An AI Identifies Unknown Soil Bacteria From DNA

BBERT, built by researchers at the Hebrew University of Jerusalem, the University of Haifa and the Volcani Institute, identifies bacterial DNA even when the microorganism is missing from existing genetic databases, distinguishing bacterial from non-bacterial DNA with about 90% accuracy across 1,969 soil datasets. The findings were published in Nucleic Acids Research, and the tool can run on a personal computer with a suitable graphics card.