Decrypting the complex phenotyping traits of plants by machine learning DOI Creative Commons

Jan Zdrazil,

Lingping Kong, Pavel Klimeš

et al.

bioRxiv (Cold Spring Harbor Laboratory), Journal Year: 2024, Volume and Issue: unknown

Published: Nov. 15, 2024

Abstract Phenotypes, defining an organism’s behaviour and physical attributes, arise from the complex, dynamic interplay of genetics, development, environment, whose interactions make it enormously challenging to forecast future phenotypic traits a plant at given moment. This work reports AMULET, modular approach that uses imaging-based high-throughput phenotyping machine learning predict morphological physiological hours days before they are visible. AMULET streamlines process by integrating detection, prediction, segmentation, data analysis, enhancing workflow efficiency reducing time. The models used over 30,000 plants, using Arabidopsis thaliana-Pseudomonas syringae pathosystem. also demonstrated its adaptability accurately detecting predicting phenotypes in vitro potato plants after minimal fine-tuning with small dataset. general implemented through will improve breeding programs agricultural management enabling pre-emptive interventions optimising health productivity.

Language: Английский

Next-generation high-throughput phenotyping with trait prediction through adaptable multi-task computational intelligence DOI Creative Commons

Jan Zdrazil,

Lingping Kong, Pavel Klimeš

et al.

Computers and Electronics in Agriculture, Journal Year: 2025, Volume and Issue: 235, P. 110390 - 110390

Published: April 12, 2025

Language: Английский

Citations

0
Leveraging multi-omics tools to comprehend responses and tolerance mechanisms of heavy metals in crop plants DOI
Sidra Charagh,

Hong Wang,

Jingxin Wang

et al.

Functional & Integrative Genomics, Journal Year: 2024, Volume and Issue: 24(6)

Published: Oct. 23, 2024

Language: Английский

Citations

2
Genotype-specific responses to in vitro drought stress in myrtle (Myrtus communis L.): integrating machine learning techniques DOI Creative Commons

Ümit Bektaş,

Musab A. Isak, Taner Bozkurt

et al.

PeerJ, Journal Year: 2024, Volume and Issue: 12, P. e18081 - e18081

Published: Oct. 7, 2024

Myrtle (

Language: Английский

Citations

0
Decrypting the complex phenotyping traits of plants by machine learning DOI Creative Commons

Jan Zdrazil,

Lingping Kong, Pavel Klimeš

et al.

bioRxiv (Cold Spring Harbor Laboratory), Journal Year: 2024, Volume and Issue: unknown

Published: Nov. 15, 2024

Abstract Phenotypes, defining an organism’s behaviour and physical attributes, arise from the complex, dynamic interplay of genetics, development, environment, whose interactions make it enormously challenging to forecast future phenotypic traits a plant at given moment. This work reports AMULET, modular approach that uses imaging-based high-throughput phenotyping machine learning predict morphological physiological hours days before they are visible. AMULET streamlines process by integrating detection, prediction, segmentation, data analysis, enhancing workflow efficiency reducing time. The models used over 30,000 plants, using Arabidopsis thaliana-Pseudomonas syringae pathosystem. also demonstrated its adaptability accurately detecting predicting phenotypes in vitro potato plants after minimal fine-tuning with small dataset. general implemented through will improve breeding programs agricultural management enabling pre-emptive interventions optimising health productivity.

Language: Английский

Citations

0