A principal odor map unifies diverse tasks in olfactory perception

Beyond the reaction kinetics: Interpretable machine learning reveals unique pathways of sulfate and carbonate radicals

Sulfate radical (SO4•-) mediated advanced oxidation process (AOP) represents a cutting-edge and energy-efficient technology for wastewater treatment with carbonate radical (CO3•-) as coexisting species in alkaline waters. The reaction mechanism of both radicals with trace organic contaminants (TrOCs) has long been accepted to occur mainly through single electron transfer (SET). However, recent studies suggested a more complex mechanism than previously thought. In this study, we conduct a thorough investigation into their reaction mechanisms, and our results reveal that the reactivity of both radicals with benzene derivatives aligns with electrophilic substitution patterns, with the presence of electron-donating groups enhancing the trend. Extending beyond benzene derivatives, we formulate linear free-energy relationships (LFERs) for a broader range of TrOCs by means of machine learning. Our results highlight that SET pathway is the rate-determining step for the reactions with a more pronounced effect in reactions initiated by CO3•- than those by SO4•-, as other pathways are as equally important as SET when SO4•- reacts with TrOCs with hydroxyl, amine, and carbonyl groups. These in-depth insights not only help to elucidate the origin of the discrepancies but also enable a better control over reactive radicals, holding the potential to the controllable byproduct transformation.

Atomevo-odor: A database for understanding olfactory receptor-odorant pairs with multi-artificial intelligence methods

Interactions between olfactory receptors (ORs) and specific odorant molecules encode many distinct odors through intricate activation patterns. In this study, in order to enhance our understanding of olfactory perception, Atomevo-Odor (http://cslodordatabase.7fx.cn/), a comprehensive database for odorants, ORs, and high-quality OR-odorant responses combining experimental data and artificial intelligence prediction, was constructed. Moreover, graph theory and unsupervised learning methods were employed to classify the odorants, and the relationship between odorant functional groups and fragrance types was examined, along with the recognition mechanism of ORs for different odorant functional groups. Furthermore, a CNN-based model was developed for the OR-odorant response prediction. Finally, predictions of unseen data facilitated the identification of potentially responsive OR-odorant pairs, which allowed for further analysis of the response and recognition mechanisms of odorants by ORs. This study provides valuable insights into the design and guidance for subsequent experiments.

Odor classification: Exploring feature performance and imbalanced data learning techniques

This research delves into olfaction, a sensory modality that remains complex and inadequately understood. We aim to fill in two gaps in recent studies that attempted to use machine learning and deep learning approaches to predict human smell perception. The first one is that molecules are usually represented with molecular fingerprints, mass spectra, and vibrational spectra; however, the influence of the selected representation method on predictive performance is inadequately documented in direct comparative studies. To fill this gap, we assembled a large novel dataset of 2606 molecules with three kinds of features: mass spectra (MS), vibrational spectra (VS) and molecular fingerprint features (FP). We evaluated their performance using four different multi-label classification models. The second objective is to address an inherent challenge in odor classification multi-label datasets (MLD)-the issue of class imbalance by random resampling techniques and an explainable, cost-sensitive multilayer perceptron model (CSMLP). Experimental results suggest significantly better performance of the molecular fingerprint-based features compared with mass and vibrational spectra with the micro-averaged F1 evaluation metric. The proposed resampling techniques and cost-sensitive model outperform the results of previous studies. We also report the predictive performance of multimodal features obtained by fusing the three mentioned features. This comprehensive and systematic study compares the predictive performance for odor classification of different features and utilises a multifaceted approach to deal with data imbalance. Our explainable model sheds further light on features and odour relations. The results hold the potential to guide the development of the electric nose and our dataset will be made publicly available.

Navigating the Fragrance Space Using Graph Generative Models and Predicting Odors

We explore a suite of generative modeling techniques to efficiently navigate and explore the complex landscapes of odor and the broader chemical space. Unlike traditional approaches, we not only generate molecules but also predict the odor likeliness with a ROC AUC score of 0.97 and assign probable odor labels. We correlate odor likeliness with physicochemical features of molecules using machine learning techniques and leverage SHAP (SHapley Additive exPlanations) to demonstrate the interpretability of the function. The whole process involves four key stages: molecule generation, stringent sanitization checks for molecular validity, fragrance likeliness screening, and odor prediction of the generated molecules. By making our code and trained models publicly accessible, we aim to facilitate the broader adoption of our research across applications in fragrance discovery and olfactory research.

