MycorrhizaFinder: a user-friendly machine-learning tool to quantify endomycorrhizal colonisation of nursery and field roots.
9 affiliations
- 1Ecosystem Stewardship, Royal Botanic Gardens, Kew, TW9 3DS, England. [email protected].
- 2Ecosystem Stewardship, Royal Botanic Gardens, Kew, TW9 3DS, England.
- 3Natural History Museum, London, SW7 5BD, England.
- 4Imperial College London, Ascot, SL57PY, England.
- 5Institut Sophia Agrobiotech, UMR INRAE 1355, Université Côte d'Azur, Sophia Antipolis, Provence-Alpes-Côte d'Azur, 06103, France.
- 6Sainsbury Laboratory, University of Cambridge, Cambridge, CB2 1LR, England.
- 7D-fine GmbH, 60313, Frankfurt, Germany.
- 8Ecosystem Stewardship, Royal Botanic Gardens, Kew, TW9 3DS, England. [email protected].
- 9Institut Botànic de Barcelona (IBB), CSIC-CMCNB, Barcelona, 08038, Spain. [email protected].
Abstract
Root colonisation by endomycorrhizal fungi has long been a widely used metric in mycorrhizal studies. However, due to the significant time required to assess colonisation using traditional microscopy techniques, studies of colonisation at large scales are impractical. Machine-learning-based approaches may increase output and facilitate ecosystem assessments. We trained a machine-learning-based tool (MycorrhizaFinder) on 42 field roots (132 unique 1 cm sections, with > 100,000 tiles) and validated on a further 37 sections from grasslands and heathlands hosting common Northern European plants with 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 engagement with morphological ambiguities, in e.g. ErM and DSE. A Macro F₁ statistic was used to assess the tool's development performance. We provide a sample workflow from root processing and microscope slide scanning to semi-automated model training and performance evaluation. Our model performance combining all classes, the Macro F₁, is conservatively 66% for arbuscular and 57% for ericoid mycorrhizal colonisation assessment. MycorrhizaFinder is user-friendly, requires no programming skills and offers flexibility for advanced agronomists or ecologists 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 traits of fungi (e.g. arbuscules), MycorrhizaFinder supports scalable and repeatable nursery experiments and monitoring across ecosystems to assess mycorrhizal status and track land-use changes over time.
Related
- Deep learning models detect neuromuscular disease and quantify functional impairment from video-derived biomechanics data
- BiomiX 3.0: A user-friendly platform for democratized multi-omics integration with graph-based learning
- Motile bacteria collectively transport soil water during host colonisation
- Microbiota-driven, strain-specific Asaia colonisation modulates mosquito vector competence
- Multimodal imaging reveals surface degradation of voice prosthesis implants resulting from colonisation by polymicrobial biofilms
BibTeX
@article{kowal2026mycorrhizafinder,
title = {{MycorrhizaFinder: a user-friendly machine-learning tool to quantify endomycorrhizal colonisation of nursery and field roots.}},
author = {Jill Kowal and Shaun Buckley and Robin Upham and Adam Kiani and Morgan Rickards and Ella Serpell and Martin I Bidartondo and Edouard Evangelisti and Sebastian Schornack and James Sibbit and Kevin P Treder and Simon Weidinger and Laura M Suz},
journal = {Mycorrhiza},
year = {2026},
month = oct,
doi = {10.1007/s00572-026-01323-x},
url = {https://europepmc.org/article/MED/42909698},
note = {CC BY},
}
RIS
TY - JOUR
TI - MycorrhizaFinder: a user-friendly machine-learning tool to quantify endomycorrhizal colonisation of nursery and field roots.
AU - Jill Kowal
AU - Shaun Buckley
AU - Robin Upham
AU - Adam Kiani
AU - Morgan Rickards
AU - Ella Serpell
AU - Martin I Bidartondo
AU - Edouard Evangelisti
AU - Sebastian Schornack
AU - James Sibbit
AU - Kevin P Treder
AU - Simon Weidinger
AU - Laura M Suz
PY - 2026
DA - 2026/10/23
JO - Mycorrhiza
DO - 10.1007/s00572-026-01323-x
UR - https://europepmc.org/article/MED/42909698
AB - Root colonisation by endomycorrhizal fungi has long been a widely used metric in mycorrhizal studies. However, due to the significant time required to assess colonisation using traditional microscopy techniques, studies of colonisation at large scales are impractical. Machine-learning-based approaches may increase output and facilitate ecosystem assessments. We trained a machine-learning-based tool (MycorrhizaFinder) on 42 field roots (132 unique 1 cm sections, with > 100,000 tiles) and validated on a further 37 sections from grasslands and heathlands hosting common Northern European plants with 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 engagement with morphological ambiguities, in e.g. ErM and DSE. A Macro F₁ statistic was used to assess the tool's development performance. We provide a sample workflow from root processing and microscope slide scanning to semi-automated model training and performance evaluation. Our model performance combining all classes, the Macro F₁, is conservatively 66% for arbuscular and 57% for ericoid mycorrhizal colonisation assessment. MycorrhizaFinder is user-friendly, requires no programming skills and offers flexibility for advanced agronomists or ecologists 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 traits of fungi (e.g. arbuscules), MycorrhizaFinder supports scalable and repeatable nursery experiments and monitoring across ecosystems to assess mycorrhizal status and track land-use changes over time.
SN - 0940-6360
SN - 1432-1890
ER -