Skip to main content

Table 1 Characteristics of microbiomic datasets used in this study

From: A comprehensive evaluation of multicategory classification methods for microbiomic data

Dataset Number of samples Number of features (OTUs) Number of classes Classification task and samples per class Max. prior probability of a class (%)
Costello Body Habitat (CBH) 552 6,979 6 Classify body habitats: Skin (357), Oral Cavity (46), External Auditory Canal (44), Hair (14), Nostril (46), Feces (45) 64.7
Costello Subject (CS) 140 2,543 7 Classify 7 subjects by microbiota (20/20/20/20/20/20/20) 14.3
Costello Skin Sites (CSS) 357 4,793 12 Classify skin sites: external nose (14), forehead (32), glans penis (8), labia minora (6), axilla (28), pinna (27), palm (64), palmar index finger (28), plantar foot (64), popliteal fossa (46), volar forearm (28), umbilicus (12) 17.9
Fierer Subject (FS) 104 1,217 3 Classify 3 subjects by microbiota (40/33/31) 38.5
Fierer Subject x Hand (FSH) 98 1,217 6 Classify by subject and left/right hand (20/18/17/14/16/13) 20.4
Blaser Psoriasis (BP) 151 13,503 3 Classify as Control (49), Psoriasis Normal (51), Psoriasis Lesion (51) 33.8
Pei Diagnosis (PDX) 200 74,018 4 Classify as Normal (28), Reflux Esophagitis (36), Barrett's Esophagus (84), Esophageal Adenocarcinoma (52) 42.0
Pei Body Site (PBS) 200 74,018 4 Classify body site: Oral Cavity (51), Esophagus (51), Stomach (48), Stool (50) 25.5