AI-enhanced marker-assisted selection concept for the multifunctional honey bee protein vitellogenin (Vg)

Authors: LIPART, VILDE - Norwegian University Of Life Sciences; AMDAM, GRO - Arizona State University; Obrien, Sharon; Pigott, Elisabeth; Dodds, Garrett; Ihle, Kate

Submitted to: Journal of Economic Entomology
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 6/26/2025
Publication Date: 8/22/2025
Citation: Lipart, V., Amdam, G.V., Obrien, S.L., Pigott, E.H., Dodds, G.E., Ihle, K.E. 2025. AI-enhanced marker-assisted selection concept for the multifunctional honey bee protein vitellogenin (Vg). Journal of Economic Entomology. https://doi.org/10.1093/jee/toaf187.
DOI: https://doi.org/10.1093/jee/toaf187

Interpretive Summary: Beekeepers have experienced heavy colony losses for more than a decade. The four major causes of these losses are parasites, disease, poor nutrition and pesticides. These sources of stress interact and can make the damage from each other worse. Scientists and beekeepers have been working to breed bees that are more resistant to all four of the major causes of colony loss, but the process is very long, can be very difficult, and can be very expensive. We have developed a method that uses artificial intelligence to predict how small changes in DNA can change the function of the protein that is build from the DNA sequence. We tested how effective this method can be in honey bees, by screening for a particular protein product made from a gene that has many important functions in honey bees. In this article, we report that we were able to successfully breed for that standard protein product. This allowed us to speed up and decrease the cost of honey bee breeding. We suggest that our method can be modified to work with many different genes and will help to ensure that we have healthy honey bee populations in the future.

Technical Abstract: Managed honey bees have experienced unsustainably high rates of annual loss driven by several interacting factors, most notably pests, pathogens, pesticides, and poor nutrition. Breeding bee stocks that can cope with these challenges is a priority. Advanced molecular methods (marker-assisted selection, MAS) have enhanced the breeding efficiency of domesticated animals in recent years, but have not contributed strongly to honey bee stock improvements. This is largely because desirable traits of bees usually emerge from collective phenotypes of workers (sterile females) instead of from the breeding individuals (queens and male drones). For collective phenotypes, single genes typically have small, additive effects, so identifying impactful MAS targets is challenging. Here, we provide proof of concept for a new approach to honey bee breeding through MAS using the multifunctional protein Vitellogenin (Vg), a protein known to interact with and mitigate the primary drivers of colony loss. Our pipeline leverages cutting-edge, artificial intelligence (AI)-driven protein structure modeling algorithms to predict the effects of genetic variants of Vg on relevant molecular functions including lipid, zinc, and DNA binding. Following the AI-powered Vg variant selection step, we use a combination of standard apicultural techniques and DNA sequencing validation to breed honey bee queens homozygous for the desirable Vg allele. Our protocol can kick-start a new area of modernized bee breeding: an AI-enhanced MAS system that allows cost-effective and nimble development of stocks to meet urgent and long-term needs of stakeholders.