EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Harnessing Deep Learning in Searching Wild Relatives of Domestic Animals

Zheng-Fei Cai, Bei Liu, Ting-Ting Yin, Cheng Ma, Zi-Teng Han, Li-Hong Gu, Chao Zhang, Fei Wu, Li-Sheng Liu, Xian Shi, Xue-Qi Wang, Ru-Nian Wu und 18 weitere

Molecular Ecology Resources · 2026-04 · 26 (3)

DOI: 10.1111/1755-0998.70133 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Molecular Ecology Resources, online erschienen am 20.04.2026. Verfasst von Zheng-Fei Cai und 29 weiteren Autor:innen. Beteiligte Einrichtung: State Key Laboratory of Genetic Evolution & Animal Models and Yunnan Key Laboratory of Molecular Biology of Domestic Animals, Kunming Institute of Zo…. Hauptthemen laut MEDLINE: Animals, Domestic, Deep Learning, Animals, Wild, Computational Biology. Die Arbeit nennt 109 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: National Key Research and Development Program of China, Yunnan International Joint Laboratory for Conservation and Gene Mining of Genetic Resources, Science and Technology Basic Resources Investigation Program of China: "Wild Germplasm Collection and Preservation in the Greater Gaoligong Mountains".

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Wild relatives of domestic animals are crucial reservoirs of genetic diversity, yet pervasive hybridization with domestic animals poses significant conservation challenges. Here, we developed a deep learning–based pipeline, consisting of a multi‐layer perceptron for SNP panel selection and a Deep & Cross Network for model training, to discern wild relatives from their closely related domestic animals using genomic SNP data. Leveraging the 1960 genomes from 164 red jungle fowl (RJF; Gallus gallus ) and 1796 domestic chicken samples, we applied this pipeline to yield the RJF identification model based on a 285‐SNP panel. We employed this model to characterize domestic chickens, RJF, and hybrids in the independent genomic datasets from contemporary samples and historical specimens, respectively. The accuracy was 97.8% for historical samples with missing genotypes. The benchmarking multiple hybrid detection tools indicated that the RJF identification model was effective and practical. The further application to the genomic data from wild boar ( Sus scrofa ), domestic pigs, and their hybrids validated the pipeline. Our method has potential in not only monitoring genetic diversity in wild relatives of domestic animals but also supporting animal genetic resource conservation and management.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Animals, DomesticDeep LearningAnimals, WildComputational BiologyAnimalsPolymorphism, Single NucleotideGenomicsChickens

Stichwörter der Autor:innen

chickendeep learninggenomicshybridpigred jungle fowlspecies identificationwild boar

Autor:innen und Institutionen

  • State Key Laboratory of Genetic Evolution & Animal Models and Yunnan Key Laboratory of Molecular Biology of Domestic Animals, Kunming Institute of Zoology, Chinese Academy of Sciences, Kunming, China.
  • School of Ecology and Environmental Science, Yunnan University, Kunming, China.
  • Kunming College of Life Science, University of Chinese Academy of Sciences, Kunming, China.
  • Department of Medical Biochemistry and Microbiology, Uppsala University, Uppsala, Sweden.
  • Institute of Animal Science and Veterinary Medicine, Hainan Academy of Agricultural Sciences, Haikou, China.
  • Department of Bioinformatics, the Province and Ministry co-Sponsored Collaborative Innovation Center for Medical Epigenetics, Key Laboratory of Immune Microenvironment and Disease (Ministry of Education), School of Basi…

ORCID-Profile: Kornsorn Srikulnath, Min-Sheng Peng

Förderung

  • National Key Research and Development Program of China
  • Yunnan International Joint Laboratory for Conservation and Gene Mining of Genetic Resources
  • Science and Technology Basic Resources Investigation Program of China: "Wild Germplasm Collection and Preservation in the Greater Gaoligong Mountains"
  • National Natural Science Foundation of China
  • Ministry of Higher Education, Science, Research and Innovation, Thailand
  • Thailand Science Research and Innovation
  • Chinese Academy of Sciences
  • Kunming Institute of Zoology, Chinese Academy of Sciences,

Zitieren

APA

Cai, Z. F., Liu, B., Yin, T. T., Ma, C., Han, Z. T., Gu, L. H., Zhang, C., Wu, F., Liu, L. S., Shi, X., Wang, X. Q., Wu, R. N., Xie, L. Z., Bai, Y., Zhang, Y. C., Zhang, S. R., Gu, L. J., Wang, M. S., Xie, G. L., …, & Peng, M. S. (2026). Harnessing Deep Learning in Searching Wild Relatives of Domestic Animals. Molecular Ecology Resources, 26(3). https://doi.org/10.1111/1755-0998.70133

Vancouver

Cai ZF, Liu B, Yin TT, Ma C, Han ZT, Gu LH, et al. Harnessing Deep Learning in Searching Wild Relatives of Domestic Animals. Molecular Ecology Resources. 2026;26(3). doi:10.1111/1755-0998.70133

BibTeX
@article{Cai2026,
  author = {Cai, Zheng-Fei and Liu, Bei and Yin, Ting-Ting and Ma, Cheng and Han, Zi-Teng and Gu, Li-Hong and Zhang, Chao and Wu, Fei and Liu, Li-Sheng and Shi, Xian and Wang, Xue-Qi and Wu, Ru-Nian and Xie, Lin-Zhe and Bai, Yue and Zhang, Yun-Chun and Zhang, Shu-Run and Gu, Li-Jiao and Wang, Ming-Shan and Xie, Guo-Li and Cheng, Wang-Kun and Lu, Jian-Gao and Luo, Yan and Li, Shao-Bin and Ashari, Hidayat and Zein, Moch Syamsul Arifin and Han, Jian-Lin and Singchat, Worapong and Srikulnath, Kornsorn and Zhang, Ya-Ping and Peng, Min-Sheng},
  title = {Harnessing Deep Learning in Searching Wild Relatives of Domestic Animals},
  journal = {Molecular Ecology Resources},
  year = {2026},
  volume = {26},
  number = {3},
  doi = {10.1111/1755-0998.70133}
}
Kostenlos starten →