Smialowski Pawel, Martin-Galiano Antonio J, Mikolajka Aleksandra, Girschick Tobias, Holak Tad A, Frishman Dmitrij
Department of Genome Oriented Bioinformatics, Technische Universität München, Wissenschaftszentrum Weihenstephan, 85350 Freising, Germany.
Bioinformatics. 2007 Oct 1;23(19):2536-42. doi: 10.1093/bioinformatics/btl623. Epub 2006 Dec 6.
Obtaining soluble proteins in sufficient concentrations is a recurring limiting factor in various experimental studies. Solubility is an individual trait of proteins which, under a given set of experimental conditions, is determined by their amino acid sequence. Accurate theoretical prediction of solubility from sequence is instrumental for setting priorities on targets in large-scale proteomics projects.
We present a machine-learning approach called PROSO to assess the chance of a protein to be soluble upon heterologous expression in Escherichia coli based on its amino acid composition. The classification algorithm is organized as a two-layered structure in which the output of primary support vector machine (SVM) classifiers serves as input for a secondary Naive Bayes classifier. Experimental progress information from the TargetDB database as well as previously published datasets were used as the source of training data. In comparison with previously published methods our classification algorithm possesses improved discriminatory capacity characterized by the Matthews Correlation Coefficient (MCC) of 0.434 between predicted and known solubility states and the overall prediction accuracy of 72% (75 and 68% for positive and negative class, respectively). We also provide experimental verification of our predictions using solubility measurements for 31 mutational variants of two different proteins.
在各种实验研究中，获得足够浓度的可溶性蛋白质一直是一个反复出现的限制因素。溶解度是蛋白质的个体特性，在给定的一组实验条件下，由其氨基酸序列决定。从序列准确理论预测溶解度有助于在大规模蛋白质组学项目中确定目标的优先级。
我们提出了一种名为PROSO的机器学习方法，用于根据蛋白质的氨基酸组成评估其在大肠杆菌中异源表达时可溶的可能性。分类算法被组织成两层结构，其中初级支持向量机（SVM）分类器的输出作为二级朴素贝叶斯分类器的输入。来自TargetDB数据库的实验进展信息以及先前发表的数据集被用作训练数据的来源。与先前发表的方法相比，我们的分类算法具有更高的判别能力，预测和已知溶解度状态之间的马修斯相关系数（MCC）为0.434，总体预测准确率为72%（阳性和阴性类别分别为75%和68%）。我们还使用两种不同蛋白质的31个突变变体的溶解度测量对我们的预测进行了实验验证。