Biomimetic Intelligent Thermal Management Materials: From Nature-Inspired Design to Machine-Learning-Driven Discovery

The development of biomimetic intelligent thermal management materials (BITMs) is essential for tackling thermal management challenges in electronics and aerospace applications. These materials possess not only exceptional thermal conductivity but also environmental compatibility. However, developing such materials necessitates overcoming intricate challenges, such as precise control over the material structure and optimization of the material's properties and stability. This review comprehensively overviews the research progress of BITMs, emphasizing the synergy between biomimetic design principles and artificial-intelligence-driven methodologies to enhance their performance. The unique nature-inspired structures are explored and valuable insights are provided into adaptive thermal management strategies, which can be further enhanced through data analytics and machine learning (ML). This review offers insights into overcoming design challenges and outlines future prospects for advanced BITMs by integrating ML and biomimetic design principles.

Explainable predictive models of short stature and exploration of related environmental growth factors: a case-control study

BACKGROUND

Short stature is a prevalent pediatric endocrine disorder for which early detection and prediction are pivotal for improving treatment outcomes. However, existing diagnostic criteria often lack the necessary sensitivity and specificity because of the complex etiology of the disorder. Hence, this study aims to employ machine learning techniques to develop an interpretable predictive model for normal-variant short stature and to explore how growth environments influence its development.

METHODS

We conducted a case‒control study including 100 patients with normal-variant short stature who were age-matched with 200 normal controls from the Endocrinology Department of Nanjing Children's Hospital from April to September 2021. Parental surveys were conducted to gather information on the children involved. We assessed 33 readily accessible medical characteristics and utilized conditional logistic regression to explore how growth environments influence the onset of normal-variant short stature. Additionally, we evaluated the performance of the nine machine learning algorithms to determine the optimal model. The Shapley additive explanation (SHAP) method was subsequently employed to prioritize factor importance and refine the final model.

RESULTS

In the multivariate logistic regression analysis, children's weight (OR = 0.92, 95% CI: 0.86, 0.99), maternal height (OR = 0.79, 95% CI: 0.72, 0.87), paternal height (OR = 0.83, 95% CI: 0.75, 0.91), sufficient nighttime sleep duration (OR = 0.48, 95% CI: 0.26, 0.89), and outdoor activity time exceeding three hours (OR = 0.02, 95% CI: 0.00, 0.66) were identified as protective factors for normal-variant short stature. This study revealed that parental height, caregiver education, and children's weight significantly influenced the prediction of normal-variant short stature risk, and both the random forest model and gradient boosting machine model exhibited the best discriminatory ability among the 9 machine learning models.

CONCLUSIONS

This study revealed a close correlation between environmental growth factors and the occurrence of normal-variant short stature, particularly anthropometric characteristics. The random forest model and gradient boosting machine model performed exceptionally well, demonstrating their potential for clinical applications. These findings provide theoretical support for clinical identification and preventive measures for short stature.

Specific Odor Coding Using a Single Thin-Film Transistor

The specificity of olfactory receptor cells (ORCs) in the human nose is the physiological basis for their powerful odor coding capacity. Ideally, artificial ORCs in bioinspired machine olfaction represented by electronic noses (e-noses) should have a desirable specificity. However, mapping gas-solid interactions at the ORC level for specific odor perception remains a key challenge because of the cross-sensitivity issues of gas sensors in e-noses. Here, we use a thin-film transistor (TFT) to generate a two-dimensional matrix code by resolving the electronic transduction process (chemical reception and electron transduction) arising from the gas-solid interactions. As a proof-of-concept experiment, we selected lead sulfide quantum dots and black phosphorus as sensitive materials and achieved specific discrimination between typical oxidizing gases. The developed coding method has physical interpretability, enabling its extension to other gas-sensitive materials and target analytes.

Fragrances of Cage Bicyclic Benzene Bioisosteres

Cubane, bicyclo[1.1.1]pentane (BCP) and bicyclo[2.2.2]octane derivatives of benzene-containing fragrances (e. g., benzyl esters) were prepared to evaluate whether odor characteristics would be retained to give same or similar scents. It was observed that each molecule maintained a distinctive aroma, sometimes quite similar to the benzene ring containing fragrance, and in other cases very different, with several perceived to produce high intensity odors. These results suggest that saturated cage bicyclic hydrocarbon bioisosteres have potential as new tools for the discovery of novel fragrances.

Advances in Food Aroma Analysis: Extraction, Separation, and Quantification Techniques

Decoding the aroma composition plays a key role in designing and producing foods that consumers prefer. Due to the complex matrix and diverse aroma compounds of foods, isolation and quantitative analytical methods were systematically reviewed. Selecting suitable and complementary aroma extraction methods based on their characteristics can provide more complete aroma composition information. Multiple mass spectrometry detectors (MS, MS/MS, TOF-MS, IMS) and specialized detectors, including flame ionization detector (FID), electron capture detector (ECD), nitrogen-phosphorus detector (NPD), and flame photometric detector (FPD), are the most important qualitative technologies in aroma identification and quantification. Furthermore, the real-time monitoring of aroma release and perception is an important developing trend in the aroma perception of future food. A combination of artificial intelligence for chromatographic analysis and characteristic databases could significantly improve the qualitative analysis efficiency and accuracy of aroma analysis. External standard method and stable isotope dilution analysis were the most popular quantification methods among the four quantification methods. The combination with flavoromics enables the decoding of aroma profile contributions and the identification of characteristic marker aroma compounds. Aroma analysis has a wide range of applications in the fields of raw materials selection, food processing monitoring, and products quality control.

