Accumulating biological experiments have shown that circRNAs are closely related to the occurrence and development of many complex human diseases. During recent years, the associations of circRNA with disease have caused more and more researchers to pay attention and to analyze their correlation mechanisms. However, experimental methods for determining the associations of circRNA with a particular disease are still expensive, difficult, and time consuming. Moreover, the available databases related to circRNA-disease correlations have only recently been updated, and only a few computational methods are constructed to predict potential circRNA-disease correlations. Taking into account the limitations of experimental studies, we develop a novel computational method, named IBNPKATZ, for predicting potential circRNA-disease associations, which integrates the bipartite network projection algorithm and KATZ measure. This model is based on the known circRNA-disease associations, combining circRNA similarity and disease similarity. Specifically, the circRNA similarity is derived from the average of the semantic similarity and the Gaussian interaction profile (GIP) kernel similarity of circRNA. Similarly, disease similarity is the mean of the semantic similarity and the GIP kernel similarity of disease. Furthermore, it is semi-supervised and does not require negative samples. Finally, IBNPKATZ achieves reliable AUC of 0.9352 in the leave-one-out cross validation, and case studies show that the circRNA-disease correlations predicted by our method can be successfully demonstrated by relevant experiments. The IBNPKATZ is expected to be a useful biomedical research tool for predicting potential circRNA-disease associations.

中文翻译：

---

整合双向网络投影和KATZ措施以识别新型CircRNA-疾病关联。

越来越多的生物学实验表明，circRNA与许多复杂的人类疾病的发生和发展密切相关。近年来，circRNA与疾病的关联引起越来越多的研究者关注并分析其相关机制。但是，用于确定circRNA与特定疾病关联的实验方法仍然昂贵，困难且耗时。此外，与circRNA疾病相关的可用数据库只是最近才更新，并且仅构建了几种计算方法来预测潜在的circRNA疾病相关。考虑到实验研究的局限性，我们开发了一种新的计算方法，称为IBNPKATZ，用于预测潜在的circRNA-疾病关联，结合了双向网络投影算法和KATZ测度。该模型基于已知的circRNA-疾病关联，并结合了circRNA相似性和疾病相似性。具体而言，circRNA相似度是从circRNA的语义相似度和高斯交互作用轮廓（GIP）内核相似度的平均值得出的。同样，疾病相似性是疾病的语义相似性和GIP内核相似性的均值。此外，它是半监督的，不需要负样本。最后，IBNPKATZ在留一法交叉验证中获得了0.9352的可靠AUC，案例研究表明，通过相关实验可以成功证明我们方法预测的circRNA-疾病相关性。