ArticleDie Naturwissenschaften2026
Predicting the absence of World Health Organization fungal priority pathogens in agricultural soils using machine learning and ITS metabarcoding.
Article in Die Naturwissenschaften, 2026. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Not yet cited in PubMed.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
0 citing papers in PubMed.
No citing paper in PubMed yet.
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
3 authors.
Funding
Abstract
Environmental fungal pathogens relevant to human and animal health pose significant risks, particularly in regions with intensive farming and climate variability. Several taxa detected in Thailand's clinical and environmental samples, such as Candida tropicalis, Talaromyces marneffei, and Mucor spp., are listed in the World Health Organization (WHO) Fungal Priority Pathogen List (FPPL). This study integrated next-generation sequencing (NGS) metabarcoding and decision tree models to characterize fungal communities and identify environmental conditions associated with pathogen absence across 18 provinces of Northeast Thailand. Soil samples (n = 121) from rice, cassava, sugarcane, and rubber tree fields were collected in 2022 and analyzed for eight environmental parameters: drought level, soil water content, organic matter, nitrogen, phosphorus, potassium, soil temperature, and soil pH. Decision tree models were trained on these samples to derive absence conditions for nine WHO FPPL taxa, which were validated using an independent test dataset (n = 12) collected in 2025. Absence conditions for Falciformispora senegalensis, Mucor spp., and Talaromyces marneffei achieved perfect precision and recall in the test dataset. Precision is the proportion of samples predicted as absent that are truly absent, and recall is the proportion of truly absent samples correctly identified by the condition. Candida tropicalis, Curvularia lunata, and Lichtheimia spp. showed perfect precision but moderate recall (0.42-0.75). Conditions for Scedosporium spp. and Acremonium spp. did not generalize due to limited representation in the training data. Over three years, the fungal community became less diverse and more taxonomically consolidated, coinciding with drought intensification and nutrient shifts. Overall, combining metabarcoding with decision tree models provides a practical framework for identifying low-risk soils and supporting agricultural practices and public health surveillance.
Indexed as
Identifiers
42479206What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.