Deep Learning for Odor Prediction on Aroma-Chemical Blends

The application of deep-learning techniques to aroma chemicals has resulted in models that surpass those of human experts in predicting olfactory qualities. However, public research in this field has been limited to predicting the qualities of individual molecules, whereas in industry, perfumers and food scientists are often more concerned with blends of multiple molecules. In this paper, we apply both established and novel approaches to a data set we compiled, which consists of labeled pairs of molecules. We present graph neural network models that accurately predict the olfactory qualities emerging from blends of aroma chemicals along with an analysis of how variations in model architecture can significantly impact predictive performance.

Molecular Odor Prediction Using Olfactory Receptor Information

In fragrance development, the framework development process is a bottleneck from the perspective of labor, cost, and human resource development. Odors vary greatly depending on the structure and functional groups of the molecule. Although odor has been predicted from only the structure of molecules, its practical application remains elusive. In this study, we developed a model for predicting the odor of molecules that have only small differences in structure. Focusing on the mechanism of human olfaction, we divided the mechanism into three levels and constructed three models: a classification model that predicts the presence or absence of binding between molecules and olfactory receptors, a regression model that predicts the strength of binding, and a classification model that predicts the presence or absence of odor based on the strength of binding. Olfactory receptors were used as descriptors to discriminate between similar molecular odors. Our models predicted odor differences between some similar molecules, including optical isomers.

Ex Vivo Functional Characterization of Mouse Olfactory Bulb Projection Neurons Reveals a Heterogeneous Continuum

Mitral cells (MCs) and tufted cells (TCs) in the olfactory bulb (OB) act as an input convergence hub and transmit information to higher olfactory areas. Since first characterized, they have been classed as distinct projection neurons based on size and location: laminarly arranged MCs with a diameter larger than 20 µm in the mitral layer (ML) and smaller TCs spread across both the ML and external plexiform layers (EPL). Recent in vivo work has shown that these neurons encode complementary olfactory information, akin to parallel channels in other sensory systems. Yet, many ex vivo studies still collapse them into a single class, mitral/tufted, when describing their physiological properties and impact on circuit function. Using immunohistochemistry and whole-cell patch-clamp electrophysiology in fixed or acute slices from adult mice, we attempted to align in vivo and ex vivo data and test a soma size-based classifier of bulbar projection neurons using passive and intrinsic firing properties. We found that there is no clear separation between cell types based on passive or active properties. Rather, there is a heterogeneous continuum with three loosely clustered subgroups: TCs in the EPL, and putative tufted or putative MCs in the ML. These findings illustrate the large functional heterogeneity present within the OB projection neurons and complement existing literature highlighting how heterogeneity in sensory systems is preponderant and possibly used in the OB to decode complex olfactory information.

Design Principles From Natural Olfaction for Electronic Noses

Natural olfactory systems possess remarkable sensitivity and precision beyond what is currently achievable by engineered gas sensors. Unlike their artificial counterparts, noses are capable of distinguishing scents associated with mixtures of volatile molecules in complex, typically fluctuating environments and can adapt to changes. This perspective examines the multifaceted biological principles that provide olfactory systems their discriminatory prowess, and how these ideas can be ported to the design of electronic noses for substantial improvements in performance across metrics such as sensitivity and ability to speciate chemical mixtures. The topics examined herein include the fluid dynamics of odorants in natural channels; specificity and kinetics of odorant interactions with olfactory receptors and mucus linings; complex signal processing that spatiotemporally encodes physicochemical properties of odorants; active sampling techniques, like biological sniffing and nose repositioning; biological priming; and molecular chaperoning. Each of these components of natural olfactory systems are systmatically investigated, as to how they have been or can be applied to electronic noses. While not all artificial sensors can employ these strategies simultaneously, integrating a subset of bioinspired principles can address issues like sensitivity, drift, and poor selectivity, offering advancements in many sectors such as environmental monitoring, industrial safety, and disease diagnostics.

