Matrix factorization-based data fusion for the prediction of lncRNA-disease associations

GEnDDn: An lncRNA-Disease Association Identification Framework Based on Dual-Net Neural Architecture and Deep Neural Network

Accumulating studies have demonstrated close relationships between long non-coding RNAs (lncRNAs) and diseases. Identification of new lncRNA-disease associations (LDAs) enables us to better understand disease mechanisms and further provides promising insights into cancer targeted therapy and anti-cancer drug design. Here, we present an LDA prediction framework called GEnDDn based on deep learning. GEnDDn mainly comprises two steps: First, features of both lncRNAs and diseases are extracted by combining similarity computation, non-negative matrix factorization, and graph attention auto-encoder, respectively. And each lncRNA-disease pair (LDP) is depicted as a vector based on concatenation operation on the extracted features. Subsequently, unknown LDPs are classified by aggregating dual-net neural architecture and deep neural network. Using six different evaluation metrics, we found that GEnDDn surpassed four competing LDA identification methods (SDLDA, LDNFSGB, IPCARF, LDASR) on the lncRNADisease and MNDR databases under fivefold cross-validation experiments on lncRNAs, diseases, LDPs, and independent lncRNAs and independent diseases, respectively. Ablation experiments further validated the powerful LDA prediction performance of GEnDDn. Furthermore, we utilized GEnDDn to find underlying lncRNAs for lung cancer and breast cancer. The results elucidated that there may be dense linkages between IFNG-AS1 and lung cancer as well as between HIF1A-AS1 and breast cancer. The results require further biomedical experimental verification. GEnDDn is publicly available at https://github.com/plhhnu/GEnDDn.

Neighborhood based computational approaches for the prediction of lncRNA-disease associations

MOTIVATION

Long non-coding RNAs (lncRNAs) are a class of molecules involved in important biological processes. Extensive efforts have been provided to get deeper understanding of disease mechanisms at the lncRNA level, guiding towards the detection of biomarkers for disease diagnosis, treatment, prognosis and prevention. Unfortunately, due to costs and time complexity, the number of possible disease-related lncRNAs verified by traditional biological experiments is very limited. Computational approaches for the prediction of disease-lncRNA associations allow to identify the most promising candidates to be verified in laboratory, reducing costs and time consuming.

RESULTS

We propose novel approaches for the prediction of lncRNA-disease associations, all sharing the idea of exploring associations among lncRNAs, other intermediate molecules (e.g., miRNAs) and diseases, suitably represented by tripartite graphs. Indeed, while only a few lncRNA-disease associations are still known, plenty of interactions between lncRNAs and other molecules, as well as associations of the latters with diseases, are available. A first approach presented here, NGH, relies on neighborhood analysis performed on a tripartite graph, built upon lncRNAs, miRNAs and diseases. A second approach (CF) relies on collaborative filtering; a third approach (NGH-CF) is obtained boosting NGH by collaborative filtering. The proposed approaches have been validated on both synthetic and real data, and compared against other methods from the literature. It results that neighborhood analysis allows to outperform competitors, and when it is combined with collaborative filtering the prediction accuracy further improves, scoring a value of AUC equal to 0966.

AVAILABILITY

Source code and sample datasets are available at: https://github.com/marybonomo/LDAsPredictionApproaches.git.

NFMCLDA: Predicting miRNA-based lncRNA-disease associations by network fusion and matrix completion

In recent years, emerging evidence has revealed a strong association between dysregulations of long non-coding RNAs (lncRNAs) and sophisticated human diseases. Biological experiments are adequate to identify such associations, but they are costly and time-consuming. Therefore, developing high-quality computational methods is a challenging and urgent task in the field of bioinformatics. This paper proposes a new lncRNA-disease association inference approach NFMCLDA (Network Fusion and Matrix Completion lncRNA-Disease Association), which can effectively integrate multi-source association data. In this approach, miRNA information is used as the transition path, and an unbalanced random walk method on three-layer heterogeneous network is adopted in the preprocessing. Therefore, more effective information between networks can be mined and the sparsity problem of the association matrix can be solved. Finally, the matrix completion method accurately predicts associations. The results show that NFMCLDA can provide more accurate lncRNA-disease associations than state-of-the-art methods. The areas under the receiver operating characteristic curves are 0.9648 and 0.9713, respectively, through the cross-validation of 5-fold and 10-fold. Data from published case studies on four diseases - lung cancer, osteosarcoma, cervical cancer, and colon cancer - have confirmed the reliable predictive potential of NFMCLDA model.

Learning Association Characteristics by Dynamic Hypergraph and Gated Convolution Enhanced Pairwise Attributes for Prediction of Disease-Related lncRNAs

As the long non-coding RNAs (lncRNAs) play important roles during the incurrence and development of various human diseases, identifying disease-related lncRNAs can contribute to clarifying the pathogenesis of diseases. Most of the recent lncRNA-disease association prediction methods utilized the multi-source data about the lncRNAs and diseases. A single lncRNA may participate in multiple disease processes, and multiple lncRNAs usually are involved in the same disease process synergistically. However, the previous methods did not completely exploit the biological characteristics to construct the informative prediction models. We construct a prediction model based on adaptive hypergraph and gated convolution for lncRNA-disease association prediction (AGLDA), to embed and encode the biological characteristics about lncRNA-disease associations, the topological features from the entire heterogeneous graph perspective, and the gated enhanced pairwise features. First, the strategy for constructing hyperedges is designed to reflect the biological characteristic that multiple lncRNAs are involved in multiple disease processes. Furthermore, each hyperedge has its own biological perspective, and multiple hyperedges are beneficial for revealing the diverse relationships among multiple lncRNAs and diseases. Second, we encode the biological features of each lncRNA (disease) node using a strategy based on dynamic hypergraph convolutional networks. The strategy may adaptively learn the features of the hyperedges and formulate the dynamically evolved hypergraph topological structure. Third, a group convolutional network is established to integrate the entire heterogeneous topological structure and multiple types of node attributes within an lncRNA-disease-miRNA graph. Finally, a gated convolutional strategy is proposed to enhance the informative features of the lncRNA-disease node pairs. The comparison experiments indicate that AGLDA outperforms seven advanced prediction methods. The ablation studies confirm the effectiveness of major innovations, and the case studies validate AGLDA's ability in application for discovering potential disease-related lncRNA candidates.

Finding potential lncRNA-disease associations using a boosting-based ensemble learning model

Introduction: Long non-coding RNAs (lncRNAs) have been in the clinical use as potential prognostic biomarkers of various types of cancer. Identifying associations between lncRNAs and diseases helps capture the potential biomarkers and design efficient therapeutic options for diseases. Wet experiments for identifying these associations are costly and laborious. Methods: We developed LDA-SABC, a novel boosting-based framework for lncRNA-disease association (LDA) prediction. LDA-SABC extracts LDA features based on singular value decomposition (SVD) and classifies lncRNA-disease pairs (LDPs) by incorporating LightGBM and AdaBoost into the convolutional neural network. Results: The LDA-SABC performance was evaluated under five-fold cross validations (CVs) on lncRNAs, diseases, and LDPs. It obviously outperformed four other classical LDA inference methods (SDLDA, LDNFSGB, LDASR, and IPCAF) through precision, recall, accuracy, F1 score, AUC, and AUPR. Based on the accurate LDA prediction performance of LDA-SABC, we used it to find potential lncRNA biomarkers for lung cancer. The results elucidated that 7SK and HULC could have a relationship with non-small-cell lung cancer (NSCLC) and lung adenocarcinoma (LUAD), respectively. Conclusion: We hope that our proposed LDA-SABC method can help improve the LDA identification.

HRGCNLDA: Forecasting of lncRNA-disease association based on hierarchical refinement graph convolutional neural network

Long non-coding RNA (lncRNA) is considered to be a crucial regulator involved in various human biological processes, including the regulation of tumor immune checkpoint proteins. It has great potential as both a cancer biomolecular biomarker and therapeutic target. Nevertheless, conventional biological experimental techniques are both resource-intensive and laborious, making it essential to develop an accurate and efficient computational method to facilitate the discovery of potential links between lncRNAs and diseases. In this study, we proposed HRGCNLDA, a computational approach utilizing hierarchical refinement of graph convolutional neural networks for forecasting lncRNA-disease potential associations. This approach effectively addresses the over-smoothing problem that arises from stacking multiple layers of graph convolutional neural networks. Specifically, HRGCNLDA enhances the layer representation during message propagation and node updates, thereby amplifying the contribution of hidden layers that resemble the ego layer while reducing discrepancies. The results of the experiments showed that HRGCNLDA achieved the highest AUC-ROC (area under the receiver operating characteristic curve, AUC for short) and AUC-PR (area under the precision versus recall curve, AUPR for short) values compared to other methods. Finally, to further demonstrate the reliability and efficacy of our approach, we performed case studies on the case of three prevalent human diseases, namely, breast cancer, lung cancer and gastric cancer.

