A review of multimodal deep learning methods for genomic-enabled prediction in plant breeding
2024

Review of Deep Learning Methods for Plant Breeding

publication Evidence: moderate

Author Information

Author(s): Montesinos-López Osval A, Chavira-Flores Moises, Kismiantini, Crespo-Herrera Leo, Saint Piere Carolina, Li HuiHui, Fritsche-Neto Roberto, Al-Nowibet Khalid, Montesinos-López Abelardo, Crossa José

Hypothesis

Multimodal deep learning methods can enhance genomic prediction in plant breeding.

Conclusion

Multimodal deep learning shows promise in improving prediction accuracy for plant breeding by integrating diverse data sources.

Supporting Evidence

  • Deep learning methods have been shown to enhance prediction accuracy in plant breeding.
  • Multimodal deep learning integrates various data types for improved genomic predictions.
  • Careful selection of architectures and fusion strategies is crucial for effective application.

Takeaway

This study looks at how using different types of data together can help scientists predict how plants will grow better.

Methodology

The review discusses various multimodal deep learning architectures and their applications in genomic prediction.

Limitations

The review notes that while multimodal deep learning can improve predictions, it requires significant computational resources and careful application.

Digital Object Identifier (DOI)

10.1093/genetics/iyae161

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication