Chemical features mining provides new descriptive structure-odor relationships

Regression Study of Odorant Chemical Space, Molecular Structural Diversity, and Natural Language Description

Odor is analyzed on the human olfactometry systems in various steps. The mapping from chemical structures to olfactory perceptions of smell is an extremely challenging task. Scientists have been unable to find a measure to distinguish the perceptual similarity between odorants. In this study, we report regression analysis and visualization based on the odorant chemical space. We discuss the relation between the odor descriptors and their structural diversity for odorants groups associated with each odor descriptor. We studied the influence of structural diversity on the odor descriptor predictability. The results suggest that the diversity of molecular structures, which is associated with the same odor descriptor, is related to the resolutional confusion with the odor descriptor.

Decomposition of an odorant in olfactory perception and neural representation

Molecules-the elementary units of substances-are commonly considered the units of processing in olfactory perception, giving rise to undifferentiated odour objects invariant to environmental variations. By selectively perturbing the processing of chemical substructures with adaptation ('the psychologist's microelectrode') in a series of psychophysical and neuroimaging experiments (458 participants), we show that two perceptually distinct odorants sharing part of their structural features become significantly less discernible following adaptation to a third odorant containing their non-shared structural features, in manners independent of olfactory intensity, valence, quality or general olfactory adaptation. The effect is accompanied by reorganizations of ensemble activity patterns in the posterior piriform cortex that parallel subjective odour quality changes, in addition to substructure-based neural adaptations in the anterior piriform cortex and amygdala. Central representations of odour quality and the perceptual outcome thus embed submolecular structural information and are malleable by recent olfactory encounters.

XGBoost odor prediction model: finding the structure-odor relationship of odorant molecules using the extreme gradient boosting algorithm

Determining the structure-odor relationship has always been a very challenging task. The main challenge in investigating the correlation between the molecular structure and its associated odor is the ambiguous and obscure nature of verbally defined odor descriptors, particularly when the odorant molecules are from different sources. With the recent developments in machine learning (ML) technology, ML and data analytic techniques are significantly being used for quantitative structure-activity relationship (QSAR) in the chemistry domain toward knowledge discovery where the traditional Edisonian methods have not been useful. The smell perception of odorant molecules is one of the aforementioned tasks, as olfaction is one of the least understood senses as compared to other senses. In this study, the XGBoost odor prediction model was generated to classify smells of odorant molecules from their SMILES strings. We first collected the dataset of 1278 odorant molecules with seven basic odor descriptors, and then 1875 physicochemical properties of odorant molecules were calculated. To obtain relevant physicochemical features, a feature reduction algorithm called PCA was also employed. The ML model developed in this study was able to predict all seven basic smells with high precision (>99%) and high sensitivity (>99%) when tested on an independent test dataset. The results of the proposed study were also compared with three recently conducted studies. The results indicate that the XGBoost-PCA model performed better than the other models for predicting common odor descriptors. The methodology and ML model developed in this study may be helpful in understanding the structure-odor relationship.Communicated by Ramaswamy H. Sarma.

Physicochemical features partially explain olfactory crossmodal correspondences

During the olfactory perception process, our olfactory receptors are thought to recognize specific chemical features. These features may contribute towards explaining our crossmodal perception. The physicochemical features of odors can be extracted using an array of gas sensors, also known as an electronic nose. The present study investigates the role that the physicochemical features of olfactory stimuli play in explaining the nature and origin of olfactory crossmodal correspondences, which is a consistently overlooked aspect of prior work. Here, we answer the question of whether the physicochemical features of odors contribute towards explaining olfactory crossmodal correspondences and by how much. We found a similarity of 49% between the perceptual and the physicochemical spaces of our odors. All of our explored crossmodal correspondences namely, the angularity of shapes, smoothness of textures, perceived pleasantness, pitch, and colors have significant predictors for various physicochemical features, including aspects of intensity and odor quality. While it is generally recognized that olfactory perception is strongly shaped by context, experience, and learning, our findings show that a link, albeit small (6-23%), exists between olfactory crossmodal correspondences and their underlying physicochemical features.

