Augmenting chemical databases for atomistic machine learning by sampling conformational space
Machine learning (ML) has become a standard tool for the exploration of the chemical space. Much of the performance of such models depends on the chosen database for a given task. Here, this aspect is investigated for “chemical tasks” including the prediction of hybridization, oxidation, substituent...
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Dokumenttyp: | Article (Journal) |
| Sprache: | Englisch |
| Veröffentlicht: |
August 4, 2025
|
| In: |
Journal of chemical information and modeling
Year: 2025, Jahrgang: 65, Heft: 16, Pages: 8563-8578 |
| ISSN: | 1549-960X |
| DOI: | 10.1021/acs.jcim.5c00752 |
| Online-Zugang: | Verlag, kostenfrei, Volltext: https://doi.org/10.1021/acs.jcim.5c00752 Verlag, kostenfrei, Volltext: https://pubs.acs.org/doi/10.1021/acs.jcim.5c00752 
|
| Verfasserangaben: | Luis Itza Vazquez-Salazar and Markus Meuwly |
MARC
| LEADER | 00000naa a2200000 c 4500 | ||
|---|---|---|---|
| 001 | 1942597304 | ||
| 003 | DE-627 | ||
| 005 | 20251126133917.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 251126s2025 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1021/acs.jcim.5c00752 |2 doi | |
| 035 | |a (DE-627)1942597304 | ||
| 035 | |a (DE-599)KXP1942597304 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rda | ||
| 041 | |a eng | ||
| 084 | |a 30 |2 sdnb | ||
| 100 | 1 | |a Vazquez-Salazar, Luis Itza |e VerfasserIn |0 (DE-588)1382728360 |0 (DE-627)1942598467 |4 aut | |
| 245 | 1 | 0 | |a Augmenting chemical databases for atomistic machine learning by sampling conformational space |c Luis Itza Vazquez-Salazar and Markus Meuwly |
| 264 | 1 | |c August 4, 2025 | |
| 300 | |a 16 | ||
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a Computermedien |b c |2 rdamedia | ||
| 338 | |a Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Gesehen am 26.11.2025 | ||
| 520 | |a Machine learning (ML) has become a standard tool for the exploration of the chemical space. Much of the performance of such models depends on the chosen database for a given task. Here, this aspect is investigated for “chemical tasks” including the prediction of hybridization, oxidation, substituent effects, and aromaticity, starting from an initial “restricted” database (iRD). Choosing molecules for augmenting this iRD, including increasing numbers of conformations generated at different temperatures, and retraining the models can improve predictions of the models on the selected “tasks”. Addition of a small percentage of conformations (1%) obtained at 300 K improves the performance in almost all cases. On the other hand, and in line with previous studies, redundancy and highly deformed structures in the augmentation set compromise prediction quality. Energy and bond distributions were evaluated by means of Kullback-Leibler (DKL) and Jensen-Shannon (DJS) divergence and Wasserstein distance (W1). The findings of this work provide a baseline for the rational augmentation of chemical databases or the creation of synthetic databases. | ||
| 700 | 1 | |a Meuwly, Markus |e VerfasserIn |0 (DE-588)1162233664 |0 (DE-627)1025706129 |0 (DE-576)507288262 |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Journal of chemical information and modeling |d Washington, DC : American Chemical Society, 2005 |g 65(2025), 16, Seite 8563-8578 |h Online-Ressource |w (DE-627)302467327 |w (DE-600)1491237-5 |w (DE-576)090855124 |x 1549-960X |7 nnas |a Augmenting chemical databases for atomistic machine learning by sampling conformational space |
| 773 | 1 | 8 | |g volume:65 |g year:2025 |g number:16 |g pages:8563-8578 |g extent:16 |a Augmenting chemical databases for atomistic machine learning by sampling conformational space |
| 856 | 4 | 0 | |u https://doi.org/10.1021/acs.jcim.5c00752 |x Verlag |x Resolving-System |z kostenfrei |3 Volltext |
| 856 | 4 | 0 | |u https://pubs.acs.org/doi/10.1021/acs.jcim.5c00752 |x Verlag |z kostenfrei |3 Volltext |
| 951 | |a AR | ||
| 992 | |a 20251126 | ||
| 993 | |a Article | ||
| 994 | |a 2025 | ||
| 998 | |g 1382728360 |a Vazquez-Salazar, Luis Itza |m 1382728360:Vazquez-Salazar, Luis Itza |d 130000 |d 130300 |e 130000PV1382728360 |e 130300PV1382728360 |k 0/130000/ |k 1/130000/130300/ |p 1 |x j | ||
| 999 | |a KXP-PPN1942597304 |e 4814234643 | ||
| BIB | |a Y | ||
| SER | |a journal | ||
| JSO | |a {"title":[{"title":"Augmenting chemical databases for atomistic machine learning by sampling conformational space","title_sort":"Augmenting chemical databases for atomistic machine learning by sampling conformational space"}],"person":[{"display":"Vazquez-Salazar, Luis Itza","roleDisplay":"VerfasserIn","role":"aut","family":"Vazquez-Salazar","given":"Luis Itza"},{"display":"Meuwly, Markus","roleDisplay":"VerfasserIn","role":"aut","family":"Meuwly","given":"Markus"}],"note":["Gesehen am 26.11.2025"],"type":{"bibl":"article-journal","media":"Online-Ressource"},"language":["eng"],"recId":"1942597304","origin":[{"dateIssuedKey":"2025","dateIssuedDisp":"August 4, 2025"}],"id":{"eki":["1942597304"],"doi":["10.1021/acs.jcim.5c00752"]},"name":{"displayForm":["Luis Itza Vazquez-Salazar and Markus Meuwly"]},"physDesc":[{"extent":"16 S."}],"relHost":[{"origin":[{"publisher":"American Chemical Society","dateIssuedDisp":"[2005]-","publisherPlace":"Washington, DC"}],"id":{"issn":["1549-960X"],"zdb":["1491237-5"],"eki":["302467327"]},"physDesc":[{"extent":"Online-Ressource"}],"title":[{"title":"Journal of chemical information and modeling","title_sort":"Journal of chemical information and modeling"}],"type":{"media":"Online-Ressource","bibl":"periodical"},"note":["Gesehen am 03.05.2023"],"disp":"Augmenting chemical databases for atomistic machine learning by sampling conformational spaceJournal of chemical information and modeling","recId":"302467327","language":["eng"],"pubHistory":["Volume 45, issue 1 (January 2005)-"],"part":{"pages":"8563-8578","issue":"16","year":"2025","extent":"16","text":"65(2025), 16, Seite 8563-8578","volume":"65"}}]} | ||
| SRT | |a VAZQUEZSALAUGMENTING4202 | ||