基于多层感知机的蛋白质变性温度预测  

Using multi-layer perceptron to predict protein melting temperature

作　　者：丁雪松 黄立群 张步忠[1] 杨洋[1,2] 吕强 Ding Xuesong;Huang Liqun;Zhang Buzhong;Yang Yang;Lyu Qiang(School of Computer Science & Technology,Soochow University,Suzhou Jiangsu 215006,China;Jiangsu Provincial Key Laboratory for Computer Information Processing Technologies,Soochow University,Suzhou Jiangsu 215006,China)

机构地区：[1]苏州大学计算机科学与技术学院,江苏苏州215006 [2]苏州大学江苏省计算机信息处理技术重点实验室,江苏苏州215006

出　　处：《计算机应用研究》2019年第8期2421-2423,共3页Application Research of Computers

基　　金：国家自然科学基金资助项目(61170125,61602332);江苏省高校自然基金资助项目(14KJB520035);NSFC-广东联合基金(第二期)超级计算科学应用研究专项资助和国家超级计算广州中心支持

摘　　要：准确预测蛋白质变性温度在蛋白质工程和药物研制等领域具有重要意义。将全局特征和序列特征作为初始特征向量,利用提出的基于权值的降维算法对初始特征向量进行降维,降维后的特征输入多层感知机模型预测蛋白质变性温度。在盲测数据集上,该方法预测结果与实验测定结果的PCC值由降维前的0.77增加到0.8,RMSE值由降维前的0.17降低到了0.16,蛋白质变性温度预测值的分类准确率与现有方法比较有明显提升。It is significant to predict accurate protein melting temperature in protein engineering and drug design. This paper proposed a novel weight-based dimensionality reduction algorithm, and applied it to obtain the input features of MLP model by using combination with global and sequential features as preliminary features. On blind test sets, the PCC value of predicted and experimental melting temperatures increased from 0.77 to 0.8, and RMSE value decreased from 0.17 to 0.16. The classification accuracy of predicted protein melting temperatures by this algorithm was significantly improved over the up-to-date method.

关 键 词：蛋白质变性温度 多层感知机 回归预测 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]