Network-based ranking methods for prediction of novel disease associated microRNAs

MicroRNA-98: the multifaceted regulator in human cancer progression and therapy

MicroRNA-98 (miR-98) stands as an important molecule in the intricate landscape of oncology. As a subset of microRNAs, these small non-coding RNAs have accompanied a new era in cancer research, underpinning their significant roles in tumorigenesis, metastasis, and therapeutic interventions. This review provides a comprehensive insight into the biogenesis, molecular properties, and physiological undertakings of miR-98, highlighting its double-edged role in cancer progression-acting both as a tumor promoter and suppressor. Intriguingly, miR-98 has profound implications for various aspects of cancer progression, modulating key cellular functions, including proliferation, apoptosis, and the cell cycle. Given its expression patterns, the potential of miR-98 as a diagnostic and prognostic biomarker, especially in liquid biopsies and tumor tissues, is explored, emphasizing the hurdles in translating these findings clinically. The review concludes by evaluating therapeutic avenues to modulate miR-98 expression, addressing the challenges in therapy resistance, and assessing the efficacy of miR-98 interventions. In conclusion, while miR-98's involvement in cancer showcases promising diagnostic and therapeutic avenues, future research should pivot towards understanding its role in tumor-stroma interactions, immune modulation, and metabolic regulation, thereby unlocking novel strategies for cancer management.

Random walk with restart on multilayer networks: from node prioritisation to supervised link prediction and beyond

BACKGROUND

Biological networks have proven invaluable ability for representing biological knowledge. Multilayer networks, which gather different types of nodes and edges in multiplex, heterogeneous and bipartite networks, provide a natural way to integrate diverse and multi-scale data sources into a common framework. Recently, we developed MultiXrank, a Random Walk with Restart algorithm able to explore such multilayer networks. MultiXrank outputs scores reflecting the proximity between an initial set of seed node(s) and all the other nodes in the multilayer network. We illustrate here the versatility of bioinformatics tasks that can be performed using MultiXrank.

RESULTS

We first show that MultiXrank can be used to prioritise genes and drugs of interest by exploring multilayer networks containing interactions between genes, drugs, and diseases. In a second study, we illustrate how MultiXrank scores can also be used in a supervised strategy to train a binary classifier to predict gene-disease associations. The classifier performance are validated using outdated and novel gene-disease association for training and evaluation, respectively. Finally, we show that MultiXrank scores can be used to compute diffusion profiles and use them as disease signatures. We computed the diffusion profiles of more than 100 immune diseases using a multilayer network that includes cell-type specific genomic information. The clustering of the immune disease diffusion profiles reveals shared shared phenotypic characteristics.

CONCLUSION

Overall, we illustrate here diverse applications of MultiXrank to showcase its versatility. We expect that this can lead to further and broader bioinformatics applications.

A method to improve the prediction performance of cancer-gene association by screening negative training samples through gene network data

This work focuses on data sampling in cancer-gene association prediction. Currently, researchers are using machine learning methods to predict genes that are more likely to produce cancer-causing mutations. To improve the performance of machine learning models, methods have been proposed, one of which is to improve the quality of the training data. Existing methods focus mainly on positive data, i.e. cancer driver genes, for screening selection. This paper proposes a low-cancer-related gene screening method based on gene network and graph theory algorithms to improve the negative samples selection. Genetic data with low cancer correlation is used as negative training samples. After experimental verification, using the negative samples screened by this method to train the cancer gene classification model can improve prediction performance. The biggest advantage of this method is that it can be easily combined with other methods that focus on enhancing the quality of positive training samples. It has been demonstrated that significant improvement is achieved by combining this method with three state-of-the-arts cancer gene prediction methods.

Application value of miRNA-182 as a biomarker for cancer diagnosis: a systematic review with meta-analysis

Aim: This study aims to establish the potential reliability and validity of miRNA-182 as a diagnostic tool in oncology, and hence to contribute to the decision-making process in clinical settings. Materials & methods: To further evaluate the role of miRNA-182 as a cancer biomarker, we conducted a search of the PubMed, Cochrane Library, Wanfang and China National Knowledge Infrastructure databases of existing literature. Conclusion: These results suggest that miRNA-182 could function as a potential molecular marker for cancer detection and diagnosis. The effect of miRNA-182 on tumor development should be further studied to confirm these results and add to the current understanding of its role in cancer.