Fusing graph transformer with multi-aggregate GCN for enhanced drug-disease associations prediction

BACKGROUND

Identification of potential drug-disease associations is important for both the discovery of new indications for drugs and for the reduction of unknown adverse drug reactions. Exploring the potential links between drugs and diseases is crucial for advancing biomedical research and improving healthcare. While advanced computational techniques play a vital role in revealing the connections between drugs and diseases, current research still faces challenges in the process of mining potential relationships between drugs and diseases using heterogeneous network data.

RESULTS

In this study, we propose a learning framework for fusing Graph Transformer Networks and multi-aggregate graph convolutional network to learn efficient heterogenous information graph representations for drug-disease association prediction, termed WMAGT. This method extensively harnesses the capabilities of a robust graph transformer, effectively modeling the local and global interactions of nodes by integrating a graph convolutional network and a graph transformer with self-attention mechanisms in its encoder. We first integrate drug-drug, drug-disease, and disease-disease networks to construct heterogeneous information graph. Multi-aggregate graph convolutional network and graph transformer are then used in conjunction with neural collaborative filtering module to integrate information from different domains into highly effective feature representation.

CONCLUSIONS

Rigorous cross-validation, ablation studies examined the robustness and effectiveness of the proposed method. Experimental results demonstrate that WMAGT outperforms other state-of-the-art methods in accurate drug-disease association prediction, which is beneficial for drug repositioning and drug safety research.

Predicting lncRNA-disease associations using multiple metapaths in hierarchical graph attention networks

BACKGROUND

Many biological studies have shown that lncRNAs regulate the expression of epigenetically related genes. The study of lncRNAs has helped to deepen our understanding of the pathogenesis of complex diseases at the molecular level. Due to the large number of lncRNAs and the complex and time-consuming nature of biological experiments, applying computer techniques to predict potential lncRNA-disease associations is very effective. To explore information between complex network structures, existing methods rely mainly on lncRNA and disease information. Metapaths have been applied to network models as an effective method for exploring information in heterogeneous graphs. However, existing methods are dominated by lncRNAs or disease nodes and tend to ignore the paths provided by intermediate nodes.

METHODS

We propose a deep learning model based on hierarchical graphical attention networks to predict unknown lncRNA-disease associations using multiple types of metapaths to extract features. We have named this model the MMHGAN. First, the model constructs a lncRNA-disease-miRNA heterogeneous graph based on known associations and two homogeneous graphs of lncRNAs and diseases. Second, for homogeneous graphs, the features of neighboring nodes are aggregated using a multihead attention mechanism. Third, for the heterogeneous graph, metapaths of different intermediate nodes are selected to construct subgraphs, and the importance of different types of metapaths is calculated and aggregated to obtain the final embedded features. Finally, the features are reconstructed using a fully connected layer to obtain the prediction results.

RESULTS

We used a fivefold cross-validation method and obtained an average AUC value of 96.07% and an average AUPR value of 93.23%. Additionally, ablation experiments demonstrated the role of homogeneous graphs and different intermediate node path weights. In addition, we studied lung cancer, esophageal carcinoma, and breast cancer. Among the 15 lncRNAs associated with these diseases, 15, 12, and 14 lncRNAs were validated by the lncRNA Disease Database and the Lnc2Cancer Database, respectively.

CONCLUSION

We compared the MMHGAN model with six existing models with better performance, and the case study demonstrated that the model was effective in predicting the correlation between potential lncRNAs and diseases.

Node-adaptive graph Transformer with structural encoding for accurate and robust lncRNA-disease association prediction

BACKGROUND

Long noncoding RNAs (lncRNAs) are integral to a plethora of critical cellular biological processes, including the regulation of gene expression, cell differentiation, and the development of tumors and cancers. Predicting the relationships between lncRNAs and diseases can contribute to a better understanding of the pathogenic mechanisms of disease and provide strong support for the development of advanced treatment methods.

RESULTS

Therefore, we present an innovative Node-Adaptive Graph Transformer model for predicting unknown LncRNA-Disease Associations, named NAGTLDA. First, we utilize the node-adaptive feature smoothing (NAFS) method to learn the local feature information of nodes and encode the structural information of the fusion similarity network of diseases and lncRNAs using Structural Deep Network Embedding (SDNE). Next, the Transformer module is used to capture potential association information between the network nodes. Finally, we employ a Transformer module with two multi-headed attention layers for learning global-level embedding fusion. Network structure coding is added as the structural inductive bias of the network to compensate for the missing message-passing mechanism in Transformer. NAGTLDA achieved an average AUC of 0.9531 and AUPR of 0.9537 significantly higher than state-of-the-art methods in 5-fold cross validation. We perform case studies on 4 diseases; 55 out of 60 associations between lncRNAs and diseases have been validated in the literatures. The results demonstrate the enormous potential of the graph Transformer structure to incorporate graph structural information for uncovering lncRNA-disease unknown correlations.

CONCLUSIONS

Our proposed NAGTLDA model can serve as a highly efficient computational method for predicting biological information associations.

GCN-Based Heterogeneous Complex Feature Learning to Enhance Predictability for LncRNA-Disease Associations

Using computational models to predict potential lncRNA-disease associations (LDAs) has emerged as an effective supplement to bioexperiments for exploring the pathogenesis of diseases. However, current computational models still face limitations in their ability to learn the complex features of bionetworks. In this study, HGCNLDA, a model which combines graph convolutional network (GCN)-based aggregation, heterogeneous information fusion, and a bilinear-decoder to infer LDAs was proposed. Recognizing the need to extract essential features during data processing, our HGCNLDA explored four key steps for uncovering interaction patterns within the bionetwork: (1) a novel type of tripartite heterogeneous network, known as the lncRNA-disease-miRNA network (LDMN), was constructed using computed similarities and known associations. (2) Homogeneous and heterogeneous features of nodes were extracted from domains within the LDMN by a GCN-based encoder. (3) Feature fusions, including bipolymerization operations and attention mechanism, were employed to capture a more accurate and comprehensive representation of nodes. (4) Bilinear-decoder was used to rebuild the edge type (or rating type) for a specific node pair, resulting in the predicted association score. Through a 5-fold cross-validation on two data sets, namely, data set1 and data set2, our HGCNLDA consistently demonstrated superior performance compared to five related models. It almost achieved the highest AUROC and AUPR values on both data sets, especially on data set2 where the results obtained were more challenging and objective. Case studies involving three real cancer scenarios further validated the practicality of HGCNLDA in identifying potential LDAs in real-world contexts. The source code and data for this study are available at https://github.com/zywait/HGCNLDA.

GCNFORMER: graph convolutional network and transformer for predicting lncRNA-disease associations

BACKGROUND

A growing body of researches indicate that the disrupted expression of long non-coding RNA (lncRNA) is linked to a range of human disorders. Therefore, the effective prediction of lncRNA-disease association (LDA) can not only suggest solutions to diagnose a condition but also save significant time and labor costs.

METHOD

In this work, we proposed a novel LDA predicting algorithm based on graph convolutional network and transformer, named GCNFORMER. Firstly, we integrated the intraclass similarity and interclass connections between miRNAs, lncRNAs and diseases, and built a graph adjacency matrix. Secondly, to completely obtain the features between various nodes, we employed a graph convolutional network for feature extraction. Finally, to obtain the global dependencies between inputs and outputs, we used a transformer encoder with a multiheaded attention mechanism to forecast lncRNA-disease associations.

RESULTS

The results of fivefold cross-validation experiment on the public dataset revealed that the AUC and AUPR of GCNFORMER achieved 0.9739 and 0.9812, respectively. We compared GCNFORMER with six advanced LDA prediction models, and the results indicated its superiority over the other six models. Furthermore, GCNFORMER's effectiveness in predicting potential LDAs is underscored by case studies on breast cancer, colon cancer and lung cancer.

CONCLUSIONS

The combination of graph convolutional network and transformer can effectively improve the performance of LDA prediction model and promote the in-depth development of this research filed.

