A team of researchers has created a novel machine learning tool that's cracking open one of biology's trickiest puzzles: finding the rarest microbes on Earth. Think of it like finding a needle in a haystack, except the needle is microscopic and might hold the key to how our ecosystems work.
The tool, called ulrb, uses AI to spot these elusive microorganisms that, despite their tiny numbers, pack a serious punch in keeping our planet's ecosystems healthy. It's like having a super-smart detective that can pick out the rare gems from billions of other microbes.
This pioneering open-source software, developed through collaboration between the University of Ottawa, Dalhousie university, Interdisciplinary Center for Marine and Environmental Research (CIIMAR), Institute for Bioengineering and Biosciences of Instituto Superior Técnico, and the University of Porto,addresses long-standing challenges in microbial ecology and opens new doors for ecological research.
“This tool solves a major issue in microbial ecology: how do we define rare microorganisms?” says co-author Paula Branco, Associate Professor at the University of Ottawa’s School of Electrical Engineering and Computer Science. “With ulrb, we’ve created a method that is precise, adaptable, and capable of improving biodiversity assessments. Before, we were basically guessing at what counted as 'rare' in the microbial world. Now we have a precise way to figure it out.”
“Our findings show that ulrb not only identifies rare microorganisms but also works with non-microbial data, such as tree census datasets,” explains Francisco Pascoal, PhD Candidate at CIIMAR (Interdisciplinary Center for Marine and Environmental Research), who led the development of the ulrb R package as part of his doctoral research. “This versatility makes it a powerful tool for ecological applications.”
“With ulrb, we’ve created a method that is precise, adaptable, and capable of improving biodiversity assessments”
Paula Branco
— Associate Professor, School of Electrical Engineering and Computer Science
Conducted entirely computationally, the study tested ulrb against various microbiome datasets. The software demonstrated statistical robustness and practical applications, such as characterizing coral microbiomes.
Available as open-source software on CRAN and GitHub, ulrb includes tutorials to assist users worldwide. Its impact extends beyond academia by enhancing biodiversity assessments and aiding evaluations of climate change effects on microbial communities.
The project, initiated in 2022, has recently been published in Communications Biology under the title “Definition of the microbial rare biosphere through unsupervised machine learning”. marking a new chapter in how we study the hidden world of microorganisms.