Discerning the Prospects of miRNAs as a Multi-Target Therapeutic and Diagnostic for Alzheimer's Disease

Although over the last few decades, numerous attempts have been made to halt Alzheimer's disease (AD) progression and mitigate its symptoms, only a few have been proven beneficial. Most medications available, still only cater to the symptoms of the disease rather than fixing the cause at the root level. A novel approach involving the use of miRNAs, which work on the principle of gene silencing, is being explored by scientists. Naturally present miRNAs in the biological system help to regulate various genes than may be implicated in AD-like BACE-1 and APP. One miRNA thus, holds the power to keep a check on several genes, conferring it the ability to be used as a multi-target therapeutic. With aging and the onset of diseased pathology, dysregulation of these miRNAs is observed. This flawed miRNA expression is responsible for the unusual buildup of amyloid proteins, fibrillation of tau proteins in the brain, neuronal death and other hallmarks leading to AD. The use of miRNA mimics and miRNA inhibitors provides an attractive perspective for fixing the upregulation and downregulation of miRNAs that led to abnormal cellular activities. Furthermore, the detection of miRNAs in the CSF and serum of diseased patients might be considered an earlier biomarker for the disease. While most of the therapies designed around AD have not succeeded completely, the targeting of dysregulated miRNAs in AD patients might give a new direction to scholars to develop an effective treatment for Alzheimer's disease.

MAPT rs17649553 T allele is associated with better verbal memory and higher small-world properties in Parkinson's disease

Currently, over 90 genetic loci have been found to be associated with Parkinson's disease (PD) in genome-wide association studies, nevertheless, the effects of these genetic variants on the clinical features and brain structure of PD patients are largely unknown. This study investigated the effects of microtubule-associated protein tau (MAPT) rs17649553 (C>T), a genetic variant associated with reduced PD risk, on the clinical manifestations and brain networks of PD patients. We found MAPT rs17649553 T allele was associated with better verbal memory in PD patients. In addition, MAPT rs17649553 significantly shaped the topology of gray matter covariance network and white matter network. Both the network metrics in gray matter covariance network and white matter network were correlated with verbal memory, however, the mediation analysis showed that it was the small-world properties in white matter network that mediated the effects of MAPT rs17649553 on verbal memory. These results suggest that MAPT rs17649553 T allele is associated with higher small-world properties in structural network and better verbal memory in PD.

MDA-GCNFTG: identifying miRNA-disease associations based on graph convolutional networks via graph sampling through the feature and topology graph

Accurate identification of the miRNA-disease associations (MDAs) helps to understand the etiology and mechanisms of various diseases. However, the experimental methods are costly and time-consuming. Thus, it is urgent to develop computational methods towards the prediction of MDAs. Based on the graph theory, the MDA prediction is regarded as a node classification task in the present study. To solve this task, we propose a novel method MDA-GCNFTG, which predicts MDAs based on Graph Convolutional Networks (GCNs) via graph sampling through the Feature and Topology Graph to improve the training efficiency and accuracy. This method models both the potential connections of feature space and the structural relationships of MDA data. The nodes of the graphs are represented by the disease semantic similarity, miRNA functional similarity and Gaussian interaction profile kernel similarity. Moreover, we considered six tasks simultaneously on the MDA prediction problem at the first time, which ensure that under both balanced and unbalanced sample distribution, MDA-GCNFTG can predict not only new MDAs but also new diseases without known related miRNAs and new miRNAs without known related diseases. The results of 5-fold cross-validation show that the MDA-GCNFTG method has achieved satisfactory performance on all six tasks and is significantly superior to the classic machine learning methods and the state-of-the-art MDA prediction methods. Moreover, the effectiveness of GCNs via the graph sampling strategy and the feature and topology graph in MDA-GCNFTG has also been demonstrated. More importantly, case studies for two diseases and three miRNAs are conducted and achieved satisfactory performance.

Discovery of potential serum and urine-based microRNA as minimally-invasive biomarkers for breast and gynecological cancer

BACKGROUND

Deregulated microRNAs (miRNAs) in breast and gynecological cancer might contribute to improve early detection of female malignancies.

OBJECTIVE

Specification of miRNA types in serum and urine as minimally-invasive biomarkers for breast (BC), endometrial (EC) and ovarian cancer (OC).

