Enhancing Prediction Accuracy of Foliar Essential Oil Content, Growth, and Stem Quality in Using Multi-trait Deep Learning Models

Overview

Journal Front Plant Sci

Date 2024 Oct 25

PMID 39450087

Authors

Daniel Mieres-Castro

Carlos Maldonado

Freddy Mora-Poblete

Affiliations

Soon will be listed here.

Abstract

Labill., is a recognized multipurpose tree, which stands out not only for the valuable qualities of its wood but also for the medicinal applications of the essential oil extracted from its leaves. In this study, we implemented an integrated strategy comprising genomic and phenomic approaches to predict foliar essential oil content, stem quality, and growth-related traits within a 9-year-old breeding population of . The strategy involved evaluating Uni/Multi-trait deep learning (DL) models by incorporating genomic data related to single nucleotide polymorphisms (SNPs) and haplotypes, as well as the phenomic data from leaf near-infrared (NIR) spectroscopy. Our results showed that essential oil content (oil yield) ranged from 0.01 to 1.69% v/fw and had no significant correlation with any growth-related traits. This suggests that selection solely based on growth-related traits did n The emphases (colored text) from revisions were removed throughout the article. Confirm that this change is fine. ot influence the essential oil content. Genomic heritability estimates ranged from 0.25 (diameter at breast height (DBH) and oil yield) to 0.71 (DBH and stem straightness (ST)), while pedigree-based heritability exhibited a broader range, from 0.05 to 0.88. Notably, oil yield was found to be moderate to highly heritable, with genomic values ranging from 0.25 to 0.60, alongside a pedigree-based estimate of 0.48. The DL prediction models consistently achieved higher prediction accuracy (PA) values with a Multi-trait approach for most traits analyzed, including oil yield (0.699), tree height (0.772), DBH (0.745), slenderness coefficient (0.616), stem volume (0.757), and ST (0.764). The Uni-trait approach achieved superior PA values solely for branching quality (0.861). NIR spectral absorbance was the best omics data for CNN or MLP models with a Multi-trait approach. These results highlight considerable genetic variation within the progeny trial, particularly regarding oil production. Our results contribute significantly to understanding omics-assisted deep learning models as a breeding strategy to improve growth-related traits and optimize essential oil production in this species.

References

Maldonado C, Mora-Poblete F, Contreras-Soto R, Ahmar S, Chen J, Teixeira do Amaral Junior A . Genome-Wide Prediction of Complex Traits in Two Outcrossing Plant Species Through Deep Learning and Bayesian Regularized Neural Network. Front Plant Sci. 2020; 11:593897. PMC: 7728740. DOI: 10.3389/fpls.2020.593897. View

Rincent R, Charpentier J, Faivre-Rampant P, Paux E, Le Gouis J, Bastien C . Phenomic Selection Is a Low-Cost and High-Throughput Method Based on Indirect Predictions: Proof of Concept on Wheat and Poplar. G3 (Bethesda). 2018; 8(12):3961-3972. PMC: 6288839. DOI: 10.1534/g3.118.200760. View

Drake J, Aspinwall M, Pfautsch S, Rymer P, Reich P, Smith R . The capacity to cope with climate warming declines from temperate to tropical latitudes in two widely distributed Eucalyptus species. Glob Chang Biol. 2014; 21(1):459-72. DOI: 10.1111/gcb.12729. View

Jung M, Keller B, Roth M, Aranzana M, Auwerkerken A, Guerra W . Genetic architecture and genomic predictive ability of apple quantitative traits across environments. Hortic Res. 2022; . PMC: 8976694. DOI: 10.1093/hr/uhac028. View

Ballesta P, Ahmar S, Lobos G, Mieres-Castro D, Jimenez-Aspee F, Mora-Poblete F . Heritable Variation of Foliar Spectral Reflectance Enhances Genomic Prediction of Hydrogen Cyanide in a Genetically Structured Population of . Front Plant Sci. 2022; 13:871943. PMC: 9008590. DOI: 10.3389/fpls.2022.871943. View

Kent M, Fonseca J, Klein P, Klein R, Hayes C, Rooney W . Use of genomic prediction to screen sorghum B-lines in hybrid testcrosses. Plant Genome. 2023; 16(3):e20369. DOI: 10.1002/tpg2.20369. View

Parveen R, Kumar M, Swapnil , Singh D, Shahani M, Imam Z . Understanding the genomic selection for crop improvement: current progress and future prospects. Mol Genet Genomics. 2023; 298(4):813-821. DOI: 10.1007/s00438-023-02026-0. View

Valenzuela C, Ballesta P, Ahmar S, Fiaz S, Heidari P, Maldonado C . Haplotype- and SNP-Based GWAS for Growth and Wood Quality Traits in Trees under Arid Conditions. Plants (Basel). 2021; 10(1). PMC: 7828368. DOI: 10.3390/plants10010148. View

Aumond Jr M, de Araujo Jr A, de Oliveira Junkes C, de Almeida M, Matsuura H, de Costa F . Events Associated with Early Age-Related Decline in Adventitious Rooting Competence of Labill. Front Plant Sci. 2017; 8:1734. PMC: 5641372. DOI: 10.3389/fpls.2017.01734. View

10.

Tyagi A, Bukvicki D, Gottardi D, Tabanelli G, Montanari C, Malik A . Eucalyptus essential oil as a natural food preservative: in vivo and in vitro antiyeast potential. Biomed Res Int. 2014; 2014:969143. PMC: 4142273. DOI: 10.1155/2014/969143. View

11.

Ballesta P, Maldonado C, Perez-Rodriguez P, Mora F . SNP and Haplotype-Based Genomic Selection of Quantitative Traits in . Plants (Basel). 2019; 8(9). PMC: 6783840. DOI: 10.3390/plants8090331. View

12.

Pedrotti C, Marcon A, Sergio , Echeverrigaray L, Ribeiro R, Schwambach J . Essential oil as sustainable alternative for diseases management of grapes in postharvest and in vineyard and its influence on wine. J Environ Sci Health B. 2020; 56(1):73-81. DOI: 10.1080/03601234.2020.1838827. View

13.

Hamed A, Awad A, Abdel-Mobdy A, Alzahrani A, Salamatullah A . Buffalo Yogurt Fortified with Eucalyptus () and Myrrh () Essential Oils: New Insights into the Functional Properties and Extended Shelf Life. Molecules. 2021; 26(22). PMC: 8625777. DOI: 10.3390/molecules26226853. View

14.

Kaler A, Purcell L, Beissinger T, Gillman J . Genomic prediction models for traits differing in heritability for soybean, rice, and maize. BMC Plant Biol. 2022; 22(1):87. PMC: 8881851. DOI: 10.1186/s12870-022-03479-y. View

15.

Perez-Enciso M, Zingaretti L . A Guide for Using Deep Learning for Complex Trait Genomic Prediction. Genes (Basel). 2019; 10(7). PMC: 6678200. DOI: 10.3390/genes10070553. View

16.

Ballesta P, Bush D, Silva F, Mora F . Genomic Predictions Using Low-Density SNP Markers, Pedigree and GWAS Information: A Case Study with the Non-Model Species . Plants (Basel). 2020; 9(1). PMC: 7020392. DOI: 10.3390/plants9010099. View

17.

Mora-Poblete F, Ballesta P, Lobos G, Molina-Montenegro M, Gleadow R, Ahmar S . Genome-wide association study of cyanogenic glycosides, proline, sugars, and pigments in Eucalyptus cladocalyx after 18 consecutive dry summers. Physiol Plant. 2021; 172(3):1550-1569. DOI: 10.1111/ppl.13349. View

18.

Cui Z, Dong H, Zhang A, Ruan Y, He Y, Zhang Z . Assessment of the Potential for Genomic Selection To Improve Husk Traits in Maize. G3 (Bethesda). 2020; 10(10):3741-3749. PMC: 7534435. DOI: 10.1534/g3.120.401600. View

19.

Kainer D, Padovan A, Degenhardt J, Krause S, Mondal P, Foley W . High marker density GWAS provides novel insights into the genomic architecture of terpene oil yield in Eucalyptus. New Phytol. 2019; 223(3):1489-1504. DOI: 10.1111/nph.15887. View

20.

Paiva J, Prat E, Vautrin S, Santos M, San-Clemente H, Brommonschenkel S . Advancing Eucalyptus genomics: identification and sequencing of lignin biosynthesis genes from deep-coverage BAC libraries. BMC Genomics. 2011; 12:137. PMC: 3060884. DOI: 10.1186/1471-2164-12-137. View