Cited by 3,735Computational Drug Discovery MethodsMachine Learning in Materials ScienceAdvanced Chemical Physics Studies

The DOI matches its Crossref record; 39 of the 39 references it cites were found in a registry or an index.

Beware of q2!

Golbraikh, Alexander, Tropsha, Alexander·2002·Journal of Molecular Graphics and Modelling

DOI 10.1016/s1093-3263(01)00123-1

Open this paper in CoChat — free account

Abstract

Validation is a crucial aspect of any quantitative structure-activity relationship (QSAR) modeling. This paper examines one of the most popular validation criteria, leave-one-out cross-validated R2 (LOO q2). Often, a high value of this statistical characteristic (q2 > 0.5) is considered as a proof of the high predictive ability of the model. In this paper, we show that this assumption is generally incorrect. In the case of 3D QSAR, the lack of the correlation between the high LOO q2 and the high predictive ability of a QSAR model has been established earlier [Pharm. Acta Helv. 70 (1995) 149; J. Chemomet. 10(1996)95; J. Med. Chem. 41 (1998) 2553]. In this paper, we use two-dimensional (2D) molecular descriptors and k nearest neighbors (kNN) QSAR method for the analysis of several datasets. No correlation between the values of q2 for the training set and predictive ability for the test set was found for any of the datasets. Thus, the high value of LOO q2 appears to be the necessary but not the sufficient condition for the model to have a high predictive power. We argue that this is the general property of QSAR models developed using LOO cross-validation. We emphasize that the external validation is the only way to establish a reliable QSAR model. We formulate a set of criteria for evaluation of predictive ability of QSAR models.

Integrity signals

Registry

Crossref · 10.1016/s1093-3263(01)00123-1

Cites

39 of 39 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Graph theory
Harary, F. (1969) · Cited by 10,739
Structural Determination of Paraffin Boiling Points
Wiener, H. (1947) · Journal of the American Chemical Society · doi:10.1021/ja01193a005 · Cited by 4,184
Comparative molecular field analysis (CoMFA). 1. Effect of shape on binding of steroids to carrier proteins
Cramer, R. D., Patterson, D. E., & Bunce, J. D. (1988) · Journal of the American Chemical Society · doi:10.1021/ja00226a005 · Cited by 3,931
Characterization of molecular branching
Randić, M. (1975) · Journal of the American Chemical Society · doi:10.1021/ja00856a001 · Cited by 3,664
Substituent constants for correlation analysis in chemistry and biology
Hansch, C. H., & Leo, A. J. (1979) · Medical Entomology and Zoology · Cited by 2,910
Molecular Connectivity in Chemistry and Drug Research
(1976) · Medicinal chemistry · doi:10.1016/b978-0-12-406560-4.x5001-6 · Cited by 1,628
Applied Statistics
Sachs, L. (1984) · Springer series in statistics · doi:10.1007/978-1-4612-5246-7 · Cited by 1,016
Graph theory and molecular orbitals. XII. Acyclic polyenes
Gutman, İ., ić, B. R., Trinajstić, N., & WILCOX, C. F. J. (1975) · The Journal of Chemical Physics · doi:10.1063/1.430994 · Cited by 829
Molecular Structure Description: The Electrotopological State
Kier, L. B., & Hall, L. H. (1999) · Medical Entomology and Zoology · Cited by 467
Novel Variable Selection Quantitative Structure−Property Relationship Approach Based on the k -Nearest-Neighbor Principle
Zheng, W., & Tropsha, A. (1999) · Journal of Chemical Information and Computer Sciences · doi:10.1021/ci980033m · Cited by 450
Self-citation

Show all 39 references

Research works printed but not linked: 6

S. Clementi, S. Wold, How to choose the proper statistical method, in: H. van de Waterbeemd (Ed.), Chemometrics Methods in Molecular Design, VCH, Weinheim, 1995, pp. 319–338.
S. Wold, PLS for multivariate linear modeling, in: H. van de Waterbeemd (Ed.), Chemometrics Methods in Molecular Design, VCH, Weinheim, 1995, pp. 195–218.
L.B. Kier, L.H. Hall, Molecular Connectivity in Structure–Activity Analysis, Wiley, New York, 1986.
D. Bonchev, Overall connectivity and molecular complexity, in: J. Devillers, A.T. Balaban (Eds.), Topological Indices and Related Descriptors, Gordon and Breach, Reading, UK, 1999, pp. 361–401.
R.D. Clark, D.G. Sprous, J.M. Leonard, Validating models based on large dataset, in: H.-D. Höltje, W. Sippl (Eds.), Rational Approaches to Drug Design. Proceedings of the 13th European Symposium on Quantitative Structure–Activity Relationships, Prous Sci., 2001, 475–485.
A. Golbraikh, D. Bonchev, Y.-D. Xiao, A. Tropsha, Novel chiral topological descriptors and their applications to QSAR, in: H.-D. Höltje, W. Sippl (Eds.), Rational Approaches to Drug Design. Proceedings of the 13th European Symposium on Quantitative Structure–Activity relationships, Aug. 27–Sept. 1, 2000, Duesseldorf, Germany, Prous Science, 2001, 219–223.

