A computational model to identify fertility-related proteins using sequence information

Fertility is the most crucial step in the development process,which is controlled by many fertility-related proteins,including spermatogenesis-,oogenesis-and embryogenesis-related proteins.The identification of fertility-related proteins can provide important clues for studying the role of these proteins in development.Therefore,in this study,we constructed a two-layer classifier to identify fertility-related proteins.In this classifier,we first used the composition of amino acids(AA)and their physical and chemical properties to code these three fertility-related proteins.Then,the feature set is optimized by analysis of variance(ANOVA)and incremental feature selection(IFS)to obtain the optimal feature subset.Through five-fold cross-validation(CV)and independent data tests,the performance of models constructed by different machine learning(ML)methods is evaluated and compared.Finally,based on support vector machine(SVM),we obtained a two-layer model to classify three fertility-related proteins.On the independent test data set,the accuracy(ACC)and the area under the receiver operating characteristic curve(AUC)of the first layer classifier are 81.95%and 0.89,respectively,and them of the second layer classifier are 84.74%and 0.90,respectively.These results show that the proposed model has stable performance and satisfactory prediction accuracy,and can become a powerful model to identify more fertility related proteins.