{"id":76912,"date":"2026-02-02T09:58:45","date_gmt":"2026-02-02T16:58:45","guid":{"rendered":"https:\/\/in.nau.edu\/news\/?p=76912"},"modified":"2026-02-02T13:26:10","modified_gmt":"2026-02-02T20:26:10","slug":"fungi-and-ai-study","status":"publish","type":"post","link":"https:\/\/in.nau.edu\/news\/fungi-and-ai-study\/","title":{"rendered":"Using AI to uncover the secret lives of fungi"},"content":{"rendered":"<p><span data-contrast=\"auto\">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\u00a0don\u2019t\u00a0stick to just one job; they can switch lifestyles depending on their environment.\u00a0<\/span><span data-ccp-props=\"{&quot;335559738&quot;:180,&quot;335559739&quot;:180}\">\u00a0<\/span><\/p>\n<p><span data-contrast=\"auto\">Understanding this flexibility is vital for predicting how forests and farms will react to climate change. Unfortunately,\u00a0the information\u00a0researchers need is buried in\u00a0decades of scientific papers that would take too long to comb through manually.<\/span><span data-ccp-props=\"{&quot;335559738&quot;:180,&quot;335559739&quot;:180}\">\u00a0<\/span><\/p>\n<p><span data-contrast=\"auto\">A new study\u00a0led\u00a0by\u00a0NAU doctoral student\u00a0<\/span><b><span data-contrast=\"auto\">Beatrice M.\u00a0Bock<\/span><\/b><span data-contrast=\"auto\">\u00a0demonstrates\u00a0how AI can solve this problem. By using a\u00a0<\/span><a href=\"https:\/\/github.com\/beabock\/biobert_dualsolo\"><span data-contrast=\"none\">specialized language model called<\/span><\/a><span data-contrast=\"auto\">\u00a0<\/span><a href=\"https:\/\/github.com\/beabock\/biobert_dualsolo\"><span data-contrast=\"none\">BioBERT<\/span><\/a><span data-contrast=\"auto\">,\u00a0Bock developed an automated workflow that\u00a0assesses\u00a0scientific abstracts and accurately\u00a0identifies\u00a0whether a fungus has a single lifestyle or a dual, flexible one.<\/span><span data-ccp-props=\"{&quot;335559738&quot;:180,&quot;335559739&quot;:180}\">\u00a0<\/span><\/p>\n<p><a href=\"https:\/\/riojournal.com\/article\/176590\/list\/10\/\"><span data-contrast=\"none\">The study was recently published\u00a0in\u00a0Research Ideas and Outcomes.<\/span><\/a><span data-contrast=\"auto\">\u00a0<\/span><span data-ccp-props=\"{&quot;335559738&quot;:180,&quot;335559739&quot;:180}\">\u00a0<\/span><\/p>\n<h3><b><span data-contrast=\"auto\">A high-accuracy hack<\/span><\/b><span data-ccp-props=\"{&quot;335559738&quot;:180,&quot;335559739&quot;:180}\">\u00a0<\/span><\/h3>\n<p><span data-contrast=\"auto\">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.<\/span><span data-ccp-props=\"{&quot;335559738&quot;:180,&quot;335559739&quot;:180}\">\u00a0<\/span><\/p>\n<p><span data-contrast=\"auto\">\u201cManually identifying\u00a0fungal\u00a0versatility from the literature is time-consuming and difficult to scale,\u201d\u00a0Bock said.\u00a0\u201cBy using machine learning, we\u00a0can now scan thousands of papers in\u00a0just a few\u00a0minutes to flag species that might be switching roles\u2014such as a fungus that normally helps a plant grow but\u00a0also\u00a0turns into a decomposer when the plant dies.\u201d<\/span><span data-ccp-props=\"{&quot;335559738&quot;:180,&quot;335559739&quot;:180}\">\u00a0<\/span><\/p>\n<p><span data-contrast=\"auto\">The pilot study tested four different AI models to see which\u00a0was\u00a0best at understanding the nuances of biological language.\u00a0The top-performing model,\u00a0BioBERT, achieved\u00a0nearly 90%\u00a0accuracy in\u00a0identifying\u00a0fungal lifestyles.<\/span><span data-ccp-props=\"{&quot;335559738&quot;:180,&quot;335559739&quot;:180}\">\u00a0<\/span><\/p>\n<p><span data-contrast=\"auto\">What did\u00a0BioBERT\u00a0have that the other models\u00a0didn\u2019t? For one, it had the power of capitalization.\u00a0Bock\u00a0found that \u201ccased\u201d models\u2014those that recognize capital letters\u2014performed significantly better than those that did not.\u00a0That\u2019s\u00a0likely because\u00a0capital letters often signal\u00a0species\u2019\u00a0scientific names, like\u00a0<\/span><i><span data-contrast=\"auto\">Fusarium<\/span><\/i><span data-contrast=\"auto\">, which are crucial for AI to understand the context of the research.