Improving performance of mammalian microRNA target prediction.
Improving performance of mammalian microRNA target prediction.
复制标题
DOI：
10.1186/1471-2105-11-476
复制
发表时间：
2010-09-22
影响因子：
3
通讯作者：
Huang Y
中科院分区：
文献类型：
--
作者：
Liu H;Yue D;Chen Y;Gao SJ;Huang Y
MicroRNA（miRNAs）是一类单链非编码RNA，通过在蛋白质和/或mRNA水平上沉默基因表达来调控多种细胞过程。miRNA靶点的计算预测对于阐明miRNA的详细功能至关重要。然而，现有算法的预测特异性和灵敏度仍然较差，无法为后续的实验测试产生有意义的、可行的假设。构建更丰富、更可靠的训练数据集，并开发出一种能够合理利用这些数据集的预测算法，将是提高现有预测算法性能的关键。构建了哺乳动物miRNA的综合训练数据集，其阳性靶标来自最新的miRNA靶标库miRecords，其阴性靶标来自20个微阵列数据。提出了一种新的算法SVMicrO，该算法采用两阶段结构，包括一个站点支持向量机（SVM），然后是UTR-SVM。SVMicrO基于21个最佳位点特征和18个最佳UTR特征进行预测，这些特征是通过训练从113个位点和30个UTR特征的综合集合中选出的。SVMicrO性能的综合评估已在训练数据、蛋白质组学数据和免疫沉淀（IP）下拉数据上进行。与一些流行的算法的比较表明，在所有测试的情况下，预测特异性，灵敏度和精度的一致改善。所有相关材料，包括源代码和人类靶点的全基因组预测，都可以在http://compgenomics.utsa.edu/svmicro.html上获得。提出了一种新的基于两阶段SVM的miRNA靶点预测算法SVMicrO。SVMicrO被证明能够实现强大的性能。只要有更好的训练数据，包含额外的验证或高置信度的积极目标和适当选择的消极目标，它就有希望实现持续改进。
MicroRNAs (miRNAs) are single-stranded non-coding RNAs known to regulate a wide range of cellular processes by silencing the gene expression at the protein and/or mRNA levels. Computational prediction of miRNA targets is essential for elucidating the detailed functions of miRNA. However, the prediction specificity and sensitivity of the existing algorithms are still poor to generate meaningful, workable hypotheses for subsequent experimental testing. Constructing a richer and more reliable training data set and developing an algorithm that properly exploits this data set would be the key to improve the performance current prediction algorithms. A comprehensive training data set is constructed for mammalian miRNAs with its positive targets obtained from the most up-to-date miRNA target depository called miRecords and its negative targets derived from 20 microarray data. A new algorithm SVMicrO is developed, which assumes a 2-stage structure including a site support vector machine (SVM) followed by a UTR-SVM. SVMicrO makes prediction based on 21 optimal site features and 18 optimal UTR features, selected by training from a comprehensive collection of 113 site and 30 UTR features. Comprehensive evaluation of SVMicrO performance has been carried out on the training data, proteomics data, and immunoprecipitation (IP) pull-down data. Comparisons with some popular algorithms demonstrate consistent improvements in prediction specificity, sensitivity and precision in all tested cases. All the related materials including source code and genome-wide prediction of human targets are available at http://compgenomics.utsa.edu/svmicro.html. A 2-stage SVM based new miRNA target prediction algorithm called SVMicrO is developed. SVMicrO is shown to be able to achieve robust performance. It holds the promise to achieve continuing improvement whenever better training data that contain additional verified or high confidence positive targets and properly selected negative targets are available.
登录
查看更多内容
影响因子：
3
作者：
Kim SK;Nam JW;Rhee JK;Lee WJ;Zhang BT
通讯作者：
Zhang BT
影响因子：
64.8
作者：
Baek, Daehyun;Villen, Judit;Shin, Chanseok;Camargo, Fernando D.;Gygi, Steven P.;Bartel, David P.
通讯作者：
Bartel, David P.
影响因子：
14.9
作者：
Rusinov, V;Baev, V;Minkov, IN;Tabler, M
通讯作者：
Tabler, M
DOI：
10.1098/rspb.1994.0040
发表时间：
1994-03-22
影响因子：
4.7
作者：
SCHUSTER, P;FONTANA, W;HOFACKER, IL
通讯作者：
HOFACKER, IL
影响因子：
4.5
作者：
Sætrom, O;Snove, O;Saetrom, P
通讯作者：
Saetrom, P