LDA-VGHB: identifying potential lncRNA-disease associations with singular value decomposition, variational graph auto-encoder and heterogeneous Newton boosting machine

Long noncoding RNAs (lncRNAs) participate in various biological processes and have close linkages with diseases. In vivo and in vitro experiments have validated many associations between lncRNAs and diseases. However, biological experiments are time-consuming and expensive. Here, we introduce LDA-VGHB, an lncRNA-disease association (LDA) identification framework, by incorporating feature extraction based on singular value decomposition and variational graph autoencoder and LDA classification based on heterogeneous Newton boosting machine. LDA-VGHB was compared with four classical LDA prediction methods (i.e. SDLDA, LDNFSGB, IPCARF and LDASR) and four popular boosting models (XGBoost, AdaBoost, CatBoost and LightGBM) under 5-fold cross-validations on lncRNAs, diseases, lncRNA-disease pairs and independent lncRNAs and independent diseases, respectively. It greatly outperformed the other methods with its prominent performance under four different cross-validations on the lncRNADisease and MNDR databases. We further investigated potential lncRNAs for lung cancer, breast cancer, colorectal cancer and kidney neoplasms and inferred the top 20 lncRNAs associated with them among all their unobserved lncRNAs. The results showed that most of the predicted top 20 lncRNAs have been verified by biomedical experiments provided by the Lnc2Cancer 3.0, lncRNADisease v2.0 and RNADisease databases as well as publications. We found that HAR1A, KCNQ1DN, ZFAT-AS1 and HAR1B could associate with lung cancer, breast cancer, colorectal cancer and kidney neoplasms, respectively. The results need further biological experimental validation. We foresee that LDA-VGHB was capable of identifying possible lncRNAs for complex diseases. LDA-VGHB is publicly available at https://github.com/plhhnu/LDA-VGHB.

Graph Reasoning Method Based on Affinity Identification and Representation Decoupling for Predicting lncRNA-Disease Associations

An increasing number of studies have shown that dysregulation of lncRNAs is related to the occurrence of various diseases. Most of the previous methods, however, are designed based on homogeneity assumption that the representation of a target lncRNA (or disease) node should be updated by aggregating the attributes of its neighbor nodes. However, the assumption ignores the affinity nodes that are far from the target node. We present a novel prediction method, GAIRD, to fully leverage the heterogeneous information in the network and the decoupled node features. The first major innovation is a random walk strategy based on width-first searching and depth-first searching. Different from previous methods that only focus on homogeneous information, our new strategy learns both the homogeneous information within local neighborhoods and the heterogeneous information within higher-order neighborhoods. The second innovation is a representation decoupling module to extract the purer attributes and the purer topologies. Third, a module based on group convolution and deep separable convolution is developed to promote the pairwise intrachannel and interchannel feature learning. The experimental results show that GAIRD outperforms comparing state-of-the-art methods, and the ablation studies prove the contributions of major innovations. We also performed case studies on 3 diseases to further demonstrate the effectiveness of the GAIRD model in applications.

Predicting lncRNA-disease associations based on heterogeneous graph convolutional generative adversarial network

There is a growing body of evidence indicating the crucial roles that long non-coding RNAs (lncRNAs) play in the development and progression of various diseases, including cancers, cardiovascular diseases, and neurological disorders. However, accurately predicting potential lncRNA-disease associations remains a challenge, as existing methods have limitations in extracting heterogeneous association information and handling sparse and unbalanced data. To address these issues, we propose a novel computational method, called HGC-GAN, which combines heterogeneous graph convolutional neural networks (GCN) and generative adversarial networks (GAN) to predict potential lncRNA-disease associations. Specifically, we construct a lncRNA-miRNA-disease heterogeneous network by integrating multiple association data and sequence information. The GCN-based generator is then employed to aggregate neighbor information of nodes and obtain node embeddings, which are used to predict lncRNA-disease associations. Meanwhile, the GAN-based discriminator is trained to distinguish between real and fake lncRNA-disease associations generated by the generator, enabling the generator to improve its ability to generate accurate lncRNA-disease associations gradually. Our experimental results demonstrate that HGC-GAN performs better in predicting potential lncRNA-disease associations, with AUC and AUPR values of 0.9591 and 0.9606, respectively, under 10-fold cross-validation. Moreover, our case study further confirms the effectiveness of HGC-GAN in predicting potential lncRNA-disease associations, even for novel lncRNAs without any known lncRNA-disease associations. Overall, our proposed method HGC-GAN provides a promising approach to predict potential lncRNA-disease associations and may have important implications for disease diagnosis, treatment, and drug development.

Heterogeneous graph framework for predicting the association between lncRNA and disease and case on uterine fibroid

Long non-coding RNAs (lncRNAs) play crucial regulatory roles in various cellular processes, including gene expression, chromatin remodeling, and protein localization. Dysregulation of lncRNAs has been linked to several diseases, making it essential to understand their functions in disease mechanisms and therapeutic strategies. However, traditional experimental methods for studying lncRNA function are time-consuming, expensive, and offer limited insights. In recent years, computational methods have emerged as valuable tools for predicting lncRNA functions and their associations with diseases. However, many existing methods focus on constructing separate networks for lncRNA and disease similarity, resulting in information loss and insufficient processing capacity for isolated nodes. To address this, we developed 'RGLD' by combining Random Walk with restarting (RWR), Graph Neural Network (GNN), and Graph Attention Networks (GAT) to predict lncRNA-disease associations in a heterogeneous network. RGLD achieved an impressive AUC of 0.88, outperforming other methods. It can also predict novel associations between lncRNAs and diseases. RGLD identified HOTAIR, MEG3, and PVT1 as lncRNAs associated with uterine fibroids. Biological experiments directly or indirectly verified the involvement of these three lncRNAs in uterine fibroids, validating the accuracy of RGLD's predictions. Furthermore, we extensively discussed the functions of the target genes regulated by these lncRNAs in uterine fibroids, providing evidence for their role in the development and progression of the disease.

Multi-task prediction-based graph contrastive learning for inferring the relationship among lncRNAs, miRNAs and diseases

MOTIVATION

Identifying the relationships among long non-coding RNAs (lncRNAs), microRNAs (miRNAs) and diseases is highly valuable for diagnosing, preventing, treating and prognosing diseases. The development of effective computational prediction methods can reduce experimental costs. While numerous methods have been proposed, they often to treat the prediction of lncRNA-disease associations (LDAs), miRNA-disease associations (MDAs) and lncRNA-miRNA interactions (LMIs) as separate task. Models capable of predicting all three relationships simultaneously remain relatively scarce. Our aim is to perform multi-task predictions, which not only construct a unified framework, but also facilitate mutual complementarity of information among lncRNAs, miRNAs and diseases.

RESULTS

In this work, we propose a novel unsupervised embedding method called graph contrastive learning for multi-task prediction (GCLMTP). Our approach aims to predict LDAs, MDAs and LMIs by simultaneously extracting embedding representations of lncRNAs, miRNAs and diseases. To achieve this, we first construct a triple-layer lncRNA-miRNA-disease heterogeneous graph (LMDHG) that integrates the complex relationships between these entities based on their similarities and correlations. Next, we employ an unsupervised embedding model based on graph contrastive learning to extract potential topological feature of lncRNAs, miRNAs and diseases from the LMDHG. The graph contrastive learning leverages graph convolutional network architectures to maximize the mutual information between patch representations and corresponding high-level summaries of the LMDHG. Subsequently, for the three prediction tasks, multiple classifiers are explored to predict LDA, MDA and LMI scores. Comprehensive experiments are conducted on two datasets (from older and newer versions of the database, respectively). The results show that GCLMTP outperforms other state-of-the-art methods for the disease-related lncRNA and miRNA prediction tasks. Additionally, case studies on two datasets further demonstrate the ability of GCLMTP to accurately discover new associations. To ensure reproducibility of this work, we have made the datasets and source code publicly available at https://github.com/sheng-n/GCLMTP.

Specific topology and topological connection sensitivity enhanced graph learning for lncRNA-disease association prediction

Predicting disease-related candidate long noncoding RNAs (lncRNAs) is beneficial for exploring disease pathogenesis due to the close relations between lncRNAs and the occurrence and development of human diseases. It is a long-term and challenging task to adequately extract specific and local topologies in individual lncRNA network and individual disease network, and integrate the information of the connection relationships. We propose a new graph learning-based prediction method to encode specific and local topologies from each individual network, neighbor topologies with different connection relationships, and pairwise attributes. We first construct a lncRNA network composed of all the lncRNA nodes and their similarities, and a single disease network that contains all the disease nodes and disease similarities. Then, a network-aware graph convolutional autoencoder is constructed to encode the specific and local topologies of each network. Secondly, a heterogeneous network is established to embed all lncRNA, disease, and miRNA nodes and their various connections. Afterwards, a connection-sensitive graph neural network is designed to deeply integrate the neighbor node attributes and connection characteristics in the heterogeneous network and learn neighbor topological representations. We also construct both connection-level and topology representation-level attention mechanisms to extract informative connections and topological representations. Finally, we build a multi-layer convolutional neural networks with weighted residuals to adaptively complement the detailed features to pairwise attribute encoding. Comprehensive experiments and comparison results demonstrated that NCPred outperforms seven state-of-the-art prediction methods. The ablation studies demonstrated the importance of local topology learning, neighbor topology learning, and pairwise attribute encoding. Case studies on prostate, lung, and breast cancers further revealed NCPred's capacity to screen potential candidate disease-related lncRNAs.