Sorted by citations

Items 601–700 of 1,004

ADME properties evaluation in drug discovery: in silico prediction of blood–brain partitioning
Zhu, L., Zhao, J., Zhang, Y., Zhou, W., Yin, L., Wang, Y., Fan, Y., Chen, Y., & Liu, H. (2018) · Molecular Diversity · doi:10.1007/s11030-018-9866-8 · Cited by 48
Insight into glycogen synthase kinase-3β inhibitory activity of phyto-constituents from Melissa officinalis: in silico studies
Iwaloye, O., Elekofehinti, O. O., Oluwarotimi, E. A., Kikiowo, B., & Fadipe, T. M. (2020) · In Silico Pharmacology · doi:10.1007/s40203-020-00054-x · Cited by 48
Prediction of hERG potassium channel affinity by the CODESSA approach
Coi, A., Massarelli, I., Murgia, L., Saraceno, M., Calderone, V., & Bianucci, A. M. (2006) · Bioorganic & Medicinal Chemistry · doi:10.1016/j.bmc.2005.12.030 · Cited by 48
“In Silico” Design of New Uranyl Extractants Based on Phosphoryl-Containing Podands: QSPR Studies, Generation and Screening of Virtual Combinatorial Library, and Experimental Tests
Varnek, A. A., Fourches, D., Solov’ev, V. P., Баулин, В. Е., Turanov, A. N., Карандашев, В. К., Fara, D. C., & KATRITZKY, A. R. (2004) · Journal of Chemical Information and Computer Sciences · doi:10.1021/ci049976b · Cited by 48
Protein Quadratic Indices of the “Macromolecular Pseudograph’s α-Carbon Atom Adjacency Matrix”. 1. Prediction of Arc Repressor Alanine-mutant’s Stability
Marrero‐Ponce, Y., Marrero, R. M., Castro, E. A., de Armas, R. R., González‐Díaz, H., Zaldívar, V. R., & Torrens, F. (2004) · Molecules · doi:10.3390/91201124 · Cited by 48
Modeling Toxicity by Using Supervised Kohonen Neural Networks
Mazzatorta, P., Vračko, M., Jezierska, A., & Benfenati, E. (2003) · Journal of Chemical Information and Computer Sciences · doi:10.1021/ci0256182 · Cited by 48
Novel scaffold of natural compound eliciting sweet taste revealed by machine learning
Bouysset, C., Belloir, C., Antonczak, S., Briand, L. V., & Fiorucci, S. (2020) · Food Chemistry · doi:10.1016/j.foodchem.2020.126864 · Cited by 47
Comparison of various methods for validity evaluation of QSAR models
Shayanfar, S., & Shayanfar, A. (2022) · BMC Chemistry · doi:10.1186/s13065-022-00856-4 · Cited by 51
“and r 2 0 is the coefficient of determination between the experimental activity and predicted values and predicted versus experimental activity, respectively, based on regression through origin analysis (linear regression by least square method without a constant term) [19].”
Method
Estimation of compressive strength of waste concrete utilizing fly ash/slag in concrete with interpretable approaches: optimization and graphical user interface (GUI)
Dodo, Y. A., Arif, K., Alyami, M., Ali, M., Najeh, T., & Gamil, Y. (2024) · Scientific Reports · doi:10.1038/s41598-024-54513-y · Cited by 47
QSAR model for predicting cell viability of human embryonic kidney cells exposed to SiO2 nanoparticles
Manganelli, S., Leone, C., Toropov, A. A., Toropova, A. P., & Benfenati, E. (2015) · Chemosphere · doi:10.1016/j.chemosphere.2015.09.086 · Cited by 47
Molecular dynamics simulation study and molecular docking descriptors in structure-based QSAR on acetylcholinesterase (AChE) inhibitors
Gharaghani, S., Khayamian, T., & Ebrahimi, M. (2013) · SAR and QSAR in environmental research · doi:10.1080/1062936x.2013.792877 · Cited by 48
“We used the statistical parameters recommended by Tropsha et al. [46] and Golbraikh and Tropsha [57] for evaluation of the developed model.”
BackgroundInfluential
First report on development of quantitative interspecies structure–carcinogenicity relationship models and exploring discriminatory features for rodent carcinogenicity of diverse organic chemicals using OECD guidelines
Kar, S., & Roy, K. (2012) · Chemosphere · doi:10.1016/j.chemosphere.2011.12.019 · Cited by 47
Quantitative Structure-Property Relationship (QSPR) Modeling of Drug-Loaded Polymeric Micelles via Genetic Function Approximation
Wu, W., Zhang, C., Lin, W., Chen, Q., Guo, X., Qian, Y., & Zhang, L. (2015) · PLOS ONE · doi:10.1371/journal.pone.0119575 · Cited by 47
Development and Evaluation of a QSPR Model for the Prediction of Diamagnetic Susceptibility
Afantitis, A., Melagraki, G., Sarimveis, H., Koutentis, P. A., Markopoulos, J., & Igglessi‐Markopoulou, O. (2007) · QSAR & Combinatorial Science · doi:10.1002/qsar.200730083 · Cited by 47
A computational intelligence‐based approach for short‐term traffic flow prediction
Zargari, S. A., Siabil, S. Z., Alavi, A. H., & Gandomi, A. H. (2010) · Expert Systems · doi:10.1111/j.1468-0394.2010.00567.x · Cited by 47
“Furthermore, new criteria recommended by Golbraikh and Tropsha (2002) were checked for external validation of the models on the test data sets.”
Method
Hansch analysis of veratric acid derivatives as antimicrobial agents
Narasimhan, B., Ohlan, S., Ohlan, R., Judge, V., & Narang, R. (2008) · European Journal of Medicinal Chemistry · doi:10.1016/j.ejmech.2008.05.008 · Cited by 47
QSAR as a random event: a case of NOAEL
Toropova, A. P., Toropov, A. A., Veselinović, J. B., & Veselinović, A. M. (2014) · Environmental Science and Pollution Research · doi:10.1007/s11356-014-3977-2 · Cited by 47
“The main goal of any QSPR modeling is developing a robust model capable of predicting the property of new molecules in objective, reliable, and precise manner (Golbraikh and Tropsha 2002).”
Method
Validation of Quantitative Structure-Activity Relationship (QSAR) Model for Photosensitizer Activity Prediction
