Skip to main content
Log in

Profiling of Fusarium head blight resistance QTL haplotypes through molecular markers, genotyping-by-sequencing, and machine learning

  • Original Article
  • Published:
Theoretical and Applied Genetics Aims and scope Submit manuscript

Abstract

Key message

Marker-assisted selection is important for cultivar development. We propose a system where a training population genotyped for QTL and genome-wide markers may predict QTL haplotypes in early development germplasm.

Abstract

Breeders screen germplasm with molecular markers to identify and select individuals that have desirable haplotypes. The objective of this research was to investigate whether QTL haplotypes can be accurately predicted using SNPs derived by genotyping-by-sequencing (GBS). In the SunGrains program during 2020 (SG20) and 2021 (SG21), 1,536 and 2,352 lines submitted for GBS were genotyped with markers linked to the Fusarium head blight QTL: Qfhb.nc-1A, Qfhb.vt-1B, Fhb1, and Qfhb.nc-4A. In parallel, data were compiled from the 2011–2020 Southern Uniform Winter Wheat Scab Nursery (SUWWSN), which had been screened for the same QTL, sequenced via GBS, and phenotyped for: visual Fusarium severity rating (SEV), percent Fusarium damaged kernels (FDK), deoxynivalenol content (DON), plant height, and heading date. Three machine learning models were evaluated: random forest, k-nearest neighbors, and gradient boosting machine. Data were randomly partitioned into training–testing splits. The QTL haplotype and 100 most correlated GBS SNPs were used for training and tuning of each model. Trained machine learning models were used to predict QTL haplotypes in the testing partition of SG20, SG21, and the total SUWWSN. Mean disease ratings for the observed and predicted QTL haplotypes were compared in the SUWWSN. For all models trained using the SG20 and SG21, the observed Fhb1 haplotype estimated group means for SEV, FDK, DON, plant height, and heading date in the SUWWSN were not significantly different from any of the predicted Fhb1 calls. This indicated that machine learning may be utilized in breeding programs to accurately predict QTL haplotypes in earlier generations.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

Similar content being viewed by others

Data availability

KASP and genotyping-by-sequencing data for SunGrains and genotyping-by-sequencing data for the Southern Uniform Winter Wheat Nursery lines are unavailable. Phenotypic data for the Southern Uniform Winter Wheat Scab Nursery are freely available at < scabusa.org > . Haplotype information related to resistance QTL used in the current study for the Southern Uniform Winter Wheat Nursery is freely available at < https://www.ars.usda.gov/southeast-area/raleigh-nc/plant-science-research/docs/small-grains-genotyping-laboratory/regional-nursery-marker-reports/ > .

Code availability

All code and raw output of code used in the current study may be found at < https://github.com/zjwinn/Profiling-of-FHB-Resistance-QTL-Haplotypes-Through-MM-GBG-and-ML > .

References

Download references

Funding

The research conducted in this study was directly supported by funds from the North Carolina Small Grains Growers Association and indirectly through the United States Wheat and Barley Scab Initiative (USWBSI) over time in phenotypic evaluation of the SUWWSN and genotyping of lines in the SG20, SG21, and SUWWSN panels.

Author information

Authors and Affiliations

Authors

Contributions

J.L. and Z.J.W. were responsible for conceptualization and methodology; Z.J.W. contributed to software, validation, writing and preparing the original draft, and visualization; Z.J.W. and B.W. carried out the formal analysis; J.L., Z.J.W., and B.W. conducted investigation; Z.J.W., J.L., G.B.G., R.E.B., M.M., J.J., S.H., A.B., R.E.M., R.S., and J.P.M. performed data curation; Z.J.W., J.L., B.W., G.B.G., R.E.B., M.M., J.J., S.H., A.B., R.E.M., R.S., and J.P.M. wrote, reviewed, and edited the manuscript; J.P.M., G.B.G., and J.L. supervised the study; J.P.M. was involved in project administration; and J.P.M. and G.B.G. acquired the funding.

Corresponding author

Correspondence to Zachary J. Winn.

Ethics declarations

Conflict of interest

The author claims no conflict of interest.

Additional information

Communicated by Jochen Reif.

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary Information

Below is the link to the electronic supplementary material.

Supplementary file1 (XLSX 720 KB)

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Winn, Z.J., Lyerly, J., Ward, B. et al. Profiling of Fusarium head blight resistance QTL haplotypes through molecular markers, genotyping-by-sequencing, and machine learning. Theor Appl Genet 135, 3177–3194 (2022). https://doi.org/10.1007/s00122-022-04178-w

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00122-022-04178-w

Navigation