Table 3.

Performance comparison with different approaches

Method a	Info b	IT c		CAFA c	BC c	TREC c
		i P 1	i R 10	h F max	h R 10	M R R 10	R 10
GOTA	PM	0.42	0.69	0.42	0.73	0.39	0.49
GOTA	T+A	0.37	0.68	0.41	0.73	0.35	0.48
GOTA	T	0.39	0.66	0.39	0.70	0.34	0.44
GOCat	T+A	0.34	0.64	0.37	0.69	0.29	0.40
GOCat	T	0.30	0.64	0.36	0.69	0.28	0.40
RandFR	N/A	0.08	0.21	0.10	0.23	0.03	0.05
RandIC	N/A	0.22	0.23	0.19	0.30	0.00	0.01

^aMethod used for prediction. RandFR and RandIC are baseline predictors, based on the distribution of GO terms in the training set

^bInformations used in prediction: PM = title, abstract, references and publication year (PubMed); T+A = title and abstract; T = title; N/A = no information

^cMetrics definitions are in the “Evaluation metrics” section. For each metric, the best result is highlighted in italic