UbiSitePred: A novel method for improving the accuracy of ubiquitination sites prediction by using LASSO to select the optimal Chou's pseudo components

摘要: Abstract Ubiquitination is an essential process in protein post-translational modification, which plays a crucial role cell life activities, such as proteasomal degradation, transcriptional regulation, and DNA damage repair. Therefore, recognition of ubiquitination sites step to understand the molecular mechanisms ubiquitination. However, experimental verification numerous time-consuming costly. To alleviate these issues, computational approach needed predict sites. This paper proposes new method called UbiSitePred for predicting combined least absolute shrinkage selection operator (LASSO) feature support vector machine. First, we use binary encoding (BE), pseudo-amino acid composition (PseAAC), k-spaced amino pairs (CKSAAP), position-specific propensity matrices (PSPM) extract sequence information; thus, initial space obtained. Secondly, LASSO applied remove redundancy information selects optimal subset. Finally, subset input into machine (SVM) Five-fold cross-validation shows that model can achieve better prediction performance compared with other methods, AUC values Set1, Set2, Set3 are 0.9998, 0.8887, 0.8481, respectively. Notably, has overall accuracy rates 98.33%, 81.12%, 76.90%, The results demonstrate proposed significantly superior state-of-the-art methods provide idea modification proteins. source code all datasets available at https://github.com/QUST-AIBBDRC/UbiSitePred/ .