2022
DOI: 10.1007/s00253-022-11963-6
|View full text |Cite
|
Sign up to set email alerts
|

Machine learning: its challenges and opportunities in plant system biology

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
21
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
7
2
1

Relationship

1
9

Authors

Journals

citations
Cited by 44 publications
(31 citation statements)
references
References 264 publications
0
21
0
Order By: Relevance
“…The reliability and applicability of machine learning as one of the powerful computational approaches have been recently reviewed in different areas of plant science such as in vitro culture [4], plant breeding [27], stress phenotyping [28], and system biology [29]. Moreover, the accuracy of ANNs has been recently approved for modeling, prediction, and optimization of different in vitro culture systems such as sterilization [20,30], seed germination [5,31], callogenesis [32,33], shoot proliferation [19,[34][35][36], somatic embryogenesis [37,38], androgenesis [39], gene transformation [40,41], and secondary metabolite production [42,43].…”
Section: Discussionmentioning
confidence: 99%
“…The reliability and applicability of machine learning as one of the powerful computational approaches have been recently reviewed in different areas of plant science such as in vitro culture [4], plant breeding [27], stress phenotyping [28], and system biology [29]. Moreover, the accuracy of ANNs has been recently approved for modeling, prediction, and optimization of different in vitro culture systems such as sterilization [20,30], seed germination [5,31], callogenesis [32,33], shoot proliferation [19,[34][35][36], somatic embryogenesis [37,38], androgenesis [39], gene transformation [40,41], and secondary metabolite production [42,43].…”
Section: Discussionmentioning
confidence: 99%
“…This technology allows scientists to precisely “edit” the genes in plants, enabling them to introduce beneficial characteristics into the genome without the need for expensive and time-consuming traditional breeding approaches. Lastly, omics technologies can be used to identify and select gene combinations that confer protective benefits [ 14 ]. For instance, scientists have used transcriptomics to identify gene combinations that confer resistance to pests and diseases, allowing breeders to develop plants better suited to particular stressed environments [ 15 ].…”
Section: Introductionmentioning
confidence: 99%
“…These trained models help the machine to take decisions on different and variable situations based on the learning upon a dataset. Machine learning has been widely used in different fields of plant science such as plant breeding ( van Dijk et al, 2021 ), in vitro culture ( Hesami and Jones 2020 ), stress phenotyping ( Singh et al, 2016 ), stress physiology ( Jafari and Shahsavar 2020 ), plant system biology ( Hesami et al, 2022 ), plant identification ( Grinblat et al, 2016 ), and pathogen identification ( Mishra et al, 2019 ).…”
Section: Introductionmentioning
confidence: 99%