LLCMDA: A Novel Method for Predicting miRNA Gene and Disease Relationship Based on Locality-Constrained Linear Coding

An efficient model for predicting human diseases through miRNA based on multiple-types of contrastive learning

Multiple studies have demonstrated that microRNA (miRNA) can be deeply involved in the regulatory mechanism of human microbiota, thereby inducing disease. Developing effective methods to infer potential associations between microRNAs (miRNAs) and diseases can aid early diagnosis and treatment. Recent methods utilize machine learning or deep learning to predict miRNA-disease associations (MDAs), achieving state-of-the-art performance. However, the problem of sparse neighborhoods of nodes due to lack of data has not been well solved. To this end, we propose a new model named MTCL-MDA, which integrates multiple-types of contrastive learning strategies into a graph collaborative filtering model to predict potential MDAs. The model adopts a contrastive learning strategy based on topology, which alleviates the damage to model performance caused by sparse neighborhoods. In addition, the model also adopts a semantic-based contrastive learning strategy, which not only reduces the impact of noise introduced by topology-based contrastive learning, but also enhances the semantic information of nodes. Experimental results show that our model outperforms existing models on all evaluation metrics. Case analysis shows that our model can more accurately identify potential MDA, which is of great significance for the screening and diagnosis of real-life diseases. Our data and code are publicly available at: https://github.com/Lqingquan/MTCL-MDA.

Identification of Disease-Associated MicroRNAs Via Locality-Constrained Linear Coding-Based Ensemble Learning

Clinical trials indicate that the dysregulation of microRNAs (miRNAs) is closely associated with the development of diseases. Therefore, predicting miRNA-disease associations is significant for studying the pathogenesis of diseases. Since traditional wet-lab methods are resource-intensive, cost-saving computational models can be an effective complementary tool in biological experiments. In this work, a locality-constrained linear coding is proposed to predict associations (ILLCEL). Among them, ILLCEL adopts miRNA sequence similarity, miRNA functional similarity, disease semantic similarity, and interaction profile similarity obtained by locality-constrained linear coding (LLC) as the priori information. Next, features and similarities extracted from multiperspectives are input to the ensemble learning framework to improve the comprehensiveness of the prediction. Significantly, the introduction of hypergraph-regular terms improves the accuracy of prediction by describing complex associations between samples. The results under fivefold cross validation indicate that ILLCEL achieves superior prediction performance. In case studies, known associations are accurately predicted and novel associations are verified in HMDD v3.2, miRCancer, and existing literature. It is concluded that ILLCEL can be served as a powerful tool for inferring potential associations.

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.

miR2Trait: an integrated resource for investigating miRNA-disease associations

MicroRNAs are key components of cellular regulatory networks, and breakdown in miRNA function causes cascading effects leading to pathophenotypes. A better understanding of the role of miRNAs in diseases is essential for human health. Here, we have devised a method for comprehensively mapping the associations between miRNAs and diseases by merging on a common key between two curated omics databases. The resulting bidirectional resource, miR2Trait, is more detailed than earlier catalogs, uncovers new relationships, and includes analytical utilities to interrogate and extract knowledge from these datasets. miR2Trait provides resources to compute the disease enrichment of a user-given set of miRNAs and analyze the miRNA profile of a specified diseasome. Reproducible examples demonstrating use-cases for each of these resource components are illustrated. Furthermore we used these tools to construct pairwise miRNA-miRNA and disease-disease enrichment networks, and identified 23 central miRNAs that could underlie major regulatory functions in the human genome. miR2Trait is available as an open-source command-line interface in Python3 (URL: https://github.com/miR2Trait) with a companion wiki documenting the scripts and data resources developed, under MIT license for commercial and non-commercial use. A minimal web-based implementation has been made available at https://sas.sastra.edu/pymir18. Supplementary information is available at: https://doi.org/10.6084/m9.figshare.8288825.v3.

