MBSTAR: multiple instance learning for predicting specific functional binding sites in microRNA targets.
MBSTAR: multiple instance learning for predicting specific functional binding sites in microRNA targets.
复制标题
DOI：
10.1038/srep08004
复制
发表时间：
2015-01-23
影响因子：
4.6
通讯作者：
Zhao Z
中科院分区：
文献类型：
--
作者：
Bandyopadhyay S;Ghosh D;Mitra R;Zhao Z
MicroRNA (miRNA) 通过与其靶基因 3'非翻译区的特定位点结合来调节基因表达。基于机器学习的 miRNA 目标预测算法首先从 mRNA 中的潜在结合位点 (PBS) 中提取一组特征，然后训练分类器来区分目标和非目标。然而，他们没有考虑 PBS 是否具有功能，因此导致较高的假阳性率。这极大地影响了后续的功能验证实验。我们提出了一种基于机器学习的新颖方法，MBSTAR（miRNA 目标结合位点的多实例学习），用于准确预测真实或功能性 miRNA 结合位点。采用多实例学习框架来解决目标 mRNA 中实际结合位点信息的缺乏。从 Tarbase 6.0 中鉴定出经过生物学验证的 9531 个相互作用和 973 个非相互作用 miRNA-mRNA 对，并通过 PAR-CLIP 数据集进行了确认。结果发现，MBSTAR 与 PAR-CLIP 的结合位点重叠数量最多，最大 F 分数为 0.337。与其他方法相比，MBSTAR 还能以最高的准确度预测目标 mRNA。该工具和全基因组预测可在 http://www.isical.ac.in/~bioinfo_miu/MBStar30.htm 上获得。
MicroRNA (miRNA) regulates gene expression by binding to specific sites in the 3′untranslated regions of its target genes. Machine learning based miRNA target prediction algorithms first extract a set of features from potential binding sites (PBSs) in the mRNA and then train a classifier to distinguish targets from non-targets. However, they do not consider whether the PBSs are functional or not, and consequently result in high false positive rates. This substantially affects the follow up functional validation by experiments. We present a novel machine learning based approach, MBSTAR (Multiple instance learning of Binding Sites of miRNA TARgets), for accurate prediction of true or functional miRNA binding sites. Multiple instance learning framework is adopted to handle the lack of information about the actual binding sites in the target mRNAs. Biologically validated 9531 interacting and 973 non-interacting miRNA-mRNA pairs are identified from Tarbase 6.0 and confirmed with PAR-CLIP dataset. It is found that MBSTAR achieves the highest number of binding sites overlapping with PAR-CLIP with maximum F-Score of 0.337. Compared to the other methods, MBSTAR also predicts target mRNAs with highest accuracy. The tool and genome wide predictions are available at http://www.isical.ac.in/~bioinfo_miu/MBStar30.htm.