School of Computer Science, Guangdong University of Technology, Guangzhou, China.
Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China.
Mol Genet Genomics. 2019 Dec;294(6):1477-1486. doi: 10.1007/s00438-019-01590-8. Epub 2019 Jun 28.
Long noncoding RNAs play a significant role in the occurrence of diseases. Thus, studying the relationship prediction between lncRNAs and disease is becoming more popular. Researchers hope to determine effective treatments by revealing the occurrence and development of diseases at the molecular level. However, the traditional biological experimental way to verify the association between lncRNAs and disease is very time-consuming and expensive. Therefore, we developed a method called LLCLPLDA to predict potential lncRNA-disease associations. First, locality-constrained linear coding (LLC) is leveraged to project the features of lncRNAs and diseases to local-constraint features, and then, a label propagation (LP) strategy is used to mix up the initial association matrix and the obtained features of lncRNAs and diseases. To demonstrate the performance of our method, we compared LLCLPLDA with five methods in the leave-one-out cross-validation and fivefold cross-validation scheme, and the experimental results show that the proposed method outperforms the other five methods. Additionally, we conducted case studies on three diseases: cervical cancer, gliomas, and breast cancer. The top five predicted lncRNAs for cervical cancer and gliomas were verified, and four of the five lncRNAs for breast cancer were also confirmed.
长链非编码 RNA 在疾病的发生中起着重要作用。因此，研究 lncRNA 与疾病之间的关系预测变得越来越流行。研究人员希望通过揭示疾病在分子水平上的发生和发展来确定有效的治疗方法。然而，传统的生物实验方法验证 lncRNA 与疾病之间的关联非常耗时且昂贵。因此，我们开发了一种名为 LLCLPLDA 的方法来预测潜在的 lncRNA-疾病关联。首先，利用局部约束线性编码 (LLC) 将 lncRNA 和疾病的特征映射到局部约束特征，然后使用标签传播 (LP) 策略来混合初始关联矩阵和获得的 lncRNA 和疾病特征。为了证明我们方法的性能，我们在留一交叉验证和五重交叉验证方案中比较了 LLCLPLDA 与五种方法，实验结果表明，所提出的方法优于其他五种方法。此外，我们对三种疾病（宫颈癌、神经胶质瘤和乳腺癌）进行了案例研究。验证了宫颈癌和神经胶质瘤的前五个预测 lncRNA，并且乳腺癌的五个 lncRNA 中有四个也得到了证实。
