MDNN: memetic deep neural network for genomic prediction
Briefings in Bioinformatics · 2025
DOI: 10.1093/bib/bbaf352 ↗Kurz gefasst
Fachartikel in der Zeitschrift Briefings in Bioinformatics, 2025. Verfasst von Yijun Mao und 9 weiteren Autor:innen. Beteiligte Einrichtung: College of Mathematics and Informatics, South China Agricultural University, 483 Wushan Road, Tianhe District, Guangzhou 510642, China. Hauptthemen laut MEDLINE: Genomics, Neural Networks, Computer, Triticum, Deep Learning. Die Arbeit nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Research and Application of Data Elementization Security Protection Technology for Big Data Platforms, National Natural Science Foundation of China, Guangdong University Featured Innovation Program Project.
Abstract (Originalsprache)
Genomic prediction (GP) has made significant progress in the field of breeding. Traditional linear models perform well in handling simple traits but have limitations in extracting nonlinear features for complex traits. The introduction of deep learning (DL) techniques has provided a new approach to GP, especially suited for high-dimensional data processing and complex trait prediction. However, traditional DL models require manual design of the network architecture, which necessitates continuous experimentation and modification. In this paper, we propose a new framework, MDNN, that utilizes the memetic algorithm for neural architecture search and automatically optimizes the network architecture. Compared with the DNNGP, MDNN achieved a 36.49% improvement in the average Pearson correlation coefficient on the wheat599 dataset and a 12.28% improvement on the wheat2000 dataset.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- College of Mathematics and Informatics, South China Agricultural University, 483 Wushan Road, Tianhe District, Guangzhou 510642, China.
- National Key Laboratory of Data Space Technology and System, 3 Minzhuang Road, Haidian District, Beijing 100195, China.
- College of Cyber Security, Jinan University, 601 West Huangpu Avenue, Tianhe District, GuangZhou 510632, China.
- Department of Digital Process, Wens Foodstuff Group CO., LTD., 9 Dongdi North Road, Xinxing County, YunFu 527400, China.
- State Key Laboratory of Green Pesticide, College of Plant Protection, South China Agricultural University, 483 Wushan Road, Tianhe District, Guangzhou 510642, China.
- School of Computer and Information Engineering, Guangdong Polytechnic of Industry and Commerce, 1098 North Guangzhou Avenue, Tianhe District, Guangzhou 510510, China.
ORCID-Profile: Xingcheng Peng
Förderung
- Research and Application of Data Elementization Security Protection Technology for Big Data Platforms
- National Natural Science Foundation of China
- Guangdong University Featured Innovation Program Project
- National Key R&D Program of China
- National Key Laboratory of Data Space Technology and System
Zitieren
APA
Mao, Y., Peng, X., Weng, J., Jiang, R., Kuang, Y., Weng, J., Pang, R., Xiong, Y., Gu, W., & Tang, D. (2025). MDNN: memetic deep neural network for genomic prediction. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbaf352
Vancouver
Mao Y, Peng X, Weng J, Jiang R, Kuang Y, Weng J, et al. MDNN: memetic deep neural network for genomic prediction. Briefings in Bioinformatics. 2025. doi:10.1093/bib/bbaf352
BibTeX
@article{Mao2025,
author = {Mao, Yijun and Peng, Xingcheng and Weng, Jian and Jiang, Rongjin and Kuang, Yingjie and Weng, Jiasi and Pang, Rui and Xiong, Yunyan and Gu, Wanrong and Tang, Deyu},
title = {MDNN: memetic deep neural network for genomic prediction},
journal = {Briefings in Bioinformatics},
year = {2025},
doi = {10.1093/bib/bbaf352}
}
EUVIMED