Predicting human olfactory perception by odorant structure and receptor activation profile

Humans possess a remarkable ability to discriminate a wide range of odors with high precision. This process begins with olfactory receptors (ORs) detecting and responding to the molecular structures of odorants. Recent studies have aimed to associate the activity of a single OR to an odor descriptor or predict odor descriptors using 2D molecular representation. However, predicting a limited number of odor descriptors is insufficient to fully understand the widespread and elaborate olfactory perception process. Therefore, we conducted structure-activity relationship analyses for ORs of eugenol, vanillin, and structurally similar compounds, investigating the correlation between molecular structures, OR activity profiles, and perceptual odor similarity. Our results indicated that these structurally similar compounds primarily activated 6 ORs, and the activity profiles of these ORs correlated with their perception. This enabled the development of a prediction model for the eugenol-similarity score from OR activity profiles (coefficient of determination, R2 = 0.687). Furthermore, the molecular structures of odorants were represented as 3D shapes and pharmacophore fingerprints, considering the 3D structural similarities between various odorants with multiple conformations. These 3D shape and pharmacophore fingerprints could also predict the perceptual odor similarity (R2 = 0.514). Finally, we identified key molecular structural features that contributed to predicting sensory similarities between compounds structurally similar to eugenol and vanillin. Our models, which predict odor from OR activity profiles and similarities in the 3D structure of odorants, may aid in understanding olfactory perception by compressing the information from a vast number of odorants into the activity profiles of 400 ORs.

Olfactory perception complexity induced by key odorants perceptual interactions of alcoholic beverages: Wine as a focus case example

The odorants in alcoholic beverages are frequently experienced as complex mixtures, and there is a complex array of influence factors and interactions involved during consumption that deeply increase its olfactory perception complexity, especially the complexity induced by perceptual interactions between different odorants. In this review, the effect of olfactory perceptual interactions and other factors related to the complexity of olfactory perception of alcoholic beverages are discussed. The classification, influencing factors, and mechanisms of olfactory perceptual interactions are outlined. Recent research progress as well as the methodologies applied in these studies on perceptual interactions between odorants observed in representative alcoholic beverages, especially wine, are briefly summarized. In the future, unified theory or systematic research methodology need to be established, since up to now, the rules of perceptual interaction between multiple odorants, which is critical to the alcoholic beverage industry to improve the flavor of their products, are still not revealed.

Spiers Memorial Lecture: How to do impactful research in artificial intelligence for chemistry and materials science

Machine learning has been pervasively touching many fields of science. Chemistry and materials science are no exception. While machine learning has been making a great impact, it is still not reaching its full potential or maturity. In this perspective, we first outline current applications across a diversity of problems in chemistry. Then, we discuss how machine learning researchers view and approach problems in the field. Finally, we provide our considerations for maximizing impact when researching machine learning for chemistry.

Coverage bias in small molecule machine learning

Small molecule machine learning aims to predict chemical, biochemical, or biological properties from molecular structures, with applications such as toxicity prediction, ligand binding, and pharmacokinetics. A recent trend is developing end-to-end models that avoid explicit domain knowledge. These models assume no coverage bias in training and evaluation data, meaning the data are representative of the true distribution. However, the domain of applicability is rarely considered in such models. Here, we investigate how well large-scale datasets cover the space of known biomolecular structures. For doing so, we propose a distance measure based on solving the Maximum Common Edge Subgraph (MCES) problem, which aligns well with chemical similarity. Although this method is computationally hard, we introduce an efficient approach combining Integer Linear Programming and heuristic bounds. Our findings reveal that many widely-used datasets lack uniform coverage of biomolecular structures, limiting the predictive power of models trained on them. We propose two additional methods to assess whether training datasets diverge from known molecular distributions, potentially guiding future dataset creation to improve model performance.

Odorant Binding Proteins Facilitate the Gas-Phase Uptake of Odorants Through the Nasal Mucus

Mammalian odorant binding proteins (OBPs) have long been suggested to transport hydrophobic odorant molecules through the aqueous environment of the nasal mucus. While the function of OBPs as odorant transporters is supported by their hydrophobic beta-barrel structure, no rationale has been provided on why and how these proteins facilitate the uptake of odorants from the gas phase. Here, a multi-scale computational approach validated through available high-resolution spectroscopy experiments reveals that the conformational space explored by carvone inside the binding cavity of porcine OBP (pOBP) is much closer to the gas than the aqueous phase, and that pOBP effectively manages to transport odorants by lowering the free energy barrier of odorant uptake. Understanding such perireceptor events is crucial to fully unravel the molecular processes underlying the olfactory sense and move towards the development of protein-based biomimetic sensor units that can serve as artificial noses.

Artificial intelligence and food flavor: How AI models are shaping the future and revolutionary technologies for flavor food development

The food flavor science, traditionally reliant on experimental methods, is now entering a promising era with the help of artificial intelligence (AI). By integrating existing technologies with AI, researchers can explore and develop new flavor substances in a digital environment, saving time and resources. More and more research will use AI and big data to enhance product flavor, improve product quality, meet consumer needs, and drive the industry toward a smarter and more sustainable future. In this review, we elaborate on the mechanisms of flavor recognition and their potential impact on nutritional regulation. With the increase of data accumulation and the development of internet information technology, food flavor databases and food ingredient databases have made great progress. These databases provide detailed information on the nutritional content, flavor molecules, and chemical properties of various food compounds, providing valuable data support for the rapid evaluation of flavor components and the construction of screening technology. With the popularization of AI in various fields, the field of food flavor has also ushered in new development opportunities. This review explores the mechanisms of flavor recognition and the role of AI in enhancing food flavor analysis through high-throughput omics data and screening technologies. AI algorithms offer a pathway to scientifically improve product formulations, thereby enhancing flavor and customized meals. Furthermore, it discusses the safety challenges of integrating AI into the food flavor industry.

