Supplementary_table2.xlsx

	A	B	C	D	E	F	G	H	I	J	K	L	M
1	Group	Protein family	Cluster 0	Cluster 1	Cluster 2	Cluster 3	Cluster 4	Cluster 5	Cluster 6	Cluster 7	Cluster 8	Cluster 9	Total

2	Group 1	a) Agglomerative clustering of the Lysozyme CGCh dataset (FMI=0.88)
3
4		Lysozyme C	52	0	Not applicable (only 2 clusters)								52
5		Lysozyme G	17	0									17
6		Lysozyme Ch	0	54									54
7		Total	69	54									123
8		b) Agglomerative clustering of the Xylanase dataset (FMI=0.98)
9
10		GH10	351	1	Not applicable (only 2 clusters)								352
11		GH11	7	340									347
12		Total	358	341									699
13		c) Spectral clustering of the Chitinase dataset (FMI=0.85)
14		c) Spectral clustering of the Chitinase dataset (FMI=0.85)
15		GH18	439	23	Not applicable (only 2 clusters)								462
16		GH19	43	151									194
17		Total	482	174									656
18	Group 2	d) K-means, Gaussian mixture model, agglomerative, and spectral clustering of the Lysozyme CaLA dataset (FMI=1.00)
19
20		α-Lactalbumin	22	0	Not applicable (only 2 clusters)								22
21		Lysozyme C	0	52									52
22		Total	22	52									74
23		e) Agglomerative and spectral clustering of the Protease dataset (FMI=0.70)
24
25		Trypsin	56	11	Not applicable (only 2 clusters)								67
26		Chymotrypsin	16	0									16
27		Total	72	11									83
28		f) Spectral clustering of the Ferredoxin dataset (FMI=0.75)
29		f) Spectral clustering of the Ferredoxin dataset (FMI=0.75)
30		FDX1	1	8	Not applicable (only 2 clusters)								9
31		FDX2	6	1									7
32		Total	7	9									16
33	Group 3	g) Agglomerative clustering of the β-Glucosidase dataset (FMI=0.78)
34
35		GH1	287	1	60	Not applicable (only 3 clusters)							348
36		GH3	21	153	30								204
37		Total	308	154	90								552
38		h) K-means and Gaussian mixture model of the Lysozyme dataset (FMI=0.44)
39
40		GH24	6	0	0	25	0	0	0	0	0	0	31
41		GH22	0	40	26	0	30	13	7	12	0	7	135
42		GH23	0	0	0	39	0	1	0	0	4	3	47
43		Total	6	40	26	64	30	14	7	12	4	10	213
44		i) Gaussian mixture model of the β-Galactosidase dataset (FMI=0.86)
45
46		GH2	74	0	43	Not applicable (only 3 clusters)							117
47		GH35	5	283	7								295
48		GH42	39	0	44								83
49		Total	118	283	94								495
50	Group 4	j) K-means, Gaussian mixture model, and agglomerative clustering of the GH2 dataset (FMI=0.37)
51
52		β-Glucuronidase	27	29	5	0	4	2	1	4	5	8	85
53		β-Galactosidase	0	4	15	24	20	20	14	12	6	2	117
54		Total	27	33	20	24	24	22	15	16	11	10	202
55		k) Spectral clustering of the GH3 dataset (FMI=0.62)
56		k) Spectral clustering of the GH3 dataset (FMI=0.62)
57		β-Glucosidase	162	42	Not applicable (only 2 clusters)								204
58		1,4-β-Xylosidase	89	10									99
59		Total	251	52									303
60		l) Spectral clustering of the GH5 dataset (FMI=0.59)
61		l) Spectral clustering of the GH5 dataset (FMI=0.59)
62		Cellulase	112	230	Not applicable (only 2 clusters)								342
63		Endo-β-Mannanase	63	64									127
64		Total	175	294									469
65	Group 5	m) K-means and Gaussian mixture model of the SNARE dataset (FMI=0.86)
66
67		SNARE	1	56	Not applicable (only 2 clusters)								57
68		non-SNARE	53	8									61
69		Total	54	64									118
70		n) Gaussian mixture model of the GPCR1 (FMI=0.658)
71		n) Gaussian mixture model of the GPCR1 (FMI=0.658)
72		GPCR	1692	5	Not applicable (only 2 clusters)								1697
73		non-GPCR (TM)	1635	272									1907
74		Total	3327	277									3604
75		o) Gaussian mixture model of the GPCR2 dataset (FMI=0.94)
76		o) Gaussian mixture model of the GPCR2 dataset (FMI=0.94)
77		GPCR	1650	47	Not applicable (only 2 clusters)								1697
78		non-GPCR (no TM)	55	1806									1861
79		Total	1705	1853									3558
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100