Accurate Prediction of Adiabatic Ionization Potentials of Organic Molecules using Quantum Chemistry Assisted Machine Learning
In previous work (Dandu et al., J. Phys. Chem. A, 2022, 126, 4528-4536), we were successful in predicting accurate atomization energies of organic molecules using machine learning (ML) models, obtaining an accuracy as low as 0.1 kcal/mol compared to the G4MP2 method. In this work, we extend the use of these ML models to adiabatic ionization potentials on data sets of energies generated using quantum chemical calculations. Atomic specific corrections that were found to improve atomization energies from quantum chemical calculations have also been used in this study to improve ionization potentials. The quantum chemical calculations were performed on 3405 molecules containing eight or fewer non-hydrogen atoms derived from the QM9 data set, using the B3LYP functional with the 6-31G(2df,p) basis set for optimization. Low-fidelity IPs for these structures were obtained using two density functional methods: B3LYP/6-31+G(2df,p) and ωB97XD/6-311+G(3df,2p). Highly accurate G4MP2 calculations were performed on these optimized structures to obtain high-fidelity IPs to use in ML models based on the low-fidelity IPs. Our best performing ML methods gave IPs of organic molecules within a mean absolute deviation of 0.035 eV from the G4MP2 IPs for the whole data set. This work demonstrates that ML predictions assisted by quantum chemical calculations can be used to successfully predict IPs of organic molecules for use in high throughput screening.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2023 |
|---|---|
| Erschienen: |
2023 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:127 |
|---|---|
| Enthalten in: |
The journal of physical chemistry. A - 127(2023), 28 vom: 20. Juli, Seite 5914-5920 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Dandu, Naveen K [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
|---|
| Anmerkungen: |
Date Revised 20.07.2023 published: Print-Electronic Citation Status PubMed-not-MEDLINE |
|---|
| doi: |
10.1021/acs.jpca.3c00823 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM359073611 |
|---|
| LEADER | 01000naa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM359073611 | ||
| 003 | DE-627 | ||
| 005 | 20231226080109.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 231226s2023 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1021/acs.jpca.3c00823 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1196.xml |
| 035 | |a (DE-627)NLM359073611 | ||
| 035 | |a (NLM)37406209 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Dandu, Naveen K |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Accurate Prediction of Adiabatic Ionization Potentials of Organic Molecules using Quantum Chemistry Assisted Machine Learning |
| 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 Revised 20.07.2023 | ||
| 500 | |a published: Print-Electronic | ||
| 500 | |a Citation Status PubMed-not-MEDLINE | ||
| 520 | |a In previous work (Dandu et al., J. Phys. Chem. A, 2022, 126, 4528-4536), we were successful in predicting accurate atomization energies of organic molecules using machine learning (ML) models, obtaining an accuracy as low as 0.1 kcal/mol compared to the G4MP2 method. In this work, we extend the use of these ML models to adiabatic ionization potentials on data sets of energies generated using quantum chemical calculations. Atomic specific corrections that were found to improve atomization energies from quantum chemical calculations have also been used in this study to improve ionization potentials. The quantum chemical calculations were performed on 3405 molecules containing eight or fewer non-hydrogen atoms derived from the QM9 data set, using the B3LYP functional with the 6-31G(2df,p) basis set for optimization. Low-fidelity IPs for these structures were obtained using two density functional methods: B3LYP/6-31+G(2df,p) and ωB97XD/6-311+G(3df,2p). Highly accurate G4MP2 calculations were performed on these optimized structures to obtain high-fidelity IPs to use in ML models based on the low-fidelity IPs. Our best performing ML methods gave IPs of organic molecules within a mean absolute deviation of 0.035 eV from the G4MP2 IPs for the whole data set. This work demonstrates that ML predictions assisted by quantum chemical calculations can be used to successfully predict IPs of organic molecules for use in high throughput screening | ||
| 650 | 4 | |a Journal Article | |
| 700 | 1 | |a Ward, Logan |e verfasserin |4 aut | |
| 700 | 1 | |a Assary, Rajeev S |e verfasserin |4 aut | |
| 700 | 1 | |a Redfern, Paul C |e verfasserin |4 aut | |
| 700 | 1 | |a Curtiss, Larry A |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t The journal of physical chemistry. A |d 1997 |g 127(2023), 28 vom: 20. Juli, Seite 5914-5920 |w (DE-627)NLM098261479 |x 1520-5215 |7 nnns |
| 773 | 1 | 8 | |g volume:127 |g year:2023 |g number:28 |g day:20 |g month:07 |g pages:5914-5920 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1021/acs.jpca.3c00823 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 127 |j 2023 |e 28 |b 20 |c 07 |h 5914-5920 | ||