Machine learning‐based identification of general transcriptional predictors for plant disease
- 21 November 2024
- journal article
- research article
- Published by Wiley in New Phytologist
- Vol. 245 (2) , 785-806
Abstract
Summary: This study investigated the generalizability of Arabidopsis thaliana immune responses across diverse pathogens, including Botrytis cinerea, Sclerotinia sclerotiorum, and Pseudomonas syringae, using a data‐driven, machine learning approach. Machine learning models were trained to predict disease development from early transcriptional responses. Feature selection techniques based on network science and topology were used to train models employing only a fraction of the transcriptome. Machine learning models trained on one pathosystem where then validated by predicting disease development in new pathosystems. The identified feature selection gene sets were enriched for pathways related to biotic, abiotic, and stress responses, though the specific genes involved differed between feature sets. This suggests common immune responses to diverse pathogens that operate via different gene sets. The study demonstrates that machine learning can uncover both established and novel components of the plant's immune response, offering insights into disease resistance mechanisms. These predictive models highlight the potential to advance our understanding of multigenic outcomes in plant immunity and can be further refined for applications in disease prediction.Keywords
Funding Information
- Division of Computing and Communication Foundations (1837131)
- Division of Molecular and Cellular Biosciences (1936775, 1936800)
- Army Research Office (W911NF‐23‐1‐0111)
- Division of Computer and Network Systems (1453860, 1932620)
- Defense Advanced Research Projects Agency (N66001‐17‐1‐4044)
- Division of Civil, Mechanical and Manufacturing Innovation (1936624)
- National Institute of Food and Agriculture (2018‐67013‐28492)
This publication has 98 references indexed in Scilit:
- Direct inhibition of phosphate transport by immune signaling in ArabidopsisCurrent Biology, 2022
- A phosphate starvation response-centered network regulates mycorrhizal symbiosisCell, 2021
- Comparative analysis of image classification algorithms based on traditional machine learning and deep learningPattern Recognition Letters, 2021
- Transcriptional Regulation of Pattern-Triggered Immunity in PlantsCell Host & Microbe, 2016
- The arabidopsis information resource: Making and mining the “gold standard” annotated reference plant genomeGenesis, 2015
- Mechanisms Underlying Robustness and Tunability in a Plant Immune Signaling NetworkCell Host & Microbe, 2014
- Measurement of mRNA abundance using RNA-seq data: RPKM measure is inconsistent among samplesTheory in Biosciences, 2012
- The Arabidopsis NPR1 Protein Is a Receptor for the Plant Defense Hormone Salicylic AcidCell Reports, 2012
- Fluorescence Imaging-Based Screen Identifies ARF GEF Component of Early Endosomal TraffickingCurrent Biology, 2009
- Three QTLs for Botrytis cinerea resistance in tomatoTheoretical and Applied Genetics, 2006