METHODS

In a discovery phase, serum and urine samples from 17 BC, five EC and five OC patients vs. ten healthy controls (CTRL) were analyzed with Agilent human miRNA microarray chip. Selected miRNA types were further investigated by RT-qPCR in serum (31 BC, 13 EC, 15 OC patients, 32 CTRL) and urine (25 BC, 10 EC, 10 OC patients, 30 CTRL) applying two-sample t-tests.

RESULTS

Several miRNA biomarker candidates exhibited diagnostic features due to distinctive expression levels (serum: 26; urine: 22). Among these, miR-518b, -4719 and -6757-3p were found specifically deregulated in BC serum. Four, non-entity-specific, novel biomarker candidates with unknown functional roles were identified in urine (miR-3973; -4426; -5089-5p and -6841). RT-qPCR identified miR-484/-23a (all p⩽ 0.001) in serum as potential diagnostic markers for EC and OC while miR-23a may also serve as an endogenous control in BC diagnosis.

CONCLUSIONS

Promising miRNAs as liquid biopsy-based tools in the detection of BC, EC and OC qualified for external validation in larger cohorts.

RWRMTN: a tool for predicting disease-associated microRNAs based on a microRNA-target gene network

BACKGROUND

The misregulation of microRNA (miRNA) has been shown to cause diseases. Recently, we have proposed a computational method based on a random walk framework on a miRNA-target gene network to predict disease-associated miRNAs. The prediction performance of our method is better than that of some existing state-of-the-art network- and machine learning-based methods since it exploits the mutual regulation between miRNAs and their target genes in the miRNA-target gene interaction networks.

RESULTS

To facilitate the use of this method, we have developed a Cytoscape app, named RWRMTN, to predict disease-associated miRNAs. RWRMTN can work on any miRNA-target gene network. Highly ranked miRNAs are supported with evidence from the literature. They then can also be visualized based on the rankings and in relationships with the query disease and their target genes. In addition, automation functions are also integrated, which allow RWRMTN to be used in workflows from external environments. We demonstrate the ability of RWRMTN in predicting breast and lung cancer-associated miRNAs via workflows in Cytoscape and other environments.

CONCLUSIONS

Considering a few computational methods have been developed as software tools for convenient uses, RWRMTN is among the first GUI-based tools for the prediction of disease-associated miRNAs which can be used in workflows in different environments.

Analyzing the regulation of miRNAs on protein-protein interaction network in Hodgkin lymphoma

Background

Hodgkin Lymphoma (HL) is a type of aggressive malignancy in lymphoma that has high incidence in young adults and elderly patients. Identification of reliable diagnostic markers and efficient therapeutic targets are especially important for the diagnosis and treatment of HL. Although many HL-related molecules have been identified, our understanding on the molecular mechanisms underlying the disease is still far from complete due to its complex and heterogeneous characteristics. In such situation, exploring the molecular mechanisms underlying HL via systems biology approaches provides a promising option. In this study, we try to elucidate the molecular mechanisms related to the disease and identify potential pharmaceutical targets from a network-based perspective.

Results

We constructed a series of network models. Based on the analysis of these networks, we attempted to identify the biomarkers and elucidate the molecular mechanisms underlying HL. Initially, we built three different but related protein networks, i.e., background network, HL-basic network and HL-specific network. By analyzing these three networks, we investigated the connection characteristic of the HL-related proteins. Subsequently, we explored the miRNA regulation on HL-specific network and analyzed three kinds of simple regulation patterns, i.e., co-regulation of protein pairs, as well as the direct and indirect regulation of triple proteins. Finally, we constructed a simplified protein network combined with the regulation of miRNAs on proteins to better understand the relation between HL-related proteins and miRNAs.

Conclusions

We find that the HL-related proteins are more likely to connect with each other compared to other proteins. Moreover, the HL-specific network can be further divided into five sub-networks and 49 proteins as the backbone of HL-specific network make up and connect these 5 sub-networks. Thus, they may be closely associated with HL. In addition, we find that the co-regulation of protein pairs is the main regulatory pattern of miRNAs on the protein network in the HL-specific network. According to the regulation of miRNA on protein network, we have identified 5 core miRNAs as the potential biomarkers for diagnostic of HL. Finally, several protein pathways have been identified to closely associated with HL, which provides deep insights into underlying mechanism of HL.

Electronic supplementary material

The online version of this article (10.1186/s12859-019-3041-9) contains supplementary material, which is available to authorized users.

