AI Science Tracker
EN

Random forests nominate fungal taxa associated with leaf-warming samples

University of Miami; University of Toronto; University of Waikato; North Carolina State University · 6 Nov 2026 · biology

Discovery

Random forests nominate fungal taxa associated with leaf-warming samples

Source check: Source checked. Not independent scientific confirmation.

Finding: An exploratory random forest identified three fungal sequence variants associated with warmed versus control leaf samples across six Florida plant species. Kondoa and Zasmidium candidates had lower mean counts in warmed samples, while a Cystobasidiomycetes variant had higher counts. Overall community richness and composition tests were null. These descriptive candidate associations do not establish differential abundance, causal taxon-specific warming effects or host-independent generalization.

Technology: Random forest; Boruta feature selection; naive Bayes taxonomy classifier

Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.

AI contribution
A naive-Bayes classifier assigns sequence taxonomy; random forests and Boruta select three taxa informative for warming-treatment classification.
Test and result
Exploratory RF/Boruta feature selection and OOB classification on measured leaf-community counts, alongside paired conventional community tests.
Limitation / still unknown
Taxon-specific differential abundance, blocked host/plant robustness, causal effects and functional host/ecosystem consequences remain unestablished.
Evidence sources and annotation context

Evidence context (descriptions follow the cited sources; test type is a catalog classification):

Evidence sources: https://pmc.ncbi.nlm.nih.gov/articles/PMC13743924/

Source checked · editorial details

The source page was checked against this entry. Independent confirmation is not assessed by this label.

Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.

Review date: 21 Nov 2026. Review scope: Primary full relevant taxonomy/classifier Methods, experimental Results and limitations, exact article-meta identity, current PubMed notice relationships and catalog identity checked..

No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.

Editorial assessment: Impact 2/5 · Validation 2/5 · Novelty 2/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.

Open in the full catalog for filters, charts and related discoveries. Browse biology discoveries.