Machine Learning Models for Predicting Molecular UV-Vis Spectra with Quantum Mechanical Properties
Accurate understanding of ultraviolet-visible (UV-vis) spectra is critical for the high-throughput synthesis of compounds for drug discovery. Experimentally determining UV-vis spectra can become expensive when dealing with a large quantity of novel compounds. This provides us an opportunity to drive computational advances in molecular property predictions using quantum mechanics and machine learning methods. In this work, we use both quantum mechanically (QM) predicted and experimentally measured UV-vis spectra as input to devise four different machine learning architectures, UVvis-SchNet, UVvis-DTNN, UVvis-Transformer, and UVvis-MPNN, and assess the performance of each method. We find that the UVvis-MPNN model outperforms the other models when using optimized 3D coordinates and QM predicted spectra as input features. This model has the highest performance for predicting UV-vis spectra with a training RMSE of 0.06 and validation RMSE of 0.08. Most importantly, our model can be used for the challenging task of predicting differences in the UV-vis spectral signatures of regioisomers.
Medienart: |
E-Artikel |
---|
Erscheinungsjahr: |
2023 |
---|---|
Erschienen: |
2023 |
Enthalten in: |
Zur Gesamtaufnahme - volume:63 |
---|---|
Enthalten in: |
Journal of chemical information and modeling - 63(2023), 5 vom: 13. März, Seite 1462-1471 |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
McNaughton, Andrew D [VerfasserIn] |
---|
Links: |
---|
Themen: |
---|
Anmerkungen: |
Date Completed 14.03.2023 Date Revised 05.06.2023 published: Print-Electronic Citation Status MEDLINE |
---|
doi: |
10.1021/acs.jcim.2c01662 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM353536962 |
---|
LEADER | 01000naa a22002652 4500 | ||
---|---|---|---|
001 | NLM353536962 | ||
003 | DE-627 | ||
005 | 20231226060229.0 | ||
007 | cr uuu---uuuuu | ||
008 | 231226s2023 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1021/acs.jcim.2c01662 |2 doi | |
028 | 5 | 2 | |a pubmed24n1178.xml |
035 | |a (DE-627)NLM353536962 | ||
035 | |a (NLM)36847578 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a McNaughton, Andrew D |e verfasserin |4 aut | |
245 | 1 | 0 | |a Machine Learning Models for Predicting Molecular UV-Vis Spectra with Quantum Mechanical Properties |
264 | 1 | |c 2023 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a ƒaComputermedien |b c |2 rdamedia | ||
338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
500 | |a Date Completed 14.03.2023 | ||
500 | |a Date Revised 05.06.2023 | ||
500 | |a published: Print-Electronic | ||
500 | |a Citation Status MEDLINE | ||
520 | |a Accurate understanding of ultraviolet-visible (UV-vis) spectra is critical for the high-throughput synthesis of compounds for drug discovery. Experimentally determining UV-vis spectra can become expensive when dealing with a large quantity of novel compounds. This provides us an opportunity to drive computational advances in molecular property predictions using quantum mechanics and machine learning methods. In this work, we use both quantum mechanically (QM) predicted and experimentally measured UV-vis spectra as input to devise four different machine learning architectures, UVvis-SchNet, UVvis-DTNN, UVvis-Transformer, and UVvis-MPNN, and assess the performance of each method. We find that the UVvis-MPNN model outperforms the other models when using optimized 3D coordinates and QM predicted spectra as input features. This model has the highest performance for predicting UV-vis spectra with a training RMSE of 0.06 and validation RMSE of 0.08. Most importantly, our model can be used for the challenging task of predicting differences in the UV-vis spectral signatures of regioisomers | ||
650 | 4 | |a Journal Article | |
650 | 4 | |a Research Support, U.S. Gov't, Non-P.H.S. | |
700 | 1 | |a Joshi, Rajendra P |e verfasserin |4 aut | |
700 | 1 | |a Knutson, Carter R |e verfasserin |4 aut | |
700 | 1 | |a Fnu, Anubhav |e verfasserin |4 aut | |
700 | 1 | |a Luebke, Kevin J |e verfasserin |4 aut | |
700 | 1 | |a Malerich, Jeremiah P |e verfasserin |4 aut | |
700 | 1 | |a Madrid, Peter B |e verfasserin |4 aut | |
700 | 1 | |a Kumar, Neeraj |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t Journal of chemical information and modeling |d 2005 |g 63(2023), 5 vom: 13. März, Seite 1462-1471 |w (DE-627)NLM153268735 |x 1549-960X |7 nnns |
773 | 1 | 8 | |g volume:63 |g year:2023 |g number:5 |g day:13 |g month:03 |g pages:1462-1471 |
856 | 4 | 0 | |u http://dx.doi.org/10.1021/acs.jcim.2c01662 |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d 63 |j 2023 |e 5 |b 13 |c 03 |h 1462-1471 |