An overview on olfaction in the biological, analytical, computational, and machine learning fields

Recently, the comprehension of odor perception has advanced, unveiling the mysteries of the molecular receptors within the nasal passages and the intricate mechanisms governing signal transmission between these receptors, the olfactory bulb, and the brain. This review provides a comprehensive panorama of odors, encompassing various topics ranging from the structural and molecular underpinnings of odorous substances to the physiological intricacies of olfactory perception. It extends to elucidate the analytical methods used for their identification and explores the frontiers of computational methodologies.

Predictive Machine Learning Models for Olfaction

A classical problem in neuroscience, biology, and chemistry is linking the chemical structure of odorants to their olfactory perception. This difficulty arises from the subjective nature of odor perception, incomplete understanding of the physiological mechanisms involved, and the absence of standardized odor descriptions. Machine learning and other computational approaches have recently been applied to tackle this challenge. This chapter presents a comprehensive workflow for constructing machine learning models for odor prediction, covering everything from problem formulation to model evaluation and real-world deployment. We also delve into recent advancements to enhance and interpret data-driven predictions while acknowledging the current limitations. The methodology outlined here offers a valuable framework for synthetic chemists and data scientists, enabling them to address the broader issue of olfaction and cater to specific needs within the fragrance and perfume industries.

Automatic scent creation by cheminformatics method

The sense of smell is fundamental for various aspects of human existence including the flavor perception, environmental awareness, and emotional impact. However, unlike other senses, it has not been digitized. Its digitalization faces challenges such as the lack of reliable odor sensing technology or the precise scent delivery through olfactory displays. Its subjective nature and context dependence add complexity to the process. Moreover, the method of converting odors to digital information remains unclear. This work focuses on one of the most challenging aspects of digital olfaction: automatic scent creation. We propose a method that automatically creates a desired odor profile with the addition of one specific odor descriptor. It is based on a deep neural network that predicts odor descriptors from the multidimensional sensing data, such as mass spectra and an odor reproduction technique using odor components. The results demonstrate that the proposed method can successfully create a scent with the desired odor profile and that its performance depends on the accuracy of the underlying odor predicting method. This opens up the possibility of automatic scent creation, allowing for the presentation of scents with specific odor profiles with an olfactory display.

Odor prediction of whiskies based on their molecular composition

Aroma compositions are usually complex mixtures of odor-active compounds exhibiting diverse molecular structures. Due to chemical interactions of these compounds in the olfactory system, assessing or even predicting the olfactory quality of such mixtures is a difficult task, not only for statistical models, but even for trained assessors. Here, we combine fast automated analytical assessment tools with human sensory data of 11 experienced panelists and machine learning algorithms. Using 16 previously analyzed whisky samples (American or Scotch origin), we apply the linear classifier OWSum to distinguish the samples based on their detected molecules and to gain insights into the key molecular structure characteristics and odor descriptors for sample type. Moreover, we use OWSum and a Convolutional Neural Network (CNN) architecture to classify the five most relevant odor attributes of each sample and predict their sensory scores with promising accuracies (up to F1: 0.71, MCC: 0.68, ROCAUC: 0.78). The predictions outperform the inter-panelist agreement and thus demonstrate previously impossible data-driven sensory assessment in mixtures.

The Dimensions of dimensionality

Cognitive scientists often infer multidimensional representations from data. Whether the data involve text, neuroimaging, neural networks, or human judgments, researchers frequently infer and analyze latent representational spaces (i.e., embeddings). However, the properties of a latent representation (e.g., prediction performance, interpretability, compactness) depend on the inference procedure, which can vary widely across endeavors. For example, dimensions are not always globally interpretable and the dimensionality of different embeddings may not be readily comparable. Moreover, the dichotomy between multidimensional spaces and purportedly richer representational formats, such as graph representations, is misleading. We review what the different notions of dimension in cognitive science imply for how these latent representations should be used and interpreted.

Artificial intelligence and machine learning applications for cultured meat

Cultured meat has the potential to provide a complementary meat industry with reduced environmental, ethical, and health impacts. However, major technological challenges remain which require time-and resource-intensive research and development efforts. Machine learning has the potential to accelerate cultured meat technology by streamlining experiments, predicting optimal results, and reducing experimentation time and resources. However, the use of machine learning in cultured meat is in its infancy. This review covers the work available to date on the use of machine learning in cultured meat and explores future possibilities. We address four major areas of cultured meat research and development: establishing cell lines, cell culture media design, microscopy and image analysis, and bioprocessing and food processing optimization. In addition, we have included a survey of datasets relevant to CM research. This review aims to provide the foundation necessary for both cultured meat and machine learning scientists to identify research opportunities at the intersection between cultured meat and machine learning.

