Department of Biomedical Informatics, Ministry of Education Key Lab of Cardiovascular Sciences, School of Basic Medical Sciences, Peking University, Beijing 100191, China.
Int J Mol Sci. 2021 Dec 19;22(24):13607. doi: 10.3390/ijms222413607.
MicroRNAs (miRNAs) are associated with various complex human diseases and some miRNAs can be directly involved in the mechanisms of disease. Identifying disease-causative miRNAs can provide novel insight in disease pathogenesis from a miRNA perspective and facilitate disease treatment. To date, various computational models have been developed to predict general miRNA-disease associations, but few models are available to further prioritize causal miRNA-disease associations from non-causal associations. Therefore, in this study, we constructed a Levenshtein-Distance-Enhanced miRNA-disease Causal Association Predictor (LE-MDCAP), to predict potential causal miRNA-disease associations. Specifically, Levenshtein distance matrixes covering the sequence, expression and functional miRNA similarities were introduced to enhance the previous Gaussian interaction profile kernel-based similarity matrix. LE-MDCAP integrated miRNA similarity matrices, disease semantic similarity matrix and known causal miRNA-disease associations to make predictions. For regular causal vs. non-disease association discrimination task, LF-MDCAP achieved area under the receiver operating characteristic curve (AUROC) of 0.911 and 0.906 in 10-fold cross-validation and independent test, respectively. More importantly, LE-MDCAP prominently outperformed the previous MDCAP model in distinguishing causal versus non-causal miRNA-disease associations (AUROC 0.820 vs. 0.695). Case studies performed on diabetic retinopathy and hsa-mir-361 also validated the accuracy of our model. In summary, LE-MDCAP could be useful for screening causal miRNA-disease associations from general miRNA-disease associations.
微小 RNA（miRNA）与各种复杂的人类疾病有关，一些 miRNA 可以直接参与疾病的机制。鉴定疾病因果 miRNA 可以从 miRNA 的角度提供疾病发病机制的新见解，并促进疾病的治疗。迄今为止，已经开发了各种计算模型来预测一般的 miRNA-疾病关联，但很少有模型可用于进一步从非因果关联中优先考虑因果 miRNA-疾病关联。因此，在这项研究中，我们构建了一个基于 Levenshtein 距离增强的 miRNA-疾病因果关联预测器（LE-MDCAP），用于预测潜在的因果 miRNA-疾病关联。具体来说，引入了涵盖序列、表达和功能 miRNA 相似性的 Levenshtein 距离矩阵，以增强先前基于高斯相互作用轮廓核的相似性矩阵。LE-MDCAP 整合了 miRNA 相似性矩阵、疾病语义相似性矩阵和已知的因果 miRNA-疾病关联来进行预测。对于常规的因果 vs. 非疾病关联判别任务，LF-MDCAP 在 10 折交叉验证和独立测试中的 AUROC 分别为 0.911 和 0.906。更重要的是，LE-MDCAP 在区分因果与非因果 miRNA-疾病关联方面明显优于先前的 MDCAP 模型（AUROC 0.820 与 0.695）。在糖尿病视网膜病变和 hsa-mir-361 上进行的案例研究也验证了我们模型的准确性。总之，LE-MDCAP 可用于从一般 miRNA-疾病关联中筛选因果 miRNA-疾病关联。