Data-Driven Elucidation of Flavor Chemistry

Flavor molecules are commonly used in the food industry to enhance product quality and consumer experiences but are associated with potential human health risks, highlighting the need for safer alternatives. To address these health-associated challenges and promote reasonable application, several databases for flavor molecules have been constructed. However, no existing studies have comprehensively summarized these data resources according to quality, focused fields, and potential gaps. Here, we systematically summarized 25 flavor molecule databases published within the last 20 years and revealed that data inaccessibility, untimely updates, and nonstandard flavor descriptions are the main limitations of current studies. We examined the development of computational approaches (e.g., machine learning and molecular simulation) for the identification of novel flavor molecules and discussed their major challenges regarding throughput, model interpretability, and the lack of gold-standard data sets for equitable model evaluation. Additionally, we discussed future strategies for the mining and designing of novel flavor molecules based on multi-omics and artificial intelligence to provide a new foundation for flavor science research.

OWSum: algorithmic odor prediction and insight into structure-odor relationships

We derived and implemented a linear classification algorithm for the prediction of a molecule's odor, called Olfactory Weighted Sum (OWSum). Our approach relies solely on structural patterns of the molecules as features for algorithmic treatment and uses conditional probabilities combined with tf-idf values. In addition to the prediction of molecular odor, OWSum provides insights into properties of the dataset and allows to understand how algorithmic classifications are reached by quantitatively assigning structural patterns to odors. This provides chemists with an intuitive understanding of underlying interactions. To deal with ambiguities of the natural language used to describe odor, we introduced descriptor overlap as a metric for the quantification of semantic overlap between descriptors. Thus, grouping of descriptors and derivation of higher-level descriptors becomes possible. Our approach poses a large leap forward in our capabilities to understand and predict molecular features.

A Perspective on Explanations of Molecular Prediction Models

Chemists can be skeptical in using deep learning (DL) in decision making, due to the lack of interpretability in "black-box" models. Explainable artificial intelligence (XAI) is a branch of artificial intelligence (AI) which addresses this drawback by providing tools to interpret DL models and their predictions. We review the principles of XAI in the domain of chemistry and emerging methods for creating and evaluating explanations. Then, we focus on methods developed by our group and their applications in predicting solubility, blood-brain barrier permeability, and the scent of molecules. We show that XAI methods like chemical counterfactuals and descriptor explanations can explain DL predictions while giving insight into structure-property relationships. Finally, we discuss how a two-step process of developing a black-box model and explaining predictions can uncover structure-property relationships.

Mapping odorant sensitivities reveals a sparse but structured representation of olfactory chemical space by sensory input to the mouse olfactory bulb

In olfactory systems, convergence of sensory neurons onto glomeruli generates a map of odorant receptor identity. How glomerular maps relate to sensory space remains unclear. We sought to better characterize this relationship in the mouse olfactory system by defining glomeruli in terms of the odorants to which they are most sensitive. Using high-throughput odorant delivery and ultrasensitive imaging of sensory inputs, we imaged responses to 185 odorants presented at concentrations determined to activate only one or a few glomeruli across the dorsal olfactory bulb. The resulting datasets defined the tuning properties of glomeruli - and, by inference, their cognate odorant receptors - in a low-concentration regime, and yielded consensus maps of glomerular sensitivity across a wide range of chemical space. Glomeruli were extremely narrowly tuned, with ~25% responding to only one odorant, and extremely sensitive, responding to their effective odorants at sub-picomolar to nanomolar concentrations. Such narrow tuning in this concentration regime allowed for reliable functional identification of many glomeruli based on a single diagnostic odorant. At the same time, the response spectra of glomeruli responding to multiple odorants was best predicted by straightforward odorant structural features, and glomeruli sensitive to distinct odorants with common structural features were spatially clustered. These results define an underlying structure to the primary representation of sensory space by the mouse olfactory system.

