Cargando…

Comparing molecular representations, e-nose signals, and other featurization, for learning to smell aroma molecules

Recent research has attempted to predict our perception of odorants using Machine Learning models. The featurization of the olfactory stimuli usually represents the odorants using molecular structure parameters, molecular fingerprints, mass spectra, or e-nose signals. However, the impact of the choi...

Descripción completa

Detalles Bibliográficos
Autores principales: Debnath, Tanoy, Badreddine, Samy, Kumari, Priyadarshini, Spranger, Michael
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10420360/
https://www.ncbi.nlm.nih.gov/pubmed/37566580
http://dx.doi.org/10.1371/journal.pone.0289881
_version_ 1785088760994594816
author Debnath, Tanoy
Badreddine, Samy
Kumari, Priyadarshini
Spranger, Michael
author_facet Debnath, Tanoy
Badreddine, Samy
Kumari, Priyadarshini
Spranger, Michael
author_sort Debnath, Tanoy
collection PubMed
description Recent research has attempted to predict our perception of odorants using Machine Learning models. The featurization of the olfactory stimuli usually represents the odorants using molecular structure parameters, molecular fingerprints, mass spectra, or e-nose signals. However, the impact of the choice of featurization on predictive performance remains poorly reported in direct comparative studies. This paper experiments with different sensory features for several olfactory perception tasks. We investigate the multilabel classification of aroma molecules in odor descriptors. We investigate single-label classification not only in fine-grained odor descriptors (‘orange’, ‘waxy’, etc.), but also in odor descriptor groups. We created a database of odor vectors for 114 aroma molecules to conduct our experiments using a QCM (Quartz Crystal Microbalance) type smell sensor module (Aroma Coder®V2 Set). We compare these smell features with different baseline features to evaluate the cluster composition, considering the frequencies of the top odor descriptors carried by the aroma molecules. Experimental results suggest a statistically significant better performance of the QCM type smell sensor module compared with other baseline features with F1 evaluation metric.
format Online
Article
Text
id pubmed-10420360
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Public Library of Science
record_format MEDLINE/PubMed
spelling pubmed-104203602023-08-12 Comparing molecular representations, e-nose signals, and other featurization, for learning to smell aroma molecules Debnath, Tanoy Badreddine, Samy Kumari, Priyadarshini Spranger, Michael PLoS One Research Article Recent research has attempted to predict our perception of odorants using Machine Learning models. The featurization of the olfactory stimuli usually represents the odorants using molecular structure parameters, molecular fingerprints, mass spectra, or e-nose signals. However, the impact of the choice of featurization on predictive performance remains poorly reported in direct comparative studies. This paper experiments with different sensory features for several olfactory perception tasks. We investigate the multilabel classification of aroma molecules in odor descriptors. We investigate single-label classification not only in fine-grained odor descriptors (‘orange’, ‘waxy’, etc.), but also in odor descriptor groups. We created a database of odor vectors for 114 aroma molecules to conduct our experiments using a QCM (Quartz Crystal Microbalance) type smell sensor module (Aroma Coder®V2 Set). We compare these smell features with different baseline features to evaluate the cluster composition, considering the frequencies of the top odor descriptors carried by the aroma molecules. Experimental results suggest a statistically significant better performance of the QCM type smell sensor module compared with other baseline features with F1 evaluation metric. Public Library of Science 2023-08-11 /pmc/articles/PMC10420360/ /pubmed/37566580 http://dx.doi.org/10.1371/journal.pone.0289881 Text en © 2023 Debnath et al https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
spellingShingle Research Article
Debnath, Tanoy
Badreddine, Samy
Kumari, Priyadarshini
Spranger, Michael
Comparing molecular representations, e-nose signals, and other featurization, for learning to smell aroma molecules
title Comparing molecular representations, e-nose signals, and other featurization, for learning to smell aroma molecules
title_full Comparing molecular representations, e-nose signals, and other featurization, for learning to smell aroma molecules
title_fullStr Comparing molecular representations, e-nose signals, and other featurization, for learning to smell aroma molecules
title_full_unstemmed Comparing molecular representations, e-nose signals, and other featurization, for learning to smell aroma molecules
title_short Comparing molecular representations, e-nose signals, and other featurization, for learning to smell aroma molecules
title_sort comparing molecular representations, e-nose signals, and other featurization, for learning to smell aroma molecules
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10420360/
https://www.ncbi.nlm.nih.gov/pubmed/37566580
http://dx.doi.org/10.1371/journal.pone.0289881
work_keys_str_mv AT debnathtanoy comparingmolecularrepresentationsenosesignalsandotherfeaturizationforlearningtosmellaromamolecules
AT badreddinesamy comparingmolecularrepresentationsenosesignalsandotherfeaturizationforlearningtosmellaromamolecules
AT kumaripriyadarshini comparingmolecularrepresentationsenosesignalsandotherfeaturizationforlearningtosmellaromamolecules
AT sprangermichael comparingmolecularrepresentationsenosesignalsandotherfeaturizationforlearningtosmellaromamolecules