Toward Novel Universal Descriptors: Charge Fingerprints

被引：29

作者：

Burden, Frank R. ^{[2
,3
]}

Polley, Mitchell J. ^{[1
]}

Winkler, David A. ^{[1
]}

机构：

[1] CSIRO Mol & Hlth Technol, Clayton, Vic 3169, Australia

[2] Monash Univ, Sch Chem, Clayton, Vic 3168, Australia

[3] SciMetrics Ltd, Carlton N, Vic 3054, Australia

来源：

JOURNAL OF CHEMICAL INFORMATION AND MODELING | 2009年 / 49卷 / 03期

关键词：

ELECTRONEGATIVITY EQUALIZATION METHOD; SIGNATURE MOLECULAR DESCRIPTOR; REGULARIZED NEURAL-NETWORKS; QUANTITATIVE STRUCTURE; ACUTE TOXICITY; PARTITION-COEFFICIENTS; ATOMIC CHARGES; PREDICTION; QSAR; SURFACE;

D O I：

10.1021/ci800290h

中图分类号：

R914 [药物化学];

学科分类号：

100701 ;

摘要：

Although there are a myriad of molecular descriptors for QSAR described in the literature, many descriptors contain similar information as others or are information poor. Recent work has suggested that it may be possible to discover a relatively small pool of 'universal' descriptors from which subsets can be drawn to build a diverse variety of models. We describe a new type of descriptor of this type, the charge fingerprint. This descriptor family can build good QSAR models of a diverse range of physicochemical and biological properties and can be calculated quickly and easily. It appears to be useful for modeling large data sets and has potential for screening large virtual libraries.

引用

页码：710 / 715

页数：6

共 33 条

[1] The electronegativity equalization method I: Parametrization and validation for atomic charge calculations
Bultinck, P
Langenaeker, W
Lahorte, P
De Proft, F
Geerlings, P
Waroquier, M
Tollenaere, JP
[J]. JOURNAL OF PHYSICAL CHEMISTRY A, 2002, 106 (34) : 7887 - 7894
[2] Quantitative structure - Activity relationship studies using gaussian processes
Burden, FR
[J]. JOURNAL OF CHEMICAL INFORMATION AND COMPUTER SCIENCES, 2001, 41 (03): : 830 - 835
[3] New QSAR methods applied to structure-activity mapping and combinatorial chemistry
Burden, FR
Winkler, DA
[J]. JOURNAL OF CHEMICAL INFORMATION AND COMPUTER SCIENCES, 1999, 39 (02): : 236 - 242
[4] Robust QSAR models using Bayesian regularized neural networks
Burden, FR
Winkler, DA
[J]. JOURNAL OF MEDICINAL CHEMISTRY, 1999, 42 (16) : 3183 - 3187
[5] A chemically intuitive molecular index based on the eigenvalues of a modified adjacency matrix
Burden, FR
[J]. QUANTITATIVE STRUCTURE-ACTIVITY RELATIONSHIPS, 1997, 16 (04): : 309 - 314
[6] A quantitative structure-activity relationships model for the acute toxicity of substituted benzenes to Tetrahymena pyriformis using Bayesian-regularized neural networks
Burden, FR
Winkler, DA
[J]. CHEMICAL RESEARCH IN TOXICOLOGY, 2000, 13 (06) : 436 - 440
[7] Use of automatic relevance determination in QSAR studies using Bayesian neural networks
Burden, FR
Ford, MG
Whitley, DC
Winkler, DA
[J]. JOURNAL OF CHEMICAL INFORMATION AND COMPUTER SCIENCES, 2000, 40 (06): : 1423 - 1430
[8] QSAR and QSPR based solely on surface properties?
Clark, T
[J]. JOURNAL OF MOLECULAR GRAPHICS & MODELLING, 2004, 22 (06) : 519 - 525
[9] Native atom types for knowledge-based potentials: Application to binding energy prediction
Dominy, BN
Shakhnovich, EI
[J]. JOURNAL OF MEDICINAL CHEMISTRY, 2004, 47 (18) : 4538 - 4558
[10] New molecular descriptors based on local properties at the molecular surface and a boiling-point model derived from them
Ehresmann, B
de Groot, MJ
Alex, A
Clark, T
[J]. JOURNAL OF CHEMICAL INFORMATION AND COMPUTER SCIENCES, 2004, 44 (02): : 658 - 668

← 1 2 3 4 →