EUVIMEDScopri EUVIMED
Crossref

Deep learning‐based prediction of insect odorant receptor–ligand interactions for behavioral regulator discovery

Sibo Wang iD, Penghao Wang, Aniruddha Agnihotri, Wei Xu iD, Guirong Wang iD

Pest Management Science · 2026-11-01

DOI: 10.1002/ps.71454 ↗

At a glance

Journal article in Pest Management Science, published online on 2026-11-01. Written by Sibo Wang and 4 co-authors. Institution: School of Agricultural Sciences, College of Environmental and Life Sciences, Murdoch University, Murdoch, Western Australia, Australia. 46 references. Funded by: National Natural Science Foundation of China, Financial Support for Outstanding scientific and technological innovation Talents Training Fund in Shenzhen.

AbstractSubjectsDati bibliograficiCiteRelated studies

Abstract (original language)

BACKGROUND Widespread chemical insecticide use causes resistance and ecological damage, driving need for sustainable pest control via olfaction‐based behavioral regulators targeting odorant receptors (ORs). Conventional screening is costly and low‐throughput. Deep learning (DL) offers solutions but faces challenges of scarce data, distinct OR–ligand binding properties, and requirements for explainability to guide regulator design. RESULTS To explore effective representations of volatile compounds under a limited data setting, we developed three deep learning models based on molecular descriptors (Concat‐Desc), molecular graphs (Concat‐GNN), and Simplified Molecular Input Line Entry System (SMILES) sequences (Cross‐Attn) for OR–ligand interaction prediction. Trained on 4566 experimental pairs from M2iOR database, all DL models outperformed quantitative structure–activity relationship (QSAR) baselines. Concat‐Desc and Cross‐Attn achieved superior performance (test area under the receiver operating characteristic curve (AUC) = 0.891–0.927; accuracy = 0.810–0.843). The explainability modules highlighted model‐associated ligand features and protein sequence positions. CONCLUSION Molecular descriptors and SMILES are effective for volatile compounds in data‐limited scenarios, while graph representations require further optimization. Integrated explainability modules provide testable hypotheses for experimental validation and future design, establishing a computational framework for artificial intelligence (AI)‐driven insect chemical ecology. Limitations include data scarcity and limited species coverage that future studies must address. © 2026 Society of Chemical Industry.

Subjects

Author keywords

behavioral regulatorscompound representationdeep learningexplainabilityinsect odorant receptors

Authors and institutions

  • School of Agricultural Sciences, College of Environmental and Life Sciences, Murdoch University, Murdoch, Western Australia, Australia.
  • Shenzhen Branch, Guangdong Laboratory for Lingnan Modern Agriculture, Synthetic Biology Laboratory of the Ministry of Agriculture and Rural Affairs, Agricultural Genomics Institute at Shenzhen, Chinese Academy of Agricu…
  • Cooper Medical School of Rowan University, Camden, NJ, USA.
  • School of Medical, Molecular and Forensic Sciences, Murdoch University, Murdoch, Western Australia, Australia.

ORCID profiles: Sibo Wang, Wei Xu, Guirong Wang

Funding

  • National Natural Science Foundation of China
  • Financial Support for Outstanding scientific and technological innovation Talents Training Fund in Shenzhen

Cite

APA

Wang, S., Wang, P., Agnihotri, A., Xu, W., & Wang, G. (2026). Deep learning‐based prediction of insect odorant receptor–ligand interactions for behavioral regulator discovery. Pest Management Science. https://doi.org/10.1002/ps.71454

Vancouver

Wang S, Wang P, Agnihotri A, Xu W, Wang G. Deep learning‐based prediction of insect odorant receptor–ligand interactions for behavioral regulator discovery. Pest Management Science. 2026. doi:10.1002/ps.71454

BibTeX
@article{Wang2026,
  author = {Wang, Sibo and Wang, Penghao and Agnihotri, Aniruddha and Xu, Wei and Wang, Guirong},
  title = {Deep learning‐based prediction of insect odorant receptor–ligand interactions for behavioral regulator discovery},
  journal = {Pest Management Science},
  year = {2026},
  doi = {10.1002/ps.71454}
}
Start for free →