Frimayanti, N., Yam, M. L., Lee, H. B., Othman, R., Zain, S. M., & Rahman, N. A. (2011) · International Journal of Molecular Sciences · doi:10.3390/ijms12128626 · Cited by 47
“Residual plots (scatter) are used to detect the existence of outliers from a QSAR model [21,22].”
BackgroundMethod
Molecular docking assisted 3D-QSAR study of benzylidene-2,4-thiazolidinedione derivatives as PTP-1B inhibitors for the management of Type-2 diabetes mellitus
Verma, S. K., & Thareja, S. (2016) · RSC Advances · doi:10.1039/c6ra03067j · Cited by 47
Performance of machine learning algorithms for qualitative and quantitative prediction drug blockade of hERG1 channel
Wacker, S., & Noskov, S. Y. (2017) · Computational Toxicology · doi:10.1016/j.comtox.2017.05.001 · Cited by 47
“To estimate the model performance it was recommended to use multiple metrics and based on cross-validation and external data, that was not used to select or train the model 35–37 .”
BackgroundMethod
Toxicity of contaminants of emerging concern to Dugesia japonica: QSTR modeling and toxicity relationship with Daphnia magna
Önlü, S., & Saçan, M. T. (2018) · Journal of Hazardous Materials · doi:10.1016/j.jhazmat.2018.02.046 · Cited by 47
QSAR Models for Nitrogen Containing Monophosphonate and Bisphosphonate Derivatives as Human Farnesyl Pyrophosphate Synthase Inhibitors Based on Monte Carlo Method
Kumar, P. P., Kumar, A., Sindhu, J., & Lal, S. (2018) · Drug Research · doi:10.1055/a-0652-5290 · Cited by 47
“Cross-validated Q2 interpret the predictive ability of the model [73, 74].”
MethodInfluential
Prediction of the adsorption coefficients of some aromatic compounds on multi-wall carbon nanotubes by the Monte Carlo method
Ahmadi, S., & Akbari, A. (2018) · SAR and QSAR in environmental research · doi:10.1080/1062936x.2018.1526821 · Cited by 47
“In order to nullify this error and to better indicate the predicted property values of the test set compounds, values of modified r(2) (r2 m) [43] with the threshold value of 0.”
Background
New machine learning prediction models for compressive strength of concrete modified with glass cullet
Mirzahosseini, M., Jiao, P., Barri, K., Riding, K. A., & Alavi, A. H. (2019) · Engineering Computations · doi:10.1108/ec-08-2018-0348 · Cited by 47
In silico design of diacylglycerol acyltransferase-1 (DGAT1) inhibitors based on SMILES descriptors using Monte-Carlo method
Kumar, P. P., Kumar, A., & Sindhu, J. (2019) · SAR and QSAR in environmental research · doi:10.1080/1062936x.2019.1629998 · Cited by 47
“Golbraikh and Tropsha [40] recommended that the correlation coefficient for the external validation set, r2ext should be close to 1 and r 2 O, its origin-based counterpart.”
Background
Mechanistic QSAR models for interpreting degradation rates of sulfonamides in UV-photocatalysis systems
Huang, X., Feng, Y., Hu, C., Xiao, X., Yu, D., & Zou, X. (2015) · Chemosphere · doi:10.1016/j.chemosphere.2015.05.075 · Cited by 47
New Ground-Motion Prediction Equations Using Multi Expression Programing
Alavi, A. H., Gandomi, A. H., Modaresnezhad, M., & Mousavi, M. (2011) · Journal of Earthquake Engineering · doi:10.1080/13632469.2010.526752 · Cited by 47
Organic compounds passage through RO membranes
Libotean, D., Giralt, J., Ralló, R., Cohen, Y., Giralt, F., Ridgway, H. F., Rodriguez, G., & Phipps, D. (2007) · Journal of Membrane Science · doi:10.1016/j.memsci.2007.11.052 · Cited by 47
A novel machine learning approach for estimation of electricity demand: An empirical evidence from Thailand
Mostafavi, E. S., Mostafavi, S. I., Jaafari, A., & Hosseinpour, F. (2013) · Energy Conversion and Management · doi:10.1016/j.enconman.2013.06.031 · Cited by 47
Application of in vitro PAMPA technique and in silico computational methods for blood-brain barrier permeability prediction of novel CNS drug candidates
Radan, M., Djikić, T., Obradović, D., & Nikolic, K. M. (2021) · European Journal of Pharmaceutical Sciences · doi:10.1016/j.ejps.2021.106056 · Cited by 48
Machine Learning in the Development of Adsorbents for Clean Energy Application and Greenhouse Gas Capture
Mai, H., Le, T. C., Chen, D., Winkler, D. A., & Caruso, R. A. (2022) · Advanced Science · doi:10.1002/advs.202203899 · Cited by 46
Machine learning approaches for stability prediction of rectangular tunnels in natural clays based on MLP and RBF neural networks
Jitchaijaroen, W., Keawsawasvong, S., Wipulanusat, W., Kumar, D. R., Jamsawang, P., & Sunkpho, J. (2024) · Intelligent Systems with Applications · doi:10.1016/j.iswa.2024.200329 · Cited by 46
Forecasting the strength of graphene nanoparticles-reinforced cementitious composites using ensemble learning algorithms
Khan, M., Nassar, R., Anwar, W., Rasheed, M., Najeh, T., Gamil, Y., & Farooq, F. (2024) · Results in Engineering · doi:10.1016/j.rineng.2024.101837 · Cited by 46
A Measure of Domain of Applicability for QSAR Modelling Based on Intelligent K‐Means Clustering
Stanforth, R., Kolossov, E., & Mirkin, B. (2007) · QSAR & Combinatorial Science · doi:10.1002/qsar.200630086 · Cited by 46
Interpretable, Probability-Based Confidence Metric for Continuous Quantitative Structure–Activity Relationship Models
Keefer, C. E., Kauffman, G. W., & Gupta, R. R. (2013) · Journal of Chemical Information and Modeling · doi:10.1021/ci300554t · Cited by 48
Antimicrobial evaluation, QSAR and docking studies of amide-linked 1,4-disubstituted 1,2,3-bistriazoles
