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. Long non-coding RNAs (lncRNAs) refer to non-coding RNAs with lengths exceeding 200 nucleotides, and they play pivotal roles in various diseases, including cancer, cardiovascular, and neurological disorders. However, accurately predicting their associations with diseases presents a formidable challenge, particularly given the limitations of existing methods in handling complex and diverse data as well as sparse information. To address these issues, we introduce a novel computational approach known as HGC-GAN. This method combines the robust capabilities of heterogeneous graph convolutional neural networks (GCN) and generative adversarial networks (GAN) to predict potential associations between lncRNAs and diseases. Leveraging rich biological information, it overcomes challenges related to data scarcity and the absence of negative samples. Our empirical results demonstrate that HGC-GAN outperforms existing models and achieves impressive results in predicting the associations between lncRNAs and diseases under rigorous cross-validation. Notably, HGC-GAN has proven its reliability across datasets of varying scales. Furthermore, our case studies illustrate its ability to predict associations of novel lncRNAs with diseases that have no known links. We believe that HGC-GAN holds great promise in advancing disease diagnosis, treatment, and drug development.