Skip to main content

Table 1 Number of datasets samples and features

From: Kernel principal components based cascade forest towards disease identification with human microbiota

ID

Data sources

Disease label and sample size

f-level features

g-level features

1

cdi_schubert [41]

CDI(93), nonCDI(89), H(154)

80

198

2

crc_baxter [15]

CRC(120), H(172), adenoma(198)

93

255

3

ibd_papa [42]

nonIBD(24), UC(43), CD(23)

49

142

4

ob_goodrich [43]

OB(185), OW(336),H(428)

79

199