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

A novel microbe-drug association prediction model based on stacked autoencoder with multi-head attention mechanism

Microbes are intimately tied to the occurrence of various diseases that cause serious hazards to human health, and play an essential role in drug discovery, clinical application, and drug quality control. In this manuscript, we put forward a novel prediction model named MDASAE based on a stacked autoencoder (SAE) with multi-head attention mechanism to infer potential microbe-drug associations. In MDASAE, we first constructed three kinds of microbe-related and drug-related similarity matrices based on known microbe-disease-drug associations respectively. And then, we fed two kinds of microbe-related and drug-related similarity matrices respectively into the SAE to learn node attribute features, and introduced a multi-head attention mechanism into the output layer of the SAE to enhance feature extraction. Thereafter, we further adopted the remaining microbe and drug similarity matrices to derive inter-node features by using the Restart Random Walk algorithm. After that, the node attribute features and inter-node features of microbes and drugs would be fused together to predict scores of possible associations between microbes and drugs. Finally, intensive comparison experiments and case studies based on different well-known public databases under 5-fold cross-validation and 10-fold cross-validation respectively, proved that MDASAE can effectively predict the potential microbe-drug associations.

A network-based method for predicting disease-associated enhancers

Background

Enhancers regulate transcription of target genes, causing a change in expression level. Thus, the aberrant activity of enhancers can lead to diseases. To date, a large number of enhancers have been identified, yet a small portion of them have been found to be associated with diseases. This raises a pressing need to develop computational methods to predict associations between diseases and enhancers.

Results

In this study, we assumed that enhancers sharing target genes could be associated with similar diseases to predict the association. Thus, we built an enhancer functional interaction network by connecting enhancers significantly sharing target genes, then developed a network diffusion method RWDisEnh, based on a random walk with restart algorithm, on networks of diseases and enhancers to globally measure the degree of the association between diseases and enhancers. RWDisEnh performed best when the disease similarities are integrated with the enhancer functional interaction network by known disease-enhancer associations in the form of a heterogeneous network of diseases and enhancers. It was also superior to another network diffusion method, i.e., PageRank with Priors, and a neighborhood-based one, i.e., MaxLink, which simply chooses the closest neighbors of known disease-associated enhancers. Finally, we showed that RWDisEnh could predict novel enhancers, which are either directly or indirectly associated with diseases.

Conclusions

Taken together, RWDisEnh could be a potential method for predicting disease-enhancer associations.

Predicting miRNA-disease associations using improved random walk with restart and integrating multiple similarities

Predicting beneficial and valuable miRNA-disease associations (MDAs) by doing biological laboratory experiments is costly and time-consuming. Proposing a forceful and meaningful computational method for predicting MDAs is essential and captivated many computer scientists in recent years. In this paper, we proposed a new computational method to predict miRNA-disease associations using improved random walk with restart and integrating multiple similarities (RWRMMDA). We used a WKNKN algorithm as a pre-processing step to solve the problem of sparsity and incompletion of data to reduce the negative impact of a large number of missing associations. Two heterogeneous networks in disease and miRNA spaces were built by integrating multiple similarity networks, respectively, and different walk probabilities could be designated to each linked neighbor node of the disease or miRNA node in line with its degree in respective networks. Finally, an improve extended random walk with restart algorithm based on miRNA similarity-based and disease similarity-based heterogeneous networks was used to calculate miRNA-disease association prediction probabilities. The experiments showed that our proposed method achieved a momentous performance with Global LOOCV AUC (Area Under Roc Curve) and AUPR (Area Under Precision-Recall Curve) values of 0.9882 and 0.9066, respectively. And the best AUC and AUPR values under fivefold cross-validation of 0.9855 and 0.8642 which are proven by statistical tests, respectively. In comparison with other previous related methods, it outperformed than NTSHMDA, PMFMDA, IMCMDA and MCLPMDA methods in both AUC and AUPR values. In case studies of Breast Neoplasms, Carcinoma Hepatocellular and Stomach Neoplasms diseases, it inferred 1, 12 and 7 new associations out of top 40 predicted associated miRNAs for each disease, respectively. All of these new inferred associations have been confirmed in different databases or literatures.

Recent development of bioinformatics tools for microRNA target prediction

MicroRNAs (miRNAs) are central players that regulate the post-transcriptional processes of gene expression. Binding of miRNAs to target mRNAs can repress their translation by inducing the degradation or by inhibiting the translation of the target mRNAs. High-throughput experimental approaches for miRNA target identification are costly and time-consuming, depending on various factors. It is vitally important to develop the bioinformatics methods for accurately predicting miRNA targets. With the increase of RNA sequences in the post-genomic era, bioinformatics methods are being developed for miRNA studies specially for miRNA target prediction. This review summarizes the current development of state-of-the-art bioinformatics tools for miRNA target prediction, points out the progress and limitations of the available miRNA databases, and their working principles. Finally, we discuss the caveat and perspectives of the next-generation algorithms for the prediction of miRNA targets.

