Novel enhanced applications of QSPR models: Temperature dependence of aqueous solubility

被引:14
作者
Klimenko, Kyrylo [1 ,2 ]
Kuz'min, Victor [1 ]
Ognichenko, Liudmila [1 ]
Gorb, Leonid [3 ]
Shukla, Manoj [4 ]
Vinas, Natalia [4 ]
Perkins, Edward [4 ]
Polishchuk, Pavel [5 ]
Artemenko, Anatoly [1 ]
Leszczynski, Jerzy [6 ]
机构
[1] Natl Acad Sci Ukraine, Dept Mol Struct & Chemoinformat, AV Bogatsky Phys Chem Inst, Lustdorfskaya Doroga 86, UA-65080 Odessa, Ukraine
[2] Univ Strasbourg, CNRS, UniStra, Lab Chemoinformat,UMR 7140, 1 Rue B Pascal, F-67000 Strasbourg, France
[3] HX5 LLC, Vichsburg, MS 39180 USA
[4] US Army Engineer Res & Dev Ctr, Vicksburg, MS 39180 USA
[5] Palacky Univ, Inst Mol & Translat Med, Hnevotinska 1333-5, Olomouc 77900, Czech Republic
[6] Jackson State Univ, Dept Chem, Interdisciplinary Ctr Nanotox, Jackson, MS 39217 USA
基金
美国国家科学基金会;
关键词
QSPR; feature net; temperature-dependent; aqueous solubility; RANDOM FOREST; SIMPLEX REPRESENTATION; PREDICTION; QSAR; ETHANOL; WATER; SYSTEM; ACID;
D O I
10.1002/jcc.24424
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
A model developed to predict aqueous solubility at different temperatures has been proposed based on quantitative structure-property relationships (QSPR) methodology. The prediction consists of two steps. The first one predicts the value of k parameter in the linear equation lgSw=kT+c, where S-w is the value of solubility and T is the value of temperature. The second step uses Random Forest technique to create high-efficiency QSPR model. The performance of the model is assessed using cross-validation and external test set prediction. Predictive capacity of developed model is compared with COSMO-RS approximation, which has quantum chemical and thermodynamic foundations. The comparison shows slightly better prediction ability for the QSPR model presented in this publication. (c) 2016 Wiley Periodicals, Inc.
引用
收藏
页码:2045 / 2051
页数:7
相关论文
共 41 条
[1]   Solubilities of L-aspartic, DL-aspartic, DL-glutamic, p-hydroxybenzoic, o-anistic, p-anisic, and itaconic acids in water from T = 278 K to T = 345 K [J].
Apelblat, A ;
Manzurola, E .
JOURNAL OF CHEMICAL THERMODYNAMICS, 1997, 29 (12) :1527-1533
[2]   Solubilities of o-acetylsalicylic, 4-aminosalicylic, 3,5-dinitrosalicylic, and p-toluic acid, and magnesium-DL-aspartate in water from T = (278 to 348) K [J].
Apelblat, A ;
Manzurola, E .
JOURNAL OF CHEMICAL THERMODYNAMICS, 1999, 31 (01) :85-91
[3]  
Avdeef A., 2003, Absorption and Drug Development, P91
[4]   Random forests [J].
Breiman, L .
MACHINE LEARNING, 2001, 45 (01) :5-32
[5]  
Butina D, 2003, J CHEM INF COMP SCI, V43, P837, DOI 10.1021/6020279y
[6]   QSAR study of antimicrobial activity of some 3-nitrocoumarins and related compounds [J].
Debeljak, Zeljko ;
Skrbo, Armin ;
Jasprica, Ivona ;
Mornar, Ana ;
Plecko, Vanda ;
Banjanac, Mihajlo ;
Medic-Saric, Marica .
JOURNAL OF CHEMICAL INFORMATION AND MODELING, 2007, 47 (03) :918-926
[7]  
Ioffe B. V., 1983, CHEM REFRACTOMETRIC, P350
[8]   Structure-toxicity relationships of nitroaromatic compounds [J].
Isayev, Olexandr ;
Rasulev, Bakhtiyor ;
Gorb, Leonid ;
Leszczynski, Jerzy .
MOLECULAR DIVERSITY, 2006, 10 (02) :233-245
[9]   ESTIMATION OF ATOMIC CHARGES BY AN ELECTRONEGATIVITY EQUALIZATION PROCEDURE CALIBRATED WITH CORE BINDING-ENERGIES [J].
JOLLY, WL ;
PERRY, WB .
JOURNAL OF THE AMERICAN CHEMICAL SOCIETY, 1973, 95 (17) :5442-5450
[10]   Structurally diverse quantitative structure-property relationship correlations of technologically relevant physical properties [J].
Katritzky, AR ;
Maran, U ;
Lobanov, VS ;
Karelson, M .
JOURNAL OF CHEMICAL INFORMATION AND COMPUTER SCIENCES, 2000, 40 (01) :1-18