Table 1 Overview of the Datasets
Dataset | Sample size | Number of samples in each subdataset | Number of microbial features | Number of metabolite features |
|---|---|---|---|---|
MFGM [24] | 277 | With.comp.food': 50, 'Without.comp.food': 92, 'Month12': 68,'Baseline': 67 | 30 | 81 |
ASD [25] | 44 | 'Autistic': 23, 'Neurotypical': 21 | 107 | 53 |
INFANTS_DIABETES [26] | 103 | 'Case': 66, 'Control': 37 | 33 | 184 |
PRETERMS [27] | 75 | 'Septic': 23, 'Nec': 14, 'GI': 37, 'Control': 1 | 31 | 453 |
SINHA_CRC [28] | 131 | 'CRC': 42, 'Control': 89 | 31 | 530 |
ADENOMAS [29] | 240 | 'Adenoma': 102, 'Carcinoma': 36, 'Control': 102 | 55 | 462 |
BIO_ML [30] | 164 | 'Healthy': 164 | 29 | 489 |
IBD_RELATIVES [31] | 90 | 'UC': 10, 'CD': 26, 'Normal': 54 | 117 | 1052 |
IBS [32] | 444 | 'C': 133, 'D': 172, 'H': 139 | 1186 | 43 |
CRC [33] | 347 | 'Stage_I_II': 69, 'Stage_III_IV': 54, 'Stage_0': 27, 'HS': 30, 'MP': 40, 'Healthy': 127 | 2983 | 165 |
GC [34] | 96 | 'Gastrectomy': 42, 'Healthy': 54 | 6441 | 144 |
ESRD [35] | 287 | 'ESRD': 220, 'Control': 67 | 7492 | 276 |
IBD [36] | 220 | 'UC': 76, 'CD': 88, 'Control': 56 | 5604 | 7156 |
IBDMDB [37] | 382 | 'UC': 101, 'CD': 177, 'Control': 104 | 2875 | 81,867 |