Predicting absolute aqueous solubility by applying a machine learning model for an artificially liquid-state as proxy for the solid-state
Abstract In this study, we use machine learning algorithms with QM-derived COSMO-RS descriptors, along with Morgan fingerprints, to predict the absolute solubility of drug-like compounds. The QM-derived descriptors account for the molecular properties of the solute, i.e., the solute–solute interactions in an artificial-liquid-state (super-cooled liquid), and the solute–solvent interactions in solution. We employ two main approaches to predict solubility: (i) a hypothetical pathway that involves melting the solute at room temperature T = T¯ (%${\Delta }_{fus}{G}_{A}^{\ominus }%$) and mixing the artificially liquid solute into the solvent (%${\Delta }_{m}{G}_{\left(A:B\right)}^{\ominus }%$). In this approach %${\Delta }_{fus}{G}_{A}^{\ominus }%$ is predicted using machine learning models, and the %${\Delta }_{m}{G}_{\left(A:B\right)}^{\ominus }%$ is obtained from COSMO-RS calculations; (ii) direct solubility prediction using machine learning algorithms. The models were trained on a large number of Bayer in-house compounds for which water solubility data is available at physiological pH of 6.5 and ambient temperature. We also evaluated our models using external datasets from a solubility challenge. Our models present great improvements compared to the absolute solubility prediction with the QSAR model for the artificial liquid state as implemented in the COSMOtherm software, for both in-house and external datasets. We are furthermore able to demonstrate the superiority of QM-derived descriptors compared to cheminformatics descriptors. We finally present low-cost alternative models using fragment-based COSMOquick calculations with only marginal reduction in the quality of predicted solubility..
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2023 |
|---|---|
| Erschienen: |
2023 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:37 |
|---|---|
| Enthalten in: |
Journal of computer aided molecular design - 37(2023), 12 vom: 25. Okt., Seite 765-789 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Gheta, Sadra Kashef Ol [VerfasserIn] |
|---|
| Links: |
Volltext [lizenzpflichtig] |
|---|
| Themen: |
|---|
| Anmerkungen: |
© The Author(s), under exclusive licence to Springer Nature Switzerland AG 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. |
|---|
| doi: |
10.1007/s10822-023-00538-w |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
SPR05358726X |
|---|
| LEADER | 01000naa a22002652 4500 | ||
|---|---|---|---|
| 001 | SPR05358726X | ||
| 003 | DE-627 | ||
| 005 | 20231101064656.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 231101s2023 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1007/s10822-023-00538-w |2 doi | |
| 035 | |a (DE-627)SPR05358726X | ||
| 035 | |a (SPR)s10822-023-00538-w-e | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Gheta, Sadra Kashef Ol |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Predicting absolute aqueous solubility by applying a machine learning model for an artificially liquid-state as proxy for the solid-state |
| 264 | 1 | |c 2023 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a Computermedien |b c |2 rdamedia | ||
| 338 | |a Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. | ||
| 520 | |a Abstract In this study, we use machine learning algorithms with QM-derived COSMO-RS descriptors, along with Morgan fingerprints, to predict the absolute solubility of drug-like compounds. The QM-derived descriptors account for the molecular properties of the solute, i.e., the solute–solute interactions in an artificial-liquid-state (super-cooled liquid), and the solute–solvent interactions in solution. We employ two main approaches to predict solubility: (i) a hypothetical pathway that involves melting the solute at room temperature T = T¯ (%${\Delta }_{fus}{G}_{A}^{\ominus }%$) and mixing the artificially liquid solute into the solvent (%${\Delta }_{m}{G}_{\left(A:B\right)}^{\ominus }%$). In this approach %${\Delta }_{fus}{G}_{A}^{\ominus }%$ is predicted using machine learning models, and the %${\Delta }_{m}{G}_{\left(A:B\right)}^{\ominus }%$ is obtained from COSMO-RS calculations; (ii) direct solubility prediction using machine learning algorithms. The models were trained on a large number of Bayer in-house compounds for which water solubility data is available at physiological pH of 6.5 and ambient temperature. We also evaluated our models using external datasets from a solubility challenge. Our models present great improvements compared to the absolute solubility prediction with the QSAR model for the artificial liquid state as implemented in the COSMOtherm software, for both in-house and external datasets. We are furthermore able to demonstrate the superiority of QM-derived descriptors compared to cheminformatics descriptors. We finally present low-cost alternative models using fragment-based COSMOquick calculations with only marginal reduction in the quality of predicted solubility. | ||
| 650 | 4 | |a Solubility |7 (dpeaa)DE-He213 | |
| 650 | 4 | |a Machine learning |7 (dpeaa)DE-He213 | |
| 650 | 4 | |a Physics-based descriptors |7 (dpeaa)DE-He213 | |
| 700 | 1 | |a Bonin, Anne |4 aut | |
| 700 | 1 | |a Gerlach, Thomas |4 aut | |
| 700 | 1 | |a Göller, Andreas H. |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Journal of computer aided molecular design |d Dordrecht [u.a.] : Springer Science + Business Media B.V, 1987 |g 37(2023), 12 vom: 25. Okt., Seite 765-789 |w (DE-627)SPR013556029 |w (DE-600)2008643-X |x 1573-4951 |7 nnns |
| 773 | 1 | 8 | |g volume:37 |g year:2023 |g number:12 |g day:25 |g month:10 |g pages:765-789 |
| 856 | 4 | 0 | |u https://dx.doi.org/10.1007/s10822-023-00538-w |z lizenzpflichtig |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_SPRINGER | ||
| 951 | |a AR | ||
| 952 | |d 37 |j 2023 |e 12 |b 25 |c 10 |h 765-789 | ||