QSAR model as a random event: A case of rat toxicity

被引:32
作者
Toropova, Alla P. [1 ]
Toropov, Andrey A. [1 ]
Benfenati, Emilio [1 ]
Leszczynska, Danuta [2 ]
Leszczynski, Jerzy [3 ]
机构
[1] IRCCS Ist Ric Farmacol Mario Negri, I-20156 Milan, Italy
[2] Jackson State Univ, Dept Civil & Environm Engn, Interdisciplinary Nanotox Ctr, Jackson, MS 39217 USA
[3] Jackson State Univ, Dept Chem & Biochem, Interdisciplinary Nanotox Ctr, Jackson, MS 39217 USA
基金
美国国家科学基金会;
关键词
QSAR; Validation; Domain of applicability; Oral rat toxicity; CORAL software; MONTE-CARLO METHOD; OPTIMAL DESCRIPTORS; QSPR MODELS; INHIBITORS; BALANCE; SMILES; CORAL; VALIDATION; PREDICTION; CARCINOGENICITY;
D O I
10.1016/j.bmc.2015.01.055
中图分类号
Q5 [生物化学]; Q7 [分子生物学];
学科分类号
071010 ; 081704 ;
摘要
Quantitative structure-property/activity relationships (QSPRs/QSARs) can be used to predict physicochemical and/or biochemical behavior of substances which were not studied experimentally. Typically predicted values for chemicals in the training set are accurate since they were used to build the model. QSPR/QSAR models must be validated before they are used in practice. Unfortunately, the majority of the suggested approaches of the validation of QSPR/QSAR models are based on consideration of geometrical features of clusters of data points in the plot of experimental versus calculated values of an endpoint. We believe these geometrical criteria can be more useful if they are analyzed for several splits into the training and test sets. In this way, one can estimate the reproducibility of the model with various splits and better evaluate model reliability. The probability of the correct prediction of an endpoint for external validation set (in the series of the above-mentioned splits) can provide an useful way to evaluate the domain of applicability of the model. (C) 2015 Elsevier Ltd. All rights reserved.
引用
收藏
页码:1223 / 1230
页数:8
相关论文
共 37 条
[1]   Ligand - based virtual screening procedure for the prediction and the identification of novel β-amyloid aggregation inhibitors using Kohonen maps and Counterpropagation Artificial Neural Networks [J].
Afantitis, Antreas ;
Melagraki, Georgia ;
Koutentis, Panayiotis A. ;
Sarimveis, Haralambos ;
Kollias, George .
EUROPEAN JOURNAL OF MEDICINAL CHEMISTRY, 2011, 46 (02) :497-508
[2]  
[Anonymous], 2011, ACD CHEMSKETCH FREEW
[3]   Relation between second and third geometric-arithmetic indices of trees [J].
Furtula, Boris ;
Gutman, Ivan .
JOURNAL OF CHEMOMETRICS, 2011, 25 (02) :87-91
[4]   A comparative QSAR on 1,2,5-thiadiazolidin-3-one 1,1-dioxide compounds as selective inhibitors of human serine proteinases [J].
Garcia, Javier ;
Duchowicz, Pablo R. ;
Rozas, Maria F. ;
Caram, Jose A. ;
Mirifico, Maria V. ;
Fernandez, Francisco M. ;
Castro, Eduardo A. .
JOURNAL OF MOLECULAR GRAPHICS & MODELLING, 2011, 31 :10-19
[5]   QSAR Study and Molecular Design of Open-Chain Enaminones as Anticonvulsant Agents [J].
Garro Martinez, Juan C. ;
Duchowicz, Pablo R. ;
Estrada, Mario R. ;
Zamarbide, Graciela N. ;
Castro, Eduardo A. .
INTERNATIONAL JOURNAL OF MOLECULAR SCIENCES, 2011, 12 (12) :9354-9368
[6]   Beware of q2! [J].
Golbraikh, A ;
Tropsha, A .
JOURNAL OF MOLECULAR GRAPHICS & MODELLING, 2002, 20 (04) :269-276
[7]  
Hollas B, 2005, CROAT CHEM ACTA, V78, P489
[8]   QSAR on aryl-piperazine derivatives with activity on malaria [J].
Ibezim, Emmanuel ;
Duchowicz, Pablo R. ;
Ortiz, Erlinda V. ;
Castro, Eduardo A. .
CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS, 2012, 110 (01) :81-88
[9]   QSAR Modelling of Rat Acute Toxicity on the Basis of PASS Prediction [J].
Lagunin, Alexey ;
Zakharov, Alexey ;
Filimonov, Dmitry ;
Poroikov, Vladimir .
MOLECULAR INFORMATICS, 2011, 30 (2-3) :241-250
[10]   Ligand and Structure Based Virtual Screening Strategies for Hit-Finding and Optimization of Hepatitis C Virus (HCV) Inhibitors [J].
Melagraki, G. ;
Afantitis, A. .
CURRENT MEDICINAL CHEMISTRY, 2011, 18 (17) :2612-2619