Classifies the protein fold by combing the results from two algorithms, HH-fold and support vector machines (SVM)-fold. TA-fold is an ensemble approach proposed to combine the results of these algorithms. HH-fold is a template-based fold assignment algorithm using the Hidden Markov Model (HMM)-HMM alignment program HHsearch. SVM-fold is a support vector machine-based ab-initio classification algorithm. When there are homologous templates to the query protein, HH-fold prediction is reported. Otherwise, the SVM-fold prediction is returned.
Department of Physics, Northeast Forestry University, Harbin, China; Center for Applied Mathematics, Tianjin University, Tianjin, China; School of Mathematical Sciences, Nankai University, Tianjin, China
TA-fold funding source(s)
The project is supported in part by National Natural Science Foundation of China (11501306, 11501407), China National 863 High-Tech Program (2015AA020101) and the Thousand Youth Talents Plan of China.