Using Sequence Similarity Based on CKSNP Features and a Graph Neural Network Model to Identify miRNA-Disease Associations

Among many machine learning models for analyzing the relationship between miRNAs and diseases, the prediction results are optimized by establishing different machine learning models, and less attention is paid to the feature information contained in the miRNA sequence itself. This study focused on the impact of the different feature information of miRNA sequences on the relationship between miRNA and disease. It was found that when the graph neural network used was the same and the miRNA features based on the K-spacer nucleic acid pair composition (CKSNAP) feature were adopted, a better graph neural network prediction model of miRNA-disease relationship could be built (AUC = 93.71%), which was 0.15% greater than the best model in the literature based on the same benchmark dataset. The optimized model was also used to predict miRNAs related to lung tumors, esophageal tumors, and kidney tumors, and 47, 47, and 37 of the top 50 miRNAs related to three diseases predicted separately by the model were consistent with descriptions in the wet experiment validation database (dbDEMC).

SFGAE: a self-feature-based graph autoencoder model for miRNA-disease associations prediction

Increasing evidence has suggested that microRNAs (miRNAs) are important biomarkers of various diseases. Numerous graph neural network (GNN) models have been proposed for predicting miRNA-disease associations. However, the existing GNN-based methods have over-smoothing issue-the learned feature embeddings of miRNA nodes and disease nodes are indistinguishable when stacking multiple GNN layers. This issue makes the performance of the methods sensitive to the number of layers, and significantly hurts the performance when more layers are employed. In this study, we resolve this issue by a novel self-feature-based graph autoencoder model, shortened as SFGAE. The key novelty of SFGAE is to construct miRNA-self embeddings and disease-self embeddings, and let them be independent of graph interactions between two types of nodes. The novel self-feature embeddings enrich the information of typical aggregated feature embeddings, which aggregate the information from direct neighbors and hence heavily rely on graph interactions. SFGAE adopts a graph encoder with attention mechanism to concatenate aggregated feature embeddings and self-feature embeddings, and adopts a bilinear decoder to predict links. Our experiments show that SFGAE achieves state-of-the-art performance. In particular, SFGAE improves the average AUC upon recent GAEMDA [1] on the benchmark datasets HMDD v2.0 and HMDD v3.2, and consistently performs better when less (e.g. 10%) training samples are used. Furthermore, SFGAE effectively overcomes the over-smoothing issue and performs stably well on deeper models (e.g. eight layers). Finally, we carry out case studies on three human diseases, colon neoplasms, esophageal neoplasms and kidney neoplasms, and perform a survival analysis using kidney neoplasm as an example. The results suggest that SFGAE is a reliable tool for predicting potential miRNA-disease associations.

Data Integration Using Tensor Decomposition for The Prediction of miRNA-Disease Associations

Dysfunction of miRNAs has an important relationship with diseases by impacting their target genes. Identifying disease-related miRNAs is of great significance to prevent and treat diseases. Integrating information of genes related miRNAs and/or diseases in calculational methods for miRNA-disease association studies is meaningful because of the complexity of biological mechanisms. Therefore, in this study, we propose a novel method based on tensor decomposition, termed TDMDA, to integrate multi-type data for identifying pathogenic miRNAs. First, we construct a three-order association tensor to express the associations of miRNA-disease pairs, the associations of miRNA-gene pairs, and the associations of gene-disease pairs simultaneously. Then, a tensor decomposition-based method with auxiliary information is applied to reconstruct the association tensor for predicting miRNA-disease associations, and the auxiliary information includes biological similarity information and adjacency information. The performance of TDMDA is compared with other advanced methods under 5-fold cross-validations. The experimental results indicate the TDMDA is a competitive method.

Multi-view Multichannel Attention Graph Convolutional Network for miRNA-disease association prediction

MOTIVATION

In recent years, a growing number of studies have proved that microRNAs (miRNAs) play significant roles in the development of human complex diseases. Discovering the associations between miRNAs and diseases has become an important part of the discovery and treatment of disease. Since uncovering associations via traditional experimental methods is complicated and time-consuming, many computational methods have been proposed to identify the potential associations. However, there are still challenges in accurately determining potential associations between miRNA and disease by using multisource data.

RESULTS

In this study, we develop a Multi-view Multichannel Attention Graph Convolutional Network (MMGCN) to predict potential miRNA-disease associations. Different from simple multisource information integration, MMGCN employs GCN encoder to obtain the features of miRNA and disease in different similarity views, respectively. Moreover, our MMGCN can enhance the learned latent representations for association prediction by utilizing multichannel attention, which adaptively learns the importance of different features. Empirical results on two datasets demonstrate that MMGCN model can achieve superior performance compared with nine state-of-the-art methods on most of the metrics. Furthermore, we prove the effectiveness of multichannel attention mechanism and the validity of multisource data in miRNA and disease association prediction. Case studies also indicate the ability of the method for discovering new associations.

