Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
The paper introduces VIANA, a novel "tri-pillar" framework that integrates Graph Convolutional Networks (GCNs) for molecular structure, Principal Odor Map (POM) embeddings for semantic odor character values, and Hill's law for biological dose-response logic to predict odorant intensity. The study found that naive knowledge transfer from semantic data can lead to "information overload," but distilling semantic variance using PCA yields a superior "signal distillation" effect. VIANA achieves a peak R^2 of 0.996 and a test MSE of 0.19, outperforming baseline structural models and effectively capturing the nuances of human olfactory perception.
Domain knowledge can actually *hurt* deep learning models if you don't carefully distill the signal from the noise.
Predicting the perceived intensity of odorants remains a fundamental challenge in sensory science due to the complex, non-linear behavior of their response, as well as the difficulty in correlating molecular structure with human perception. While traditional deep learning models, such as Graph Convolutional Networks (GCNs), excel at capturing molecular topology, they often fail to account for the biological and perceptual context of olfaction. This study introduces VIANA, a novel"tri-pillar"framework that integrates structural graph theory, character value embeddings, and phenomenological behavior. This methodology systematically evaluates knowledge transfer across three distinct domains: molecular structure via GCNs, semantic odor character values via Principal Odor Map (POM) embeddings, and biological dose-response logic via Hill's law. We demonstrate that knowledge transfer is not inherently positive; rather, a balance must be maintained in the volume of information provided to the model. While raw semantic data led to"information overload"in domain-informed models, applying Principal Component Analysis (PCA) to distill the 95% most impactful semantic variance yielded a superior"signal distillation"effect. Results indicate that the synthesis of these three knowledge transfer pillars significantly outperforms baseline structural models, with VIANA achieving a peak R^2 of 0.996 and a test Mean Squared Error (MSE) of 0.19. In this context, VIANA successfully captures the physical ceiling of saturation, the sensitivity of detection thresholds, and the nuance of odor character value expression, providing a domain grounded simulation of the human olfactory experience. This research provides a robust framework for digital olfaction, effectively bridging the gap between molecular informatics and sensory perception.