Motional representation; the ability to predict odor characters using molecular vibrations
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909798306414592 |
|---|---|
| author | Harada, Yuki Maeda, Shuichi Shen, Junwei Misonou, Taku Hori, Hirokazu Nakamura, Shinichiro |
| author_facet | Harada, Yuki Maeda, Shuichi Shen, Junwei Misonou, Taku Hori, Hirokazu Nakamura, Shinichiro |
| contents | The prediction of odor characters is still impossible based on the odorant molecular structure. We designed a CNN-based regressor for computed parameters in molecular vibrations (CNN\_vib), in order to investigate the ability to predict odor characters of molecular vibrations. In this study, we explored following three approaches for the predictability; (i) CNN with molecular vibrational parameters, (ii) logistic regression based on vibrational spectra, and (iii) logistic regression with molecular fingerprint(FP). Our investigation demonstrates that both (i) and (ii) provide predictablity, and also that the vibrations as an explanatory variable (i and ii) and logistic regression with fingerprints (iii) show nearly identical tendencies. The predictabilities of (i) and (ii), depending on odor descriptors, are comparable to those of (iii). Our research shows that odor is predictable by odorant molecular vibration as well as their shapes alone. Our findings provide insight into the representation of molecular motional features beyond molecular structures. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_16245 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Motional representation; the ability to predict odor characters using molecular vibrations Harada, Yuki Maeda, Shuichi Shen, Junwei Misonou, Taku Hori, Hirokazu Nakamura, Shinichiro Chemical Physics Machine Learning The prediction of odor characters is still impossible based on the odorant molecular structure. We designed a CNN-based regressor for computed parameters in molecular vibrations (CNN\_vib), in order to investigate the ability to predict odor characters of molecular vibrations. In this study, we explored following three approaches for the predictability; (i) CNN with molecular vibrational parameters, (ii) logistic regression based on vibrational spectra, and (iii) logistic regression with molecular fingerprint(FP). Our investigation demonstrates that both (i) and (ii) provide predictablity, and also that the vibrations as an explanatory variable (i and ii) and logistic regression with fingerprints (iii) show nearly identical tendencies. The predictabilities of (i) and (ii), depending on odor descriptors, are comparable to those of (iii). Our research shows that odor is predictable by odorant molecular vibration as well as their shapes alone. Our findings provide insight into the representation of molecular motional features beyond molecular structures. |
| title | Motional representation; the ability to predict odor characters using molecular vibrations |
| topic | Chemical Physics Machine Learning |
| url | https://arxiv.org/abs/2509.16245 |