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.

A graph auto-encoder model for miRNA-disease associations prediction

Emerging evidence indicates that the abnormal expression of miRNAs involves in the evolution and progression of various human complex diseases. Identifying disease-related miRNAs as new biomarkers can promote the development of disease pathology and clinical medicine. However, designing biological experiments to validate disease-related miRNAs is usually time-consuming and expensive. Therefore, it is urgent to design effective computational methods for predicting potential miRNA-disease associations. Inspired by the great progress of graph neural networks in link prediction, we propose a novel graph auto-encoder model, named GAEMDA, to identify the potential miRNA-disease associations in an end-to-end manner. More specifically, the GAEMDA model applies a graph neural networks-based encoder, which contains aggregator function and multi-layer perceptron for aggregating nodes' neighborhood information, to generate the low-dimensional embeddings of miRNA and disease nodes and realize the effective fusion of heterogeneous information. Then, the embeddings of miRNA and disease nodes are fed into a bilinear decoder to identify the potential links between miRNA and disease nodes. The experimental results indicate that GAEMDA achieves the average area under the curve of $93.56\pm 0.44\%$ under 5-fold cross-validation. Besides, we further carried out case studies on colon neoplasms, esophageal neoplasms and kidney neoplasms. As a result, 48 of the top 50 predicted miRNAs associated with these diseases are confirmed by the database of differentially expressed miRNAs in human cancers and microRNA deregulation in human disease database, respectively. The satisfactory prediction performance suggests that GAEMDA model could serve as a reliable tool to guide the following researches on the regulatory role of miRNAs. Besides, the source codes are available at https://github.com/chimianbuhetang/GAEMDA.

Heterogeneous Graph Convolutional Networks and Matrix Completion for miRNA-Disease Association Prediction

Due to the cost and complexity of biological experiments, many computational methods have been proposed to predict potential miRNA-disease associations by utilizing known miRNA-disease associations and other related information. However, there are some challenges for these computational methods. First, the relationships between miRNAs and diseases are complex. The computational network should consider the local and global influence of neighborhoods from the network. Furthermore, predicting disease-related miRNAs without any known associations is also very important. This study presents a new computational method that constructs a heterogeneous network composed of a miRNA similarity network, disease similarity network, and known miRNA-disease association network. The miRNA similarity considers the miRNAs and their possible families and clusters. The information of each node in heterogeneous network is obtained by aggregating neighborhood information with graph convolutional networks (GCNs), which can pass the information of a node to its intermediate and distant neighbors. Disease-related miRNAs with no known associations can be predicted with the reconstructed heterogeneous matrix. We apply 5-fold cross-validation, leave-one-disease-out cross-validation, and global and local leave-one-out cross-validation to evaluate our method. The corresponding areas under the curves (AUCs) are 0.9616, 0.9946, 0.9656, and 0.9532, confirming that our approach significantly outperforms the state-of-the-art methods. Case studies show that this approach can effectively predict new diseases without any known miRNAs.

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.

Predicting human disease-associated circRNAs based on locality-constrained linear coding

Circular RNAs (circRNAs) are a new kind of endogenous non-coding RNAs, which have been discovered continuously. More and more studies have shown that circRNAs are related to the occurrence and development of human diseases. Identification of circRNAs associated with diseases can contribute to understand the pathogenesis, diagnosis and treatment of diseases. However, experimental methods of circRNA prediction remain expensive and time-consuming. Therefore, it is urgent to propose novel computational methods for the prediction of circRNA-disease associations. In this study, we develop a computational method called LLCDC that integrates the known circRNA-disease associations, circRNA semantic similarity network, disease semantic similarity network, reconstructed circRNA similarity network, and reconstructed disease similarity network to predict circRNAs related to human diseases. Specifically, the reconstructed similarity networks are obtained by using Locality-Constrained Linear Coding (LLC) on the known association matrix, cosine similarities of circRNAs and diseases. Then, the label propagation method is applied to the similarity networks, and four relevant score matrices are respectively obtained. Finally, we use 5-fold cross validation (5-fold CV) to evaluate the performance of LLCDC, and the AUC value of the method is 0.9177, indicating that our method performs better than the other three methods. In addition, case studies on gastric cancer, breast cancer and papillary thyroid carcinoma further verify the reliability of our method in predicting disease-associated circRNAs.