OdoriFy: A conglomerate of artificial intelligence-driven prediction engines for olfactory decoding

The molecular mechanisms of olfaction, or the sense of smell, are relatively underexplored compared with other sensory systems, primarily because of its underlying molecular complexity and the limited availability of dedicated predictive computational tools. Odorant receptors (ORs) allow the detection and discrimination of a myriad of odorant molecules and therefore mediate the first step of the olfactory signaling cascade. To date, odorant (or agonist) information for the majority of these receptors is still unknown, limiting our understanding of their functional relevance in odor-induced behavioral responses. In this study, we introduce OdoriFy, a Web server featuring powerful deep neural network-based prediction engines. OdoriFy enables (1) identification of odorant molecules for wildtype or mutant human ORs (Odor Finder); (2) classification of user-provided chemicals as odorants/nonodorants (Odorant Predictor); (3) identification of responsive ORs for a query odorant (OR Finder); and (4) interaction validation using Odorant-OR Pair Analysis. In addition, OdoriFy provides the rationale behind every prediction it makes by leveraging explainable artificial intelligence. This module highlights the basis of the prediction of odorants/nonodorants at atomic resolution and for the ORs at amino acid levels. A key distinguishing feature of OdoriFy is that it is built on a comprehensive repertoire of manually curated information of human ORs with their known agonists and nonagonists, making it a highly interactive and resource-enriched Web server. Moreover, comparative analysis of OdoriFy predictions with an alternative structure-based ligand interaction method revealed comparable results. OdoriFy is available freely as a web service at https://odorify.ahujalab.iiitd.edu.in/olfy/.

Smell compounds classification using UMAP to increase knowledge of odors and molecular structures linkages

This study aims to highlight the relationships between the structure of smell compounds and their odors. For this purpose, heterogeneous data sources were screened, and 6038 odorant compounds and their known associated odors (162 odor notes) were compiled, each individual molecule being represented with a set of 1024 structural fingerprint. Several dimensional reduction techniques (PCA, MDS, t-SNE and UMAP) with two clustering methods (k-means and agglomerative hierarchical clustering AHC) were assessed based on the calculated fingerprints. The combination of UMAP with k-means and AHC methods allowed to obtain a good representativeness of odors by clusters, as well as the best visualization of the proximity of odorants on the basis of their molecular structures. The presence or absence of molecular substructures has been calculated on odorant in order to link chemical groups to odors. The results of this analysis bring out some associations for both the odor notes and the chemical structures of the molecules such as "woody" and "spicy" notes with allylic and bicyclic structures, "balsamic" notes with unsaturated rings, both "sulfurous" and "citrus" with aldehydes, alcohols, carboxylic acids, amines and sulfur compounds, and "oily", "fatty" and "fruity" characterized by esters and with long carbon chains. Overall, the use of UMAP associated to clustering is a promising method to suggest hypotheses on the odorant structure-odor relationships.

Deconstructing the mouse olfactory percept through an ethological atlas

Odor perception in non-humans is poorly understood. Here, we generated the most comprehensive mouse olfactory ethological atlas to date, consisting of behavioral responses to a diverse panel of 73 odorants, including 12 at multiple concentrations. These data revealed that mouse behavior is incredibly diverse and changes in response to odorant identity and concentration. Using only behavioral responses observed in other mice, we could predict which of two odorants was presented to a held-out mouse 82% of the time. Considering all 73 possible odorants, we could uniquely identify the target odorant from behavior on the first try 20% of the time and 46% within five attempts. Although mouse behavior is difficult to predict from human perception, they share three fundamental properties: first, odor valence parameters explained the highest variance of olfactory perception. Second, physicochemical properties of odorants can be used to predict the olfactory percept. Third, odorant concentration quantitatively and qualitatively impacts olfactory perception. These results increase our understanding of mouse olfactory behavior and how it compares to human odor perception and provide a template for future comparative studies of olfactory percepts among species.

