Method for Predicting Odor Intensity of Perfumery Raw Materials Using Dose–Response Curve Database

Pyrfume: A window to the world's olfactory data

Advances in theoretical understanding are frequently unlocked by access to large, diverse experimental datasets. Our understanding of olfactory neuroscience and psychophysics remain years behind the other senses, in part because rich datasets linking olfactory stimuli with their corresponding percepts, behaviors, and neural pathways remain scarce. Here we present a concerted effort to unlock and unify dozens of stimulus-linked olfactory datasets across species and modalities under a unified framework called Pyrfume. We present examples of how researchers might use Pyrfume to conduct novel analyses uncovering new principles, introduce trainees to the field, or construct benchmarks for machine olfaction.

Predicting odor from vibrational spectra: a data-driven approach

This study investigates olfaction, a complex and not well-understood sensory modality. The chemical mechanism behind smell can be described by so far proposed two theories: vibrational and docking theories. The vibrational theory has been gaining acceptance lately but needs more extensive validation. To fill this gap for the first time, we, with the help of data-driven classification, clustering, and Explainable AI techniques, systematically analyze a large dataset of vibrational spectra (VS) of 3018 molecules obtained from the atomistic simulation. The study utlizes image representations of VS using Gramian Angular Fields and Markov Transition Fields, allowing computer vision techniques to be applied for better feature extraction and improved odor classification. Furthermore, we fuse the PCA-reduced fingerprint features with image features, which show additional improvement in classification results. We use two clustering methods, agglomerative hierarchical (AHC) and k-means, on dimensionality reduced (UMAP, MDS, t-SNE, and PCA) VS and image features, which shed further insight into the connections between molecular structure, VS, and odor. Additionally, we contrast our method with an earlier work that employed traditional machine learning on fingerprint features for the same dataset, and demonstrate that even with a representative subset of 3018 molecules, our deep learning model outperforms previous results. This comprehensive and systematic analysis highlights the potential of deep learning in furthering the field of olfactory research while confirming the vibrational theory of olfaction.

Perfume and Flavor Engineering: A Chemical Engineering Perspective

In the last two decades, scientific methodologies for the prediction of the design, performance and classification of fragrance mixtures have been developed at the Laboratory of Separation and Reaction Engineering. This review intends to give an overview of such developments. It all started with the question: what do we smell? The Perfumery Ternary Diagram enables us to determine the dominant odor for each perfume composition. Evaporation and 1D diffusion model is analyzed based on vapor-liquid equilibrium and Fick's law for diffusion giving access to perfume performance parameters. The effect of matrix and skin is addressed and the trail of perfumes analyzed. Classification of perfumes with the perfumery radar is discussed. The methodology is extended to flavor and taste engineering. Finally, future research directions are suggested.

Visual Analysis of Odor Interaction Based on Support Vector Regression Method

The complex odor interaction between odorants makes it difficult to predict the odor intensity of their mixtures. The analysis method is currently one of the factors limiting our understanding of the odor interaction laws. We used a support vector regression algorithm to establish odor intensity prediction models for binary esters, aldehydes, and aromatic hydrocarbon mixtures, respectively. The prediction accuracy to both training samples and test samples demonstrated the high prediction capacity of the support vector regression model. Then the optimized model was used to generate extra odor data by predicting the odor intensity of more simulated samples with various mixing ratios and concentration levels. Based on these olfactory measured and model predicted data, the odor interaction was analyzed in the form of contour maps. This intuitive method showed more details about the odor interaction pattern in the binary mixture. We found that that the antagonism effect was commonly observed in these binary mixtures and the interaction degree was more intense when the components’ mixing ratio was close. Meanwhile, the odor intensity level of the odor mixture barely influenced the interaction degree. The machine learning algorithms were considered promising tools in odor researches.