Peanut oils from roasting operations: An overview of production technologies, flavor compounds, formation mechanisms, and affecting factors

Fragrant peanut oils (FPOs) are commonly defined as edible peanut oils having strong natural roasted peanut flavor without peculiar unpleasant odors and produced from peanut kernels through roasting/steaming and pressing operations, etc. The flavor of FPOs plays a crucial role in their acceptability and applications and their flavor profiles are an important factor in determining their overall quality. This paper presents a systematic literature review of recent advances and knowledge on FPOs, especially their flavors, in which it is focused on the evaluation of volatile compounds, the factors influencing the formation of flavor compounds, and formation mechanisms of those typical flavor compounds. More than 300 volatiles are found in FPOs, while some key aroma-active compounds and their potential formation pathways are examined. Factors that have big influences on flavor are discussed also, including the properties of raw materials, processing technologies, and storage conditions. Ultimately, the paper highlights the challenges facing, including the challenges in flavor analysis, the relationship between volatile compounds and sensory attributes, as well as the opening of the blackboxes of flavor formations during the processing steps, etc.

Overcoming the Limits of Cross-Sensitivity: Pattern Recognition Methods for Chemiresistive Gas Sensor Array

As information acquisition terminals for artificial olfaction, chemiresistive gas sensors are often troubled by their cross-sensitivity, and reducing their cross-response to ambient gases has always been a difficult and important point in the gas sensing area. Pattern recognition based on sensor array is the most conspicuous way to overcome the cross-sensitivity of gas sensors. It is crucial to choose an appropriate pattern recognition method for enhancing data analysis, reducing errors and improving system reliability, obtaining better classification or gas concentration prediction results. In this review, we analyze the sensing mechanism of cross-sensitivity for chemiresistive gas sensors. We further examine the types, working principles, characteristics, and applicable gas detection range of pattern recognition algorithms utilized in gas-sensing arrays. Additionally, we report, summarize, and evaluate the outstanding and novel advancements in pattern recognition methods for gas identification. At the same time, this work showcases the recent advancements in utilizing these methods for gas identification, particularly within three crucial domains: ensuring food safety, monitoring the environment, and aiding in medical diagnosis. In conclusion, this study anticipates future research prospects by considering the existing landscape and challenges. It is hoped that this work will make a positive contribution towards mitigating cross-sensitivity in gas-sensitive devices and offer valuable insights for algorithm selection in gas recognition applications.

Multioxide combinatorial libraries: fusing synthetic approaches and additive technologies for highly orthogonal electronic noses

This study evaluates the performance advancement of electronic noses, on-chip engineered multisensor systems, exploiting a combinatorial approach. We analyze a spectrum of metal oxide semiconductor materials produced by individual methods of liquid-phase synthesis and a combination of chemical deposition and sol-gel methods with hydrothermal treatment. These methods are demonstrated to enable obtaining a fairly wide range of nanomaterials that differ significantly in chemical composition, crystal structure, and morphological features. While synthesis routes foster diversity in material properties, microplotter printing ensures targeted precision in making on-chip arrays for evaluation of a combinatorial selectivity concept in the task of organic vapor, like alcohol homologs, acetone, and benzene, classification. The synthesized nanomaterials demonstrate a high chemiresistive response, with a limit of detection beyond ppm level. A specific combination of materials is demonstrated to be relevant when the number of sensors is low; however, such importance diminishes with an increase in the number of sensors. We show that on-chip material combinations could favor selectivity to a specific analyte, disregarding the others. Hence, modern synthesis methods and printing protocols supported by combinatorial analysis might pave the way for fabricating on-chip orthogonal multisensor systems.

Advances in olfactory augmented virtual reality towards future metaverse applications

Recent advances in virtual reality technologies accelerate the immersive interaction between human and augmented 3D virtual worlds. Here, the authors discuss olfactory feedback technologies that facilitate interaction with real and virtual objects and the evolution of wearable devices for immersive VR/AR applications.

Deciphering Odor Perception through EEG Brain Activity and Gas Sensors

Recent technological advances have led to innovations like electronic noses and gas sensors, proficient in detecting distinct odors. Despite this, the field of AI and robotics has only marginally explored olfaction, a sense crucial for evoking emotions and memories. Our study investigates the correlation between gas sensor signals and EEG activity during odor recognition. By comparing our findings with questionnaire results, we suggest that individual experiences might influence odor recognition in the human brain. We designed an odor-dispensing system and recorded EEG responses from 15 subjects to six odors, alongside concentration data of four gases for each odor. These EEG and gas sensor data were analyzed using two neural networks for odor classification. Combining EEG and gas sensor data, we attained a 44% accuracy in 6-class odor discrimination, indicating the potential of this integrated approach as a unique 'odor fingerprint' for odor identification.