GDCL-NcDA: identifying non-coding RNA-disease associations via contrastive learning between deep graph learning and deep matrix factorization

Non-coding RNAs (ncRNAs) draw much attention from studies widely in recent years because they play vital roles in life activities. As a good complement to wet experiment methods, computational prediction methods can greatly save experimental costs. However, high false-negative data and insufficient use of multi-source information can affect the performance of computational prediction methods. Furthermore, many computational methods do not have good robustness and generalization on different datasets. In this work, we propose an effective end-to-end computing framework, called GDCL-NcDA, of deep graph learning and deep matrix factorization (DMF) with contrastive learning, which identifies the latent ncRNA-disease association on diverse multi-source heterogeneous networks (MHNs). The diverse MHNs include different similarity networks and proven associations among ncRNAs (miRNAs, circRNAs, and lncRNAs), genes, and diseases. Firstly, GDCL-NcDA employs deep graph convolutional network and multiple attention mechanisms to adaptively integrate multi-source of MHNs and reconstruct the ncRNA-disease association graph. Then, GDCL-NcDA utilizes DMF to predict the latent disease-associated ncRNAs based on the reconstructed graphs to reduce the impact of the false-negatives from the original associations. Finally, GDCL-NcDA uses contrastive learning (CL) to generate a contrastive loss on the reconstructed graphs and the predicted graphs to improve the generalization and robustness of our GDCL-NcDA framework. The experimental results show that GDCL-NcDA outperforms highly related computational methods. Moreover, case studies demonstrate the effectiveness of GDCL-NcDA in identifying the associations among diversiform ncRNAs and diseases.

A lncRNA-disease association prediction model based on the two-step PU learning and fully connected neural networks

Long non-coding RNAs (lncRNAs) have been shown to play a regulatory role in various processes of human diseases. However, lncRNA experiments are inefficient, time-consuming and highly subjective, so that the number of experimentally verified associations between lncRNA and diseases is limited. In the era of big data, numerous machine learning methods have been proposed to predict the potential association between lncRNA and diseases, but the characteristics of the associated data were seldom explored. In these methods, negative samples are randomly selected for model training and the model is prone to learn the potential positive association error, thus affecting the prediction accuracy. In this paper, we proposed a cyclic optimization model of predicting lncRNA-disease associations (COPTLDA in short). In COPTLDA, the two-step training strategy is adopted to search for the samples with the greater probability of being negative examples from unlabeled samples and the determined samples are treated as negative samples, which are combined together with known positive samples to train the model. The searching and training steps are repeated until the best model is obtained as the final prediction model. In order to evaluate the performance of the model, 30% of the known positive samples are used to calculate the model accuracy and 10% of positive samples are used to calculate the recall rate of the model. The sampling strategy used in this paper can improve the accuracy and the AUC value reaches 0.9348. The results of case studies showed that the model could predict the potential associations between lncRNA and malignant tumors such as colorectal cancer, gastric cancer, and breast cancer. The predicted top 20 associated lncRNAs included 10 colorectal cancer lncRNAs, 2 gastric cancer lncRNAs, and 8 breast cancer lncRNAs.

LDAEXC: LncRNA-Disease Associations Prediction with Deep Autoencoder and XGBoost Classifier

Numerous scientific evidences have revealed that long non-coding RNAs (lncRNAs) are involved in the progression of human complex diseases and biological life activities. Therefore, identifying novel and potential disease-related lncRNAs is helpful to diagnosis, prognosis and therapy of many human complex diseases. Since traditional laboratory experiments are cost and time-consuming, a great quantity of computer algorithms have been proposed for predicting the relationships between lncRNAs and diseases. However, there are still much room for the improvement. In this paper, we introduce an accurate framework named LDAEXC to infer LncRNA-Disease Associations with deep autoencoder and XGBoost Classifier. LDAEXC utilizes different similarity views of lncRNAs and human diseases to construct features for each data sources. Then, the reduced features are obtained by feeding the constructed feature vectors into a deep autoencoder, and at last an XGBoost classifier is leveraged to calculate the latent lncRNA-disease-associated scores using reduced features. The fivefold cross-validation experiments on four datasets showed that LDAEXC reached AUC scores of 0.9676 ± 0.0043, 0.9449 ± 0.022, 0.9375 ± 0.0331 and 0.9556 ± 0.0134, respectively, significantly higher than other advanced similar computer methods. Extensive experiment results and case studies of two complex diseases (colon and breast cancers) further indicated the practicability and excellent prediction performance of LDAEXC in inferring unknown lncRNA-disease associations. TLDAEXC utilizes disease semantic similarity, lncRNA expression similarity, and Gaussian interaction profile kernel similarity of lncRNAs and diseases for feature construction. The constructed features are fed to a deep autoencoder to extract reduced features, and an XGBoost classifier is used to predict the lncRNA-disease associations based on the reduced features. The fivefold and tenfold cross-validation experiments on a benchmark dataset showed that LDAEXC could achieve AUC scores of 0.9676 and 0.9682, respectively, significantly higher than other state-of-the-art similar methods.

Semantic Meta-Path Enhanced Global and Local Topology Learning for lncRNA-Disease Association Prediction

Since abnormal expression of long non-coding RNAs (lncRNAs) is associated with various human diseases, identifying disease-related lncRNAs helps reveal the pathogenesis of diseases. Existing methods for lncRNA-disease association prediction mainly focus on multi-sourced data related to lncRNAs and diseases. The rich semantic information of meta-paths, composed of multiple kinds of connections between lncRNA and disease nodes, is neglected. We propose a new prediction method, MGLDA, to encode and integrate the semantics of multiple meta-paths, the global topology of heterogeneous graph, and pairwise attributes of lncRNA and disease nodes. First, a tri-layer heterogeneous graph is constructed to associate multi-sourced data across the lncRNA, disease, and miRNA nodes. Afterwards, we establish multiple meta-paths connecting the lncRNA and disease nodes to derive and denote various semantics. Each meta-path contains its specific semantics formulated by an embedding strategy, and each embedding covers local topology formed by the diverse semantic connections among the lncRNA, disease, and miRNA nodes. We construct multiple graph convolutional autoencoders (GCA) with topology-level attention to learn global and multiple local topologies from the tri-layer graph and each meta-path, respectively. The topology-level attention mechanism can learn the importance of various global and local topologies for adaptive pairwise topology fusion. Finally, a convolutional autoencoder learns the attribute representations of lncRNA-disease pairs, which integrates the learnt detailed and representative pairwise features. Experimental results show that MGLDA outperforms other state-of-the-art prediction methods in comparison and retrieves more real lncRNA-disease associations in the top-ranked candidates. The ablation study also demonstrates the important contributions of the local and global topology learning, and pairwise attribute learning. Case studies on three diseases further demonstrate MGLDA's ability to identify potential disease-related lncRNAs.

LPIH2V: LncRNA-protein interactions prediction using HIN2Vec based on heterogeneous networks model

LncRNA-protein interaction plays an important role in the development and treatment of many human diseases. As the experimental approaches to determine lncRNA-protein interactions are expensive and time-consuming, considering that there are few calculation methods, therefore, it is urgent to develop efficient and accurate methods to predict lncRNA-protein interactions. In this work, a model for heterogeneous network embedding based on meta-path, namely LPIH2V, is proposed. The heterogeneous network is composed of lncRNA similarity networks, protein similarity networks, and known lncRNA-protein interaction networks. The behavioral features are extracted in a heterogeneous network using the HIN2Vec method of network embedding. The results showed that LPIH2V obtains an AUC of 0.97 and ACC of 0.95 in the 5-fold cross-validation test. The model successfully showed superiority and good generalization ability. Compared to other models, LPIH2V not only extracts attribute characteristics by similarity, but also acquires behavior properties by meta-path wandering in heterogeneous networks. LPIH2V would be beneficial in forecasting interactions between lncRNA and protein.

Recent advances in predicting lncRNA-disease associations based on computational methods

Mutations in and dysregulation of long non-coding RNAs (lncRNAs) are closely associated with the development of various human complex diseases, but only a few lncRNAs have been experimentally confirmed to be associated with human diseases. Predicting new potential lncRNA-disease associations (LDAs) will help us to understand the pathogenesis of human diseases and to detect disease markers, as well as in disease diagnosis, prevention and treatment. Computational methods can effectively narrow down the screening scope of biological experiments, thereby reducing the duration and cost of such experiments. In this review, we outline recent advances in computational methods for predicting LDAs, focusing on LDA databases, lncRNA/disease similarity calculations, and advanced computational models. In addition, we analyze the limitations of various computational models and discuss future challenges and directions for development.

