNA‒mRNA and mRNA-RBP-pseudogene networks in type 2 diabetes mellitus and breast cancer

Type 2 diabetes mellitus (T2DM) has been confirmed to be closely associated with breast cancer (BC). However, the shared mechanisms between these diseases remain unclear. By comparing different datasets, we identified shared differentially expressed (DE) RNAs in T2DM and BC, including 427 mRNAs and 6 miRNAs from the GEO(Gene Expression Omnibus) database. We used databases to predict interactions to construct two critical networks. The transcription factor (TF)-miRNA‒mRNA network contained 236 TFs, while the RNA binding protein (RBP)-pseudogene-mRNA network showed that the pseudogene S-phase kinase associated protein 1 pseudogene 1 (SKP1P1) might play a key role in regulating gene expression. The shared mRNAs between T2DM and BC were enriched in cytochrome (CYP) pathways, and further analysis of CPEB1 and COLEC12 expression in cell lines, single cells and other cancers showed that they were strongly correlated with the survival and prognosis of patients with BC. This result suggested that patients with T2DM presenting the downregulation of CPEB1 and COLEC12 might have a higher risk of developing BC. Overall, our work revealed that high expression of CYPs in patients with T2DM might be a susceptibility factor for BC and identified novel gene candidates and immune features that are promising targets for immunotherapy in patients with BC.

High-dimension to high-dimension screening for detecting genome-wide epigenetic and noncoding RNA regulators of gene expression

MOTIVATION

The advancement of high-throughput technology characterizes a wide variety of epigenetic modifications and noncoding RNAs across the genome involved in disease pathogenesis via regulating gene expression. The high dimensionality of both epigenetic/noncoding RNA and gene expression data make it challenging to identify the important regulators of genes. Conducting univariate test for each possible regulator-gene pair is subject to serious multiple comparison burden, and direct application of regularization methods to select regulator-gene pairs is computationally infeasible. Applying fast screening to reduce dimension first before regularization is more efficient and stable than applying regularization methods alone.

RESULTS

We propose a novel screening method based on robust partial correlation to detect epigenetic and noncoding RNA regulators of gene expression over the whole genome, a problem that includes both high-dimensional predictors and high-dimensional responses. Compared to existing screening methods, our method is conceptually innovative that it reduces the dimension of both predictor and response, and screens at both node (regulators or genes) and edge (regulator-gene pairs) levels. We develop data-driven procedures to determine the conditional sets and the optimal screening threshold, and implement a fast iterative algorithm. Simulations and applications to long noncoding RNA and microRNA regulation in Kidney cancer and DNA methylation regulation in Glioblastoma Multiforme illustrate the validity and advantage of our method.

AVAILABILITY AND IMPLEMENTATION

The R package, related source codes and real datasets used in this article are provided at https://github.com/kehongjie/rPCor.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Updated review of advances in microRNAs and complex diseases: taxonomy, trends and challenges of computational models

Since the problem proposed in late 2000s, microRNA-disease association (MDA) predictions have been implemented based on the data fusion paradigm. Integrating diverse data sources gains a more comprehensive research perspective, and brings a challenge to algorithm design for generating accurate, concise and consistent representations of the fused data. After more than a decade of research progress, a relatively simple algorithm like the score function or a single computation layer may no longer be sufficient for further improving predictive performance. Advanced model design has become more frequent in recent years, particularly in the form of reasonably combing multiple algorithms, a process known as model fusion. In the current review, we present 29 state-of-the-art models and introduce the taxonomy of computational models for MDA prediction based on model fusion and non-fusion. The new taxonomy exhibits notable changes in the algorithmic architecture of models, compared with that of earlier ones in the 2017 review by Chen et al. Moreover, we discuss the progresses that have been made towards overcoming the obstacles to effective MDA prediction since 2017 and elaborated on how future models can be designed according to a set of new schemas. Lastly, we analysed the strengths and weaknesses of each model category in the proposed taxonomy and proposed future research directions from diverse perspectives for enhancing model performance.

Comparison of plasma- and saliva-derived exosomal miRNA profiles reveals diagnostic potential in head and neck cancer

Background: Head and neck squamous cell carcinomas (HNSCC) lack tumor-specific biomarkers. Exosomes from HNSCC patients carry immunomodulatory molecules, and correlate with clinical parameters. We compared miRNA profiles of plasma- and saliva-derived exosomes to reveal liquid biomarker candidates for HNSCC.

