1. Applying negative sample denoising and multi-view feature for lncRNA-disease association prediction.
- Author
-
Dengju Yao, Bo Zhang, Xiangkui Li, Xiaojuan Zhan, Xiaorong Zhan, and Binbin Zhang
- Subjects
LINCRNA ,INDIVIDUALIZED medicine ,FEATURE extraction - Abstract
Increasing evidence indicates that mutations and dysregulation of long noncoding RNA (lncRNA) play a crucial role in the pathogenesis and prognosis of complex human diseases. Computational methods for predicting the association between lncRNAs and diseases have gained increasing attention. However, these methods face two key challenges: obtaining reliable negative samples and incorporating lncRNA-disease association (LDA) information from multiple perspectives. This paper proposes a method called NDMLDA, which combines multi-view feature extraction, unsupervised negative sample denoising, and stacking ensemble classifier. Firstly, an unsupervised method (K-means) is used to design a negative sample denoising module to alleviate the imbalance of samples and the impact of potential noise in the negative samples on model performance. Secondly, graph attention networks are employed to extract multiview features of both lncRNAs and diseases, thereby enhancing the learning of association information between them. Finally, lncRNA-disease association prediction is implemented through a stacking ensemble classifier. Existing research datasets are integrated to evaluate performance, and 5-fold crossvalidation is conducted on this dataset. Experimental results demonstrate that NDMLDA achieves an AUC of 0.9907and an AUPR of 0.9927, with a 5-fold crossvalidation variance of less than 0.1%. These results outperform the baseline methods. Additionally, case studies further illustrate the model's potential in cancer diagnosis and precision medicine implementation. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF