Automated discretization of ‘transpiration restriction to increasing VPD’ features from outdoors high-throughput phenotyping data

Kar, S and Tanaka, R and Korbu, L B and Kholová, J and Iwata, H and Durbha, S S and Adinarayana, J and Vadez, V (2020) Automated discretization of ‘transpiration restriction to increasing VPD’ features from outdoors high-throughput phenotyping data. Plant Methods (TSI), 16 (1). pp. 1-20. ISSN 1746-4811

PDF - Published Version Download (7MB)

Abstract

Abstract Background: Restricting transpiration under high vapor pressure deficit (VPD) is a promising water-saving trait for drought adaptation. However, it is often measured under controlled conditions and at very low throughput, unsuitable for breeding. A few high-throughput phenotyping (HTP) studies exist, and have considered only maximum transpiration rate in analyzing genotypic differences in this trait. Further, no study has precisely identified the VPD breakpoints where genotypes restrict transpiration under natural conditions. Therefore, outdoors HTP data (15 min frequency) of a chickpea population were used to automate the generation of smooth transpiration profiles, extract informative features of the transpiration response to VPD for optimal genotypic discretization, identify VPD breakpoints, and compare genotypes. Results: Fifteen biologically relevant features were extracted from the transpiration rate profiles derived from load cells data. Genotypes were clustered (C1, C2, C3) and 6 most important features (with heritability > 0.5) were selected using unsupervised Random Forest. All the wild relatives were found in C1, while C2 and C3 mostly comprised high TE and low TE lines, respectively. Assessment of the distinct p-value groups within each selected feature revealed highest genotypic variation for the feature representing transpiration response to high VPD condition. Sensitivity analysis on a multi-output neural network model (with R of 0.931, 0.944, 0.953 for C1, C2, C3, respectively) found C1 with the highest water saving ability, that restricted transpiration at relatively low VPD levels, 56% (i.e. 3.52 kPa) or 62% (i.e. 3.90 kPa), depending whether the influence of other environmental variables was minimum or maximum. Also, VPD appeared to have the most striking influence on the transpiration response independently of other environment variable, whereas light, temperature, and relative humidity alone had little/no effect. Conclusion: Through this study, we present a novel approach to identifying genotypes with drought-tolerance potential, which overcomes the challenges in HTP of the water-saving trait. The six selected features served as proxy phenotypes for reliable genotypic discretization. The wild chickpeas were found to limit water-loss faster than the water-profligate cultivated ones. Such an analytic approach can be directly used for prescriptive breeding applications, applied to other traits, and help expedite maximized information extraction from HTP data.

Item Type:	Article
Divisions:	Research Program : Innovation Systems for the Drylands (ISD)
CRP:	UNSPECIFIED
Uncontrolled Keywords:	High throughput phenotyping, Transpiration rate, Vapor pressure deficit, Time series, Machine learning, Feature selection, Unsupervised random-forest, Gini index, Neural network, Sensitivity analysis
Subjects:	Others > Crop Physiology
Depositing User:	Mr Arun S
Date Deposited:	13 Nov 2020 15:10
Last Modified:	13 Nov 2020 15:10
URI:	http://oar.icrisat.org/id/eprint/11648
Official URL:	https://doi.org/10.1186/s13007-020-00680-8
Projects:	UNSPECIFIED
Funders:	UNSPECIFIED
Acknowledgement:	The senior author was partially supported by the grant from the Bill and Melinda Gates Foundation to develop this framework (“Sorghum Genomics Toolbox” project). The write-up of the paper took place in the scope of the Make Our Planet Great Again (MOPGA) ICARUS project (Improve Crops in Arid Regions and future climates) funded by the Agence Nationale de la Recherche (ANR, grant ANR-17-MPGA-0011). The authors would like to thank ICRISAT, Patancheru, India, with special thanks to Ms. Rekha Baddam, for providing chickpea reference dataset from the LeasyScan, HTP platform, Dr. James D. Burridge, Institute de Recherche pour le Dèveloppment (IRD) for his constructive suggestions in editing, and the DST-JST joint lab research initiative, DSFS for extending support in carrying out this work.
Links:	Google Scholar

View Statistics

Actions (login required)

View Item