Methods: Exosomes were isolated by differential ultracentrifugation from corresponding plasma and saliva samples from 11 HNSCC patients and five healthy donors (HD). Exosomal miRNA profiles, as determined by nCounter^® SPRINT technology, were analyzed regarding their diagnostic and prognostic potential, correlated to clinical data and integrated into network analysis.

Results: 119 miRNAs overlapped between plasma- and saliva-derived exosomes of HNSCC patients, from which 29 tumor-exclusive miRNAs, associated with TP53, TGFB1, PRDM1, FOX O 1 and CDH1 signaling, were selected. By intra-correlation of tumor-exclusive miRNAs from plasma and saliva, top 10 miRNA candidates with the strongest correlation emerged as diagnostic panels to discriminate cancer and healthy as well as potentially prognostic panels for disease-free survival (DFS). Further, exosomal miRNAs were differentially represented in human papillomavirus (HPV) positive and negative as well as low and high stage disease.

Conclusion: A plasma- and a saliva-derived panel of tumor-exclusive exosomal miRNAs hold great potential as liquid biopsy for discrimination between cancer and healthy as well as HPV status and disease stage. Exosomal miRNAs from both biofluids represent a promising tool for future biomarker studies, emphasizing the possibility to substitute plasma by less-invasive saliva collection.

Prediction of biomarker-disease associations based on graph attention network and text representation

MOTIVATION

The associations between biomarkers and human diseases play a key role in understanding complex pathology and developing targeted therapies. Wet lab experiments for biomarker discovery are costly, laborious and time-consuming. Computational prediction methods can be used to greatly expedite the identification of candidate biomarkers.

RESULTS

Here, we present a novel computational model named GTGenie for predicting the biomarker-disease associations based on graph and text features. In GTGenie, a graph attention network is utilized to characterize diverse similarities of biomarkers and diseases from heterogeneous information resources. Meanwhile, a pretrained BERT-based model is applied to learn the text-based representation of biomarker-disease relation from biomedical literature. The captured graph and text features are then integrated in a bimodal fusion network to model the hybrid entity representation. Finally, inductive matrix completion is adopted to infer the missing entries for reconstructing relation matrix, with which the unknown biomarker-disease associations are predicted. Experimental results on HMDD, HMDAD and LncRNADisease data sets showed that GTGenie can obtain competitive prediction performance with other state-of-the-art methods.

AVAILABILITY

The source code of GTGenie and the test data are available at: https://github.com/Wolverinerine/GTGenie.

idenMD-NRF: a ranking framework for miRNA-disease association identification

Identifying miRNA-disease associations is an important task for revealing pathogenic mechanism of complicated diseases. Different computational methods have been proposed. Although these methods obtained encouraging performance for detecting missing associations between known miRNAs and diseases, how to accurately predict associated diseases for new miRNAs is still a difficult task. In this regard, a ranking framework named idenMD-NRF is proposed for miRNA-disease association identification. idenMD-NRF treats the miRNA-disease association identification as an information retrieval task. Given a novel query miRNA, idenMD-NRF employs Learning to Rank algorithm to rank associated diseases based on high-level association features and various predictors. The experimental results on two independent test datasets indicate that idenMD-NRF is superior to other compared predictors. A user-friendly web server of idenMD-NRF predictor is freely available at http://bliulab.net/idenMD-NRF/.

MicroRNA Methylome Signature and Their Functional Roles in Colorectal Cancer Diagnosis, Prognosis, and Chemoresistance

Colorectal cancer (CRC) is one of the leading causes of cancer-related deaths worldwide. Despite significant advances in the diagnostic services and patient care, several gaps remain to be addressed, from early detection, to identifying prognostic variables, effective treatment for the metastatic disease, and the implementation of tailored treatment strategies. MicroRNAs, the short non-coding RNA species, are deregulated in CRC and play a significant role in the occurrence and progression. Nevertheless, microRNA research has historically been based on expression levels to determine its biological significance. The exact mechanism underpinning microRNA deregulation in cancer has yet to be elucidated, but several studies have demonstrated that epigenetic mechanisms play important roles in the regulation of microRNA expression, particularly DNA methylation. However, the methylation profiles of microRNAs remain unknown in CRC patients. Methylation is the next major paradigm shift in cancer detection since large-scale epigenetic alterations are potentially better in identifying and classifying cancers at an earlier stage than somatic mutations. This review aims to provide insight into the current state of understanding of microRNA methylation in CRC. The new knowledge from this study can be utilized for personalized health diagnostics, disease prediction, and monitoring of treatment.