Lal, K., Kaushik, C. P., & Kumar, A. (2015) · Medicinal Chemistry Research · doi:10.1007/s00044-015-1378-9 · Cited by 46
“5 (Golbraikh and Tropsha, 2002), and low values of RMSE and MAE.”
Background
Predicting the cytotoxicity of ionic liquids using QSAR model based on SMILES optimal descriptors
Ghaedi, A. M. (2015) · Journal of Molecular Liquids · doi:10.1016/j.molliq.2015.04.049 · Cited by 46
Comparison of artificial neural network and multivariate regression models for prediction of Azotobacteria population in soil under different land uses
Ebrahimi, M., Sinegani, A. A. S., Sarikhani, M. R., & Mohammadi, S. A. (2017) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2017.06.019 · Cited by 46
Genetic programming based formulation for compressive and flexural strength of cement mortar containing nano and micro silica after freeze and thaw cycles
Emamian, S. A., & Eskandari‐Naddaf, H. (2020) · Construction and Building Materials · doi:10.1016/j.conbuildmat.2020.118027 · Cited by 45
QSAR modeling, molecular docking and ADMET/pharmacokinetic studies: a chemometrics approach to search for novel inhibitors of norepinephrine transporter as potent antipsychotic drugs
Olasupo, S. B., Uzairu, A., Shallangwa, G. A., & Uba, S. (2020) · Journal of the Iranian Chemical Society · doi:10.1007/s13738-020-01902-5 · Cited by 47
Antiviral Activity of Isoimperatorin Against Influenza A Virus in vitro and its Inhibition of Neuraminidase
Lai, Y., Han, T., Zhan, S., Jiang, Y., Liu, X., & Li, G. (2021) · Frontiers in Pharmacology · doi:10.3389/fphar.2021.657826 · Cited by 46
“A score of >6 is considered to indicate better activity, and a score of ≥9 is considered to indicate very good activity (Golbraikh and Tropsha, 2002).”
Background
First molecular modeling report on novel arylpyrimidine kynurenine monooxygenase inhibitors through multi-QSAR analysis against Huntington’s disease: A proposal to chemists!
Amin, S. A., Adhikari, N., Jha, T., & Gayen, S. (2016) · Bioorganic & Medicinal Chemistry Letters · doi:10.1016/j.bmcl.2016.10.058 · Cited by 45
Forecasting Strength of CFRP Confined Concrete Using Multi Expression Programming
Ilyas, I., Zafar, A., Javed, M. F., Farooq, F., Aslam, F., Musarat, M. A., & Vatin, N. I. (2021) · Materials · doi:10.3390/ma14237134 · Cited by 45
“The proposed parameters by [102] have been incorporated in this study to perform an external validation of the established model, as mentioned in Table 7.”
Method
Effects of binder types and other significant variables on the unconfined compressive strength of chemical-stabilized clayey soil using gene-expression programming
Pham, V., Oh, E., & Ong, D. E. L. (2022) · Neural Computing and Applications · doi:10.1007/s00521-022-06931-0 · Cited by 45
“Golbraikh [66] provided some criteria as the external validation models for checking the testing dataset.”
Method
A survey on computational taste predictors
Malavolta, M., Pallante, L., Mavkov, B., Stojceski, F., Grasso, G., Korfiati, A., Mavroudi, S. P., Kalogeras, A. P., Alexakos, C., Martos, V., et al. (2022) · European Food Research and Technology · doi:10.1007/s00217-022-04044-5 · Cited by 48
“Model performance Predictive performance is assessed through Golbraikh and Tropsha criteria [70], and the AdaBoost Tree was considered the best method for both models.”
Method
An evolutionary machine learning-based model to estimate the rheological parameters of fresh concrete
Nazar, S., Yang, J., Javed, M. F., Khan, K., Li, L., & Liu, Q. (2023) · Structures · doi:10.1016/j.istruc.2023.01.019 · Cited by 45
Identification of potential N-substituted 5-benzylidenethiazolidine-2,4‑dione derivatives as α-amylase inhibitors: Computational cum synthetic studies
Gupta, S., Baweja, G. S., Gupta, G. D., & Asati, V. (2023) · Journal of Molecular Structure · doi:10.1016/j.molstruc.2023.135596 · Cited by 45
Predicting fluorescence to singlet oxygen generation quantum yield ratio for BODIPY dyes using QSPR and machine learning
Chebotaev, P. P., Buglak, A. A., Sheehan, A., & Filatov, M. A. (2024) · Physical Chemistry Chemical Physics · doi:10.1039/d4cp02471k · Cited by 45
Dependence of QSAR Models on the Selection of Trial Descriptor Sets: A Demonstration Using Nanotoxicity Endpoints of Decorated Nanotubes
Shao, C.-Y., Chen, S.-Z., Su, B., Tseng, Y. J., Esposito, E. X., & Hopfinger, A. J. (2012) · Journal of Chemical Information and Modeling · doi:10.1021/ci3005308 · Cited by 46
Novel ligands for the human histamine H1 receptor: Synthesis, pharmacology, and comparative molecular field analysis studies of 2-dimethylamino-5-(6)-phenyl-1,2,3,4-tetrahydronaphthalenes
Ghoneim, O. M., Legere, J. A., Golbraikh, A., Tropsha, A., & Booth, R. G. (2006) · Bioorganic & Medicinal Chemistry · doi:10.1016/j.bmc.2006.05.077 · Cited by 45
Self-citation
Structural Determinants of Tau Aggregation Inhibitor Potency
Schafer, K. N., Cisek, K. K., Huseby, C. J., Chang, E. S., & Kuret, J. (2013) · Journal of Biological Chemistry · doi:10.1074/jbc.m113.503474 · Cited by 43
“a Target values from Golbraikh and Tropsha (46).”
BackgroundMethodInfluential
Quantitative study of the structure–retention index relationship in the imine family
Acevedo-Martínez, J., Arranz, J. C. E., Rojas, A. V., Palmero, F. T., Pérez-Rosés, R., González, L. A., & Carrasco‐Velar, R. (2005) · Journal of Chromatography A · doi:10.1016/j.chroma.2005.10.019 · Cited by 45