CAMIRADA: Cancer microRNA association discovery algorithm, a case study on breast cancer

In recent studies, non-coding protein RNAs have been identified as microRNA that can be used as biomarkers for early diagnosis and treatment of cancer, that decrease mortality in cancer. A microRNA may target hundreds or thousands of genes and a gene may regulate several microRNAs, so determining which microRNA is associated with which cancer is a big challenge. Many computational methods have been performed to detect micoRNAs association with cancer, but more effort is needed with higher accuracy. Increasing research has shown that relationship between microRNAs and TFs play a significant role in the diagnosis of cancer. Therefore, we developed a new computational framework (CAMIRADA) to identify cancer-related microRNAs based on the relationship between microRNAs and disease genes (DG) in the protein network, the functional relationships between microRNAs and Transcription Factors (TF) on the co-expression network, and the relationship between microRNAs and the Differential Expression Gene (DEG) on co-expression network. The CAMIRADA was applied to assess breast cancer data from two HMDD and miR2Disease databases. In this study, the AUC for the 65 microRNAs of the top of the list was 0.95, which was more accurate than the similar methods used to detect microRNAs associated with the cancer artery.

Bipartite Heterogeneous Network Method Based on Co-neighbor for MiRNA-Disease Association Prediction

In recent years, miRNA variation and dysregulation have been found to be closely related to human tumors, and identifying miRNA-disease associations is helpful for understanding the mechanisms of disease or tumor development and is greatly significant for the prognosis, diagnosis, and treatment of human diseases. This article proposes a Bipartite Heterogeneous network link prediction method based on co-neighbor to predict miRNA-disease association (BHCN). According to the structural characteristics of the bipartite network, the concept of bipartite network co-neighbors is proposed, and the co-neighbors were used to represent the probability of association between disease and miRNA. To predict the isolated diseases and the new miRNA based on the association probability expressed by co-neighbors, we utilized the similarity between disease nodes and the similarity between miRNA nodes in heterogeneous networks to represent the association probability between disease and miRNA. The model's predictive performance was evaluated by the leave-one-out cross validation (LOOCV) on different datasets. The AUC value of BHCN on the gold benchmark dataset was 0.7973, and the AUC obtained on the prediction dataset was 0.9349, which was better than that of the classic global algorithm. In this case study, we conducted predictive studies on breast neoplasms and colon neoplasms. Most of the top 50 predicted results were confirmed by three databases, namely, HMDD, miR2disease, and dbDEMC, with accuracy rates of 96 and 82%. In addition, BHCN can be used for predicting isolated diseases (without any known associated diseases) and new miRNAs (without any known associated miRNAs). In the isolated disease case study, the top 50 of breast neoplasm and colon neoplasm potentials associated with miRNAs predicted an accuracy of 100 and 96%, respectively, thereby demonstrating the favorable predictive power of BHCN for potentially relevant miRNAs.

LSGSP: a novel miRNA–disease association prediction model using a Laplacian score of the graphs and space projection federated method

Lots of research findings have indicated that miRNAs (microRNAs) are involved in many important biological processes; their mutations and disorders are closely related to diseases, therefore, determining the associations between human diseases and miRNAs is key to understand pathogenic mechanisms. Existing biological experimental methods for identifying miRNA–disease associations are usually expensive and time consuming. Therefore, the development of efficient and reliable computational methods for identifying disease-related miRNAs has become an important topic in the field of biological research in recent years. In this study, we developed a novel miRNA–disease association prediction model using a Laplacian score of the graphs and space projection federated method (LSGSP). This integrates experimentally validated miRNA–disease associations, disease semantic similarity scores, miRNA functional scores, and miRNA family information to build a new disease similarity network and miRNA similarity network, and then obtains the global similarities of these networks through calculating the Laplacian score of the graphs, based on which the miRNA–disease weighted network can be constructed through combination with the miRNA–disease Boolean network. Finally, the miRNA–disease score was obtained via projecting the miRNA space and disease space onto the miRNA–disease weighted network. Compared with several other state-of-the-art methods, using leave-one-out cross validation (LOOCV) to evaluate the accuracy of LSGSP with respect to a benchmark dataset, prediction dataset and compare dataset, LSGSP showed excellent predictive performance with high AUC values of 0.9221, 0.9745 and 0.9194, respectively. In addition, for prostate neoplasms and lung neoplasms, the consistencies between the top 50 predicted miRNAs (obtained from LSGSP) and the results (confirmed from the updated HMDD, miR2Disease, and dbDEMC databases) reached 96% and 100%, respectively. Similarly, for isolated diseases (diseases not associated with any miRNAs), the consistencies between the top 50 predicted miRNAs (obtained from LSGSP) and the results (confirmed from the above-mentioned three databases) reached 98% and 100%, respectively. These results further indicate that LSGSP can effectively predict potential associations between miRNAs and diseases.