DNRLCNN: A CNN Framework for Identifying MiRNA-Disease Associations Using Latent Feature Matrix Extraction with Positive Samples

Emerging evidence indicates that miRNAs have strong relationships with many human diseases. Investigating the associations will contribute to elucidating the activities of miRNAs and pathogenesis mechanisms, and providing new opportunities for disease diagnosis and drug discovery. Therefore, it is of significance to identify potential associations between miRNAs and diseases. The existing databases about the miRNA-disease associations (MDAs) only provide the known MDAs, which can be regarded as positive samples. However, the unknown MDAs are not sufficient to regard as reliable negative samples. To deal with this uncertainty, we proposed a convolutional neural network (CNN) framework, named DNRLCNN, based on a latent feature matrix extracted by only positive samples to predict MDAs. First, by only considering the positive samples into the calculation process, we captured the latent feature matrix for complex interactions between miRNAs and diseases in low-dimensional space. Then, we constructed a feature vector for each miRNA and disease pair based on the feature representation. Finally, we adopted a modified CNN for the feature vector to predict MDAs. As a result, our model achieves better performance than other state-of-the-art methods which based CNN in fivefold cross-validation on both miRNA-disease association prediction task (average AUC of 0.9030) and miRNA-phenotype association prediction task (average AUC of 0. 9442). In addition, we carried out case studies on two human diseases, and all the top-50 predicted miRNAs for lung neoplasms are confirmed by HMDD v3.2 and dbDEMC 2.0 databases, 98% of the top-50 predicted miRNAs for heart failure are confirmed. The experiment results show that our model has the capability of inferring potential disease-related miRNAs.

dbDEMC 3.0: Functional Exploration of Differentially Expressed miRNAs in Cancers of Human and Model Organisms

MicroRNAs (miRNAs) are important regulators in gene expression. The dysregulation of miRNA expression is widely reported in the transformation from physiological to pathological states of cells. A large number of differentially expressed miRNAs (DEMs) have been identified in various human cancers by using high-throughput technologies, such as microarray and miRNA-seq. Through mining of published studies with high-throughput experiment information, the database of DEMs in human cancers (dbDEMC) was constructed with the aim of providing a systematic resource for the storage and query of the DEMs. Here we report an update of the dbDEMC to version 3.0, which contains two-fold more data entries than the second version and now includes also data from mice and rats. The dbDEMC 3.0 contains 3268 unique DEMs in 40 different cancer types. The current datasets for differential expression analysis have expanded to 9 generalized categories. Moreover, the current release integrates functional annotations of DEMs obtained by using experimentally validated targets. The annotations can be of great benefit to the intensive analysis of the roles of DEMs in cancer. In summary, dbDEMC 3.0 provides a valuable resource for characterizing molecular functions and regulatory mechanisms of DEMs in human cancers. The dbDEMC 3.0 is freely accessible at https://www.biosino.org/dbDEMC.

In silico Methods for Identification of Potential Therapeutic Targets

At the initial stage of drug discovery, identifying novel targets with maximal efficacy and minimal side effects can improve the success rate and portfolio value of drug discovery projects while simultaneously reducing cycle time and cost. However, harnessing the full potential of big data to narrow the range of plausible targets through existing computational methods remains a key issue in this field. This paper reviews two categories of in silico methods—comparative genomics and network-based methods—for finding potential therapeutic targets among cellular functions based on understanding their related biological processes. In addition to describing the principles, databases, software, and applications, we discuss some recent studies and prospects of the methods. While comparative genomics is mostly applied to infectious diseases, network-based methods can be applied to infectious and non-infectious diseases. Nonetheless, the methods often complement each other in their advantages and disadvantages. The information reported here guides toward improving the application of big data-driven computational methods for therapeutic target discovery.

