caa a22 4500 463186516 CHVBK 20180406164854.0 cr unu---uuuuu 170326e20071101xx s 000 0 eng 10.1007/s00726-006-0465-0 doi (NATIONALLICENCE)springer-10.1007/s00726-006-0465-0 Prediction of mitochondrial proteins based on genetic algorithm - partial least squares and support vector machine [Elektronische Daten] [F. Tan, X. Feng, Z. Fang, M. Li, Y. Guo, L. Jiang] Summary.: Mitochondria are essential cell organelles of eukaryotes. Hence, it is vitally important to develop an automated and reliable method for timely identification of novel mitochondrial proteins. In this study, mitochondrial proteins were encoded by dipeptide composition technology; then, the genetic algorithm-partial least square (GA-PLS) method was used to evaluate the dipeptide composition elements which are more important in recognizing mitochondrial proteins; further, these selected dipeptide composition elements were applied to support vector machine (SVM)-based classifiers to predict the mitochondrial proteins. All the models were trained and validated by the jackknife cross-validation test. The prediction accuracy is 85%, suggesting that it performs reasonably well in predicting the mitochondrial proteins. Our results strongly imply that not all the dipeptide compositions are informative and indispensable for predicting proteins. The source code of MATLAB and the dataset are available on request under liml@scu.edu.cn. Springer-Verlag, 2007 Keywords: Mitochondrial proteins - Dipeptide composition - Genetic algorithm-partial least square - Support vector machine nationallicence Tan F. College of Chemistry, Sichuan University, Chengdu, China aut Feng X. College of Chemistry, Sichuan University, Chengdu, China aut Fang Z. College of Chemistry, Sichuan University, Chengdu, China aut Li M. College of Chemistry, Sichuan University, Chengdu, China aut Guo Y. College of Chemistry, Sichuan University, Chengdu, China aut Jiang L. College of Chemistry, Sichuan University, Chengdu, China aut Amino Acids Springer-Verlag 33/4(2007-11-01), 669-675 0939-4451 33:4<669 2007 33 726 https://doi.org/10.1007/s00726-006-0465-0 text/html Onlinezugriff via DOI 1 research-article jats NATIONALLICENCE 856 40 https://doi.org/10.1007/s00726-006-0465-0 text/html Onlinezugriff via DOI NATIONALLICENCE 700 1- Tan F. College of Chemistry, Sichuan University, Chengdu, China aut NATIONALLICENCE 700 1- Feng X. College of Chemistry, Sichuan University, Chengdu, China aut NATIONALLICENCE 700 1- Fang Z. College of Chemistry, Sichuan University, Chengdu, China aut NATIONALLICENCE 700 1- Li M. College of Chemistry, Sichuan University, Chengdu, China aut NATIONALLICENCE 700 1- Guo Y. College of Chemistry, Sichuan University, Chengdu, China aut NATIONALLICENCE 700 1- Jiang L. College of Chemistry, Sichuan University, Chengdu, China aut NATIONALLICENCE 773 0- Amino Acids Springer-Verlag 33/4(2007-11-01), 669-675 0939-4451 33:4<669 2007 33 726 Metadata rights reserved Springer special CC-BY-NC licence nationallicence BK010053 XK010053 XK010000 NATIONALLICENCE NATIONALLICENCE NL-springer