Data resources and computational methods for lncRNA-disease association prediction

Increasing interest has been attracted in deciphering the potential disease pathogenesis through lncRNA-disease association (LDA) prediction, regarding to the diverse functional roles of lncRNAs in genome regulation. Whilst, computational models and algorithms benefit systematic biology research, even facilitate the classical biological experimental procedures. In this review, we introduce representative diseases associated with lncRNAs, such as cancers, cardiovascular diseases, and neurological diseases. Current publicly available resources related to lncRNAs and diseases have also been included. Furthermore, all of the 64 computational methods for LDA prediction have been divided into 5 groups, including machine learning-based methods, network propagation-based methods, matrix factorization- and completion-based methods, deep learning-based methods, and graph neural network-based methods. The common evaluation methods and metrics in LDA prediction have also been discussed. Finally, the challenges and future trends in LDA prediction have been discussed. Recent advances in LDA prediction approaches have been summarized in the GitHub repository at https://github.com/sheng-n/lncRNA-disease-methods.

Screening potential lncRNA biomarkers for breast cancer and colorectal cancer combining random walk and logistic matrix factorization

Breast cancer and colorectal cancer are two of the most common malignant tumors worldwide. They cause the leading causes of cancer mortality. Many researches have demonstrated that long noncoding RNAs (lncRNAs) have close linkages with the occurrence and development of the two cancers. Therefore, it is essential to design an effective way to identify potential lncRNA biomarkers for them. In this study, we developed a computational method (LDA-RWLMF) by integrating random walk with restart and Logistic Matrix Factorization to investigate the roles of lncRNA biomarkers in the prognosis and diagnosis of the two cancers. We first fuse disease semantic and Gaussian association profile similarities and lncRNA functional and Gaussian association profile similarities. Second, we design a negative selection algorithm to extract negative LncRNA-Disease Associations (LDA) based on random walk. Third, we develop a logistic matrix factorization model to predict possible LDAs. We compare our proposed LDA-RWLMF method with four classical LDA prediction methods, that is, LNCSIM1, LNCSIM2, ILNCSIM, and IDSSIM. The results from 5-fold cross validation on the MNDR dataset show that LDA-RWLMF computes the best AUC value of 0.9312, outperforming the above four LDA prediction methods. Finally, we rank all lncRNA biomarkers for the two cancers after determining the performance of LDA-RWLMF, respectively. We find that 48 and 50 lncRNAs have the highest association scores with breast cancer and colorectal cancer among all lncRNAs known to associate with them on the MNDR dataset, respectively. We predict that lncRNAs HULC and HAR1A could be separately potential biomarkers for breast cancer and colorectal cancer and need to biomedical experimental validation.

Multi-view contrastive heterogeneous graph attention network for lncRNA-disease association prediction

MOTIVATION

Exploring the potential long noncoding RNA (lncRNA)-disease associations (LDAs) plays a critical role for understanding disease etiology and pathogenesis. Given the high cost of biological experiments, developing a computational method is a practical necessity to effectively accelerate experimental screening process of candidate LDAs. However, under the high sparsity of LDA dataset, many computational models hardly exploit enough knowledge to learn comprehensive patterns of node representations. Moreover, although the metapath-based GNN has been recently introduced into LDA prediction, it discards intermediate nodes along the meta-path and results in information loss.

RESULTS

This paper presents a new multi-view contrastive heterogeneous graph attention network (GAT) for lncRNA-disease association prediction, MCHNLDA for brevity. Specifically, MCHNLDA firstly leverages rich biological data sources of lncRNA, gene and disease to construct two-view graphs, feature structural graph of feature schema view and lncRNA-gene-disease heterogeneous graph of network topology view. Then, we design a cross-contrastive learning task to collaboratively guide graph embeddings of the two views without relying on any labels. In this way, we can pull closer the nodes of similar features and network topology, and push other nodes away. Furthermore, we propose a heterogeneous contextual GAT, where long short-term memory network is incorporated into attention mechanism to effectively capture sequential structure information along the meta-path. Extensive experimental comparisons against several state-of-the-art methods show the effectiveness of proposed framework.The code and data of proposed framework is freely available at https://github.com/zhaoxs686/MCHNLDA.

Predicting lncRNA-disease associations based on combining selective similarity matrix fusion and bidirectional linear neighborhood label propagation

Recent studies have revealed that long noncoding RNAs (lncRNAs) are closely linked to several human diseases, providing new opportunities for their use in detection and therapy. Many graph propagation and similarity fusion approaches can be used for predicting potential lncRNA-disease associations. However, existing similarity fusion approaches suffer from noise and self-similarity loss in the fusion process. To address these problems, a new prediction approach, termed SSMF-BLNP, based on organically combining selective similarity matrix fusion (SSMF) and bidirectional linear neighborhood label propagation (BLNP), is proposed in this paper to predict lncRNA-disease associations. In SSMF, self-similarity networks of lncRNAs and diseases are obtained by selective preprocessing and nonlinear iterative fusion. The fusion process assigns weights to each initial similarity network and introduces a unit matrix that can reduce noise and compensate for the loss of self-similarity. In BLNP, the initial lncRNA-disease associations are employed in both lncRNA and disease directions as label information for linear neighborhood label propagation. The propagation was then performed on the self-similarity network obtained from SSMF to derive the scoring matrix for predicting the relationships between lncRNAs and diseases. Experimental results showed that SSMF-BLNP performed better than seven other state of-the-art approaches. Furthermore, a case study demonstrated up to 100% and 80% accuracy in 10 lncRNAs associated with hepatocellular carcinoma and 10 lncRNAs associated with renal cell carcinoma, respectively. The source code and datasets used in this paper are available at: https://github.com/RuiBingo/SSMF-BLNP.

CapsNet-LDA: predicting lncRNA-disease associations using attention mechanism and capsule network based on multi-view data

Cumulative studies have shown that many long non-coding RNAs (lncRNAs) are crucial in a number of diseases. Predicting potential lncRNA-disease associations (LDAs) can facilitate disease prevention, diagnosis and treatment. Therefore, it is vital to develop practical computational methods for LDA prediction. In this study, we propose a novel predictor named capsule network (CapsNet)-LDA for LDA prediction. CapsNet-LDA first uses a stacked autoencoder for acquiring the informative low-dimensional representations of the lncRNA-disease pairs under multiple views, then the attention mechanism is leveraged to implement an adaptive allocation of importance weights to them, and they are subsequently processed using a CapsNet-based architecture for predicting LDAs. Different from the conventional convolutional neural networks (CNNs) that have some restrictions with the usage of scalar neurons and pooling operations. the CapsNets use vector neurons instead of scalar neurons that have better robustness for the complex combination of features and they use dynamic routing processes for updating parameters. CapsNet-LDA is superior to other five state-of-the-art models on four benchmark datasets, four perturbed datasets and an independent test set in the comparison experiments, demonstrating that CapsNet-LDA has excellent performance and robustness against perturbation, as well as good generalization ability. The ablation studies verify the effectiveness of some modules of CapsNet-LDA. Moreover, the ability of multi-view data to improve performance is proven. Case studies further indicate that CapsNet-LDA can accurately predict novel LDAs for specific diseases.

SCCPMD: Probability matrix decomposition method subject to corrected similarity constraints for inferring long non-coding RNA-disease associations

Accumulating evidence has demonstrated various associations of long non-coding RNAs (lncRNAs) with human diseases, such as abnormal expression due to microbial influences that cause disease. Gaining a deeper understanding of lncRNA-disease associations is essential for disease diagnosis, treatment, and prevention. In recent years, many matrix decomposition methods have also been used to predict potential lncRNA-disease associations. However, these methods do not consider the use of microbe-disease association information to enrich disease similarity, and also do not make more use of similarity information in the decomposition process. To address these issues, we here propose a correction-based similarity-constrained probability matrix decomposition method (SCCPMD) to predict lncRNA-disease associations. The microbe-disease associations are first used to enrich the disease semantic similarity matrix, and then the logistic function is used to correct the lncRNA and disease similarity matrix, and then these two corrected similarity matrices are added to the probability matrix decomposition as constraints to finally predict the potential lncRNA-disease associations. The experimental results show that SCCPMD outperforms the five advanced comparison algorithms. In addition, SCCPMD demonstrated excellent prediction performance in a case study for breast cancer, lung cancer, and renal cell carcinoma, with prediction accuracy reaching 80, 100, and 100%, respectively. Therefore, SCCPMD shows excellent predictive performance in identifying unknown lncRNA-disease associations.

lncRNA-disease association prediction based on the weight matrix and projection score

