Improving genomic selection accuracy using a dual‐path convolutional neural network framework: a terpenoid case study
New Phytologist · 2026
DOI: 10.1111/nph.70727 ↗Kurz gefasst
Fachartikel in der Zeitschrift New Phytologist, 2026. Verfasst von Fuchuan Han und 7 weiteren Autor:innen. Beteiligte Einrichtung: State Key Laboratory of Tree Genetics and Breeding, Chinese Academy of Forestry, Beijing, 100091, China. Hauptthemen laut MEDLINE: Terpenes, Genomics, Neural Networks, Computer, Selection, Genetic. Die Arbeit nennt 44 Literaturangaben. Gefördert von: Key Scientific and Technological Grant of Zhejiang for Breeding New Agricultural Varieties, Ten Thousand People Plan of Science and Technology Innovation Leading Talent of Zhejiang, China, Funda-mental Research Funds of CAF.
Abstract (Originalsprache)
Genomic selection (GS) accelerates forest tree early breeding. Using Litsea cubeba , a representative species of the Lauraceae family, as an example, this study aimed to uncover the genetic basis of terpenoid biosynthesis and to develop deep learning‐based GS strategies for efficient genetic improvement. Whole‐genome resequencing of 945 L. cubeba germplasms and GC‐MS terpenoid quantification for 310 samples were done. Genome‐wide association studies (GWAS) identified loci for key compounds (citral, geranial, and neral). To improve GS predictive ability, the PKDP deep learning model was developed: it uses parallel paths for distinct feature extraction from GWAS‐identified loci and genome‐wide markers, fusing them to combine prior knowledge with broad genomic information. GWAS identified 125 candidate genes for terpenoid biosynthesis, including two terpene synthase (TPS) gene clusters and MVA/MEP pathway enzymes. The PKDP model improved predictive ability for key terpenoids (citral, geranial, and neral) by 2–10% over traditional rrBLUP. Key genetic factors for L. cubeba terpenoid synthesis were identified, aiding molecular mechanism studies. By integrating multiscale genomic information, PKDP substantially enhanced GS prediction, providing an efficient tool for L. cubeba genetic improvement and innovative strategies for breeding complex traits in forest trees.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- State Key Laboratory of Tree Genetics and Breeding, Chinese Academy of Forestry, Beijing, 100091, China.
- Research Institute of Subtropical Forestry, Chinese Academy of Forestry, Hangzhou, 311400, China.
- State Key Laboratory of Tree Genetics and Breeding, Nanjing Forestry University, Nanjing, 210037, China.
ORCID-Profile: Fuchuan Han, Ming Gao, Yunxiao Zhao, Changwei Bi, Yangdong Wang, Yicun Chen
Förderung
- Key Scientific and Technological Grant of Zhejiang for Breeding New Agricultural Varieties
- Ten Thousand People Plan of Science and Technology Innovation Leading Talent of Zhejiang, China
- Funda-mental Research Funds of CAF
Zitieren
APA
Han, F., Gao, M., Zhao, Y., Bi, C., Yang, Y., Zhang, J., Wang, Y., & Chen, Y. (2026). Improving genomic selection accuracy using a dual‐path convolutional neural network framework: a terpenoid case study. New Phytologist. https://doi.org/10.1111/nph.70727
Vancouver
Han F, Gao M, Zhao Y, Bi C, Yang Y, Zhang J, et al. Improving genomic selection accuracy using a dual‐path convolutional neural network framework: a terpenoid case study. New Phytologist. 2026. doi:10.1111/nph.70727
BibTeX
@article{Han2026,
author = {Han, Fuchuan and Gao, Ming and Zhao, Yunxiao and Bi, Changwei and Yang, Yang and Zhang, Jiantao and Wang, Yangdong and Chen, Yicun},
title = {Improving genomic selection accuracy using a dual‐path convolutional neural network framework: a terpenoid case study},
journal = {New Phytologist},
year = {2026},
doi = {10.1111/nph.70727}
}
EUVIMED