ACmix-Swin Deep Learning of 4-Day-Old Apis mellifera Larval Transcriptomes Reveals Early Caste-Biased Regulatory Hubs

TL;DR

This study uses deep learning to identify early genetic differences in honeybee larvae that influence caste and sex development.

Contribution

A novel deep learning model, ACmix-Swin, is introduced for identifying caste-biased regulatory genes in honeybee larvae.

Findings

Caste- and sex-specific divergence was observed in cuticle formation, hormone metabolism, and reproductive signaling.

ACmix-Swin outperformed baseline models in classifying larvae and identifying key regulators like Vg and LOC725841.

qPCR validation confirmed the RNA-seq results, supporting the model's accuracy.

Abstract

Background/Objectives: Early larval development is critical for caste and sex differentiation in honeybees. This study investigates molecular divergence in 4-day-old Apis mellifera larvae and introduces a customized deep learning model for hub-gene discovery. Methods: Genome-guided RNA-seq, DEGs, WGCNA, and splicing analyses were integrated. A hybrid convolution–attention model, ACmix-Swin, combined with WGAN-GP augmentation, was developed to classify larvae and prioritize caste-biased genes. Selected genes were validated by qPCR. Results: Significant caste- and sex-specific divergence was detected in cuticle formation, hormone metabolism, and reproductive signaling. ACmix-Swin achieved the highest accuracy among baseline models and consistently identified key regulators, including Vg, LOC725841, LOC412768, and LOC100576841. qPCR confirmed RNA-seq trends. Conclusions: Caste- and sex-specific transcriptional programs are established early in larval development. The ACmix-Swin framework provides an effective strategy for high-dimensional transcriptome interpretation and robust hub-gene identification.

Figures