Lots of research findings have indicated that the mutations and disorders of miRNAs (microRNAs) are closely related to diseases. Therefore, determining the associations between human diseases and miRNAs is key to understand the pathogenic mechanisms.

Drug Repositioning by Integrating Known Disease-Gene and Drug-Target Associations in a Semi-supervised Learning Model

Computational drug repositioning has been proven as a promising and efficient strategy for discovering new uses from existing drugs. To achieve this goal, a number of computational methods have been proposed, which are based on different data sources of drugs and diseases. These methods approach the problem using either machine learning- or network-based models with an assumption that similar drugs can be used for similar diseases to identify new indications of drugs. Therefore, similarities between drugs and between diseases are usually used as inputs. In addition, known drug-disease associations are also needed for the methods as prior information. It should be noted that those associations are still not well established due to the fact that many of marketed drugs have been withdrawn and this could affect the outcome of the methods. In this study, we propose a novel method named RLSDR (Regularized Least Square for Drug Repositioning) to find new uses of drugs. More specifically, it relies on a semi-supervised learning model, Regularized Least Square, thus it does not require definition of non-drug-disease associations as previously proposed machine learning-based methods. In addition, the similarity between drugs measured by chemical structures of drug compounds and the similarity between diseases which share phenotypes can be represented in a form of either similarity network or similarity matrix as inputs of the method. Moreover, instead of using a gold-standard set of known drug-disease associations, we construct an artificial set of the associations based on known disease-gene and drug-target associations. Experiment results demonstrate that RLSDR achieves better prediction performance on the artificial set of drug-disease associations than that on the gold-standard ones in terms of area under the Receiver Operating Characteristic (ROC) curve (AUC). In addition, it outperforms two representative network-based methods irrespective of the prior information of drug-disease associations. Novel indications for a number of drugs are also identified and validated by evidences from a different data resource.

Predicting MicroRNA-Disease Associations Based on Improved MicroRNA and Disease Similarities

MicroRNAs (miRNAs) are a type of non-coding RNAs with about ∼22nt nucleotides. Increasing evidences have shown that miRNAs play critical roles in many human diseases. The identification of human disease-related miRNAs is helpful to explore the underlying pathogenesis of diseases. More and more experimental validated associations between miRNAs and diseases have been reported in the recent studies, which provide useful information for new miRNA-disease association discovery. In this study, we propose a computational framework, KBMF-MDI, to predict the associations between miRNAs and diseases based on their similarities. The sequence and function information of miRNAs are used to measure similarity among miRNAs while the semantic and function information of disease are used to measure similarity among diseases, respectively. In addition, the kernelized Bayesian matrix factorization method is employed to infer potential miRNA-disease associations by integrating these data sources. We applied this method to 6,084 known miRNA-disease associations and utilized 5-fold cross validation to evaluate the performance. The experimental results demonstrate that our method can effectively predict unknown miRNA-disease associations.

The Emerging Potential for Network Analysis to Inform Precision Cancer Medicine

Precision cancer medicine promises to tailor clinical decisions to patients using genomic information. Indeed, successes of drugs targeting genetic alterations in tumors, such as imatinib that targets BCR-ABL in chronic myelogenous leukemia, have demonstrated the power of this approach. However, biological systems are complex, and patients may differ not only by the specific genetic alterations in their tumor, but also by more subtle interactions among such alterations. Systems biology and more specifically, network analysis, provides a framework for advancing precision medicine beyond clinical actionability of individual mutations. Here we discuss applications of network analysis to study tumor biology, early methods for N-of-1 tumor genome analysis, and the path for such tools to the clinic.

