计算机科学
核糖核酸
疾病
图形
非编码RNA
人工智能
逻辑回归
计算生物学
机器学习
数据挖掘
理论计算机科学
生物
医学
遗传学
基因
病理
作者
Julong Li,Jianrui Chen,Zhihui Wang,Xiujuan Lei
标识
DOI:10.1016/j.artmed.2024.102775
摘要
CircRNA and miRNA are crucial non-coding RNAs, which are associated with biological diseases. Exploring the associations between RNAs and diseases often requires a significant time and financial investments, which has been greatly alleviated and improved with the application of deep learning methods in bioinformatics. However, existing methods often fail to achieve higher accuracy and cannot be universal between multiple RNAs. Moreover, complex RNA–disease associations hide important higher-order topology information. To address these issues, we learn higher-order structure information for predicting RNA–disease associations (HoRDA). Firstly, the correlations between RNAs and the correlations between diseases are fully explored by combining similarity and higher-order graph attention network. Then, a higher-order graph convolutional network is constructed to aggregate neighbor information, and further obtain the representations of RNAs and diseases. Meanwhile, due to the large number of complex and variable higher-order structures in biological networks, we design a higher-order negative sampling strategy to gain more desirable negative samples. Finally, the obtained embeddings of RNAs and diseases are feed into logistic regression model to acquire the probabilities of RNA–disease associations. Diverse simulation results demonstrate the superiority of the proposed method. In the end, the case study is conducted on breast neoplasms, colorectal neoplasms, and gastric neoplasms. We validate the proposed higher-order strategies through ablative and exploratory analyses and further demonstrate the practical applicability of HoRDA. HoRDA has a certain contribution in RNA–disease association prediction.
科研通智能强力驱动
Strongly Powered by AbleSci AI