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.

Hypermethylation-Mediated lncRNA MAGI2-AS3 Downregulation Facilitates Malignant Progression of Laryngeal Squamous Cell Carcinoma via Interacting With SPT6

Long noncoding RNAs (lncRNAs) have an effect on the occurrence and progression of a considerable number of diseases, especially cancer. Existing research has suggested that MAGI2 antisense RNA 3 (MAGI2-AS3) takes on a critical significance in the development of hepatocellular carcinoma and lung cancer. However, the functions of MAGI2-AS3 in laryngeal squamous cell carcinoma (LSCC) remain unclear. In this study, MAGI2-AS3 expression level in LSCC tissue and cell lines was detected, and the effect of MAGI2-AS3 overexpressed on LSCC phenotypes and the possible influence mechanisms were examined. MAGI2-AS3 was downregulated in the tissues of LSCC patients versus non-tumor tissues, and it was correlated with advanced TNM (tumor, node, metastasis) stage and lymph node metastases, as indicated by the results of this study. MAGI2-AS3 inhibited the proliferation, migration, and invasion of LSCC cells in vitro and in vivo. Furthermore, the hypermethylation level of the MAGI2-AS3 promoter region was indicated by bisulfite genomic sequencing and methylation-specific polymerase chain reaction, such that MAGI2-AS3 expression was downregulated. Besides, MAGI2-AS3 promoter hypermethylation was regulated by DNA methyltransferase 1 (DNMT1), and MAGI2-AS3 expression was reversed by 5-Aza-2'-deoxycytidine (5-Aza). Moreover, the result of the RNA pull-down experiment suggested that 38 proteins were enriched in the MAGI2-AS3 group versus the control group in TU177 cells. To be specific, SPT6 (ie, a conserved protein) was enriched by fold change >10. SPT6 knockdown reduced the antitumor effect of MAGI2-AS3 in TU177 and AMC-HN-8 cells. Meanwhile, SPT6 overexpression inhibited the proliferation, metastasis, and invasion of TU177 and AMC-HN-8 cells. As revealed by the above findings, DNMT1-regulated MAGI2-AS3 promoter hypermethylation led to downregulated MAGI2-AS3 expression, such that the presence and progression of LSCC were inhibited in an SPT6 binding-dependent manner.

HEGANLDA: A Computational Model for Predicting Potential Lncrna-Disease Associations Based On Multiple Heterogeneous Networks

Long non-coding RNAs (lncRNAs) play vital regulatory roles in many human complex diseases, however, the number of validated lncRNA-disease associations is notable rare so far. How to predict potential lncRNA-disease associations precisely through computational methods remains challenging. In this study, we proposed a novel method, LDVCHN (LncRNA-Disease Vector Calculation Heterogeneous Networks), and also developed the corresponding model, HEGANLDA (Heterogeneous Embedding Generative Adversarial Networks LncRNA-Disease Association), for predicting potential lncRNA-disease associations. In HEGANLDA, the graph embedding algorithm (HeGAN) was introduced for mapping all nodes in the lncRNA-miRNA-disease heterogeneous network into the low-dimensional vectors which severed as the inputs of LDVCHN. HEGANLDA effectively adopted the XGBoost (eXtreme Gradient Boosting) classifier, which was trained by the low-dimensional vectors, to predict potential lncRNA-disease associations. The 10-fold cross-validation method was utilized to evaluate the performance of our model, our model finally achieved an area under the ROC curve of 0.983. According to the experiment results, HEGANLDA outperformed any one of five current state-of-the-art methods. To further evaluate the effectiveness of HEGANLDA in predicting potential lncRNA-disease associations, both case studies and robustness tests were performed and the results confirmed its effectiveness and robustness. The source code and data of HEGANLDA are available at https://github.com/HEGANLDA/HEGANLDA.

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.

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

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

NCP-BiRW: A Hybrid Approach for Predicting Long Noncoding RNA-Disease Associations by Network Consistency Projection and Bi-Random Walk

Long non-coding RNAs (lncRNAs) play significant roles in the disease process. Understanding the pathological mechanisms of lncRNAs during the course of various diseases will help clinicians prevent and treat diseases. With the emergence of high-throughput techniques, many biological experiments have been developed to study lncRNA-disease associations. Because experimental methods are costly, slow, and laborious, a growing number of computational models have emerged. Here, we present a new approach using network consistency projection and bi-random walk (NCP-BiRW) to infer hidden lncRNA-disease associations. First, integrated similarity networks for lncRNAs and diseases were constructed by merging similarity information. Subsequently, network consistency projection was applied to calculate space projection scores for lncRNAs and diseases, which were then introduced into a bi-random walk method for association prediction. To test model performance, we employed 5- and 10-fold cross-validation, with the area under the receiver operating characteristic curve as the evaluation indicator. The computational results showed that our method outperformed the other five advanced algorithms. In addition, the novel method was applied to another dataset in the Mammalian ncRNA-Disease Repository (MNDR) database and showed excellent performance. Finally, case studies were carried out on atherosclerosis and leukemia to confirm the effectiveness of our method in practice. In conclusion, we could infer lncRNA-disease associations using the NCP-BiRW model, which may benefit biomedical studies in the future.

