Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Jun 26, 2026

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

Published on: December 15, 2023

Gsformer: a dual-architecture deep learning framework with CNN-self-attention and sparse-attention for genomic

Tingting Yang¹, Weicong Wu¹, Yahui Xue²

¹Guangdong Provincial Key Laboratory of Animal Molecular Design and Precise Breeding, School of Animal Science and Technology, Foshan University, Foshan, 528000, China.

Genetics, Selection, Evolution : GSE

|June 4, 2026

Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Degradable Tumor-Responsive Iron-Doped Phosphate-Based Glass Nanozyme for H<sub>2</sub>O<sub>2</sub> Self-Supplying Cancer Therapy.

ACS applied materials & interfaces·2022

Same author

Polarization of tumor-associated macrophages by TLR7/8 conjugated radiosensitive peptide hydrogel for overcoming tumor radioresistance.

Bioactive materials·2022

Same author

In-biofilm generation of nitric oxide using a magnetically-targetable cascade-reaction container for eradication of infectious biofilms.

Bioactive materials·2022

Same author

Trace amine-associated receptor 1 and drug abuse.

Advances in pharmacology (San Diego, Calif.)·2022

Same author

Surface quality of laser paint removal of marine steel: a comparative study using a Gaussian beam and a flat-top beam.

Applied optics·2022

Same author

Chemical Compounds Emitted from <i>Mentha spicata</i> Repel <i>Aromia bungii</i> Females.

Insects·2022

Gsformer, a new deep learning framework, improves genomic prediction accuracy in plants and animals. Its efficient NSA architecture is recommended for breeding programs when computational cost is a concern.

Area of Science:

Genomics
Bioinformatics
Animal and Plant Breeding

Background:

Genomic selection (GS) utilizes genome-wide SNPs for modern breeding.
Deep learning models show superior predictive performance over traditional GS methods.
Existing deep learning approaches for GS require further optimization for complex genetic architectures.

Purpose of the Study:

Introduce Gsformer, a novel deep learning framework for phenotype prediction.
Model complex genetic architectures using two distinct Gsformer architectures: CSA and NSA.
Evaluate Gsformer's predictive performance across diverse animal and plant species.

Main Methods:

Developed Gsformer with two architectures: CSA (CNNs + self-attention) and NSA (native sparse attention).

Related Experiment Videos

Last Updated: Jun 26, 2026

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

Published on: December 15, 2023

Evaluated Gsformer on six datasets (pig, cattle, chicken, mouse, wheat, maize).

Compared Gsformer against five established GS methods (DNNGP, MLP, LightGBM, SVR, GBLUP).

Main Results:

Gsformer consistently ranked among the top two models across all datasets.
Gsformer-CSA improved cattle fat percentage prediction; Gsformer-NSA excelled in predicting chicken egg weight, pig weight, and mouse anxiety.
Gsformer-NSA demonstrated comparable or superior performance to Gsformer-CSA with hyperparameter tuning, with lower computational cost.

Conclusions:

Gsformer provides a flexible and powerful framework for genomic prediction in animals and plants.
Gsformer-NSA is recommended for breeding applications prioritizing computational efficiency.
Identified influential SNPs and biologically relevant pathways for growth and body size traits in pigs using SHAP analysis.