Tag: fungi diversity

Using AI to Uncover the Secret Lives of Fungi

AI holds the potential to automatically identify fungal versatility from the available scientific literature.

Fungi are the hidden architects of our ecosystems, acting as everything from helpful partners for plants to aggressive decomposers that recycle dead wood. However, many fungi don’t stick to just one job; they can switch lifestyles depending on their environment.  

Understanding this flexibility is vital for predicting how forests and farms will react to climate change. Unfortunately, the information researchers need is buried in decades of scientific papers that would take too long to comb through manually. 

A new study led by Northern Arizona University doctoral student Beatrice M. Bock and published in the open-access journal Research Ideas and Outcomes demonstrates how AI can solve this problem. By using a specialized language model called BioBERT, Bock developed an automated workflow that assesses scientific abstracts and accurately identifies whether a fungus has a single lifestyle or a dual, flexible one. 

A high-accuracy hack 

Bock said that for years, mycologists have relied on manual databases to track what different fungi do in the environment. While these tools are essential, they are difficult to keep updated as new research is published every day. 

“Manually identifying fungal versatility from the literature is time-consuming and difficult to scale. By using machine learning, we can now scan thousands of papers in just a few minutes to flag species that might be switching roles—such as a fungus that normally helps a plant grow but also turns into a decomposer when the plant dies.” 

Beatrice M. Bock

The pilot study tested four different AI models to see which was best at understanding the nuances of biological language. The top-performing model, BioBERT, achieved nearly 90% accuracy in identifying fungal lifestyles. 

What did BioBERT have that the other models didn’t? For one, it had the power of capitalization. Bock found that “cased” models—those that recognize capital letters—performed significantly better than those that did not. That’s likely because capital letters often signal species’ scientific names, like Fusarium, which are crucial for AI to understand the context of the research. 

The path ahead 

Bock said that in a commitment to transparency, she has made all the code and data available for free online, allowing other scientists to build upon her work and track traits in other organisms, like insects or plants. 

While Bock’s study focused on a small group of papers as a proof-of-concept, it opens the door for much larger projects. Future versions of the tool could predict how a fungus’s behavior might change under specific environmental conditions, such as drought or extreme heat. 

“As fungal trait databases continue to grow in importance for biodiversity assessments, automated text mining offers a path toward more efficient, consistent and comprehensive trait annotation.”

Beatrice M. Bock

Original sources:

Bock B (2026) Automated extraction of fungal trophic modes from literature using BioBERT: an open pilot workflow. Research Ideas and Outcomes 12: e176590. https://doi.org/10.3897/rio.12.e176590

Story originally published by: EurekAlert! (2026). Using AI to uncover the secret lives of fungi. [online] Available at: https://www.eurekalert.org/news-releases/1114462 [Accessed 2 Feb. 2026]. Republished with permission.

Follow the latest publications and news from the Research Ideas and Outcomes (RIO) journal on Bluesky, Facebook and LinkedIn.

Underwater mushrooms: Curious lake fungi under every turned over stone

While fungi are well known for being essential in cycling carbon and nutrients, there are only about 100,000 described species in contrast to the 1.5 to 3 millions, assumed to exist on Earth. Of these, barely 3000 fungi belong to aquatic habitats. In fact, freshwater fungi have been researched so little, it is only now that an international research team provide the first lake-wide fungal diversity estimate in the open access journal MycoKeys.

Over the spring and the early summer of 2010, a large team of scientists, led by Dr Christian Wurzbacher and Dr Norman Warthmann, affiliated with the Leibniz-Institute of Freshwater Ecology and Inland Fisheries and the Berlin Center for Genomics in Biodiversity Research, Germany (currently at University of Gothenburg, Sweden, and the Australian National University, Australia, respectively), collected a total of 216 samples from 54 locations, encompassing eight different habitats within Lake Stechlin in North-East Germany.image-1

Having recovered samples on three occasions over the course of the study, their aim was to test how habitat specificity affects the fungal community and whether fungal groups would reflect the availability of particulate organic matter as substrate. Unlike previous studies of aquatic fungi that compared water samples among different lakes or seasons, theirs would compare the diversity among habitats within a single lake. This included the study of fungi living in the water and the sediments, as well as fungi living on the surfaces of plants and other animals.

As a result, the scientists concluded that every type of habitat, i.e. sediments, biofilms, and submerged macrophytes (large aquatic plants), has a specific fungal community that varies more than initially expected. Of these, lake biofilms, representing a group of microorganisms, whose cells stick to each other, and cling together to a surface, turned out to be the hotspots for aquatic fungi.

“Our study provides the first estimate of lake-wide fungal diversity and highlights the important contribution of habitat heterogeneity to overall diversity and community composition,” the scientists summarise. “Habitat diversity should be considered in any sampling strategy aiming to assess the fungal diversity of a water body.”

###

Original source:

Wurzbacher C, Warthmann N, Bourne EC, Attermeyer K, Allgaier M, Powell JR, Detering H, Mbedi S, Grossart H-P, Monaghan MT (2016) High habitat-specificity in fungal communities in oligo-mesotrophic, temperate Lake Stechlin (North-East Germany). MycoKeys 16: 17-44. https://doi.org/10.3897/mycokeys.16.9646