Annotating Diseases Using Human Phenotype Ontology Improves Prediction of Disease-Associated Long Non-coding RNAs

Recently, many long non-coding RNAs (lncRNAs) have been identified and their biological function has been characterized; however, our understanding of their underlying molecular mechanisms related to disease is still limited. To overcome the limitation in experimentally identifying disease-lncRNA associations, computational methods have been proposed as a powerful tool to predict such associations. These methods are usually based on the similarities between diseases or lncRNAs since it was reported that similar diseases are associated with functionally similar lncRNAs. Therefore, prediction performance is highly dependent on how well the similarities can be captured. Previous studies have calculated the similarity between two diseases by mapping exactly each disease to a single Disease Ontology (DO) term, and then use a semantic similarity measure to calculate the similarity between them. However, the problem of this approach is that a disease can be described by more than one DO terms. Until now, there is no annotation database of DO terms for diseases except for genes. In contrast, Human Phenotype Ontology (HPO) is designed to fully annotate human disease phenotypes. Therefore, in this study, we constructed disease similarity networks/matrices using HPO instead of DO. Then, we used these networks/matrices as inputs of two representative machine learning-based and network-based ranking algorithms, that is, regularized least square and heterogeneous graph-based inference, respectively. The results showed that the prediction performance of the two algorithms on HPO-based is better than that on DO-based networks/matrices. In addition, our method can predict 11 novel cancer-associated lncRNAs, which are supported by literature evidence.

miR-484/MAP2/c-Myc-positive regulatory loop in glioma promotes tumor-initiating properties through ERK1/2 signaling

Glioma is the most common intracranial malignant tumor. Cancer stem cells (CSCs) are resistant to chemotherapy and radiotherapy, and are closely related to cancer metastasis and recurrence. In this study, we aimed to explore the effect of miR-484 on glioma stemness and the underlying mechanism involved. miR-484 enhanced glioma tumor-initiating properties in vitro and in vivo. Moreover, miR-484 was shown to directly target MAP2, resulting in activation of ERK1/2 signaling and promotion of stemness in glioma. The ERK1/2 signaling facilitated the formation of a miR-484/MAP2/c-Myc positive feedback loop in glioma. High miR-484 expression predicted a poor prognosis for glioma patients, and high MAP2 expression predicted a good prognosis for glioma patients. Low miR-484 expression and high MAP2 expression was associated with the best prognosis in glioma. Our study suggests that miR-484 and MAP2 can be utilized as predictors for the clinical diagnosis and prognosis of glioma, and miR-484 and MAP2 are potential targets for the treatment of glioma.

A novel information diffusion method based on network consistency for identifying disease related microRNAs

The abnormal expression of miRNAs is directly related to the development of human diseases. Predicting the potential candidate miRNAs associated with diseases can contribute to the detection, diagnosis, treatment and prevention of human complex diseases. The effective inference of the calculation method of the relationship between miRNAs and diseases is an effective supplement to biological experiments. It is of great help in the prevention, treatment and prognosis of complex diseases. This paper proposes a novel information diffusion method based on network consistency (IDNC) for identifying disease related microRNAs. The model first synthesizes the miRNA family information and the miRNA function similarity to reconstruct the miRNA network, and reconstruct the disease network by using the known disease and miRNA-related information and the semantic score between diseases. Then the global similarity of the two networks is obtained by using the Laplacian score of graphs. The global similarity score is a measure of the similarity between diseases and miRNAs. The disease–miRNA relation network was reconstructed by integrating the global similarity relation. The network consistency diffusion seed is then obtained by combining the global similarity network with the reconstructed disease–miRNA association network. Thereafter, the stable diffusion spectrum is generated as the prediction score by using the restarted random walk algorithm. The AUC value obtained by performing the LOOCV in the gold benchmark dataset is 0.8814. The AUC value obtained by performing the LOOCV in the predictive dataset is 0.9512. Compared with other frontier methods, our method has higher accuracy, which is further illustrated by case studies of breast neoplasms and colon neoplasms to prove that IDNC is valuable.

The abnormal expression of miRNAs is directly related to the development of human diseases.

Random walks on mutual microRNA-target gene interaction network improve the prediction of disease-associated microRNAs

BACKGROUND

MicroRNAs (miRNAs) have been shown to play an important role in pathological initiation, progression and maintenance. Because identification in the laboratory of disease-related miRNAs is not straightforward, numerous network-based methods have been developed to predict novel miRNAs in silico. Homogeneous networks (in which every node is a miRNA) based on the targets shared between miRNAs have been widely used to predict their role in disease phenotypes. Although such homogeneous networks can predict potential disease-associated miRNAs, they do not consider the roles of the target genes of the miRNAs. Here, we introduce a novel method based on a heterogeneous network that not only considers miRNAs but also the corresponding target genes in the network model.