Prediction of lncRNA-Disease Associations via Closest Node Weight Graphs of the Spatial Neighborhood Based on the Edge Attention Graph Convolutional Network

Accumulated evidence of biological clinical trials has shown that long non-coding RNAs (lncRNAs) are closely related to the occurrence and development of various complex human diseases. Research works on lncRNA–disease relations will benefit to further understand the pathogenesis of human complex diseases at the molecular level, but only a small proportion of lncRNA–disease associations has been confirmed. Considering the high cost of biological experiments, exploring potential lncRNA–disease associations with computational approaches has become very urgent. In this study, a model based on closest node weight graph of the spatial neighborhood (CNWGSN) and edge attention graph convolutional network (EAGCN), LDA-EAGCN, was developed to uncover potential lncRNA–disease associations by integrating disease semantic similarity, lncRNA functional similarity, and known lncRNA–disease associations. Inspired by the great success of the EAGCN method on the chemical molecule property recognition problem, the prediction of lncRNA–disease associations could be regarded as a component recognition problem of lncRNA–disease characteristic graphs. The CNWGSN features of lncRNA–disease associations combined with known lncRNA–disease associations were introduced to train EAGCN, and correlation scores of input data were predicted with EAGCN for judging whether the input lncRNAs would be associated with the input diseases. LDA-EAGCN achieved a reliable AUC value of 0.9853 in the ten-fold cross-over experiments, which was the highest among five state-of-the-art models. Furthermore, case studies of renal cancer, laryngeal carcinoma, and liver cancer were implemented, and most of the top-ranking lncRNA–disease associations have been proven by recently published experimental literature works. It can be seen that LDA-EAGCN is an effective model for predicting potential lncRNA–disease associations. Its source code and experimental data are available at https://github.com/HGDKMF/LDA-EAGCN.

SVDNVLDA: predicting lncRNA-disease associations by Singular Value Decomposition and node2vec

Background

Numerous studies on discovering the roles of long non-coding RNAs (lncRNAs) in the occurrence, development and prognosis progresses of various human diseases have drawn substantial attentions. Since only a tiny portion of lncRNA-disease associations have been properly annotated, an increasing number of computational methods have been proposed for predicting potential lncRNA-disease associations. However, traditional predicting models lack the ability to precisely extract features of biomolecules, it is urgent to find a model which can identify potential lncRNA-disease associations with both efficiency and accuracy.

Results

In this study, we proposed a novel model, SVDNVLDA, which gained the linear and non-linear features of lncRNAs and diseases with Singular Value Decomposition (SVD) and node2vec methods respectively. The integrated features were constructed from connecting the linear and non-linear features of each entity, which could effectively enhance the semantics contained in ultimate representations. And an XGBoost classifier was employed for identifying potential lncRNA-disease associations eventually.

Conclusions

We propose a novel model to predict lncRNA-disease associations. This model is expected to identify potential relationships between lncRNAs and diseases and further explore the disease mechanisms at the lncRNA molecular level.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12859-021-04457-1.

lncRNA-disease association prediction based on latent factor model and projection

Computer aided research of lncRNA-disease association is an important way to study the development of lncRNA-disease. The correlation analysis of existing data, the establishment of prediction model, prediction of unknown lncRNA-disease association, can make the biological experiment targeted, improve the accuracy of biological experiment. In this paper, a lncRNA-disease association prediction model based on latent factor model and projection is proposed (LFMP). This method uses lncRNA-miRNA association data and miRNA-disease association data to predict the unknown lncRNA-disease association, so this method does not need lncRNA-disease association data. The simulation results show that under the LOOCV framework, the AUC of LFMP can reach 0.8964. Better than the latest results. Through the case study of lung and colorectal tumors, LFMP can effectively infer the undetected lncRNA-disease association.

MLCDForest: multi-label classification with deep forest in disease prediction for long non-coding RNAs

The long non-coding RNAs (lncRNAs) are subject of intensive recent studies due to its association with various human diseases. It is desirable to build the artificial intelligence-based models for prediction of diseases or tissues based on the lncRNAs data, which will be useful in disease diagnosis and therapy. The accuracy and robustness of existing models based on the machine learning techniques are subject to further improvement. In this study, we propose a deep learning model, called Multi-Label Classifications with Deep Forest, termed MLCDForest, to address multi-label classification on tissue prediction for a given lncRNA, which can be regarded as an implementation of the deep forest model in multi-label classification. The MLCDForest is a sequential multi-label-grained scanning method, which distinguishes from the standard deep forest model. It is proposed to train in sequential of multi-labels with label correlation considered. A systematic comparison using the lncRNA-disease association datasets demonstrates that our method consistently shows superior performance over the state-of-the-art methods in disease prediction. Considering label correlation in the sequential multi-label-grained scanning, our model provides a powerful tool to make multi-label classification and tissue prediction based on given lncRNAs.

Probing lncRNA-Protein Interactions: Data Repositories, Models, and Algorithms

Identifying lncRNA-protein interactions (LPIs) is vital to understanding various key biological processes. Wet experiments found a few LPIs, but experimental methods are costly and time-consuming. Therefore, computational methods are increasingly exploited to capture LPI candidates. We introduced relevant data repositories, focused on two types of LPI prediction models: network-based methods and machine learning-based methods. Machine learning-based methods contain matrix factorization-based techniques and ensemble learning-based techniques. To detect the performance of computational methods, we compared parts of LPI prediction models on Leave-One-Out cross-validation (LOOCV) and fivefold cross-validation. The results show that SFPEL-LPI obtained the best performance of AUC. Although computational models have efficiently unraveled some LPI candidates, there are many limitations involved. We discussed future directions to further boost LPI predictive performance.