...organisms. For model training, we mainly focused on six species: Arabidopsis thaliana, Caenorhabditis elegans, Drosophila melanogaster, Escherichia coli, Geobacillus subterraneus, Geobacter pickeringii. The respective positive sample counts for these species
are 125,628, 68,917, 109,289, 2068, 14...