Table 1 MetaSUB metagenomic dataset description
From: A machine learning framework to determine geolocations from metagenomic profiling
Set | City | Country | Sample count |
|---|---|---|---|
Training Set | Auckland (AKL) | New Zealand | 14 |
Berlin (BER) | Germany | 21 | |
Bogota (BOG) | Colombia | 15 | |
Hamilton (HAM) | New Zealand | 16 | |
Hong Kong (HGK) | China | 18 | |
Ilorin (ILR) | Nigeria | 24 | |
London (LON) | U.K. | 24 | |
Marseille (MAR) | France | 10 | |
New York (NYC) | U.S.A. | 26 | |
Offa (OFA) | Nigeria | 20 | |
Porto (PXO) | Portugal | 20 | |
Sacramento (SAC) | U.S.A. | 18 | |
Sao Paulo (SAO) | Brazil | 24 | |
Sofia (SOF) | Bulgaria | 10 | |
Stockholm (STO) | Sweden | 20 | |
Tokyo (TOK) | Japan | 25 | |
Total size | 779 Gb | ||
Testing Set | Rio de Janerio | Brazil | 12 |
Santiago de Chile | Chile | 6 | |
Kiev | Ukraine | 8 | |
Brisbane | Australia | 7 | |
Vienna | Austria | 5 | |
Doha | Qatar | 3 | |
Pairs | France | 8 | |
Oslo | Norway | 12 | |
Total size | 219 Gb | ||