Multi-modal deep learning improves grain yield prediction in wheat breeding by fusing genomics and phenomics
Bioinformatics · 01.06.2023 · 39 (6)
DOI: 10.1093/bioinformatics/btad336 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioinformatics, online erschienen am 23.05.2023. Verfasst von Matteo Togninalli und 12 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biosystems Science and Engineering, ETH Zurich, Basel, Switzerland. Hauptthemen laut MEDLINE: Phenomics, Deep Learning. Die Arbeit wurde bisher 57-mal zitiert (Crossref) und nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science Foundation.
Abstract (Originalsprache)
Motivation Developing new crop varieties with superior performance is highly important to ensure robust and sustainable global food security. The speed of variety development is limited by long field cycles and advanced generation selections in plant breeding programs. While methods to predict yield from genotype or phenotype data have been proposed, improved performance and integrated models are needed. Results We propose a machine learning model that leverages both genotype and phenotype measurements by fusing genetic variants with multiple data sources collected by unmanned aerial systems. We use a deep multiple instance learning framework with an attention mechanism that sheds light on the importance given to each input during prediction, enhancing interpretability. Our model reaches 0.754 ± 0.024 Pearson correlation coefficient when predicting yield in similar environmental conditions; a 34.8% improvement over the genotype-only linear baseline (0.559 ± 0.050). We further predict yield on new lines in an unseen environment using only genotypes, obtaining a prediction accuracy of 0.386 ± 0.010, a 13.5% improvement over the linear baseline. Our multi-modal deep learning architecture efficiently accounts for plant health and environment, distilling the genetic contribution and providing excellent predictions. Yield prediction algorithms leveraging phenotypic observations during training therefore promise to improve breeding programs, ultimately speeding up delivery of improved varieties. Availability and implementation Available at https://github.com/BorgwardtLab/PheGeMIL (code) and https://doi.org/doi:10.5061/dryad.kprr4xh5p (data).
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Biosystems Science and Engineering, ETH Zurich, Basel, Switzerland.
- Swiss Institute of Bioinformatics, Lausanne, Switzerland.
- Visium, Lausanne, Switzerland.
- Department of Plant Pathology, Kansas State University, Manhattan, KS, United States.
- Department of Agricultural and Biological Engineering, IFAS Gulf Coast Research and Education Center, University of Florida, Wimauma, FL, United States.
- Department of Machine Learning and Systems Biology, Max Planck Institute of Biochemistry, Martinsried, Germany.
ORCID-Profile: Matteo Togninalli, Tim Kucera, Philomin Juliana, Suchismita Mondal, Francisco Pinto, Leonardo Crespo-Herrera, Karsten Borgwardt
Förderung
- National Science Foundation
Zitieren
APA
Togninalli, M., Wang, X., Kucera, T., Shrestha, S., Juliana, P., Mondal, S., Pinto, F., Govindan, V., Crespo-Herrera, L., Huerta-Espino, J., Singh, R. P., Borgwardt, K., & Poland, J. (2023). Multi-modal deep learning improves grain yield prediction in wheat breeding by fusing genomics and phenomics. Bioinformatics, 39(6). https://doi.org/10.1093/bioinformatics/btad336
Vancouver
Togninalli M, Wang X, Kucera T, Shrestha S, Juliana P, Mondal S, et al. Multi-modal deep learning improves grain yield prediction in wheat breeding by fusing genomics and phenomics. Bioinformatics. 2023;39(6). doi:10.1093/bioinformatics/btad336
BibTeX
@article{Togninalli2023,
author = {Togninalli, Matteo and Wang, Xu and Kucera, Tim and Shrestha, Sandesh and Juliana, Philomin and Mondal, Suchismita and Pinto, Francisco and Govindan, Velu and Crespo-Herrera, Leonardo and Huerta-Espino, Julio and Singh, Ravi P and Borgwardt, Karsten and Poland, Jesse},
title = {Multi-modal deep learning improves grain yield prediction in wheat breeding by fusing genomics and phenomics},
journal = {Bioinformatics},
year = {2023},
volume = {39},
number = {6},
doi = {10.1093/bioinformatics/btad336}
}
EUVIMED