Machine learning provides specific detection of salt and drought stresses in cucumber based on miRNA characteristics.

Abstract

Background Specific detection of the type and severity of plant abiotic stresses helps prevent yield loss by considering timely actions. This study introduces a novel method to detect the type and severity of stress in cucumber plants under salinity and drought conditions. Various features, i.e., morphological (image textural features), physiological/biochemical (relative water content, chlorophyll, catalase activity, anthocyanins, phenol content, and proline), as well as miRNA characteristics (the concentration of miRNA-156a, miRNA-166i, miRNA-399g, and miRNA-477b) were extracted from plant leaves, and machine learning methods were used to predict the type and severity of stress by having these features. Support vector machine (SVM) with parameters optimized by genetic algorithm (GA) and particle swarm optimization (PSO) was used for machine learning. Results The coefficient of determination of predicting the stress type and severity in plants under both stresses was 0.61, 0.82, and 0.99 using morphological, physiological/biochemical, and miRNA characteristics, respectively. This reveals machine learning methods optimized by metaheuristic optimization techniques can provide specific detection of salt and drought stresses in cucumber plants based on miRNA characteristics. Among the study miRNAs, miRNA-477b and miRNA-399g had the highest and lowest contribution to salt and drought stresses, respectively. Conclusions Comapred to conventional plant traits, miRNAs are more reliable features for providing us with valuable information about plant abiotic diseases at early stages. Using an electrochemical miRNA biosensor similar to one used in this work to measure the miRNA concentration in plant leaves and using a machine learning algorithm such as SVM enable farmers to detect the salt and drought stress at early stages in cucumber plants with very high accuracy.

Plant phenotyping relevance

キュウリ葉から抽出した画像・生理・miRNA特徴を用いて、機械学習で塩・乾燥ストレスの種類と重症度を推定する手法が研究の中心であり、植物の状態を直接評価するフェノタイピング手法に該当する。

Code and data availability

The paper's cucumber salt/drought stress phenotype dataset (morphological image-texture, physiological/biochemical, and miRNA concentration measurements, 240 samples) is described as raw data in Additional file 1: Table S1, but the Data Availability Statement says datasets are available only from the corresponding作者 on

No evidence-backed public reproduction asset is currently recorded.