With the development of medical science, long noncoding RNA (lncRNA), originally considered as a noise gene, has been found to participate in a variety of biological activities. Several recent studies have shown the involvement of lncRNA in various human diseases, such as gastric cancer, prostate cancer, lung cancer, and so forth. However, obtaining lncRNA-disease relationship only through biological experiments not only costs manpower and material resources but also gains little. Therefore, developing effective computational models for predicting lncRNA-disease association relationship is extremely important. This study aimed to propose an lncRNA-disease association prediction model based on the weight matrix and projection score (LDAP-WMPS). The model used the relatively perfect lncRNA-miRNA relationship data and miRNA-disease relationship data to predict the lncRNA-disease relationship. The integrated lncRNA similarity matrix and the integrated disease similarity matrix were established by fusing various methods to calculate the similarity between lncRNA and disease. This study improved the existing weight algorithm, applied it to the lncRNA-miRNA-disease triple network, and thus proposed a new lncRNA-disease weight matrix calculation method. Combined with the improved projection algorithm, the lncRNA-miRNA relationship and miRNA-disease relationship were used to predict the lncRNA-disease relationship. The simulation results showed that under the Leave-One-Out-Cross-Validation framework, the area under the receiver operating characteristic curve of LDAP-WMPS could reach 0.8822, which was better than the latest result. Taking adenocarcinoma and colorectal cancer as examples, the LDAP-WMPS model was found to effectively infer the lncRNA-disease relationship. The simulation results showed good prediction performance of the LDAP-WMPS model, which was an important supplement to the research of lncRNA-disease association prediction without lncRNA-disease relationship data.

lncRNA-disease association prediction method based on the nearest neighbor matrix completion model

State-of-the-art medical studies proved that long noncoding ribonucleic acids (lncRNAs) are closely related to various diseases. However, their large-scale detection in biological experiments is problematic and expensive. To aid screening and improve the efficiency of biological experiments, this study introduced a prediction model based on the nearest neighbor concept for lncRNA-disease association prediction. We used a new similarity algorithm in the model that fused potential associations. The experimental validation of the proposed algorithm proved its superiority over the available Cosine, Pearson, and Jaccard similarity algorithms. Satisfactory results in the comparative leave-one-out cross-validation test (with AUC = 0.96) confirmed its excellent predictive performance. Finally, the proposed model's reliability was confirmed by performing predictions using a new dataset, yielding AUC = 0.92.

A weighted non-negative matrix factorization approach to predict potential associations between drug and disease

BACKGROUND

Associations of drugs with diseases provide important information for expediting drug development. Due to the number of known drug-disease associations is still insufficient, and considering that inferring associations between them through traditional in vitro experiments is time-consuming and costly. Therefore, more accurate and reliable computational methods urgent need to be developed to predict potential associations of drugs with diseases.

METHODS

In this study, we present the model called weighted graph regularized collaborative non-negative matrix factorization for drug-disease association prediction (WNMFDDA). More specifically, we first calculated the drug similarity and disease similarity based on the chemical structures of drugs and medical description information of diseases, respectively. Then, to extend the model to work for new drugs and diseases, weighted [Formula: see text] nearest neighbor was used as a preprocessing step to reconstruct the interaction score profiles of drugs with diseases. Finally, a graph regularized non-negative matrix factorization model was used to identify potential associations between drug and disease.

RESULTS

During the cross-validation process, WNMFDDA achieved the AUC values of 0.939 and 0.952 on Fdataset and Cdataset under ten-fold cross validation, respectively, which outperforms other competing prediction methods. Moreover, case studies for several drugs and diseases were carried out to further verify the predictive performance of WNMFDDA. As a result, 13(Doxorubicin), 13(Amiodarone), 12(Obesity) and 12(Asthma) of the top 15 corresponding candidate diseases or drugs were confirmed by existing databases.

CONCLUSIONS

The experimental results adequately demonstrated that WNMFDDA is a very effective method for drug-disease association prediction. We believe that WNMFDDA is helpful for relevant biomedical researchers in follow-up studies.

Recent advances in machine learning methods for predicting LncRNA and disease associations

Long non-coding RNAs (lncRNAs) are involved in almost the entire cell life cycle through different mechanisms and play an important role in many key biological processes. Mutations and dysregulation of lncRNAs have been implicated in many complex human diseases. Therefore, identifying the relationship between lncRNAs and diseases not only contributes to biologists' understanding of disease mechanisms, but also provides new ideas and solutions for disease diagnosis, treatment, prognosis and prevention. Since the existing experimental methods for predicting lncRNA-disease associations (LDAs) are expensive and time consuming, machine learning methods for predicting lncRNA-disease associations have become increasingly popular among researchers. In this review, we summarize some of the human diseases studied by LDAs prediction models, association and similarity features of LDAs prediction, performance evaluation methods of models and some advanced machine learning prediction models of LDAs. Finally, we discuss the potential limitations of machine learning-based methods for LDAs prediction and provide some ideas for designing new prediction models.

LDAformer: predicting lncRNA-disease associations based on topological feature extraction and Transformer encoder

The identification of long noncoding RNA (lncRNA)-disease associations is of great value for disease diagnosis and treatment, and it is now commonly used to predict potential lncRNA-disease associations with computational methods. However, the existing methods do not sufficiently extract key features during data processing, and the learning model parts are either less powerful or overly complex. Therefore, there is still potential to achieve better predictive performance by improving these two aspects. In this work, we propose a novel lncRNA-disease association prediction method LDAformer based on topological feature extraction and Transformer encoder. We construct the heterogeneous network by integrating the associations between lncRNAs, diseases and micro RNAs (miRNAs). Intra-class similarities and inter-class associations are presented as the lncRNA-disease-miRNA weighted adjacency matrix to unify semantics. Next, we design a topological feature extraction process to further obtain multi-hop topological pathway features latent in the adjacency matrix. Finally, to capture the interdependencies between heterogeneous pathways, a Transformer encoder based on the global self-attention mechanism is employed to predict lncRNA-disease associations. The efficient feature extraction and the intuitive and powerful learning model lead to ideal performance. The results of computational experiments on two datasets show that our method outperforms the state-of-the-art baseline methods. Additionally, case studies further indicate its capability to discover new associations accurately.

MSF-UBRW: An Improved Unbalanced Bi-Random Walk Method to Infer Human lncRNA-Disease Associations

Long-non-coding RNA (lncRNA) is a transcription product that exerts its biological functions through a variety of mechanisms. The occurrence and development of a series of human diseases are closely related to abnormal expression levels of lncRNAs. Scientists have developed many computational models to identify the lncRNA-disease associations (LDAs). However, many potential LDAs are still unknown. In this paper, a novel method, namely MSF-UBRW (multiple similarities fusion based on unbalanced bi-random walk), is designed to explore new LDAs. First, two similarities (functional similarity and Gaussian Interaction Profile kernel similarity) of lncRNAs are calculated and fused linearly, also for disease data. Then, the known association matrix is preprocessed. Next, the linear neighbor similarities of lncRNAs and diseases are calculated, respectively. After that, the potential associations are predicted based on unbalanced bi-random walk. The fusion of multiple similarities improves the prediction performance of MSF-UBRW to a large extent. Finally, the prediction ability of the MSF-UBRW algorithm is measured by two statistical methods, leave-one-out cross-validation (LOOCV) and 5-fold cross-validation (5-fold CV). The AUCs of 0.9391 in LOOCV and 0.9183 (±0.0054) in 5-fold CV confirmed the reliable prediction ability of the MSF-UBRW method. Case studies of three common diseases also show that the MSF-UBRW method can infer new LDAs effectively.

BRPCA: Bounded Robust Principal Component Analysis to Incorporate Similarity Network for N7-Methylguanosine(m7G) Site-Disease Association Prediction

Recent studies have revealed that N7-methylguanosine(m⁷G) plays a pivotal role in various biological processes and disease pathogenesis. To date, transcriptome-wide m⁷G modification sites have been identified by high-throughput sequencing approaches, and some related information has been recorded in a few biological databases. However, the mechanism of site action in disease remains uncharted. Wet experiments can help identify true m⁷G sites with high confidence, but it is time-consuming to find the true ones in such a large number of sites, which will also cost too much. Thus, computational methods are emergently needed to predict the associations between m⁷G sites and various diseases, thus help to uncover potential active sites for specific diseases. In this article, we proposed a bounded robust principal component analysis (BRPCA) method to predict unknown m⁷G-disease association based on similarity information. Importantly, BRPCA tolerates the noise and redundancy existing in association and similarity information. Moreover, a suitable bounded constraint is incorporated into BRPCA to ensure that the predicted association scores locate in a meaningful interval. The extensive experiments demonstrate the superiority and robustness of the BRPCA.

Extra Trees Method for Predicting LncRNA-Disease Association Based On Multi-Layer Graph Embedding Aggregation

Lots of experimental studies have revealed the significant associations between lncRNAs and diseases. Identifying accurate associations will provide a new perspective for disease therapy. Calculation-based methods have been developed to solve these problems, but these methods have some limitations. In this paper, we proposed an accurate method, named MLGCNET, to discover potential lncRNA-disease associations. Firstly, we reconstructed similarity networks for both lncRNAs and diseases using top k similar information, and constructed a lncRNA-disease heterogeneous network (LDN). Then, we applied Multi-Layer Graph Convolutional Network on LDN to obtain latent feature representations of nodes. Finally, the Extra Trees was used to calculate the probability of association between disease and lncRNA. The results of extensive 5-fold cross-validation experiments show that MLGCNET has superior prediction performance compared to the state-of-the-art methods. Case studies confirm the performance of our model on specific diseases. All the experiment results prove the effectiveness and practicality of MLGCNET in predicting potential lncRNA-disease associations.

