A novel model to predict O-glycosylation sites using a highly unbalanced dataset
A novel model to predict O-glycosylation sites using a highly unbalanced dataset
复制标题
一种使用高度不平衡数据集预测 O-糖基化位点的新模型
DOI：
10.1007/s10719-012-9434-x
复制
发表时间：
2012-08
影响因子：
3
通讯作者：
Yang, Ling
中科院分区：
文献类型：
--
作者：
Zhou, Kun;Ai, Chunzhi;Dong, Peipei;Fan, Xuran;Yang, Ling
在硅胶中，方法已经成为研究O-糖基化的一种替代方法。在这篇文章中，我们开发了一个基于非平衡数据集的线性可解释的O-糖基化预测模型，分析了糖基化的潜在生物学知识。在这项研究中，开发了4446个点的训练集，包括468个阳性点和3978个阴性点。用氨基酸指数(AAindex)对这些位点进行编码，并采用正向逐步过程进行特征选择。采用等优先概率线性判别分析(PP-LDA)建立可解释模型。采用内部留一法交叉验证和外部验证两种方法对模型的性能进行验证。比较了有监督支持向量机和无监督自组织竞争神经网络两种非线性算法。PP-LDA模型具有更好的分类结果，交叉验证的准确率为82.1%，外部预测的准确率为80.3%。对这个线性模型的进一步分析表明，R1位的性质和与疏水性相关的性质对糖基化预测有更大的贡献。然而，C-末端的α和转折倾向以及N-末端的物理化学性质也与糖基化活性有关。该模型不仅能够利用不平衡的数据集预测糖基化的可能性，而且有助于理解糖基化的潜在生物学机制。考虑到我们的预测模型是公开可访问的，我们在提供的材料中提供了一个可下载的程序。
In silicoapproaches have become an alternative method to study O-glycosylation. In this paper, we developed a linear interpretable model for O-glycosylation prediction based on an unbalanced dataset, analyzing the underlying biological knowledge of glycosylation. A training set of 4446 sites involving 468 positive sites and 3978 negative sites was developed during this research. The sites were encoded using the amino acid index (AAindex), and the forward stepwise procedure utilized for feature selection. The linear discriminant analysis with an equala prioriprobability (PP-LDA) was employed to develop the interpretable model. Performance of the model was verified using both the internal leave-one-out cross-validation and external validation methods. Two non-linear algorithms, the supervised support vector machine and the unsupervised self-organizing competitive neural network, were used as comparisons. The PP-LDA model exhibited improved classification results with accuracy of 82.1 % for cross-validations and 80.3 % for external prediction. Further analysis of this linear model indicated that the properties at position R1and the properties relative to hydrophobicity contributed more to the glycosylation prediction. However, the alpha and turn propensities at the C-terminal, together with physicochemical properties at the N-terminal, are also relative to the glycosylation activity. This model is not only capable of predicting the possibility of glycosylation using an unbalanced dataset, but is also helpful to understand the underlying biological mechanisms of glycosylation. Considering the publicly accessibility of our prediction model, a downloadable program is provided in our supply materials.
登录
查看更多内容
DOI：
10.1016/s0021-9258(18)82168-8
发表时间：
1993-05
期刊：
The Journal of biological chemistry
影响因子：
--
作者：
Å. Elhammer;R. Poorman;E. Brown;L. Maggiora;J. G. Hoogerheide;F. Kézdy
通讯作者：
Å. Elhammer;R. Poorman;E. Brown;L. Maggiora;J. G. Hoogerheide;F. Kézdy
DOI：
10.7282/t3-vpfw-sf95
发表时间：
2001-08
期刊：
--
影响因子：
--
作者：
Gary M. Weiss;F. Provost
通讯作者：
Gary M. Weiss;F. Provost
影响因子：
14.9
作者：
Kawashima, S;Ogata, H;Kanehisa, M
通讯作者：
Kanehisa, M
影响因子：
4.1
作者：
WILSON, IBH;GAVEL, Y;VONHEIJNE, G
通讯作者：
VONHEIJNE, G
DOI：
10.1016/j.bbrc.2007.04.097
发表时间：
2007-06-22
影响因子：
3.1
作者：
Liu, Boshu;Li, Sujun;Cai, Yudong
通讯作者：
Cai, Yudong