iMPT-FDNPL: Identification of Membrane Protein Types with Functional Domains and a Natural Language Processing Approach

Table 2

Performance of different multilabel classifiers with features derived from functional domain information via a natural language processing approach.

Scheme (base classifier)	Exact match	Accuracy	Hamming loss	Integrated score
RAKEL (RF) (iMPT-FDNPL)	0.851	0.853	0.053	0.6874
RAKEL (SVM-polynomial kernel)	0.831	0.834	0.060	0.6515
RAKEL (SVM-RBF kernel)	0.846	0.848	0.054	0.6787
BR (RF)	0.781	0.782	0.054	0.5778
BR (SVM-polynomial kernel)	0.804	0.815	0.061	0.6152
BR (SVM-RBF kernel)	0.829	0.831	0.050	0.6544