Predicting human olfactory perception from chemical features of odor molecules

Abstract

It is still not possible to predict whether a given molecule will have a perceived odor, or what olfactory percept it will produce. We therefore organized the crowd-sourced DREAM Olfaction Prediction Challenge. Using a large olfactory psychophysical dataset, teams developed machine learning algorithms to predict sensory attributes of molecules based on their chemoinformatic features. The resulting models accurately predicted odor intensity and pleasantness, and also successfully predicted eight among 19 rated semantic descriptors (“garlic”, “fish”, “sweet”, “fruit,” “burnt”, “spices”, “flower”, “sour”). Regularized linear models performed nearly as well as random-forest-based ones, with a predictive accuracy that closely approaches a key theoretical limit. These models help to predict the perceptual qualities of virtually any molecule with high accuracy and also reverse-engineer the smell of a molecule.

The role of metals in mammalian olfaction of low molecular weight organosulfur compounds

“…The perception of odor, 18,19 and the memory and associations of that odor perception, are a fascinating aspect of the subject of olfaction, eloquently captured by Marcel Proust in Remembrance of Things Past : “… But when from a long distant past nothing subsists, after the people are dead, after the things are broken and scattered, still alone, more fragile but with more vitality, more unsubstantial, more persistent, more faithful, the smell and taste of things remain, poised a long time, like souls ready to remind us, waiting and hoping for their moment, amid the ruins of all the rest; and bear unfaltering in the tiny and impalpable drop of their essence, the vast structure of recollection .” 20 The strong connection between olfaction and memory recall is likely related to the proximity of neural regions important for smell and cortical areas implicated in higher order functions of emotional memory. This relationship is relevant to the understanding of neurodegenerative disease, e.g., given that changes in the sense of smell can be an early indicator for Alzheimer's disease.…”

Bioisosterism reveals new structure-odor relationships

“…There is also a significant overlap between the aliphatic and aromatic odorants, as well as non-aldehyde ACE greatly overlapping with the rest of the aldehydes. While many panels used in traditional literature on functional imaging of OSNs has categorized odorants based on their functional groups [3][4][5][6][7][8], our results suggest once again that functional groups should not be the primary distinguishing criteria for the odorants. CYC6-1 and CYC6-3, while sharing the chemical formula, TPSA, weight, and volume, show a surprisingly small amount of overlap, indicating a presence of a significant structural differentiator.…”

The optimal odor-receptor interaction network is sparse in olfactory systems: Compressed sensing by nonlinear neurons with a finite dynamic range

“…In all these cases, to achieve maximum information transmission, an "ideal" neuron should transform the input distribution into a uniform output distribution [22,31] and a population of neurons should decorrelate their responses [28,32,33]. However, unlike light or sound, which can be characterized by a single quantity such as wavelength or frequency, there are a huge number of odorants each with its own unique molecular structure and different physiochemical properties [34,35]. The high dimensionality of the odor space thus poses a severe challenge for the olfactory system to code olfactory signals.…”