A Novel Reduced Triplet Composition Based Method to Predict Apoptosis Protein Subcellular Localization

作者：Zhang, Shengli^*; Liang, Yunyun; Bai, Zhenguo

来源：MATCH-Communications in Mathematical and in Computer Chemistry, 2015, 73(2): 559-571.

• AMINO-ACID-COMPOSITION
• SUPPORT VECTOR MACHINE
• PROGRAMMED CELL-DEATH
• LOCATION PREDICTION
• REPRESENTATION
• PROFILES
• ACCURACY
• SITES
• PSSM

Apoptosis, or programmed cell death, plays an important role in development of an organism. Obtaining information on subcellular location of apoptosis proteins is very helpful to understand the apoptosis mechanism. In this paper, based on the hydropathy characteristics, a novel feature extraction method with triplet composition features for reduced protein sequence is presented, and applied to apoptosis protein subcellular localization prediction associated with support vector machine. The experiment results show that the new feature extraction method is efficient to extract the information implicated in protein sequence and the method has reached a satisfied performance despite its simplicity. The overall prediction accuracy of our proposed method on dataset ZD98 reaches 96.9% in Jackknife test. For the dataset ZW225, the overall prediction accuracy achieves 89.8%. Comparison with other existing methods shows that RTC_SVM model is a very promising prediction model for apoptosis protein subcellular localization and may at least play an important complementary role to existing methods.

• 出版日期2015
• 单位西安电子科技大学