AI: Bridging Ancient Wisdom and Modern Innovation in Traditional Chinese Medicine

The pursuit of groundbreaking health care innovations has led to the convergence of artificial intelligence (AI) and traditional Chinese medicine (TCM), thus marking a new frontier that demonstrates the promise of combining the advantages of ancient healing practices with cutting-edge advancements in modern technology. TCM, which is a holistic medical system with >2000 years of empirical support, uses unique diagnostic methods such as inspection, auscultation and olfaction, inquiry, and palpation. AI is the simulation of human intelligence processes by machines, especially via computer systems. TCM is experience oriented, holistic, and subjective, and its combination with AI has beneficial effects, which presumably arises from the perspectives of diagnostic accuracy, treatment efficacy, and prognostic veracity. The role of AI in TCM is highlighted by its use in diagnostics, with machine learning enhancing the precision of treatment through complex pattern recognition. This is exemplified by the greater accuracy of TCM syndrome differentiation via tongue images that are analyzed by AI. However, integrating AI into TCM also presents multifaceted challenges, such as data quality and ethical issues; thus, a unified strategy, such as the use of standardized data sets, is required to improve AI understanding and application of TCM principles. The evolution of TCM through the integration of AI is a key factor for elucidating new horizons in health care. As research continues to evolve, it is imperative that technologists and TCM practitioners collaborate to drive innovative solutions that push the boundaries of medical science and honor the profound legacy of TCM. We can chart a future course wherein AI-augmented TCM practices contribute to more systematic, effective, and accessible health care systems for all individuals.

PredCoffee: A binary classification approach specifically for coffee odor

Compared to traditional methods, using machine learning to assess or predict the odor of molecules can save costs in various aspects. Our research aims to collect molecules with coffee odor and summarize the regularity of these molecules, ultimately creating a binary classifier that can determine whether a molecule has a coffee odor. In this study, a total of 371 coffee-odor molecules and 9,700 non-coffee-odor molecules were collected. The Knowledge-guided Pre-training of Graph Transformer (KPGT), support vector machine (SVM), random forest (RF), multi-layer perceptron (MLP), and message-passing neural networks (MPNN) were used to train the data. The model with the best performance was selected as the basis of the predictor. The prediction accuracy value of the KPGT model exceeded 0.84 and the predictor has been deployed as a webserver PredCoffee.

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.

Integration of nontarget analysis with machine learning modeling for prioritization of odorous volatile organic compounds in surface water

Assessing the odor risk caused by volatile organic compounds (VOCs) in water has been a big challenge for water quality evaluation due to the abundance of odorants in water and the inherent difficulty in obtaining the corresponding odor sensory attributes. Here, a novel odor risk assessment approach has been established, incorporating nontarget screening for odorous VOC identification and machine learning (ML) modeling for odor threshold prediction. Twenty-nine odorous VOCs were identified using two-dimensional gas chromatography-time of flight mass spectrometry from four surface water sampling sites. These identified odorants primarily fell into the categories of ketones and ethers, and originated mainly from biological production. To obtain the odor threshold of these odorants, we trained an ML model for odor threshold prediction, which displayed good performance with accuracy of 79%. Further, an odor threshold-based prioritization approach was developed to rank the identified odorants. 2-Methylisoborneol and nonanal were identified as the main odorants contributing to water odor issues at the four sampling sites. This study provides an accessible method for accurate and quick determination of key odorants in source water, aiding in odor control and improved water quality management. ENVIRONMENTAL IMPLICATION: Water odor episodes have been persistent and significant issues worldwide, posing severe challenges to water treatment plants. Unpleasant odors in aquatic environments are predominantly caused by the occurrence of a wide range of volatile organic chemicals (VOCs). Given the vast number of newly-detected VOCs, experimental identification of the key odorants becomes difficult, making water odor issues complex to control. Herein, we propose a novel approach integrating nontarget analysis with machine learning models to accurate and quick determine the key odorants in waterbodies. We use the approach to analyze four samples with odor issues in Changsha, and prioritized the potential odorants.

Explainable chemical artificial intelligence from accurate machine learning of real-space chemical descriptors

Machine-learned computational chemistry has led to a paradoxical situation in which molecular properties can be accurately predicted, but they are difficult to interpret. Explainable AI (XAI) tools can be used to analyze complex models, but they are highly dependent on the AI technique and the origin of the reference data. Alternatively, interpretable real-space tools can be employed directly, but they are often expensive to compute. To address this dilemma between explainability and accuracy, we developed SchNet4AIM, a SchNet-based architecture capable of dealing with local one-body (atomic) and two-body (interatomic) descriptors. The performance of SchNet4AIM is tested by predicting a wide collection of real-space quantities ranging from atomic charges and delocalization indices to pairwise interaction energies. The accuracy and speed of SchNet4AIM breaks the bottleneck that has prevented the use of real-space chemical descriptors in complex systems. We show that the group delocalization indices, arising from our physically rigorous atomistic predictions, provide reliable indicators of supramolecular binding events, thus contributing to the development of Explainable Chemical Artificial Intelligence (XCAI) models.

