Prediction of pH-dependent aqueous solubility of druglike molecules

Research output: Contribution to journal › Journal article › Research › peer-review

Standard

Prediction of pH-dependent aqueous solubility of druglike molecules. / Hansen, Niclas Tue; Kouskoumvekaki, Irene; Jørgensen, Flemming Steen; Brunak, Søren; Jónsdóttir, Svava Osk.

In: Journal of Chemical Information and Modeling, Vol. 46, No. 6, 2012, p. 2601-2609.

Research output: Contribution to journal › Journal article › Research › peer-review

Harvard

Hansen, NT, Kouskoumvekaki, I, Jørgensen, FS, Brunak, S & Jónsdóttir, SO 2012, 'Prediction of pH-dependent aqueous solubility of druglike molecules', Journal of Chemical Information and Modeling, vol. 46, no. 6, pp. 2601-2609. https://doi.org/10.1021/ci600292q

APA

Hansen, N. T., Kouskoumvekaki, I., Jørgensen, F. S., Brunak, S., & Jónsdóttir, S. O. (2012). Prediction of pH-dependent aqueous solubility of druglike molecules. Journal of Chemical Information and Modeling, 46(6), 2601-2609. https://doi.org/10.1021/ci600292q

Vancouver

Hansen NT, Kouskoumvekaki I, Jørgensen FS, Brunak S, Jónsdóttir SO. Prediction of pH-dependent aqueous solubility of druglike molecules. Journal of Chemical Information and Modeling. 2012;46(6):2601-2609. https://doi.org/10.1021/ci600292q

Author

Hansen, Niclas Tue ; Kouskoumvekaki, Irene ; Jørgensen, Flemming Steen ; Brunak, Søren ; Jónsdóttir, Svava Osk. / Prediction of pH-dependent aqueous solubility of druglike molecules. In: Journal of Chemical Information and Modeling. 2012 ; Vol. 46, No. 6. pp. 2601-2609.

Bibtex

@article{7083cab0980411de8bc9000ea68e967b,
title = "Prediction of pH-dependent aqueous solubility of druglike molecules",
abstract = "In the present work, the Henderson-Hasselbalch (HH) equation has been employed for the development of a tool for the prediction of pH-dependent aqueous solubility of drugs and drug candidates. A new prediction method for the intrinsic solubility was developed, based on artificial neural networks that have been trained on a druglike PHYSPROP subset of 4548 compounds. For the prediction of acid/base dissociation coefficients, the commercial tool Marvin has been used, following validation on a data set of 467 molecules from the PHYSPROP database. The best performing network for intrinsic solubility predictions has a cross-validated root mean square error (RMSE) of 0.70 log S-units, while the Marvin pKa plug-in has an RMSE of 0.71 pH-units. A data set of 27 drugs with experimentally determined pH-solubility curves was assembled from the literature for the validation of the combined pH-dependent model, giving a mean RMSE of 0.79 log S-units. Finally, the combined model has been applied on profiling the solubility space at low pH of five large vendor libraries.",
keywords = "Chemistry, Pharmaceutical, Crystallization, Databases as Topic, Drug Design, Hydrogen-Ion Concentration, Models, Chemical, Models, Statistical, Models, Theoretical, Neural Networks (Computer), Pharmaceutical Preparations, Software, Solubility, Solvents, Technology, Pharmaceutical, Water",
author = "Hansen, {Niclas Tue} and Irene Kouskoumvekaki and J{\o}rgensen, {Flemming Steen} and S{\o}ren Brunak and J{\'o}nsd{\'o}ttir, {Svava Osk}",
year = "2012",
doi = "10.1021/ci600292q",
language = "English",
volume = "46",
pages = "2601--2609",
journal = "Journal of Chemical Information and Modeling",
issn = "1549-9596",
publisher = "American Chemical Society",
number = "6",

}

RIS

TY - JOUR

T1 - Prediction of pH-dependent aqueous solubility of druglike molecules

AU - Hansen, Niclas Tue

AU - Kouskoumvekaki, Irene

AU - Jørgensen, Flemming Steen

AU - Brunak, Søren

AU - Jónsdóttir, Svava Osk

PY - 2012

Y1 - 2012

N2 - In the present work, the Henderson-Hasselbalch (HH) equation has been employed for the development of a tool for the prediction of pH-dependent aqueous solubility of drugs and drug candidates. A new prediction method for the intrinsic solubility was developed, based on artificial neural networks that have been trained on a druglike PHYSPROP subset of 4548 compounds. For the prediction of acid/base dissociation coefficients, the commercial tool Marvin has been used, following validation on a data set of 467 molecules from the PHYSPROP database. The best performing network for intrinsic solubility predictions has a cross-validated root mean square error (RMSE) of 0.70 log S-units, while the Marvin pKa plug-in has an RMSE of 0.71 pH-units. A data set of 27 drugs with experimentally determined pH-solubility curves was assembled from the literature for the validation of the combined pH-dependent model, giving a mean RMSE of 0.79 log S-units. Finally, the combined model has been applied on profiling the solubility space at low pH of five large vendor libraries.

AB - In the present work, the Henderson-Hasselbalch (HH) equation has been employed for the development of a tool for the prediction of pH-dependent aqueous solubility of drugs and drug candidates. A new prediction method for the intrinsic solubility was developed, based on artificial neural networks that have been trained on a druglike PHYSPROP subset of 4548 compounds. For the prediction of acid/base dissociation coefficients, the commercial tool Marvin has been used, following validation on a data set of 467 molecules from the PHYSPROP database. The best performing network for intrinsic solubility predictions has a cross-validated root mean square error (RMSE) of 0.70 log S-units, while the Marvin pKa plug-in has an RMSE of 0.71 pH-units. A data set of 27 drugs with experimentally determined pH-solubility curves was assembled from the literature for the validation of the combined pH-dependent model, giving a mean RMSE of 0.79 log S-units. Finally, the combined model has been applied on profiling the solubility space at low pH of five large vendor libraries.

KW - Chemistry, Pharmaceutical

KW - Crystallization

KW - Databases as Topic

KW - Drug Design

KW - Hydrogen-Ion Concentration

KW - Models, Chemical

KW - Models, Statistical

KW - Models, Theoretical

KW - Neural Networks (Computer)

KW - Pharmaceutical Preparations

KW - Software

KW - Solubility

KW - Solvents

KW - Technology, Pharmaceutical

KW - Water

U2 - 10.1021/ci600292q

DO - 10.1021/ci600292q

M3 - Journal article

C2 - 17125200

VL - 46

SP - 2601

EP - 2609

JO - Journal of Chemical Information and Modeling

JF - Journal of Chemical Information and Modeling

SN - 1549-9596

IS - 6

ER -

ID: 14147481