SPINE X: improving protein secondary structure prediction by multistep learning coupled with prediction of solvent accessible surface area and backbone torsion angles.
SPINE X: improving protein secondary structure prediction by multistep learning coupled with prediction of solvent accessible surface area and backbone torsion angles.
复制标题
DOI：
10.1002/jcc.21968
复制
发表时间：
2012-01-30
影响因子：
3
通讯作者：
Zhou, Yaoqi
中科院分区：
文献类型：
--
作者：
Faraggi, Eshel;Zhang, Tuo;Yang, Yuedong;Kurgan, Lukasz;Zhou, Yaoqi
关键词：
蛋白质二级结构的准确预测对于精确的序列比对、三维结构建模和功能预测至关重要。然而，在过去的十年中，从头算二级构造预测的精度仅从77%左右提高到80%。在这里，我们开发了一种多步神经网络算法，通过迭代的方式将二级结构预测与溶剂可及性和主扭角预测相结合。我们的方法称为SPINE X，应用于先前为第一版SPINE构建的2640个蛋白质数据集（25%序列身份截断），并基于十倍交叉验证（Q3）实现了82.0%的准确性。通过使用独立构建的1833个蛋白质链测试数据集、最近构建的1975个蛋白质数据集和117个CASP 9靶点（结构预测关键评估技术），进一步证实了SPINE X超过81%的准确性，其准确性分别为81.3%、82.3%和81.8%。对于2640个蛋白质的数据集，如果用更一致的共识二级结构分配方法取代上述的DSSP分配方法，预测精度进一步提高到83.8%。并与流行的PSIPRED和CASP-winning结构预测技术进行了比较。在1833种蛋白质中，SPINE X预测螺旋和薄片数量的准确率为21.0%，而PSIPRED为17.6%。进一步表明，SPINE X对螺旋残基的预测更准确（6%），没有过度预测，而PSIPRED对螺旋残基的预测更准确（3-5%），超过预测7%。SPINE X服务器及其训练/测试数据集可在http://sparks.informatics.iupui.edu/上获得
Accurate prediction of protein secondary structure is essential for accurate sequence alignment, three-dimensional structure modeling, and function prediction. The accuracy of ab initio secondary structure prediction from sequence, however, has only increased from around 77% to 80% over the past decade. Here, we developed a multi-step neural-network algorithm by coupling secondary structure prediction with prediction of solvent accessibility and backbone torsion angles in an iterative manner. Our method called SPINE X was applied to a dataset of 2640 proteins (25% sequence identity cutoff) previously built for the first version of SPINE and achieved a 82.0% accuracy based on ten-fold cross validation (Q3). Surpassing 81% accuracy by SPINE X is further confirmed by employing an independently built test dataset of 1833 protein chains, a recently built dataset of 1975 proteins and 117 CASP 9 targets (Critical Assessment of Structure Prediction techniques) with an accuracy of 81.3%, 82.3% and 81.8%, respectively. The prediction accuracy is further improved to 83.8% for the dataset of 2640 proteins if the DSSP assignment employed above is replaced by a more consistent consensus secondary structure assignment method. Comparison to the popular PSIPRED and CASP-winning structure-prediction techniques is made. SPINE X predicts number of helices and sheets correctly for 21.0% of 1833 proteins, compared to 17.6% by PSIPRED. It further shows that SPINE X consistently makes more accurate prediction in helical residues (6%) without over prediction while PSIPRED makes more accurate prediction in coil residues (3–5%) and over predicts them by 7%. SPINE X Server and its training/test datasets are available at http://sparks.informatics.iupui.edu/
登录
查看更多内容
影响因子：
14.9
作者：
Cole C;Barber JD;Barton GJ
通讯作者：
Barton GJ
影响因子：
5.8
作者：
Pollastri, G;McLysaght, A
通讯作者：
McLysaght, A
分析用于二级结构预测的最佳隐藏马尔可夫模型。
影响因子：
--
作者：
Martin, Juliette;Gibrat, Jean-Francois;Rodolphe, Francois
通讯作者：
Rodolphe, Francois
影响因子：
2.9
作者：
Dor, Ofer;Zhou, Yaoqi
通讯作者：
Zhou, Yaoqi
影响因子：
2.9
作者：
Bondugula, Rajkumar;Xu, Dong
通讯作者：
Xu, Dong