Automatic disease prediction from human gut metagenomic data using boosting GraphSAGE

BMC Bioinformatics

Table 2 Description of the datasets used

Disease	Number of sick samples	Number of healthy samples	Number of features	Reference
Real dataset
IBD	336	1023	1025	[26]
CRC	229	261	319	[27]
Synthetic dataset
IBD_synthetic	3024	9207	1025
CRC_synthetic	1145	1305	319

ISSN: 1471-2105