DHNLDA: A Novel Deep Hierarchical Network Based Method for Predicting lncRNA-Disease Associations

Recent studies have found that lncRNA (long non-coding RNA) in ncRNA (non-coding RNA) is not only involved in many biological processes, but also abnormally expressed in many complex diseases. Identification of lncRNA-disease associations accurately is of great significance for understanding the function of lncRNA and disease mechanism. In this paper, a deep learning framework consisting of stacked autoencoder(SAE), multi-scale ResNet and stacked ensemble module, named DHNLDA, was constructed to predict lncRNA-disease associations, which integrates multiple biological data sources and constructing feature matrices. Among them, the biological data including the similarity and the interaction of lncRNAs, diseases and miRNAs are integrated. The feature matrices are obtained by node2vec embedding and feature extraction respectively. Then, the SAE and the multi-scale ResNet are used to learn the complementary information between nodes, and the high-level features of node attributes are obtained. Finally, the fusion of high-level feature is input into the stacked ensemble module to obtain the prediction results of lncRNA-disease associations. The experimental results of five-fold cross-validation show that the AUC of DHNLDA reaches 0.975 better than the existing methods. Case studies of stomach cancer, breast cancer and lung cancer have shown the great ability of DHNLDA to discover the potential lncRNA-disease associations.

Heterogeneous graph neural network for lncRNA-disease association prediction

Identifying lncRNA-disease associations is conducive to the diagnosis, treatment and prevention of diseases. Due to the expensive and time-consuming methods verified by biological experiments, prediction methods based on computational models have gradually become an important means of lncRNA-disease associations discovery. However, existing methods still have challenges to make full use of network topology information to identify potential associations between lncRNA and disease in multi-source data. In this study, we propose a novel method called HGNNLDA for lncRNA-disease association prediction. First, HGNNLDA constructs a heterogeneous network composed of lncRNA similarity network, lncRNA-disease association network and lncRNA-miRNA association network; Then, on this heterogeneous network, various types of strong correlation neighbors with fixed size are sampled for each node by restart random walk; Next, the embedding information of lncRNA and disease in each lncRNA-disease association pair is obtained by the method of type-based neighbor aggregation and all types combination though heterogeneous graph neural network, in which attention mechanism is introduced considering that different types of neighbors will make different contributions to the prediction of lncRNA-disease association. As a result, the area under the receiver operating characteristic curve (AUC) and the area under the precision-recall curve (AUPR) under fivefold cross-validation (5FCV) are 0.9786 and 0.8891, respectively. Compared with five state-of-art prediction models, HGNNLDA has better prediction performance. In addition, in two types of case studies, it is further verified that our method can effectively predict the potential lncRNA-disease associations, and have ability to predict new diseases without any known lncRNAs.

MHDMF: Prediction of miRNA-disease associations based on Deep Matrix Factorization with Multi-source Graph Convolutional Network

A growing number of works have proved that microRNAs (miRNAs) are a crucial biomarker in diverse bioprocesses affecting various diseases. As a good complement to high-cost wet experiment-based methods, numerous computational prediction methods have sprung up. However, there are still challenges that exist in making effective use of high false-negative associations and multi-source information for finding the potential associations. In this work, we develop an end-to-end computational framework, called MHDMF, which integrates the multi-source information on a heterogeneous network to discover latent disease-miRNA associations. Since high false-negative exist in the miRNA-disease associations, MHDMF utilizes the multi-source Graph Convolutional Network (GCN) to correct the false-negative association by reformulating the miRNA-disease association score matrix. The score matrix reformulation is based on different similarity profiles and known associations between miRNAs, genes, and diseases. Then, MHDMF employs Deep Matrix Factorization (DMF) to predict the miRNA-disease associations based on reformulated miRNA-disease association score matrix. The experimental results show that the proposed framework outperforms highly related comparison methods by a large margin on tasks of miRNA-disease association prediction. Furthermore, case studies suggest that MHDMF could be a convenient and efficient tool and may supply a new way to think about miRNA-disease association prediction.

Learning global dependencies and multi-semantics within heterogeneous graph for predicting disease-related lncRNAs

Motivation

Long noncoding RNAs (lncRNAs) play an important role in the occurrence and development of diseases. Predicting disease-related lncRNAs can help to understand the pathogenesis of diseases deeply. The existing methods mainly rely on multi-source data related to lncRNAs and diseases when predicting the associations between lncRNAs and diseases. There are interdependencies among node attributes in a heterogeneous graph composed of all lncRNAs, diseases and micro RNAs. The meta-paths composed of various connections between them also contain rich semantic information. However, the existing methods neglect to integrate attribute information of intermediate nodes in meta-paths.

Results

We propose a novel association prediction model, GSMV, to learn and deeply integrate the global dependencies, semantic information of meta-paths and node-pair multi-view features related to lncRNAs and diseases. We firstly formulate the global representations of the lncRNA and disease nodes by establishing a self-attention mechanism to capture and learn the global dependencies among node attributes. Second, starting from the lncRNA and disease nodes, respectively, multiple meta-pathways are established to reveal different semantic information. Considering that each meta-path contains specific semantics and has multiple meta-path instances which have different contributions to revealing meta-path semantics, we design a graph neural network based module which consists of a meta-path instance encoding strategy and two novel attention mechanisms. The proposed meta-path instance encoding strategy is used to learn the contextual connections between nodes within a meta-path instance. One of the two new attention mechanisms is at the meta-path instance level, which learns rich and informative meta-path instances. The other attention mechanism integrates various semantic information from multiple meta-paths to learn the semantic representation of lncRNA and disease nodes. Finally, a dilated convolution-based learning module with adjustable receptive fields is proposed to learn multi-view features of lncRNA-disease node pairs. The experimental results prove that our method outperforms seven state-of-the-art comparing methods for lncRNA-disease association prediction. Ablation experiments demonstrate the contributions of the proposed global representation learning, semantic information learning, pairwise multi-view feature learning and the meta-path instance encoding strategy. Case studies on three cancers further demonstrate our method’s ability to discover potential disease-related lncRNA candidates.

Contact

zhang@hlju.edu.cn or peiliangwu@ysu.edu.cn

Supplementary information

Supplementary data are available at Briefings in Bioinformatics online.

MCA-Net: Multi-Feature Coding and Attention Convolutional Neural Network for Predicting lncRNA-Disease Association

With the advent of the era of big data, it is troublesome to accurately predict the associations between lncRNAs and diseases based on traditional biological experiments due to its time-consuming and subjective. In this paper, we propose a novel deep learning method for predicting lncRNA-disease associations using multi-feature coding and attention convolutional neural network (MCA-Net). We first calculate six similarity features to extract different types of lncRNA and disease feature information. Second, a multi-feature coding method is proposed to construct the feature vectors of lncRNA-disease association samples by integrating the six similarity features. Furthermore, an attention convolutional neural network is developed to identify lncRNA-disease associations under 10-fold cross-validation. Finally, we evaluate the performance of MCA-Net from different perspectives including the effects of the model parameters, distinct deep learning models, and the necessity of attention mechanism. We also compare MCA-Net with several state-of-the-art methods on three publicly available datasets, i.e., LncRNADisease, Lnc2Cancer, and LncRNADisease2.0. The results show that our MCA-Net outperforms the state-of-the-art methods on all three dataset. Besides, case studies on breast cancer and lung cancer further verify that MCA-Net is effective and accurate for the lncRNA-disease association prediction.

Geometric complement heterogeneous information and random forest for predicting lncRNA-disease associations

More and more evidences have showed that the unnatural expression of long non-coding RNA (lncRNA) is relevant to varieties of human diseases. Therefore, accurate identification of disease-related lncRNAs can help to understand lncRNA expression at the molecular level and to explore more effective treatments for diseases. Plenty of lncRNA-disease association prediction models have been raised but it is still a challenge to recognize unknown lncRNA-disease associations. In this work, we have proposed a computational model for predicting lncRNA-disease associations based on geometric complement heterogeneous information and random forest. Firstly, geometric complement heterogeneous information was used to integrate lncRNA-miRNA interactions and miRNA-disease associations verified by experiments. Secondly, lncRNA and disease features consisted of their respective similarity coefficients were fused into input feature space. Thirdly, an autoencoder was adopted to project raw high-dimensional features into low-dimension space to learn representation for lncRNAs and diseases. Finally, the low-dimensional lncRNA and disease features were fused into input feature space to train a random forest classifier for lncRNA-disease association prediction. Under five-fold cross-validation, the AUC (area under the receiver operating characteristic curve) is 0.9897 and the AUPR (area under the precision-recall curve) is 0.7040, indicating that the performance of our model is better than several state-of-the-art lncRNA-disease association prediction models. In addition, case studies on colon and stomach cancer indicate that our model has a good ability to predict disease-related lncRNAs.