Graphical abstract

Construction of the miRNA-mRNA Regulatory Networks and Explore Their Role in the Development of Lung Squamous Cell Carcinoma

Purpose: MicroRNA (miRNA) binds to target mRNA and inhibit post-transcriptional gene expression. It plays an essential role in regulating gene expression, cell cycle, and biological development. This study aims to identify potential miRNA-mRNA regulatory networks that contribute to the pathogenesis of lung squamous cell carcinoma (LUSC).

Patients and Methods: MiRNA microarray and RNA-Seq datasets were obtained from the gene expression omnibus (GEO) databases, the cancer genome atlas (TCGA), miRcancer, and dbDEMC. The GEO2R tool, “limma” and “DEseq” R packages were used to perform differential expression analysis. Gene enrichment analysis was conducted using the DAVID, DIANA, and Hiplot tools. The miRNA-mRNA regulatory networks were screened from the experimentally validated miRNA-target interactions databases (miRTarBase and TarBase). External validation was carried out in 30 pairs of LUSC tissues by Real-Time Quantitative Reverse Transcription PCR (qRT-PCR). Receiver operating characteristic curve (ROC) and decision curve analysis (DCA) were conducted to evaluate the diagnostic value. Clinical, survival and phenotypic analysis of miRNA-mRNA regulatory networks were further explored.

Results: We screened 5 miRNA and 10 mRNA expression datasets from GEO and identified 7 DE-miRNAs and 270 DE-mRNAs. After databases screening and correlation analysis, four pairs of miRNA-mRNA regulatory networks were screened out. The miRNA-mRNA network of miR-205-5p (up) and PTPRM (down) was validated in 30 pairs of LUSC tissues. MiR-205-5p and PTPRM have good diagnostic efficacy and are expressed differently in different clinical features and are related to tumor immunity.

Conclusion: The research identified a potential miRNA-mRNA regulatory network, providing a new way to explore the genesis and development of LUSC.

iUMRG: multi-layered network-guided propagation modeling for the inference of susceptibility genes and potential drugs against uveal melanoma

Uveal melanoma (UM) is the most common primary malignant intraocular tumor. The use of precision medicine for UM to enable personalized diagnosis, prognosis, and treatment require the development of computer-aided strategies and predictive tools that can identify novel high-confidence susceptibility genes (HSGs) and potential therapeutic drugs. In the present study, a computational framework via propagation modeling on integrated multi-layered molecular networks (abbreviated as iUMRG) was proposed for the systematic inference of HSGs in UM. Under the leave-one-out cross-validation experiments, the iUMRG achieved superior predictive performance and yielded a higher area under the receiver operating characteristic curve value (0.8825) for experimentally verified SGs. In addition, using the experimentally verified SGs as seeds, genome-wide screening was performed to detect candidate HSGs using the iUMRG. Multi-perspective validation analysis indicated that most of the top 50 candidate HSGs were indeed markedly associated with UM carcinogenesis, progression, and outcome. Finally, drug repositioning experiments performed on the HSGs revealed 17 potential targets and 10 potential drugs, of which six have been approved for UM treatment. In conclusion, the proposed iUMRG is an effective supplementary tool in UM precision medicine, which may assist the development of new medical therapies and discover new SGs.

miRCom: Tensor Completion Integrating Multi-View Information to Deduce the Potential Disease-Related miRNA-miRNA Pairs

MicroRNAs (miRNAs) are consistently capable of regulating gene expression synergistically in a combination mode and play a key role in various biological processes associated with the initiation and development of human diseases, which indicate that comprehending the synergistic molecular mechanism of miRNAs may facilitate understanding the pathogenesis of diseases or even overcome it. However, most existing computational methods had an incomprehensive acknowledge of the miRNA synergistic effect on the pathogenesis of complex diseases, or were hard to be extended to a large-scale prediction task of miRNA synergistic combinations for different diseases. In this article, we propose a novel tensor completion framework integrating multi-view miRNAs and diseases information, called miRCom, for the discovery of potential disease-associated miRNA-miRNA pairs. We first construct an incomplete three-order association tensor and several types of similarity matrices based on existing biological knowledge. Then, we formulate an objective function via performing the factorizations of coupled tensor and matrices simultaneously. Finally, we build an optimization schema by adopting the ADMM algorithm. After that, we obtain the prediction of miRNA-miRNA pairs for different diseases from the full tensor. The contrastive experimental results with other approaches verified that miRCom effectively identify the potential disease-related miRNA-miRNA pairs. Moreover, case study results further illustrated that miRNA-miRNA pairs have more biologically significance and prognostic value than single miRNAs.