Consensus Toxicity Factors for Polychlorinated Dibenzo-p-dioxins, Dibenzofurans, and Biphenyls Combiningin SilicoModels and Extensivein VitroScreening of AhR-Mediated Effects in Human and Rodent Cells
Larsson, M., van den Berg, M., Brenerová, P., van Duursen, M. B. M., van Ede, K. I., Lohr, C., Luecke-Johansson, S., Machala, M., Neser, S., Pěnčíková, K., et al. (2015) · Chemical Research in Toxicology · doi:10.1021/tx500434j · Cited by 45
Shuffling multivariate adaptive regression splines and adaptive neuro-fuzzy inference system as tools for QSAR study of SARS inhibitors
Jalali‐Heravi, M., Asadollahi-Baboli, M., & Mani‐Varnosfaderani, A. (2009) · Journal of Pharmaceutical and Biomedical Analysis · doi:10.1016/j.jpba.2009.07.009 · Cited by 45
Co-evolutions of correlations for QSAR of toxicity of organometallic and inorganic substances: An unexpected good prediction based on a model that seems untrustworthy
Toropova, A. P., Toropov, A. A., Benfenati, E., & Gini, G. C. (2011) · Chemometrics and Intelligent Laboratory Systems · doi:10.1016/j.chemolab.2010.12.007 · Cited by 45
Comparison of Multiple Linear Regressions and Neural Networks based QSAR models for the design of new antitubercular compounds
Ventura, C. M., Latino, D. A. R. S., & Martins, F. E. L. (2013) · European Journal of Medicinal Chemistry · doi:10.1016/j.ejmech.2013.10.029 · Cited by 45
“The external validation of test set compounds still complied with the following criteria [37,71]:”
BackgroundMethod
From chemical documentation to chemoinformatics: 50 years of chemical information science
Willett, P. (2008) · Journal of Information Science · doi:10.1177/0165551507084631 · Cited by 46
“Sample-feature ratios continue to be of importance given the very large numbers of descriptors that can now be generated for a molecule [124, 125], although techniques such as cross-validation and data scrambling can help to confirm the significance of potential structure–activity correlations [126, 127].”
Background
Proteochemometric modeling in a Bayesian framework
Cortés‐Ciriano, I., van Westen, G. J. P., Lenselink, E. B., Murrell, D. S., Bender, A., & Malliavin, T. E. (2014) · Journal of Cheminformatics · doi:10.1186/1758-2946-6-35 · Cited by 45
“R 2 or Q 2 ) [27-29] while also providing individual assessment for predictions.”
BackgroundMethod
A comparative study on the binary and ternary mixture toxicity of antibiotics towards three bacteria based on QSAR investigation
Wang, D., Wu, X., Lin, Z., & Ding, Y. (2018) · Environmental Research · doi:10.1016/j.envres.2017.12.015 · Cited by 45
hERG liability classification models using machine learning techniques
Konda, L. S. K., Praba, S., & Kristam, R. (2019) · Computational Toxicology · doi:10.1016/j.comtox.2019.100089 · Cited by 44
2-Aminomethylene-5-sulfonylthiazole Inhibitors of Lysyl Oxidase (LOX) and LOXL2 Show Significant Efficacy in Delaying Tumor Growth
Smithen, D. A., Leung, L. M. H., Challinor, M., Lawrence, R., Tang, H., Niculescu‐Duvaz, D., Pearce, S. P., McLeary, R., Lopes, F., Aljarah, M., et al. (2019) · Journal of Medicinal Chemistry · doi:10.1021/acs.jmedchem.9b01112 · Cited by 45
Environment-friendly PCN derivatives design and environmental behavior simulation based on a multi-activity 3D-QSAR model and molecular dynamics
Gu, W., Li, Q. X., & Li, Y. (2020) · Journal of Hazardous Materials · doi:10.1016/j.jhazmat.2020.122339 · Cited by 45
In silico design of novel Pyrazole derivatives containing thiourea skeleton as anti-cancer agents using: 3D QSAR, Drug-Likeness studies, ADMET prediction and molecular docking
Elmchichi, L., Aissouq, A. E., Kasmi, R., Belhassan, A., El-Mernissi, R., Ouammou, A., Lakhlifi, T., & Bouachrıne, M. (2021) · Materials Today Proceedings · doi:10.1016/j.matpr.2021.03.152 · Cited by 46
Evolutionary artificial intelligence approach for performance prediction of bio-composites
Ahmad, M. R., Chen, B., Dai, J., Kazmi, S. M. S., & Munir, M. J. (2021) · Construction and Building Materials · doi:10.1016/j.conbuildmat.2021.123254 · Cited by 45
The Behavior of Hybrid Fiber-Reinforced Concrete Elements: A New Stress-Strain Model Using an Evolutionary Approach
Abdulhameed, A. A., Al‐Zuhairi, A. H., Zaidee, S. R. A., Hanoon, A. N., Zand, A. W. A., Hason, M. M., & Abdulhameed, H. A. (2022) · Applied Sciences · doi:10.3390/app12042245 · Cited by 45
“Moreover, Golbraikh and Tropsha [47] proposed a new criterion for determining the external validity of the PSO model, which they believe is more reliable.”
Background
Structural Basis for Selective Inhibition of Trypanosomatid Glyceraldehyde-3-Phosphate Dehydrogenase: Molecular Docking and 3D QSAR Studies
Guido, R. V. C., Oliva, G., Montanari, C. A., & Andricopulo, A. D. (2008) · Journal of Chemical Information and Modeling · doi:10.1021/ci700453j · Cited by 45
Atom-based stochastic and non-stochastic 3D-chiral bilinear indices and their applications to central chirality codification
Castillo‐Garit, J. A., Marrero‐Ponce, Y., Torrens, F., & Rotondo, R. (2006) · Journal of Molecular Graphics and Modelling · doi:10.1016/j.jmgm.2006.09.007 · Cited by 45
“Therefore, the quality of models was determined by examining the determination coefficients (also know as square correlation coefficient; R(2)), Fisher-ratio’s p-level [p(F)], standard deviations of the regression (s) and the leave-one-out (LOO) press statistics (q(2), scv) analogues to R(2) and s [80, 82].”
BackgroundMethod
