In biological systems, protein complexes are one of important molecules to perform as transcription factors and enzymes. Protein complexes with size more than three have been focused by most prediction methods. It, however, is known that protein complexes with smaller sizes occupy a large part of whole complexes for several species. In our previous work, we developed a method with several feature space mappings and the domain composition kernel for prediction of heterodimeric protein complexes, which outperforms existing methods. In this technical report, we propose methods for prediction of heterotrimeric protein complexes by extending the previous prediction method on the basis of some ability that heterotrimeric protein complexes are not likely to share the same protein with each other. We make use of the discriminant function in support vector machines (SVMs), and design novel feature space mappings for the second phase. As the second classifier, we examine SVMs and relevance vector machines (RVMs). We perform ten-fold cross-validation computational experiments. The results suggest that our proposed two-phase methods and SVM with the extended features and the domain composition kernel outperform the existing method NWE in terms of F-measure, which was reported to outperform other existing methods for prediction of heterotrimeric protein complexes.
展开▼