BioTAGME: A Comprehensive Platform for Biological Knowledge Network Analysis

The inference of novel knowledge and new hypotheses from the current literature analysis is crucial in making new scientific discoveries. In bio-medicine, given the enormous amount of literature and knowledge bases available, the automatic gain of knowledge concerning relationships among biological elements, in the form of semantically related terms (or entities), is rising novel research challenges and corresponding applications. In this regard, we propose BioTAGME, a system that combines an entity-annotation framework based on Wikipedia corpus (i.e., TAGME tool) with a network-based inference methodology (i.e., DT-Hybrid). This integration aims to create an extensive Knowledge Graph modeling relations among biological terms and phrases extracted from titles and abstracts of papers available in PubMed. The framework consists of a back-end and a front-end. The back-end is entirely implemented in Scala and runs on top of a Spark cluster that distributes the computing effort among several machines. The front-end is released through the Laravel framework, connected with the Neo4j graph database to store the knowledge graph.

Investigating the interference of single nucleotide polymorphisms with miRNA mediated gene regulation in pancreatic ductal adenocarcinoma: An in silico approach

BACKGROUND

Pancreatic ductal adenocarcinoma (PDAC) has a strong genetic component and single nucleotide polymorphisms (SNPs) in key genes have been found to modulate the susceptibility of the individuals to the disease. SNPs in 3'-UTR of the target genes or in miRNA seed region has gained much importance as this may lead to impairment of miRNA-mRNA interaction. Not much information about this phenomenon is available with respect to PDAC and we wanted to predict such SNPs which could affect miRNA function in the disease using bioinformatics tools.

METHODS

After identifying the deregulated miRNAs and genes in PDAC, we determined how many of those altered genes are among experimentally validated targets of those miRNAs. Subsequently, SNPs which could alter these miRNA-mRNA interactions were detected using multiple webtools following high stringent conditions. Disease relevance of the SNPs were also evaluated.

RESULTS

We identified a total of 2492 experimentally validated target genes for 303 miRNAs deregulated in PDAC. Our meta-analysis from 363 PDAC patients and 162 control individuals resulted in a set of differentially expressed genes in pancreatic cancer, which was further compared with the miRNA target genes to get targets differentially expressed in pancreatic cancer. We further detected SNPs either in 'seed' region of miRNAs or 'seed-match' sequence of mRNAs either having disruption or creation of miRNA binding site, correlated the expression for each miRNA-SNP-mRNA interaction. Selected SNPs were found to be in LD with important GWAS identified SNPs.

CONCLUSION

Our study, hereby, explores the probable effects of SNPs on miRNA-target mRNA interactions. Through stringent analytical methods, we have identified 3 common variants and 13other rare variants possibly interfering with miRNA mediated gene regulation in PDAC.

miRModuleNet: Detecting miRNA-mRNA Regulatory Modules

Increasing evidence that microRNAs (miRNAs) play a key role in carcinogenesis has revealed the need for elucidating the mechanisms of miRNA regulation and the roles of miRNAs in gene-regulatory networks. A better understanding of the interactions between miRNAs and their mRNA targets will provide a better understanding of the complex biological processes that occur during carcinogenesis. Increased efforts to reveal these interactions have led to the development of a variety of tools to detect and understand these interactions. We have recently described a machine learning approach miRcorrNet, based on grouping and scoring (ranking) groups of genes, where each group is associated with a miRNA and the group members are genes with expression patterns that are correlated with this specific miRNA. The miRcorrNet tool requires two types of -omics data, miRNA and mRNA expression profiles, as an input file. In this study we describe miRModuleNet, which groups mRNA (genes) that are correlated with each miRNA to form a star shape, which we identify as a miRNA-mRNA regulatory module. A scoring procedure is then applied to each module to further assess their contribution in terms of classification. An important output of miRModuleNet is that it provides a hierarchical list of significant miRNA-mRNA regulatory modules. miRModuleNet was further validated on external datasets for their disease associations, and functional enrichment analysis was also performed. The application of miRModuleNet aids the identification of functional relationships between significant biomarkers and reveals essential pathways involved in cancer pathogenesis. The miRModuleNet tool and all other supplementary files are available at https://github.com/malikyousef/miRModuleNet/