Prediction of protein subcellular location using a combined feature of sequence

Abstract

To understand the structure and function of a protein, an important task is to know where it occurs in the cell. Thus, a computational method for properly predicting the subcellular location of proteins would be significant in interpreting the original data produced by the large-scale genome sequencing projects. The present work tries to explore an effective method for extracting features from protein primary sequence and find a novel measurement of similarity among proteins for classifying a protein to its proper subcellular location. We considered four locations in eukaryotic cells and three locations in prokaryotic cells, which have been investigated by several groups in the past. A combined feature of primary sequence defined as a 430D (dimensional) vector was utilized to represent a protein, including 20 amino acid compositions, 400 dipeptide compositions and 10 physicochemical properties. To evaluate the prediction performance of this encoding scheme, a jackknife test based on nearest neighbor algorithm was employed. The prediction accuracies for cytoplasmic, extracellular, mitochondrial, and nuclear proteins in the former dataset were 86.3%, 89.2%, 73.5% and 89.4%, respectively, and the total prediction accuracy reached 86.3%. As for the prediction accuracies of cytoplasmic, extracellular, and periplasmic proteins in the latter dataset, the prediction accuracies were 97.4%, 86.0%, and 79.7, respectively, and the total prediction accuracy of 92.5% was achieved. The results indicate that this method outperforms some existing approaches based on amino acid composition or amino acid composition and dipeptide composition.

Predicting important classes of chemokine family based on kernel method

“…The comparison results demonstrate that all the testing methods can provide a better prediction performance for each class. Our studies also indicated that the jackknife test can provide a bias-free estimate of the accuracy at a much-reduced computational cost, which is an acceptable test for evaluating the performance of a prediction approach [24,28].…”

“…Thus, it is reasonable that kernel method combined with other properties (e.g. structural properties) of the amino acid residues will improve the prediction performance [28].…”

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

“…[82] [b] Based on a SVM model of residue-couple. [85] [c] Based on a 1-NN model of dipeptide composition. [85] FULL PAPER WWW.Q-CHEM.ORG…”

“…[82] [b] Based on a SVM model of residue-couple. [85] [c] Based on a k-NN model of complexity information. [84] FULL PAPER WWW.Q-CHEM.ORG As shown in Table 9, our approach achieved an overall accuracy of 87.7% for eukaryotic proteins.…”

“…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.…”