Khan Asad, Shah Sajid, Wahid Fazli, Khan Fiaz Gul, Jabeen Saima
Department of Computer Science COMSATS Institute of IT, Abbottabad 22060, Pakistan.
Department of Environmental Sciences COMSATS Institute of IT, Abbottabad 22060, Pakistan.
Mol Biosyst. 2017 Jul 25;13(8):1640-1645. doi: 10.1039/c7mb00115k.
MicroRNAs (also called miRNAs) are a group of short non-coding RNA molecules. They play a vital role in the gene expression of transcriptional and post-transcriptional processes. However, abnormality of their expression has been observed in cancer, heart diseases and nervous system disorders. Therefore for basic research and microRNA based therapy, it is imperative to separate real pre-miRNAs from false ones (hairpin sequences similar to pre-miRNA stem loops). Different conservation and machine learning methods have been applied for the identification of miRNAs. However, machine learning algorithms have gained more popularity than conservative based algorithms in terms of sensitivity and overall performance. Due to the avalanche of RNA sequences discovered in a post-genomic age, it is necessary to construct a predictor for the identification of pre-microRNAs in humans. We have developed a predictor called MicroR-Pred in which the RNA sequences are formulated by a hybrid feature vector. The novelty of the new predictor is in the use of the partial least squares technique followed by the Random Forest and SVM (Support Vector Machine) algorithms for dimension reduction and classification. The performance of the MicroR-Pred model is quite promising compared to other state-of-the-art miRNA predictors. It has achieved 88.40% and 93.90% accuracies for RF and SVM.
微小RNA（也称为miRNA）是一类短的非编码RNA分子。它们在转录和转录后过程的基因表达中起着至关重要的作用。然而，在癌症、心脏病和神经系统疾病中已观察到它们表达异常。因此，对于基础研究和基于微小RNA的治疗，将真正的前体微小RNA与假的（类似于前体微小RNA茎环的发夹序列）区分开来势在必行。不同的保守方法和机器学习方法已被应用于微小RNA的鉴定。然而，就敏感性和整体性能而言，机器学习算法比基于保守性的算法更受欢迎。由于在后基因组时代发现了大量的RNA序列，有必要构建一个用于鉴定人类前体微小RNA的预测器。我们开发了一种名为MicroR-Pred的预测器，其中RNA序列由混合特征向量表示。新预测器的新颖之处在于使用偏最小二乘法，随后采用随机森林和支持向量机（SVM）算法进行降维和分类。与其他最先进的miRNA预测器相比，MicroR-Pred模型的性能很有前景。它在随机森林和支持向量机上分别达到了88.40%和93.90%的准确率。
