Table 1.

Twenty GO families collected from diverse subclasses in MF of GO database by maximizing their representativeness among all MF categories. The numbers of proteins (with the sequence length of ≤1000) in these GO families were from 802 to 33 178, and the number of Pfam families covered by each GO family was from 57 to 1092. These GO families were sorted by their total numbers of proteins included

Functional GO families studied in this work	GO ID	No. of proteins	No. of Pfam families covered	No. of proteins in training data set	No. of proteins in testing data set
Cyclase activity	GO:0009975	802	57	624	178
Cyclin-dependent protein kinase activity	GO:0097472	2951	64	2295	656
Phosphoprotein phosphatase activity	GO:0004721	4324	152	3363	961
Transcription coregulator activity	GO:0003712	4684	346	3643	1041
Positive regulation of transferase activity	GO:0051347	4732	355	3680	1052
Negative regulation of catalytic activity	GO:0043086	6239	512	4853	1386
Transferase activity, transferring acyl groups	GO:0016746	8845	238	6879	1966
Ubiquitin-like protein transferase activity	GO:0019787	9553	255	7430	2123
Transferase activity, transferring glycosyl groups	GO:0016757	9694	278	7540	2154
Structural constituent of ribosome	GO:0003735	10 492	204	8160	2332
Regulation of hydrolase activity	GO:0051336	10 995	686	8551	2444
Positive regulation of catalytic activity	GO:0043085	11 803	719	9180	2623
Positive regulation of MF	GO:0044093	13 677	884	10 637	3040
Peptidase activity	GO:0008233	18 665	597	14 517	4148
DNA-binding transcription factor activity	GO:0003700	19 677	693	15 304	4373
Hydrolase activity, acting on ester bonds	GO:0016788	22 599	802	17 578	5021
Protein kinase activity	GO:0004672	23 068	642	17 942	5126
Hydrolase activity, acting on acid anhydrides	GO:0016817	28 327	779	22 032	6295
Signaling receptor activity	GO:0038023	28 700	525	22 322	6378
Catalytic complex	GO:1902494	33 178	1092	25 805	7373