<\/span><span data-ccp-props=\"{&quot;335559738&quot;:180,&quot;335559739&quot;:180}\">\u00a0<\/span><\/p>\n<h3><b><span data-contrast=\"auto\">The path ahead<\/span><\/b><span data-ccp-props=\"{&quot;335559738&quot;:180,&quot;335559739&quot;:180}\">\u00a0<\/span><\/h3>\n<p><span data-contrast=\"auto\">Bock said that in\u00a0a commitment to transparency,\u00a0she has\u00a0made\u00a0<\/span><a href=\"https:\/\/github.com\/beabock\/biobert_dualsolo\"><span data-contrast=\"none\">all the code and data available for free online<\/span><\/a><span data-contrast=\"auto\">, allowing\u00a0other scientists to build upon\u00a0her\u00a0work\u00a0and\u00a0track traits in other organisms, like insects or plants.<\/span><span data-ccp-props=\"{&quot;335559738&quot;:180,&quot;335559739&quot;:180}\">\u00a0<\/span><\/p>\n<p><span data-contrast=\"auto\">While\u00a0Bock\u2019s\u00a0study focused on a small group\u00a0of\u00a0papers as\u00a0a proof-of-concept, it opens the door for much larger projects. Future versions of the tool could predict how a\u00a0fungus\u2019s\u00a0behavior might change under specific environmental conditions, such as drought or extreme heat.<\/span><span data-ccp-props=\"{&quot;335559738&quot;:180,&quot;335559739&quot;:180}\">\u00a0<\/span><\/p>\n<p><span data-contrast=\"auto\">\u201cAs fungal trait databases continue to grow in importance for biodiversity assessments,\u00a0automated text mining offers a path toward more efficient, consistent and comprehensive trait annotation,\u201d\u00a0Bock said.<\/span><span data-ccp-props=\"{&quot;335559738&quot;:180,&quot;335559739&quot;:180}\">\u00a0<\/span><\/p>\n<p><span data-ccp-props=\"{&quot;335559738&quot;:180,&quot;335559739&quot;:180}\">\u00a0<\/span><br \/>\n<span data-ccp-props=\"{}\"><img loading=\"lazy\" decoding=\"async\" class=\"alignleft wp-image-56007\" src=\"http:\/\/in.nau.edu\/news\/wordpresst\/uploads\/sites\/153\/wp-content\/uploads\/2019\/06\/NAU_primary-281_3514.png\" alt=\"Northern Arizona University Logo\" width=\"134\" height=\"95\" srcset=\"https:\/\/in.nau.edu\/wp-content\/uploads\/sites\/402\/2019\/06\/NAU_primary-281_3514.png 905w, https:\/\/in.nau.edu\/wp-content\/uploads\/sites\/402\/2019\/06\/NAU_primary-281_3514-300x213.png 300w, https:\/\/in.nau.edu\/wp-content\/uploads\/sites\/402\/2019\/06\/NAU_primary-281_3514-768x546.png 768w, https:\/\/in.nau.edu\/wp-content\/uploads\/sites\/402\/2019\/06\/NAU_primary-281_3514-600x426.png 600w\" sizes=\"auto, (max-width: 134px) 100vw, 134px\" \/><\/span><\/p>\n<p><span data-ccp-props=\"{}\"><br \/>\nJill Kimball | NAU Communications<br \/>\n(928) 523-2282 | <a href=\"mailto:jill.kimball@nau.edu\">jill.kimball@nau.edu<\/a><\/span><\/p>\n","protected":false},"excerpt":{"rendered":"<p><a class=\"search-results-excerpt-link\" href=\"https:\/\/in.nau.edu\/news\/fungi-and-ai-study\/\">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\u00a0don\u2019t\u00a0stick to just one job; they can switch lifestyles depending on their environment.\u00a0\u00a0 Understanding this flexibility is vital for predicting how forests and farms will react to climate change. Unfortunately,\u00a0the&hellip;<\/a><\/p>\n","protected":false},"author":95,"featured_media":76913,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[11],"tags":[],"class_list":["post-76912","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-research-academics"],"acf":[],"_links":{"self":[{"href":"https:\/\/in.nau.edu\/news\/wp-json\/wp\/v2\/posts\/76912","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/in.nau.edu\/news\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/in.nau.edu\/news\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/in.nau.edu\/news\/wp-json\/wp\/v2\/users\/95"}],"replies":[{"embeddable":true,"href":"https:\/\/in.nau.edu\/news\/wp-json\/wp\/v2\/comments?post=76912"}],"version-history":[{"count":0,"href":"https:\/\/in.nau.edu\/news\/wp-json\/wp\/v2\/posts\/76912\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/in.nau.edu\/news\/wp-json\/wp\/v2\/media\/76913"}],"wp:attachment":[{"href":"https:\/\/in.nau.edu\/news\/wp-json\/wp\/v2\/media?parent=76912"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/in.nau.edu\/news\/wp-json\/wp\/v2\/categories?post=76912"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/in.nau.edu\/news\/wp-json\/wp\/v2\/tags?post=76912"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}