RCMF：一种稳健的协同矩阵分解方法，用于预测 miRNA-疾病关联。
RCMF: a robust collaborative matrix factorization method to predict miRNA-disease associations.
机构信息
School of Information Science and Engineering, Qufu Normal University, Rizhao, 276826, China.
Co-Innovation Center for Information Supply & Assurance Technology, Anhui University, Hefei, 230601, China.
出版信息
BMC Bioinformatics. 2019 Dec 24;20(Suppl 25):686. doi: 10.1186/s12859-019-3260-0.
BACKGROUND
Predicting miRNA-disease associations (MDAs) is time-consuming and expensive. It is imminent to improve the accuracy of prediction results. So it is crucial to develop a novel computing technology to predict new MDAs. Although some existing methods can effectively predict novel MDAs, there are still some shortcomings. Especially when the disease matrix is processed, its sparsity is an important factor affecting the final results.
RESULTS
A robust collaborative matrix factorization (RCMF) is proposed to predict novel MDAs. The L-norm are introduced to our method to achieve the highest AUC value than other advanced methods.
CONCLUSIONS
5-fold cross validation is used to evaluate our method, and simulation experiments are used to predict novel associations on Gold Standard Dataset. Finally, our prediction accuracy is better than other existing advanced methods. Therefore, our approach is effective and feasible in predicting novel MDAs.
背景
预测 miRNA-疾病关联 (MDAs) 既耗时又昂贵。提高预测结果的准确性迫在眉睫。因此，开发一种新的计算技术来预测新的 MDAs 至关重要。尽管一些现有的方法可以有效地预测新的 MDAs，但仍然存在一些缺点。特别是在处理疾病矩阵时，其稀疏性是影响最终结果的一个重要因素。
结果
提出了一种稳健的协同矩阵分解 (RCMF) 来预测新的 MDAs。我们的方法引入了 L-norm，以获得比其他先进方法更高的 AUC 值。
结论
使用 5 倍交叉验证来评估我们的方法，并在 Gold Standard 数据集上进行模拟实验来预测新的关联。最后，我们的预测准确性优于其他现有的先进方法。因此，我们的方法在预测新的 MDAs 方面是有效且可行的。
Zotero 插件