DeepIDA: Predicting Isoform-Disease Associations by Data Fusion and Deep Neural Networks

Alternative splicing produces different isoforms from the same gene locus, it is an important mechanism for regulating gene expression and proteome diversity. Although the prediction of gene(ncRNA)-disease associations has been extensively studied, few (or no) computational solutions have been proposed for the prediction of isoform-disease association (IDA) at a large scale, mainly due to the lack of disease annotations of isoforms. However, increasing evidences confirm the associations between diseases and isoforms, which can more precisely uncover the pathology of complex diseases. Therefore, it is highly desirable to predict IDAs. To bridge this gap, we propose a deep neural network based solution (DeepIDA) to fuse multi-type genomics and transcriptomics data to predict IDAs. Particularly, DeepIDA uses gene-isoform relations to dispatch gene-disease associations to isoforms. In addition, it utilizes two DNN sub-networks with different structures to capture nucleotide and expression features of isoforms, Gene Ontology data and miRNA target data, respectively. After that, these two sub-networks are merged in a dense layer to predict IDAs. The experimental results on public datasets show that DeepIDA can effectively predict IDAs with AUPRC (area under the precision-recall curve) of 0.9141, macro F-measure of 0.9155, G-mean of 0.9278 and balanced accuracy of 0.9303 across 732 diseases, which are much higher than those of competitive methods. Further study on sixteen isoform-disease association cases again corroborates the superiority of DeepIDA. The code of DeepIDA is available at http://mlda.swu.edu.cn/codes.php?name=DeepIDA.

HBRWRLDA: predicting potential lncRNA-disease associations based on hypergraph bi-random walk with restart

Accumulating evidence indicates that the regulation of long non-coding RNAs (lncRNAs) is closely related to a variety of diseases. Identifying meaningful lncRNA-disease associations will help to contribute to the understanding of the molecular mechanisms underlying these diseases. However, only a limited number of associations between lncRNAs and diseases have been inferred from traditional biological experiments due to the high cost and highly specialized. Therefore, computational methods are increasingly used to reduce time of biological experiments and complement biological research. In this paper, a computational method called HBRWRLDA is proposed to predict lncRNA-disease associations. First, HBRWRLDA models the relationships between multiple nodes using hypergraphs, which allows HBRWRLDA to integrate the expression similarity of lncRNAs and the semantic similarity of diseases to construct hypergraphs. Then, a bi-random walk on hypergraphs is used to predict potential lncRNA-disease associations. HBRWRLDA achieves a higher area under the curve value of 0.9551 and [Formula: see text], respectively, compared with the other five advanced methods under the framework of one-leave cross validation (LOOCV) and five-fold cross-validation (5-fold CV). In addition, the prediction effect of HBRWRLDA was confirmed case studies of three diseases: renal cell carcinoma, gastric cancer, and hepatocellular carcinoma. Case studies demonstrates the capacity of HBRWRLDA to identify potentially disease-associated lncRNAs. Overall, HBRWRLDA is excellent at predicting potential lncRNA-disease associations and could be useful in conducting further biological experiments by helping researchers identify candidates of lncRNA-disease association.

Weighted deep factorizing heterogeneous molecular network for genome-phenome association prediction

Genome-phenome association (GPA) prediction can promote the understanding of biological mechanisms about complex pathology of phenotypes (i.e., traits and diseases). Traditional heterogeneous network-based GPA approaches overwhelmingly need to project heterogeneous data toward homogeneous network for data fusion and prediction, such projections result in the loss of heterogeneous network structure information. Matrix factorization based data fusion can avoid such projection by integrating multi-type data in a coherent way, but they typically perform linear factorization and cannot mine the nonlinear relationships between molecules, which compromise the accuracy of GPA analysis. Furthermore, most of them can not selectively synergy network topology and node attribution information in a principle way. In this paper, we propose a weighted deep matrix factorization based solution (WDGPA) to predict GPAs by selectively and differentially fusing heterogeneous molecular network and diverse attributes of nodes. WDGPA firstly assigns weights to inter/intra-relational data matrices and attribute data matrices, and performs deep matrix factorization on these matrices of heterogeneous network in a cooperative manner to obtain the nonlinear representations of different nodes. In addition, it performs low-rank representation learning on the attribute data with the shared nonlinear representations. In this way, both the network topology and node attributes are jointly mined to explore the representations of molecules and complex interplays between molecules and phenotypes. WDGPA then uses the representational vectors of gene and phenotype nodes to predict GPAs. Experimental results on maize and human datasets confirm that WDGPA outperforms competitive methods by a large margin under different evaluation protocols.

Dual Attention Mechanisms and Feature Fusion Networks Based Method for Predicting LncRNA-Disease Associations

LncRNAs play a part in numerous momentous processes of biology such as disease diagnoses, preventions and treatments. The associations between various diseases and lncRNAs are one of the crucial approaches to learn the role and status of lncRNAs in human diseases. With the researches on lncRNA and diseases, multiple methods based on neural network have been employed to predict these associations. However, the deep and complicated characteristic representations of lncRNA-disease associations were failed to be extracted, and the discriminative contributions of the interactions, correlations, and similarities among miRNAs diseases, and lncRNAs for the correlation predictions were ignored. In this paper, based on the multibiology premise of lncRNAs, miRNAs, and diseases, a dual attention network was proposed to predict the model of lncRNA-disease associations for miRNAs, the disease characteristic matrix, and lncRNAs. Through two attention modules, we enable the model to learn the nonlinear, more complex and useful features of lncRNA, miRNA, and disease characteristic matrix. For the feature embedding matrix composed of lncRNA-disease, the connection between lncRNA-disease feature embedding matrix and lncRNA, miRNA, and disease characteristic matrix was enhanced through deconvolution and feature fusion layer. Compared with several latest methods, the method proposed in this paper can produce better performance. Researches on the cases of osteosarcoma, lung cancer, and gastric cancer have confirmed the effective recognition of potential lncRNA-disease associations.

LDICDL: LncRNA-Disease Association Identification Based on Collaborative Deep Learning

It has been proved that long noncoding RNA (lncRNA) plays critical roles in many human diseases. Therefore, inferring associations between lncRNAs and diseases can contribute to disease diagnosis, prognosis and treatment. To overcome the limitation of traditional experimental methods such as expensive and time-consuming, several computational methods have been proposed to predict lncRNA-disease associations by fusing different biological data. However, the prediction performance of lncRNA-disease associations identification needs to be improved. In this study, we propose a computational model (named LDICDL) to identify lncRNA-disease associations based on collaborative deep learning. It uses an automatic encoder to denoise multiple lncRNA feature information and multiple disease feature information, respectively. Then, the matrix decomposition algorithm is employed to predict the potential lncRNA-disease associations. In addition, to overcome the limitation of matrix decomposition, the hybrid model is developed to predict associations between new lncRNA (or disease) and diseases (or lncRNA). The ten-fold cross validation and de novo test are applied to evaluate the performance of method. The experimental results show LDICDL outperforms than other state-of-the-art methods in prediction performance.

Fully connected autoencoder and convolutional neural network with attention-based method for inferring disease-related lncRNAs

Since abnormal expression of long noncoding RNAs (lncRNAs) is often closely related to various human diseases, identification of disease-associated lncRNAs is helpful for exploring the complex pathogenesis. Most of recent methods concentrate on exploiting multiple kinds of data related to lncRNAs and diseases for predicting candidate disease-related lncRNAs. These methods, however, failed to deeply integrate the topology information from the meta-paths that are composed of lncRNA, disease and microRNA (miRNA) nodes. We proposed a new method based on fully connected autoencoders and convolutional neural networks, called ACLDA, for inferring potential disease-related lncRNA candidates. A heterogeneous graph that consists of lncRNA, disease and miRNA nodes were firstly constructed to integrate similarities, associations and interactions among them. Fully connected autoencoder-based module was established to extract the low-dimensional features of lncRNA, disease and miRNA nodes in the heterogeneous graph. We designed the attention mechanisms at the node feature level and at the meta-path level to learn more informative features and meta-paths. A module based on convolutional neural networks was constructed to encode the local topologies of lncRNA and disease nodes from multiple meta-path perspectives. The comprehensive experimental results demonstrated ACLDA achieves superior performance than several state-of-the-art prediction methods. Case studies on breast, lung and colon cancers demonstrated that ACLDA is able to discover the potential disease-related lncRNAs.

Feature Selection of OMIC Data by Ensemble Swarm Intelligence Based Approaches

OMIC datasets have high dimensions, and the connection among OMIC features is very complicated. It is difficult to establish linkages among these features and certain biological traits of significance. The proposed ensemble swarm intelligence-based approaches can identify key biomarkers and reduce feature dimension efficiently. It is an end-to-end method that only relies on the rules of the algorithm itself, without presets such as the number of filtering features. Additionally, this method achieves good classification accuracy without excessive consumption of computing resources.