Using Machine Learning to Measure Relatedness Between Genes: A Multi-Features Model
Using Machine Learning to Measure Relatedness Between Genes: A Multi-Features Model
复制标题
使用机器学习来测量基因之间的相关性：多特征模型
DOI：
10.1038/s41598-019-40780-7
复制
发表时间：
2019-03
影响因子：
4.6
通讯作者：
Tian Yuan
中科院分区：
文献类型：
--
作者：
Wang Yan;Yan Sen;Tian Yuan
测量一对基因之间的条件相关性是一项基本技术，仍然是计算生物学中的一个重大挑战。这种相关性可以通过基因表达相似性来评估，但错误发现率很高。同时，其他类型的特征，例如，基于先验知识的相似性，只适用于衡量全球相关性。在本文中，我们提出了一种新的机器学习模型，命名为多特征相关性（MFR），通过将表达相似性与基于先验知识的相似性结合在评估标准中，来准确测量一对基因之间的条件相关性。MFR用于预测从COXPRESdb、KEGG、HPRD和TRRUST数据库中提取的基因-基因相互作用，通过10倍交叉验证和测试验证，并鉴定从GeneFriends和DIP数据库中收集的基因-基因相互作用以进行进一步验证。结果表明，MFR达到了最高的曲线下面积（AUC）值，用于识别开发、测试和DIP数据集中的基因-基因相互作用。具体而言，它获得了1.1%的平均精度提高检测基因对高表达相似性和高先验知识为基础的相似性在所有数据集，相比其他线性模型和共表达分析方法。在癌症基因网络构建和基因功能预测方面，MFR也获得了比其他模型和方法更有生物学意义和更高平均预测精度的结果。MFR模型和相关数据集的网站可从http://bmbl.sdstate.edu/MFR访问。
Measuring conditional relatedness between a pair of genes is a fundamental technique and still a significant challenge in computational biology. Such relatedness can be assessed by gene expression similarities while suffering high false discovery rates. Meanwhile, other types of features, e.g., prior-knowledge based similarities, is only viable for measuring global relatedness. In this paper, we propose a novel machine learning model, named Multi-Features Relatedness (MFR), for accurately measuring conditional relatedness between a pair of genes by incorporating expression similarities with prior-knowledge based similarities in an assessment criterion. MFR is used to predict gene-gene interactions extracted from the COXPRESdb, KEGG, HPRD, and TRRUST databases by the 10-fold cross validation and test verification, and to identify gene-gene interactions collected from the GeneFriends and DIP databases for further verification. The results show that MFR achieves the highest area under curve (AUC) values for identifying gene-gene interactions in the development, test, and DIP datasets. Specifically, it obtains an improvement of 1.1% on average of precision for detecting gene pairs with both high expression similarities and high prior-knowledge based similarities in all datasets, comparing to other linear models and coexpression analysis methods. Regarding cancer gene networks construction and gene function prediction, MFR also obtains the results with more biological significances and higher average prediction accuracy, than other compared models and methods. A website of the MFR model and relevant datasets can be accessed from http://bmbl.sdstate.edu/MFR.
登录
查看更多内容
影响因子：
14.9
作者：
Ritchie ME;Phipson B;Wu D;Hu Y;Law CW;Shi W;Smyth GK
通讯作者：
Smyth GK
影响因子：
8.7
作者：
Du D;Rawat N;Deng Z;Gmitter FG Jr
通讯作者：
Gmitter FG Jr
影响因子：
9.9
作者：
Yang, Lifeng;Moss, Tyler;Mangala, Lingegowda S.;Marini, Juan;Zhao, Hongyun;Wahlig, Stephen;Armaiz-Pena, Guillermo;Jiang, Dahai;Achreja, Abhinav;Win, Julia;Roopaimoole, Rajesha;Rodriguez-Aguayo, Cristian;Mercado-Uribe, Imelda;Lopez-Berestein, Gabriel;Liu, Jinsong;Tsukamoto, Takashi;Sood, Anil K.;Ram, Prahlad T.;Nagrath, Deepak
通讯作者：
Nagrath, Deepak
DOI：
10.7326/0003-4819-97-5-799_2
发表时间：
1982
期刊：
--
影响因子：
--
作者：
R. Fletcher;S. Fletcher;E. Wagner
通讯作者：
R. Fletcher;S. Fletcher;E. Wagner
基因共表达网络揭示了猪肌肉表型差异的关键驱动因素
影响因子：
4.4
作者：
Zhao X;Liu ZY;Liu QX
通讯作者：
Liu QX