RESULTS

Instead of constructing homogeneous miRNA networks, we built heterogeneous miRNA networks consisting of both miRNAs and their target genes, using databases of known miRNA-target gene interactions. In addition, as recent studies demonstrated reciprocal regulatory relations between miRNAs and their target genes, we considered these heterogeneous miRNA networks to be undirected, assuming mutual miRNA-target interactions. Next, we introduced a novel method (RWRMTN) operating on these mutual heterogeneous miRNA networks to rank candidate disease-related miRNAs using a random walk with restart (RWR) based algorithm. Using both known disease-associated miRNAs and their target genes as seed nodes, the method can identify additional miRNAs involved in the disease phenotype. Experiments indicated that RWRMTN outperformed two existing state-of-the-art methods: RWRMDA, a network-based method that also uses a RWR on homogeneous (rather than heterogeneous) miRNA networks, and RLSMDA, a machine learning-based method. Interestingly, we could relate this performance gain to the emergence of "disease modules" in the heterogeneous miRNA networks used as input for the algorithm. Moreover, we could demonstrate that RWRMTN is stable, performing well when using both experimentally validated and predicted miRNA-target gene interaction data for network construction. Finally, using RWRMTN, we identified 76 novel miRNAs associated with 23 disease phenotypes which were present in a recent database of known disease-miRNA associations.

CONCLUSIONS

Summarizing, using random walks on mutual miRNA-target networks improves the prediction of novel disease-associated miRNAs because of the existence of "disease modules" in these networks.

Computational prediction of human disease-related microRNAs by path-based random walk

MicroRNAs (miRNAs) are a class of small, endogenous RNAs that are 21–25 nucleotides in length. In animals and plants, miRNAs target specific genes for degradation or translation repression. Discovering disease-related miRNA is fundamental for understanding the pathogenesis of diseases. The association between miRNA and a disease is mainly determined via biological investigation, which is complicated by increased biological information due to big data from different databases. Researchers have utilized different computational methods to harmonize experimental approaches to discover miRNA that articulates restrictively in specific environmental situations. In this work, we present a prediction model that is based on the theory of path features and random walk to obtain a relevancy score of miRNA-related disease. In this model, highly ranked scores are potential miRNA-disease associations. Features were extracted from positive and negative samples of miRNA-disease association. Then, we compared our method with other presented models using the five-fold cross-validation method, which obtained an area under the receiver operating characteristic curve of 88.6%. This indicated that our method has a better performance compared to previous methods and will help future biological investigations.

Network Consistency Projection for Human miRNA-Disease Associations Inference

Prediction and confirmation of the presence of disease-related miRNAs is beneficial to understand disease mechanisms at the miRNA level. However, the use of experimental verification to identify disease-related miRNAs is expensive and time-consuming. Effective computational approaches used to predict miRNA-disease associations are highly specific. In this study, we develop the Network Consistency Projection for miRNA-Disease Associations (NCPMDA) method to reveal the potential associations between miRNAs and diseases. NCPMDA is a non-parametric universal network-based method that can simultaneously predict miRNA-disease associations in all diseases but does not require negative samples. NCPMDA can also confirm the presence of miRNAs in isolated diseases (diseases without any known miRNA association). Leave-one-out cross validation and case studies have shown that the predictive performance of NCPMDA is superior over that of previous method.

Prediction of miRNA-disease associations with a vector space model

MicroRNAs play critical roles in many physiological processes. Their dysregulations are also closely related to the development and progression of various human diseases, including cancer. Therefore, identifying new microRNAs that are associated with diseases contributes to a better understanding of pathogenicity mechanisms. MicroRNAs also represent a tremendous opportunity in biotechnology for early diagnosis. To date, several in silico methods have been developed to address the issue of microRNA-disease association prediction. However, these methods have various limitations. In this study, we investigate the hypothesis that information attached to miRNAs and diseases can be revealed by distributional semantics. Our basic approach is to represent distributional information on miRNAs and diseases in a high-dimensional vector space and to define associations between miRNAs and diseases in terms of their vector similarity. Cross validations performed on a dataset of known miRNA-disease associations demonstrate the excellent performance of our method. Moreover, the case study focused on breast cancer confirms the ability of our method to discover new disease-miRNA associations and to identify putative false associations reported in databases.