QSAR models for reproductive toxicity and endocrine disruption in regulatory use – a preliminary investigation
Jensen, G. E., Niemelä, J. R., Wedebye, E. B., & Nikolov, N. G. (2008) · SAR and QSAR in environmental research · doi:10.1080/10629360802550473 · Cited by 45
“While drawbacks of cross-validation exist [16,17], much of the criticisms are directed towards the simpler leave-one-out crossvalidation [16].”
Background
Performance of (consensus) kNN QSAR for predicting estrogenic activity in a large diverse set of organic compounds
Asikainen, A. H., Ruuskanen, J., & Tuppurainen, K. A. (2004) · SAR and QSAR in environmental research · doi:10.1080/1062936032000169642 · Cited by 45
Prediction of Rock Strain Using Hybrid Approach of Ann and Optimization Algorithms
Pradeep, T., & Samui, P. (2022) · Geotechnical and Geological Engineering · doi:10.1007/s10706-022-02174-x · Cited by 44
Hybrid bio-inspired metaheuristic approach for design compressive strength of high-strength concrete-filled high-strength steel tube columns
Ahmadi, M., Ebadi-Jamkhaneh, M., Dalvand, A., & Eidgahee, D. R. (2024) · Neural Computing and Applications · doi:10.1007/s00521-024-09494-4 · Cited by 44
“The coefﬁcients PI1 and PI1 should also be lower than 0.1 [69].”
Influential
Exploring the role of quantum chemical descriptors in modeling acute toxicity of diverse chemicals to Daphnia magna
Reenu, R., & Vikas, V. (2015) · Journal of Molecular Graphics and Modelling · doi:10.1016/j.jmgm.2015.06.009 · Cited by 44
Molecular modeling studies on imidazo[4,5-b]pyridine derivatives as Aurora A kinase inhibitors using 3D-QSAR and docking approaches
Lan, P., Chen, W.-N., & Chen, W.-M. (2010) · European Journal of Medicinal Chemistry · doi:10.1016/j.ejmech.2010.10.017 · Cited by 44
Predicting the net heat of combustion of organic compounds from molecular structures based on ant colony optimization
Pan, Y. L., Jiang, J. C., Wang, R., & Jiang, J. J. (2010) · Journal of Loss Prevention in the Process Industries · doi:10.1016/j.jlp.2010.11.001 · Cited by 44
Phenylethyl-substituted pyrimido[2,1-f]purinediones and related compounds: Structure–activity relationships as adenosine A1 and A2A receptor ligands
Drabczyńska, A., Müller, C. E., Schiedel, A. C., Schumacher, B., Janina Karolak-wojciechowska, A., Fruziñski, A., Zobnina, W., Yuzlenko, O., & Kieć‐Kononowicz, K. (2007) · Bioorganic & Medicinal Chemistry · doi:10.1016/j.bmc.2007.07.051 · Cited by 44
Deriving an intelligent model for soil compression index utilizing multi-gene genetic programming
Danial Mohammadzadeh, S., Bazaz, J. B., Yazd, S. H. V. J., & Alavi, A. H. (2016) · Environmental Earth Sciences · doi:10.1007/s12665-015-4889-2 · Cited by 44
“Besides, Golbraikh and Tropsha (2002) defined new statistical parameters of k and k0 to validate the models on the testing data.”
BackgroundInfluential
Acute aquatic toxicity of organic solvents modeled by QSARs
Levet, A., Bordes, C., Clément, Y., Mignon, P., Morell, C., Chermette, H., Marote, P., & Lantéri, P. (2016) · Journal of Molecular Modeling · doi:10.1007/s00894-016-3156-0 · Cited by 44
“[50] or the concordance correlation coefficient [42, 51].”
Probing the origin of estrogen receptor alpha inhibition via large-scale QSAR study
Suvannang, N., Preeyanon, L., Malik, A. A., Schaduangrat, N., Shoombuatong, W., Worachartcheewan, A., Tantimongcolwat, T., & Nantasenamat, C. (2018) · RSC Advances · doi:10.1039/c7ra10979b · Cited by 44
Performance assessment of existing models to predict brittle failure modes of steel-to-timber connections loaded parallel-to-grain with dowel-type fasteners
Cabrero, J. M., & Yurrita, M. (2018) · Engineering Structures · doi:10.1016/j.engstruct.2018.03.037 · Cited by 44
“322 Additional criteria and different metrics to verify the validity of a model have been 323 proposed as replacement [67, 68].”
Background
In silico studies of diarylpyridine derivatives as novel HIV-1 NNRTIs using docking-based 3D-QSAR, molecular dynamics, and pharmacophore modeling approaches
Wan, Y., Tian, Y., Wang, W., Gu, S., Ju, X.-L., & Liu, G. (2018) · RSC Advances · doi:10.1039/c8ra06475j · Cited by 44
Discovery of Dual FGFR4 and EGFR Inhibitors by Machine Learning and Biological Evaluation
Chen, X., Xie, W., Yang, Y., Hua, Y., Xing, G., Liang, L., Deng, C., Wang, Y., Fan, Y., Liu, H., et al. (2020) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.0c00652 · Cited by 44
Thiazolides as Novel Antiviral Agents. 2. Inhibition of Hepatitis C Virus Replication
Stachulski, A. V., Pidathala, C., Row, E. C., Sharma, R., Berry, N. G., Lawrenson, A. S., Moores, S. L., Iqbal, M., Bentley, J., Allman, S. A., et al. (2011) · Journal of Medicinal Chemistry · doi:10.1021/jm201264t · Cited by 44
Design, synthesis, antimicrobial, anticancer evaluation, and QSAR studies of 4-(substituted benzylidene-amino)-1,5-dimethyl-2-phenyl-1,2-dihydropyrazol-3-ones
Sigroha, S., Narasimhan, B., Kumar, P., Khatkar, A., Ramasamy, K., Mani, V., Mishra, R. K., & Majeed, A. B. A. (2011) · Medicinal Chemistry Research · doi:10.1007/s00044-011-9906-8 · Cited by 44
“The value of q2 greater than 0.5 is the basic requirement for a QSAR model to be considered valid (Golbraikh and Tropsha, 2002).”
BackgroundInfluential
Docking and 3D-QSAR studies of influenza neuraminidase inhibitors using three-dimensional holographic vector of atomic interaction field analysis
Sun, J., Cai, S.-X., Yan, N., & Hu, M. Y. (2009) · European Journal of Medicinal Chemistry · doi:10.1016/j.ejmech.2009.11.043 · Cited by 44