MDA-CF: Predicting MiRNA-Disease associations based on a cascade forest model by fusing multi-source information

MicroRNAs (miRNAs) are significant regulators in various biological processes. They may become promising biomarkers or therapeutic targets, which provide a new perspective in diagnosis and treatment of multiple diseases. Since the experimental methods are always costly and resource-consuming, prediction of disease-related miRNAs using computational methods is in great need. In this study, we developed MDA-CF to identify underlying miRNA-disease associations based on a cascade forest model. In this method, multi-source information was integrated to represent miRNAs and diseases comprehensively, and the autoencoder was utilized for dimension reduction to obtain the optimal feature space. The cascade forest model was then employed for miRNA-disease association prediction. As a result, the average AUC of MDA-CF was 0.9464 on HMDD v3.2 in five-fold cross-validation. Compared with previous computational methods, MDA-CF performed better on HMDD v2.0 with an average AUC of 0.9258. Moreover, MDA-CF was implemented to investigate colon neoplasm, breast neoplasm, and gastric neoplasm, and 100%, 86%, 88% of the top 50 potential miRNAs were validated by authoritative databases. In conclusion, MDA-CF appears to be a reliable method to uncover disease-associated miRNAs. The source code of MDA-CF is available at https://github.com/a1622108/MDA-CF.

Identification of Therapeutic Targets for the Selective Killing of HBV-Positive Hepatocytes

The hepatitis B virus (HBV) infection is a major risk factor for cirrhosis and hepatocellular carcinoma. Most infected individuals become lifelong carriers of HBV as the drugs currently used to treat the patients can only control the disease, thereby achieving functional cure (loss of the hepatitis B surface antigen) but not complete cure (elimination of infected hepatocytes). Therefore, we aimed to identify the target genes for the selective killing of HBV-positive hepatocytes to develop a novel therapy for the treatment of HBV infection. Our strategy was to recognize the conditionally essential genes that are essential for the survival of HBV-positive hepatocytes, but non-essential for the HBV-negative hepatocytes. Using microarray gene expression data curated from the Gene Expression Omnibus database and the known essential genes from the Online GEne Essentiality database, we used two approaches, comprising the random walk with restart algorithm and the support vector machine approach, to determine the potential targets for the selective killing of HBV-positive hepatocytes. The final candidate genes list obtained using these two approaches consisted of 36 target genes, which may be conditionally essential for the cell survival of HBV-positive hepatocytes; however, this requires further experimental validation. Therefore, the genes identified in this study can be used as potential drug targets to develop novel therapeutic strategies for the treatment of HBV, and may ultimately help in achieving the elusive goal of a complete cure for hepatitis B.

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.

NTSHMDA: Prediction of Human Microbe-Disease Association Based on Random Walk by Integrating Network Topological Similarity

Accumulating clinic evidences have demonstrated that the microbes residing in human bodies play a significantly important role in the formation, development, and progression of various complex human diseases. Identifying latent related microbes for disease could provide insight into human disease mechanisms and promote disease prevention, diagnosis, and treatment. In this paper, we first construct a heterogeneous network by connecting the disease similarity network and the microbe similarity network through known microbe-disease association network, and then develop a novel computational model to predict human microbe-disease associations based on random walk by integrating network topological similarity (NTSHMDA). Specifically, each microbe-disease association pair is regarded as a distinct relationship level and, thus, assigned different weights based on network topological similarity. The experimental results show that NTSHMDA outperforms some state-of-the-art methods with average AUCs of 0.9070, 0.8896 ± 0.0038 in the frameworks of Leave-one-out cross validation and 5-fold cross validation, respectively. In case studies, 9, 18, 38 and 9, 18, 45 out of top-10, 20, 50 candidate microbes are verified by recently published literatures for asthma and inflammatory bowel disease, respectively. In conclusion, NTSHMDA has potential ability to identify novel disease-microbe associations and can also provide valuable information for drug discovery and biological researches.

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.

Benchmark of computational methods for predicting microRNA-disease associations

BACKGROUND

A series of miRNA-disease association prediction methods have been proposed to prioritize potential disease-associated miRNAs. Independent benchmarking of these methods is warranted to assess their effectiveness and robustness.

RESULTS

Based on more than 8000 novel miRNA-disease associations from the latest HMDD v3.1 database, we perform systematic comparison among 36 readily available prediction methods. Their overall performances are evaluated with rigorous precision-recall curve analysis, where 13 methods show acceptable accuracy (AUPRC > 0.200) while the top two methods achieve a promising AUPRC over 0.300, and most of these methods are also highly ranked when considering only the causal miRNA-disease associations as the positive samples. The potential of performance improvement is demonstrated by combining different predictors or adopting a more updated miRNA similarity matrix, which would result in up to 16% and 46% of AUPRC augmentations compared to the best single predictor and the predictors using the previous similarity matrix, respectively. Our analysis suggests a common issue of the available methods, which is that the prediction results are severely biased toward well-annotated diseases with many associated miRNAs known and cannot further stratify the positive samples by discriminating the causal miRNA-disease associations from the general miRNA-disease associations.

CONCLUSION

Our benchmarking results not only provide a reference for biomedical researchers to choose appropriate miRNA-disease association predictors for their purpose, but also suggest the future directions for the development of more robust miRNA-disease association predictors.

Computational Prediction of Functional MicroRNA-mRNA Interactions

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

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.

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.