A System-Wide Understanding of the Human Olfactory Percept Chemical Space

The fundamental units of olfactory perception are discrete 3D structures of volatile chemicals that each interact with specific subsets of a very large family of hundreds of odorant receptor proteins, in turn activating complex neural circuitry and posing a challenge to understand. We have applied computational approaches to analyze olfactory perceptual space from the perspective of odorant chemical features. We identify physicochemical features associated with ~150 different perceptual descriptors and develop machine-learning models. Validation of predictions shows a high success rate for test set chemicals within a study, as well as across studies more than 30 years apart in time. Due to the high success rates, we are able to map ~150 percepts onto a chemical space of nearly 0.5 million compounds, predicting numerous percept-structure combinations. The chemical structure-to-percept prediction provides a system-level view of human olfaction and opens the door for comprehensive computational discovery of fragrances and flavors.

SMILES to Smell: Decoding the Structure-Odor Relationship of Chemical Compounds Using the Deep Neural Network Approach

Finding the relationship between the structure of an odorant molecule and its associated smell has always been an extremely challenging task. The major limitation in establishing the structure-odor relation is the vague and ambiguous nature of the descriptor-labeling, especially when the sources of odorant molecules are different. With the advent of deep networks, data-driven approaches have been substantiated to achieve more accurate linkages between the chemical structure and its smell. In this study, the deep neural network (DNN) with physiochemical properties and molecular fingerprints (PPMF) and the convolution neural network (CNN) with chemical-structure images (IMG) are developed to predict the smells of chemicals using their SMILES notations. A data set of 5185 chemical compounds with 104 smell percepts was used to develop the multilabel prediction models. The accuracies of smell prediction from DNN + PPMF and CNN + IMG (Xception based) were found to be 97.3 and 98.3%, respectively, when applied on an independent test set of chemicals. The deep learning architecture combining both DNN + PPMF and CNN + IMG prediction models is proposed, which classifies smells and may help understand the generic mechanism underlying the relationship between chemical structure and smell perception.

Data based predictive models for odor perception

Machine learning and data analytics are being increasingly used for quantitative structure property relation (QSPR) applications in the chemical domain where the traditional Edisonian approach towards knowledge-discovery have not been fruitful. The perception of odorant stimuli is one such application as olfaction is the least understood among all the other senses. In this study, we employ machine learning based algorithms and data analytics to address the efficacy of using a data-driven approach to predict the perceptual attributes of an odorant namely the odorant characters (OC) of "sweet" and "musky". We first analyze a psychophysical dataset containing perceptual ratings of 55 subjects to reveal patterns in the ratings given by subjects. We then use the data to train several machine learning algorithms such as random forest, gradient boosting and support vector machine for prediction of the odor characters and report the structural features correlating well with the odor characters based on the optimal model. Furthermore, we analyze the impact of the data quality on the performance of the models by comparing the semantic descriptors generally associated with a given odorant to its perception by majority of the subjects. The study presents a methodology for developing models for odor perception and provides insights on the perception of odorants by untrained human subjects and the effect of the inherent bias in the perception data on the model performance. The models and methodology developed here could be used for predicting odor characters of new odorants.

Predicting Human Olfactory Perception from Activities of Odorant Receptors

Odor perception in humans is initiated by activation of odorant receptors (ORs) in the nose. However, the ORs linked to specific olfactory percepts are unknown, unlike in vision or taste where receptors are linked to perception of different colors and tastes. The large family of ORs (~400) and multiple receptors activated by an odorant present serious challenges. Here, we first use machine learning to screen ~0.5 million compounds for new ligands and identify enriched structural motifs for ligands of 34 human ORs. We next demonstrate that the activity of ORs successfully predicts many of the 146 different perceptual qualities of chemicals. Although chemical features have been used to model odor percepts, we show that biologically relevant OR activity is often superior. Interestingly, each odor percept could be predicted with very few ORs, implying they contribute more to each olfactory percept. A similar model is observed in Drosophila where comprehensive OR-neuron data are available.

•

Machine learning predicted activity of 34 human ORs for ~0.5 million chemicals

•

Activities of human ORs could predict odor character using machine learning

•

Few OR activities were needed to optimize predictions of each odor percept

•

Behavior predictions in Drosophila also need few olfactory receptor activities