A Novel Method for Protein Subcellular Localization: Combining Residue-Couple Model and SVM

Abstract

Subcellular localization performs an important role in genome analysis as a key functional characteristic of proteins. Therefore, an automatic, reliable and efficient prediction system for protein subcellular localization is needed for large-scale genome analysis. This paper describes a new residue-couple model using a support vector machine to predict the subcellular localization of proteins. This new approach provides better predictions than existing methods. The total prediction accuracies on Reinhardt and Hubbard's dataset reach 92.0% for prokaryotic protein sequences and 86.9% for eukaryotic protein sequences with 5-fold cross validation. For a new dataset with 8304 proteins located in 8 subcellular locations, the total accuracy achieves 88.9%. The model shows robust against N-terminal errors in the sequences. A web server is developed based on the method which was used to predict some new proteins. This paper presents a novel approach combining the residue-couple model and the SVM for subcellular localization prediction. Residue-couples contain information of the amino acid composition and the order of the amino acids in the protein sequences. The information is important for subcellular localization. These residue-couples were used to train the SVM classifiers. By using a 5-fold cross validation test, the overall prediction accuracies reach 86.9% for eukaryotic proteins and 92.1% for prokaryotic proteins. The results show that the prediction accuracy is significantly improved with the novel

Locating apoptosis proteins by incorporating the signal peptide cleavage sites into the general form of Chou's Pseudo amino acid composition

“…NNPSL dataset, constructed by Reinhardt and Hubbard, is also adopted in this work to further evaluate the performance of this method. Tables 9 and 10 are the comparisons between this method and other related methods such as Markov chain model, [82] SVM, [83] k-NN, [84] and 1-NN.…”

“…Moreover, the MCCs and the local accuracies for extracellular and mitochondrial proteins are the best among the above methods. From Table 10, we can see that, for prokaryotic sequences, the TA of Markov model [82] is 89.1%, SVM [83] is 92.0%, nearest neighbor [85] is 92.5%. And, the result of our approach is 94.8%, which is better than the other methods.…”

High performance set of PseAAC and sequence based descriptors for protein classification

“…The quasi residue couple is a model for protein representation proposed by (Nanni, 2006) and inspired by Chou's quasi-sequence-order model and Yuan's Markov chain model (Guo et al, 2005).…”

“…A residue couple model of order less than three (Guo et al, 2005) is considered to represent the sequence. Each nonzero entry in the residue couple is substituted by the corresponding value of the selected property.…”

Machine learning multi-classifiers for peptide classification

“…• Composition moment vector (CMV): It is a feature extraction method proposed in [9] which includes information about both composition and position in amino-acids sequence. It also provides functional relation with the structure content.…”