BPSO-MLR and ANFIS based modeling of lower flammability limit
Bagheri, M., Rajabi, M. A., Mirbagheri, M., & Amin, M. (2011) · Journal of Loss Prevention in the Process Industries · doi:10.1016/j.jlp.2011.10.005 · Cited by 44
QSAR Prediction of Ozone Tropospheric Degradation
Gramatica, P., Pilutti, P., & Papa, E. (2003) · QSAR & Combinatorial Science · doi:10.1002/qsar.200390026 · Cited by 44
Intelligent prediction modeling for flexural capacity of FRP-strengthened reinforced concrete beams using machine learning algorithms
Khan, M., Khan, A., Khan, A. U., Shakeel, M., Khan, K., Alabduljabbar, H., Najeh, T., & Gamil, Y. (2023) · Heliyon · doi:10.1016/j.heliyon.2023.e23375 · Cited by 43
Artificial intelligence-based prediction models of bio-treated sand strength for sustainable and green infrastructure applications
Nawaz, M. N., Akhtar, A. Y., Hassan, W., Khan, M. H. A., & Nawaz, M. M. (2024) · Transportation Geotechnics · doi:10.1016/j.trgeo.2024.101262 · Cited by 43
Bond‐Based 2D Quadratic Fingerprints in QSAR Studies: Virtual and In vitro Tyrosinase Inhibitory Activity Elucidation
Casañola‐Martín, G. M., Marrero‐Ponce, Y., Khan, M. T. H., Khan, S. B., Torrens, F., Pérez‐Jiménez, F., Rescigno, A., & Abad, C. (2010) · Chemical Biology & Drug Design · doi:10.1111/j.1747-0285.2010.01032.x · Cited by 43
“The external validation process is necessary to assess the real predictive power of any QSAR model (39,40).”
Development of Dual Inhibitors against Alzheimer’s Disease Using Fragment-Based QSAR and Molecular Docking
Goyal, M., Dhanjal, J. K., Goyal, S., Tyagi, C., Hamid, R., & Grover, A. (2014) · BioMed Research International · doi:10.1155/2014/979606 · Cited by 43
“The enhanced predicted activity, high binding score, and the presence of crucial drug like molecular properties provide substantial evidence for consideration of these compounds as potent dual inhibitors for future prospective of AD treatment.”
Application of an expert system based on Genetic Algorithm–Adaptive Neuro-Fuzzy Inference System (GA–ANFIS) in QSAR of cathepsin K inhibitors
Shahlaei, M., Madadkar‐Sobhani, A., Saghaie, L., & Fassihi, A. (2011) · Expert Systems with Applications · doi:10.1016/j.eswa.2011.11.106 · Cited by 43
“There are some techniques to approximate the quality of the developed models (Golbraikh & Tropsha, 2002; Gramatica, Giani, & Papa, 2007).”
Method
Simple yet accurate prediction method for sublimation enthalpies of organic contaminants using their molecular structure
Bagheri, M., Bagheri, M., Gandomi, A. H., & Golbraikh, A. (2012) · Thermochimica Acta · doi:10.1016/j.tca.2012.05.008 · Cited by 43
Self-citation
An in vitro comparative assessment with a series of new triphenyltin(IV) 2-/4-[(E)-2-(aryl)-1-diazenyl]benzoates endowed with anticancer activities: Structural modifications, analysis of efficacy and cytotoxicity involving human tumor cell lines
Baul, T. S. B., Paul, A., Pellerito, L., Scopelliti, M., Duthie, A., de Vos, D., Verma, R. P., & Englert, U. (2011) · Journal of Inorganic Biochemistry · doi:10.1016/j.jinorgbio.2011.10.008 · Cited by 43
Modeling the Cellular Uptake of Magnetofluorescent Nanoparticles in Pancreatic Cancer Cells: A Quantitative Structure Activity Relationship Study
Ghorbanzadeh, M., Fatemi, M. H., & Karimpour, M. (2012) · Industrial & Engineering Chemistry Research · doi:10.1021/ie3006947 · Cited by 43
Quantitative structure activity relationship (QSAR) of piperine analogsfor bacterial NorA efflux pump inhibitors
Nargotra, A., Sharma, S., Koul, J. L., Sangwan, P. L., Khan, I. A., Kumar, A., Taneja, S. C., & Koul, S. (2009) · European Journal of Medicinal Chemistry · doi:10.1016/j.ejmech.2009.05.004 · Cited by 43
Structure–activity relationship study on the binding of PBDEs with thyroxine transport proteins
Yang, W., Shen, S., Mu, L., & Yu, H. (2011) · Environmental Toxicology and Chemistry · doi:10.1002/etc.645 · Cited by 43
“predictive QSAR models because they satisfied the conditions that Golbraikh and Tropsha [26] suggested: q(2)> 0.”
MethodInfluential
Mechanistic model for interpreting the toxic effects of sulfonamides on nitrification
Huang, X., Feng, Y., Hu, C., Xiao, X., Yu, D., & Zou, X. (2015) · Journal of Hazardous Materials · doi:10.1016/j.jhazmat.2015.11.037 · Cited by 43
Evaluation of density, viscosity, surface tension and CO 2 solubility for single, binary and ternary aqueous solutions of MDEA, PZ and 12 common ILs by using artificial neural network (ANN) technique
Golzar, K., Modarress, H., & Amjad‐Iranagh, S. (2016) · International journal of greenhouse gas control · doi:10.1016/j.ijggc.2016.08.008 · Cited by 43
Monte Carlo Method Based QSAR Studies of Mer Kinase Inhibitors in Compliance with OECD Principles
Kumar, P. P., & Kumar, A. (2017) · Drug Research · doi:10.1055/s-0043-119288 · Cited by 43
“The external predictive power of the built qsar models was further tested using criteria suggested by Golbraikh and Tropsha [32], Roy and Roy [33] and Ojha et al. [34].”
Method
QSAR-derived affinity fingerprints (part 1): fingerprint construction and modeling performance for similarity searching, bioactivity classification and scaffold hopping
Škuta, C., Cortés‐Ciriano, I., Dehaen, W., Kříž, P., van Westen, G. J. P., Tetko, I. V., Bender, A., & Svozil, D. (2020) · Journal of Cheminformatics · doi:10.1186/s13321-020-00443-6 · Cited by 44

