Category Ranking
98%
Total Visits
921
Avg Visit Duration
2 minutes
Citations
20
Article Abstract
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.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC11904650 | PMC |
| http://dx.doi.org/10.1021/acsomega.4c07078 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Electrophysiological responses of the clam (Ruditapes decussatus) osphradium to amino acids and alarm cues.
J Comp Physiol A Neuroethol Sens Neural Behav Physiol
September 2025
Centre of Marine Sciences (CCMAR), University of Algarve, Campus de Gambelas, Faro, 8005- 139, Portugal.
Chemical sensing of the surrounding environment is crucial for many aspects of bivalve biology, such as food detection and predator avoidance. Aquatic organisms strongly depend on chemosensory systems; however, little is known about chemosensory systems in bivalves. To understand how the carpet shell clam (Ruditapes decussatus) senses its surrounding chemical environment, we used an electrophysiological technique - the electro-osphradiogram - to assess the sensitivity of the osphradium to different putative odorants (amino acids, bile acids) and odours (predator-released cues and signals from con- and heterospecific bivalves).
View Article and Find Full Text PDFDecoding flavor diversity in lemon varieties: a multivariate flavoromics approach coupled with statistical analysis for comprehensive flavor profiling.
Food Chem
August 2025
Department of Food Science and Technology, Zhejiang University of Technology, Zhejiang, Hangzhou 310014, China; Moganshan Research Institute at Deqing Country Zhejiang University of Technology, Huzhou 313200, China. Electronic address:
Lemon is widely valued for its bioactive components and unique flavor, which are influenced by diverse volatile organic compounds (VOCs). This study implemented flavoromics, a comprehensive profiling of flavor, combining non-volatile flavor with E-nose, HS-SPME-GC--MS, HS-GC-IMS, relative odor activity value (ROAV), and multivariate statistical analysis to systematically characterize the aroma profiles of five lemon varieties (Rough lemon, Key lime, Eureka lemon, Tahiti lime, and Rosso lemon). A total of 44 and 50 VOCs were identified by HS-SPME-GC-MS and HS-GC-IMS, respectively.
View Article and Find Full Text PDFMetabolite and Sensory Profiling of Microwave-Assisted and Ultrasonic-Assisted Alkalized Cocoa Powders.
J Food Sci
September 2025
Department of Biotechnology, Graduate School of Engineering, Osaka University, Suita, Osaka, Japan.
Microwave (MA)- and ultrasonic-assisted (UA) alkalization were applied to cocoa powders for 5, 10, and 15 min to investigate their effects on metabolite composition, sensory profile, and consumer liking. Widely targeted gas chromatography-mass spectrometry (GC-MS) analysis showed alkalization altered metabolite profiles: Natural cocoa powders contained more amino acids, sugars, and flavonoids, while alkalized samples had elevated organic acids. Compared to conventionally alkalized (CA) samples, only UA15 showed a significant increase in 3,4-dihydroxybenzoic acid.
View Article and Find Full Text PDFOdor-Chemical Correlation-Based Quality Evaluation of Atractylodes macrocephala via Electronic Nose, HPLC, and Machine Learning.
Biomed Chromatogr
October 2025
The Second Affiliated Hospital of Zhejiang Chinese Medical University, Hangzhou, China.
Atractylodis Macrocephalae Rhizoma (AMR) is a kind of traditional Chinese medicine, with the variety from Yuqian, Lin'an District, Hangzhou, considered the highest quality and termed Atractylodes macrocephalacy Yuzhu (AMY). This study examined the relationship between AMR's "scent indicates quality" principle and its chemical composition. Oil chamber analysis showed Lin'an samples had the highest density and largest chamber size.
View Article and Find Full Text PDFEffects of harvest maturity coupled with various drying methods on the quality and aroma composition of gray jujube powder.
Food Chem X
August 2025
Key Laboratory of Processing and Quality Safety Control of Characteristic Agricultural Products, Ministry of Agriculture and Rural Affairs (Jointly built by Ministry and Province), School of Food Science and Technology, Shihezi University, Shihezi, Xinjiang 832000, China.
This study aimed to explore the impact of different harvest maturity stages (white, semi-ripe, and fully ripe) and various drying methods [freeze drying (FD), freeze drying followed by heat pump drying, and FD followed by far-infrared drying (FD-FID)] on the quality and aroma profile of gray jujube powder. The results demonstrated that both the harvest maturity stage and drying methods significantly ( < 0.05) influenced the physical properties, chemical composition, and aroma profile of gray jujube powder.
View Article and Find Full Text PDF