Nature and human well-being: The olfactory pathway

The world is undergoing massive atmospheric and ecological change, driving unprecedented challenges to human well-being. Olfaction is a key sensory system through which these impacts occur. The sense of smell influences quality of and satisfaction with life, emotion, emotion regulation, cognitive function, social interactions, dietary choices, stress, and depressive symptoms. Exposures via the olfactory pathway can also lead to (anti-)inflammatory outcomes. Increased understanding is needed regarding the ways in which odorants generated by nature (i.e., natural olfactory environments) affect human well-being. With perspectives from a range of health, social, and natural sciences, we provide an overview of this unique sensory system, four consensus statements regarding olfaction and the environment, and a conceptual framework that integrates the olfactory pathway into an understanding of the effects of natural environments on human well-being. We then discuss how this framework can contribute to better accounting of the impacts of policy and land-use decision-making on natural olfactory environments and, in turn, on planetary health.

Transfer learning for a foundational chemistry model

Data-driven chemistry has garnered much interest concurrent with improvements in hardware and the development of new machine learning models. However, obtaining sufficiently large, accurate datasets of a desired chemical outcome for data-driven chemistry remains a challenge. The community has made significant efforts to democratize and curate available information for more facile machine learning applications, but the limiting factor is usually the laborious nature of generating large-scale data. Transfer learning has been noted in certain applications to alleviate some of the data burden, but this protocol is typically carried out on a case-by-case basis, with the transfer learning task expertly chosen to fit the finetuning. Herein, I develop a machine learning framework capable of accurate chemistry-relevant prediction amid general sources of low data. First, a chemical "foundational model" is trained using a dataset of ∼1 million experimental organic crystal structures. A task specific module is then stacked atop this foundational model and subjected to finetuning. This approach achieves state-of-the-art performance on a diverse set of tasks: toxicity prediction, yield prediction, and odor prediction.

Predicting and improving complex beer flavor through machine learning

The perception and appreciation of food flavor depends on many interacting chemical compounds and external factors, and therefore proves challenging to understand and predict. Here, we combine extensive chemical and sensory analyses of 250 different beers to train machine learning models that allow predicting flavor and consumer appreciation. For each beer, we measure over 200 chemical properties, perform quantitative descriptive sensory analysis with a trained tasting panel and map data from over 180,000 consumer reviews to train 10 different machine learning models. The best-performing algorithm, Gradient Boosting, yields models that significantly outperform predictions based on conventional statistics and accurately predict complex food features and consumer appreciation from chemical profiles. Model dissection allows identifying specific and unexpected compounds as drivers of beer flavor and appreciation. Adding these compounds results in variants of commercial alcoholic and non-alcoholic beers with improved consumer appreciation. Together, our study reveals how big data and machine learning uncover complex links between food chemistry, flavor and consumer perception, and lays the foundation to develop novel, tailored foods with superior flavors.

An advance in novel intelligent sensory technologies: From an implicit-tracking perspective of food perception

Food sensory evaluation mainly includes explicit and implicit measurement methods. Implicit measures of consumer perception are gaining significant attention in food sensory and consumer science as they provide effective, subconscious, objective analysis. A wide range of advanced technologies are now available for analyzing physiological and psychological responses, including facial analysis technology, neuroimaging technology, autonomic nervous system technology, and behavioral pattern measurement. However, researchers in the food field often lack systematic knowledge of these multidisciplinary technologies and struggle with interpreting their results. In order to bridge this gap, this review systematically describes the principles and highlights the applications in food sensory and consumer science of facial analysis technologies such as eye tracking, facial electromyography, and automatic facial expression analysis, as well as neuroimaging technologies like electroencephalography, magnetoencephalography, functional magnetic resonance imaging, and functional near-infrared spectroscopy. Furthermore, we critically compare and discuss these advanced implicit techniques in the context of food sensory research and then accordingly propose prospects. Ultimately, we conclude that implicit measures should be complemented by traditional explicit measures to capture responses beyond preference. Facial analysis technologies offer a more objective reflection of sensory perception and attitudes toward food, whereas neuroimaging techniques provide valuable insight into the implicit physiological responses during food consumption. To enhance the interpretability and generalizability of implicit measurement results, further sensory studies are needed. Looking ahead, the combination of different methodological techniques in real-life situations holds promise for consumer sensory science in the field of food research.