Authors: Golbraikh, A., & Tropsha, A.
Affiliations: University of North Carolina at Chapel Hill (US)
Corresponding author: Tropsha, Alexander
ORCID: Golbraikh, Alexander
Tropsha, Alexander
Venue: Journal of Molecular Graphics and Modelling
Publisher: Elsevier BV
Published: 2002-01
Volume: 20
Issue: 4
Pages: 269-276
ISSN: 1093-3263 (ISSN-L)
DOI: 10.1016/s1093-3263(01)00123-1
OpenAlex: W2087661061
Cited by: 3,735
References: 39
Citations by year: 2026: 133 · 2025: 164 · 2024: 179 · 2023: 174 · 2022: 194 · 2021: 197 · 2020: 215 · 2019: 189 · 2018: 200 · 2017: 174 · 2016: 181 · 2015: 175 · 2014: 197 · 2013: 203 · 2012: 202
FWCI: 52.71
Type: journal article
Language: en
Open access: closed
Licence: www.elsevier.com/tdm/userlicense/1.0/ (tdm)
Locations: Journal of Molecular Graphics and Modelling (publishedVersion)
PubMed (publishedVersion)
Topics: Life Sciences › Pharmacology, Toxicology and Pharmaceutics › Drug Discovery › Computational Drug Discovery Methods
Physical Sciences › Materials Science › Materials Chemistry › Machine Learning in Materials Science
Physical Sciences › Physics and Astronomy › Atomic and Molecular Physics, and Optics › Advanced Chemical Physics Studies
Keywords: leave-one-out cross-validation, QSAR model validation, predictive power, external validation, 2D molecular descriptors, overfitting, model evaluation metrics
MeSH terms: Data Interpretation, Statistical, Ligands, Mathematical Computing, Models, Molecular, Receptors, Histamine H1, Steroids, Transcortin, Databases, Factual, Quantitative Structure-Activity Relationship, Ecdysteroids

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Beware of q2!

Abstract

Overview

Integrity signals

Verification

Claims the paper makes

Claims other papers make about this one

Citations

Cites

Cited by

Related

Metadata

Record

About these checks