Contrastive Learning Improves Generalization on M2OR Olfactory Binding Dataset
- 1University of Washington
Abstract
Olfaction-based biosensors stand to have profound impacts in fields such as medical diagnostics, national security, and drug discovery. A promising mode of vapor phase biodetection mimics volatile organic compound-olfactory receptor (VOC-OR) interactions with target-specific protein or peptide probes; however, lack of experimental coverage remains a core bottleneck. Current computational approaches aim to improve prediction of VOC-OR binding to reduce experimental burden, and current machine learning approaches fail to demonstrate a level of generalization that addresses current engineering challenges. Here, using the Molecular to Olfactory Dataset (M2OR) and Insect Olfactory Binding Protein Database (iOBPdb) datasets, data partitioning methods and their performance are evaluated on a neural network and contrastive learning framework on such VOC-OR binding datasets, varying: model training, architecture, and structure of the input data distribution. It was found that holding out certain chemical or proteomic motifs from the training data diminished model performance with a two layer neural network model. The model was able to generalize to state of the art performance (0.88 AUCROC) on every data split by applying a contrastive learning objective defined by shared molecular constituents and a stochastic sampler. This suggests the contrastive objective provides a strong inductive bias for neural networks to predict novel VOC-OR pairs. These findings highlight that model performance on pairwise biological interaction datasets can be inflated through identity leakage from constituent overlap, and emphasize the need for more robust evaluation protocols. Furthermore, we show contrastive regularization mitigates dataset degeneracy through enforcement of compatibility in the models latent geometry that may extend to other binder target-datasets where identity leakage confounds evaluation.
Related
- Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction
- CMVAE: Contrastive Supervision Improves Single-Omic Latent Manifold for Breast Cancer Survival Prognosis
- Prediction of the binding modes between key differential flavor compounds in tobacco leaves at different maturity stages and the olfactory receptor OR1D2
- Predicting miRNA–Disease Associations Based on Contrastive Learning of Linear and Nonlinear Features
- How effective are contrastive learning-based approaches for activity-cliff prediction?
BibTeX
@misc{snider2026contrastive,
title = {{Contrastive Learning Improves Generalization on M2OR Olfactory Binding Dataset}},
author = {L. Snider and O. Nakano-Baker and J. D. Mackenzie},
howpublished = {bioRxiv},
year = {2026},
month = nov,
doi = {10.64898/2026.11.04.763508},
url = {https://www.biorxiv.org/content/10.64898/2026.11.04.763508v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - Contrastive Learning Improves Generalization on M2OR Olfactory Binding Dataset
AU - L. Snider
AU - O. Nakano-Baker
AU - J. D. Mackenzie
PY - 2026
DA - 2026/11/04
PB - bioRxiv
DO - 10.64898/2026.11.04.763508
UR - https://www.biorxiv.org/content/10.64898/2026.11.04.763508v1
AB - Olfaction-based biosensors stand to have profound impacts in fields such as medical diagnostics, national security, and drug discovery. A promising mode of vapor phase biodetection mimics volatile organic compound-olfactory receptor (VOC-OR) interactions with target-specific protein or peptide probes; however, lack of experimental coverage remains a core bottleneck. Current computational approaches aim to improve prediction of VOC-OR binding to reduce experimental burden, and current machine learning approaches fail to demonstrate a level of generalization that addresses current engineering challenges. Here, using the Molecular to Olfactory Dataset (M2OR) and Insect Olfactory Binding Protein Database (iOBPdb) datasets, data partitioning methods and their performance are evaluated on a neural network and contrastive learning framework on such VOC-OR binding datasets, varying: model training, architecture, and structure of the input data distribution. It was found that holding out certain chemical or proteomic motifs from the training data diminished model performance with a two layer neural network model. The model was able to generalize to state of the art performance (0.88 AUCROC) on every data split by applying a contrastive learning objective defined by shared molecular constituents and a stochastic sampler. This suggests the contrastive objective provides a strong inductive bias for neural networks to predict novel VOC-OR pairs. These findings highlight that model performance on pairwise biological interaction datasets can be inflated through identity leakage from constituent overlap, and emphasize the need for more robust evaluation protocols. Furthermore, we show contrastive regularization mitigates dataset degeneracy through enforcement of compatibility in the models latent geometry that may extend to other binder target-datasets where identity leakage confounds evaluation.
ER -