LLCLPLDA: a novel model for predicting lncRNA-disease associations

Long noncoding RNAs play a significant role in the occurrence of diseases. Thus, studying the relationship prediction between lncRNAs and disease is becoming more popular. Researchers hope to determine effective treatments by revealing the occurrence and development of diseases at the molecular level. However, the traditional biological experimental way to verify the association between lncRNAs and disease is very time-consuming and expensive. Therefore, we developed a method called LLCLPLDA to predict potential lncRNA-disease associations. First, locality-constrained linear coding (LLC) is leveraged to project the features of lncRNAs and diseases to local-constraint features, and then, a label propagation (LP) strategy is used to mix up the initial association matrix and the obtained features of lncRNAs and diseases. To demonstrate the performance of our method, we compared LLCLPLDA with five methods in the leave-one-out cross-validation and fivefold cross-validation scheme, and the experimental results show that the proposed method outperforms the other five methods. Additionally, we conducted case studies on three diseases: cervical cancer, gliomas, and breast cancer. The top five predicted lncRNAs for cervical cancer and gliomas were verified, and four of the five lncRNAs for breast cancer were also confirmed.

Integrating Bipartite Network Projection and KATZ Measure to Identify Novel CircRNA-Disease Associations

Accumulating biological experiments have shown that circRNAs are closely related to the occurrence and development of many complex human diseases. During recent years, the associations of circRNA with disease have caused more and more researchers to pay attention and to analyze their correlation mechanisms. However, experimental methods for determining the associations of circRNA with a particular disease are still expensive, difficult, and time consuming. Moreover, the available databases related to circRNA-disease correlations have only recently been updated, and only a few computational methods are constructed to predict potential circRNA-disease correlations. Taking into account the limitations of experimental studies, we develop a novel computational method, named IBNPKATZ, for predicting potential circRNA-disease associations, which integrates the bipartite network projection algorithm and KATZ measure. This model is based on the known circRNA-disease associations, combining circRNA similarity and disease similarity. Specifically, the circRNA similarity is derived from the average of the semantic similarity and the Gaussian interaction profile (GIP) kernel similarity of circRNA. Similarly, disease similarity is the mean of the semantic similarity and the GIP kernel similarity of disease. Furthermore, it is semi-supervised and does not require negative samples. Finally, IBNPKATZ achieves reliable AUC of 0.9352 in the leave-one-out cross validation, and case studies show that the circRNA-disease correlations predicted by our method can be successfully demonstrated by relevant experiments. The IBNPKATZ is expected to be a useful biomedical research tool for predicting potential circRNA-disease associations.

Adaptive multi-view multi-label learning for identifying disease-associated candidate miRNAs

Increasing evidence has indicated that microRNAs(miRNAs) play vital roles in various pathological processes and thus are closely related with many complex human diseases. The identification of potential disease-related miRNAs offers new opportunities to understand disease etiology and pathogenesis. Although there have been numerous computational methods proposed to predict reliable miRNA-disease associations, they suffer from various limitations that affect the prediction accuracy and their applicability. In this study, we develop a novel method to discover disease-related candidate miRNAs based on Adaptive Multi-View Multi-Label learning(AMVML). Specifically, considering the inherent noise existed in the current dataset, we propose to learn a new affinity graph adaptively for both diseases and miRNAs from multiple similarity profiles. We then simultaneously update the miRNA-disease association predicted from both spaces based on multi-label learning. In particular, we prove the convergence of AMVML theoretically and the corresponding analysis indicates that it has a fast convergence rate. To comprehensively illustrate the prediction performance of our method, we compared AMVML with four state-of-the-art methods under different validation frameworks. As a result, our method achieved comparable performance under various evaluation metrics, which suggests that our method is capable of discovering greater number of true miRNA-disease associations. The case study conducted on thyroid neoplasms further identified a potential diagnostic biomarker. Together, the experimental results confirms the utility of our method and we anticipate that our method could serve as a reliable and efficient tool for uncovering novel disease-related miRNAs.