Explainable Supervised Machine Learning Model To Predict Solvation Gibbs Energy
Many challenges persist in developing accurate computational models for predicting solvation free energy (ΔGsol). Despite recent developments in Machine Learning (ML) methodologies that outperformed traditional quantum mechanical models, several issues remain concerning explanatory insights for broad chemical predictions with an acceptable speed-accuracy trade-off. To overcome this, we present a novel supervised ML model to predict the ΔGsol for an array of solvent-solute pairs. Using two different ensemble regressor algorithms, we made fast and accurate property predictions using open-source chemical features, encoding complex electronic, structural, and surface area descriptors for every solvent and solute. By integrating molecular properties and chemical interaction features, we have analyzed individual descriptor importance and optimized our model though explanatory information form feature groups. On aqueous and organic solvent databases, ML models revealed the predictive relevance of solutes with increasing polar surface area and decreasing polarizability, yielding better results than state-of-the-art benchmark Neural Network methods (without complex quantum mechanical or molecular dynamic simulations). Both algorithms successfully outperformed previous ΔGsol predictions methods, with a maximum absolute error of 0.22 ± 0.02 kcal mol-1, further validated in an external benchmark database and with solvent hold-out tests. With these explanatory and statistical insights, they allow a thoughtful application of this method for predicting other thermodynamic properties, stressing the relevance of ML modeling for further complex computational chemistry problems.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2024 |
|---|---|
| Erschienen: |
2024 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:64 |
|---|---|
| Enthalten in: |
Journal of chemical information and modeling - 64(2024), 7 vom: 08. Apr., Seite 2250-2262 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Ferraz-Caetano, José [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
|---|
| Anmerkungen: |
Date Completed 09.04.2024 Date Revised 25.04.2024 published: Print-Electronic Citation Status MEDLINE |
|---|
| doi: |
10.1021/acs.jcim.3c00544 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM36102293X |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM36102293X | ||
| 003 | DE-627 | ||
| 005 | 20240425232334.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 231226s2024 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1021/acs.jcim.3c00544 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1386.xml |
| 035 | |a (DE-627)NLM36102293X | ||
| 035 | |a (NLM)37603608 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Ferraz-Caetano, José |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Explainable Supervised Machine Learning Model To Predict Solvation Gibbs Energy |
| 264 | 1 | |c 2024 | |
| 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 09.04.2024 | ||
| 500 | |a Date Revised 25.04.2024 | ||
| 500 | |a published: Print-Electronic | ||
| 500 | |a Citation Status MEDLINE | ||
| 520 | |a Many challenges persist in developing accurate computational models for predicting solvation free energy (ΔGsol). Despite recent developments in Machine Learning (ML) methodologies that outperformed traditional quantum mechanical models, several issues remain concerning explanatory insights for broad chemical predictions with an acceptable speed-accuracy trade-off. To overcome this, we present a novel supervised ML model to predict the ΔGsol for an array of solvent-solute pairs. Using two different ensemble regressor algorithms, we made fast and accurate property predictions using open-source chemical features, encoding complex electronic, structural, and surface area descriptors for every solvent and solute. By integrating molecular properties and chemical interaction features, we have analyzed individual descriptor importance and optimized our model though explanatory information form feature groups. On aqueous and organic solvent databases, ML models revealed the predictive relevance of solutes with increasing polar surface area and decreasing polarizability, yielding better results than state-of-the-art benchmark Neural Network methods (without complex quantum mechanical or molecular dynamic simulations). Both algorithms successfully outperformed previous ΔGsol predictions methods, with a maximum absolute error of 0.22 ± 0.02 kcal mol-1, further validated in an external benchmark database and with solvent hold-out tests. With these explanatory and statistical insights, they allow a thoughtful application of this method for predicting other thermodynamic properties, stressing the relevance of ML modeling for further complex computational chemistry problems | ||
| 650 | 4 | |a Journal Article | |
| 650 | 7 | |a Solvents |2 NLM | |
| 650 | 7 | |a Water |2 NLM | |
| 650 | 7 | |a 059QF0KO0R |2 NLM | |
| 650 | 7 | |a Solutions |2 NLM | |
| 700 | 1 | |a Teixeira, Filipe |e verfasserin |4 aut | |
| 700 | 1 | |a Cordeiro, M Natália D S |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Journal of chemical information and modeling |d 2005 |g 64(2024), 7 vom: 08. Apr., Seite 2250-2262 |w (DE-627)NLM153268735 |x 1549-960X |7 nnns |
| 773 | 1 | 8 | |g volume:64 |g year:2024 |g number:7 |g day:08 |g month:04 |g pages:2250-2262 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1021/acs.jcim.3c00544 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 64 |j 2024 |e 7 |b 08 |c 04 |h 2250-2262 | ||