Serpell, E. | bioRxiv Science

bioRxiv2026

MycorrhizaFinder: an efficient machine learning tool to quantify endomycorrhizal colonisation of real-world roots

AbstractO_ST_ABSBackground and aimsC_ST_ABSRoot colonisation by endomycorrhizal fungi has long been one of the most widely used metrics in mycorrhizal studies. However, due to the significant time required to assess colonisation using traditional microscope techniques, studies of colonisation at large scales are impractical. AI-powered approaches may increase output and facilitate ecosystem assessments. MethodsWe trained an AI-powered tool (MycorrhizaFinder) on field roots from diverse grasslands and heathlands hosting common Northern European plants with a range of arbuscular (AM) and ericoid mycorrhizal (ErM) fungal structures, and dark septate endophytes (DSE), also common in field-sourced roots. We incorporated a user-customized confidence threshold to encourage the user to engage with inevitable morphological ambiguities, in e.g. ErM and DSE. A Macro F1 statistic was used to assess the tools development. ResultsWe provide a sample workflow from root processing and microscope slide scanning to semi-automated model training and performance evaluation. Without human supervision, our automated baseline Macro F1 is 66% for arbuscular and at 57% for ericoid mycorrhizal colonisation assessment. ConclusionMycorrhizaFinder is user friendly, requires no programming skills and offers flexibility for advanced agronomists or ecologists who wish to train the tool using their own labelled mycorrhizal root datasets, including images acquired from different instruments or staining protocols. This adaptability allows users to customize the model for specific ecosystems or experimental designs. Leveraged with molecular identification and/or functional assessment of fungi, MycorrhizaFinder could support scalable and repeatable monitoring across ecosystems to assess mycorrhizal status and track land-use changes over time.

ecology↗

bioRxiv2023

Trials and tribulations of Neotropical plant taxonomy: pace of tree species description

O_LIOne of the main aspects of taxonomic research is the description of new species. Identifying how to describe new species more efficiently is key to completing the inventory of the Neotropical flora in an era of massive biodiversity loss. C_LIO_LIHere we calculate the interval between first specimen collection and new species publication for a group of 2126 Neotropical trees, and discuss the historical context surrounding specimen collection and new species publication events. C_LIO_LIOur results reveal that on average, it takes almost 16 years from specimen collection to publication of a new Neotropical tree species, which is considerably shorter than previous estimates for other tropical groups. The central Andes is the region that had the longest average time lags, while the Choco had the shortest. Peru had the longest average time lags by country, while Haiti had the shortest. The average time lags increased until the early 1900s, when a decrease was observed, with the shortest lags between 1941 to 1960. C_LIO_LIWe found that the majority of the species described more rapidly are from plants collected and described by the same researcher. We demonstrate how political instability and conflict can delay or impede the completion of research initiatives in the region. We argue that enhancing international collaboration and training opportunities in Latin American countries, as well as ensuring safe plant collection campaigns, are critical to complete the inventory of the Neotropical flora. C_LI Societal Impact StatementThis study aims to answer the question of how long it takes to describe a new species of tree in the Neotropics by calculating the time elapsed from collection of the first specimen to the publication of a new species. Given the current unprecedented concerns for global biodiversity loss, it is critical to identify best practices for describing new species more efficiently so we can complete the inventory of the Neotropical flora and implement appropriate conservation strategies in a timely manner.

plant biology↗