Table 1. Clustering analysis of KEGG sequence embeddings.

Taxon	K	P	C	O	F	G	S
# of Taxa	2	35	77	143	281	697	385
K	2	35	77	143	281	697	385
Homogeneity	0.11	0.88	0.94	0.94	0.96	0.97	0.98
Completeness	0.02	0.42	0.56	0.78	0.79	0.83	0.94
ARI	-0.01	0.24	0.32	0.36	0.43	0.47	0.84
AMI	0.02	0.42	0.55	0.66	0.75	0.76	0.91
NMI	0.04	0.61	0.72	0.80	0.87	0.90	0.96