Prediction of oxidoreductase subfamily classes based on RFE-SND-CC-PSSM and machine learning methods

Abstract

Oxidoreductase is an enzyme that widely exists in organisms. It plays an important role in cellular energy metabolism and biotransformation processes. Oxidoreductases have many subclasses with different functions, creating an important classification task in bioinformatics. In this paper, a dataset of 2640 oxidoreductase sequences was used to perform an analysis and comparison. The idea of dipeptides was introduced to process the Position Specific Score Matrix (PSSM), since each dipeptide consists of two amino acids and each column of PSSM corresponds to the information of one amino acid. Two kinds of dipeptide scores were proposed, the Standardization Normal Distribution PSSM (SND-PSSM) and the Correlation Coefficient PSSM (CC-PSSM). Recursive Feature Elimination (RFE) is used to extract features from the SND-PSSM and CC-PSSM, and the two sets of extracted features are combined to form a new feature matrix, the RFE-SND-CC-PSSM. The results show that, with the proposed method and a kernel-based nonlinear SVM classifier, the accuracy can reach 95.56% by the Jackknife test. Our method greatly improves the accuracy of oxidoreductase subclass prediction. Using this method to predict the categories of the 6 major types of enzymes effectively improves its prediction accuracy to 94.54%, indicating that this method has general applicability to other protein problems. The results show that our method is effective and universally applicable, and might be complementary to the existing methods.

SMOPredT4SE: An Effective Prediction of Bacterial Type IV Secreted Effectors Using SVM Training With SMO

“…where S i (1 ≤ i ≤ L) represents the amino acid residue appearing in the ith position of S, and L is the length of S [44], [45]. The so-called evolutionary profile of S is the PSSM, which has been applied to the prediction of protein sequences in numerous previous studies, achieving good results [28], [29], [46]- [49]. In this study, we performed three iterative searches of the Uniref50 database using PSI-BLAST, setting the e-value to 0.001 to generate the BLO-SUM62 replacement matrix.…”

Predicting antifreeze proteins with weighted generalized dipeptide composition and multi-regression feature selection ensemble

“…With the rapid growth of sequences genomic data, dealing with large amounts of biological sequences data requires fast and accurate automated methods for identification and annotation. Therefore, many research groups are dedicated to the study of biological sequences extraction algorithms, feature selection, and classification algorithms using machine learning and deep learning methods, such as amino acid composition (AAC), pseudo amino acid composition (PseAAC), protein position-specific scoring matrix (PSSM), dipeptide composition (DipC), tripeptide composition (TPC), 20-D condensed feature vectors (CFV), general dipeptide composition (GDipC), Lasso feature selection, neural network (NN), support vector machine (SVM), k-nearest neighbor (KNN), random forest (RF) and decision tree (DT), etc., and successfully applied them to protein structure and functional spectrum classification and prediction [ 6 – 23 ]. Recently Stochastic Gradient Descent (SGD) has been successfully applied to the field of sparse and large-scale machine learning [ 24 , 25 ].…”