Table 1. Top five results for the search query “What kind of microorganisms are in oil sands tailings ponds?”.

Sample accession number	Scorea	NCBI taxonomyb	Abundant generac
DRS011723	4.01471E–06	Marine sediment metagenome	Methanosaeta (100%)
SRS151248	4.00920E–06	Hydrocarbon metagenome	Methanoregula (57%), Methanosaeta (21%), Methanolinea (7%)
SRS151247	4.00584E–06	Hydrocarbon metagenome	Methanoregula (46%), Methanosaeta (31%), Methanolinea (7%)
SRS526819	4.00451E–06	Aquatic metagenome	Methanoplanus (41%), Methanocorpusculum (39%), Methanolobus (18%)
SRS151329	4.00358E–06	Hydrocarbon metagenome	Methanoregula (64%), Methanosaeta (16%)

^aScores of each sample were calculated as the probability to generate a query sentence based on topic compositions of each sample.

^bNCBI taxonomy labels added to each sample. Abbreviation: NCBI, National Center for Biotechnology Information.

^cTaxonomy names of abundant genera and their relative abundances in the taxonomic composition of the sample.