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 401–500 of 1,004

Data-driven modelling of the flocculation process on mineral processing tailings treatment
Qi, C., Fourie, A. B., Chen, Q., Tang, X., Zhang, Q., & Gao, R. (2018) · Journal of Cleaner Production · doi:10.1016/j.jclepro.2018.06.054 · Cited by 64
Artificial intelligence assisted technoeconomic optimization scenarios of hybrid energy systems for water management of an isolated community
Tariq, R., Cetina-Quiñones, A. J., Cardoso-Fernández, V., Daniela-Abigail, H.-L., Soberanis, M. A. E., Bassam, A., & Lille, M. V. D. (2021) · Sustainable Energy Technologies and Assessments · doi:10.1016/j.seta.2021.101561 · Cited by 68
Effect of information leakage and method of splitting (rational and random) on external predictive ability and behavior of different statistical parameters of QSAR model
Masand, V. H., Mahajan, D. T., Nazeruddin, G. M., Hadda, T. B., Rastija, V., & Alfeefy, A. M. (2014) · Medicinal Chemistry Research · doi:10.1007/s00044-014-1193-8 · Cited by 64
Support vector machines: Development of QSAR models for predicting anti-HIV-1 activity of TIBO derivatives
Darnag, R., Mazouz, E. L. M., Schmitzer, A. R., Villemin, D., Jarid, A., & Cherqaoui, D. (2010) · European Journal of Medicinal Chemistry · doi:10.1016/j.ejmech.2010.01.002 · Cited by 66
Generation of in-silico cytochrome P450 1A2, 2C9, 2C19, 2D6, and 3A4 inhibition QSAR models
Gleeson, M. P., Davis, A. M., Chohan, K. K., Paine, S. W., Boyer, S. K., Gavaghan, C. L., Arnby, C. H., Kankkonen, C., & Albertson, N. H. (2007) · Journal of Computer-Aided Molecular Design · doi:10.1007/s10822-007-9139-6 · Cited by 64
Design, synthesis and antibacterial activity of fluoroquinolones containing bulky arenesulfonyl fragment: 2D-QSAR and docking study
Abdel‐Aziz, A. A. ‐., Asiri, Y. A., & Al-Agamy, M. H. (2011) · European Journal of Medicinal Chemistry · doi:10.1016/j.ejmech.2011.09.011 · Cited by 64
QSAR modeling in ecotoxicological risk assessment: application to the prediction of acute contact toxicity of pesticides on bees (Apis mellifera L.)
Hamadache, M., Benkortbi, O., Hanini, S., & Amrane, A. (2017) · Environmental Science and Pollution Research · doi:10.1007/s11356-017-0498-9 · Cited by 66
Prediction of riprap stone size under overtopping flow using data-driven models
Najafzadeh, M., Rezaie-Balf, M., & Tafarojnoruz, A. (2018) · International Journal of River Basin Management · doi:10.1080/15715124.2018.1437738 · Cited by 64
“Golbraikh and Tropsha (2002) and Tropsha et al. (2003) suggested an external validation criterion to evaluate the models on the basis of their performance through analysis of data subsets.”
Background
Ecotoxicological QSAR modeling of organic compounds against fish: Application of fragment based descriptors in feature analysis
Khan, K., Baderna, D., Cappelli, C., Toma, C., Lombardo, A., Roy, K., & Benfenati, E. (2019) · Aquatic Toxicology · doi:10.1016/j.aquatox.2019.05.011 · Cited by 64
The Characterisation of (Quantitative) Structure-Activity Relationships: Preliminary Guidance
Worth, A., Bassan, A., Gallegos, A. F., Ti, N., Patlewicz, G. Y., Pavan, M., Tsakovska, I., & Vračko, M. (2005) · Cited by 64
Non-stochastic and stochastic linear indices of the ‘molecular pseudograph’s atom adjacency matrix’: application to ‘in silico’ studies for the rational discovery of new antimalarial compounds
Marrero‐Ponce, Y., Montero, A., Romero‐Zaldivar, C., Veitía, M. S., Peréz, M. M., & García–Sánchez, R. N. (2004) · Bioorganic & Medicinal Chemistry · doi:10.1016/j.bmc.2004.11.008 · Cited by 64
Artificial Neural Network‐Based Framework for Developing Ground‐Motion Models for Natural and Induced Earthquakes in Oklahoma, Kansas, and Texas
Khosravikia, F., Clayton, P. M., & Nagy, Z. (2018) · Seismological Research Letters · doi:10.1785/0220180218 · Cited by 63
“Moreover, Golbraikh and Tropsha (2002) suggested that at least one of the slopes of the regression of targets against estimates through the origin and that of estimates against targets through the origin for the testing subset (k and k′, respectively) should be between 0.85 and 1.15.”
BackgroundInfluential
Flocculation-dewatering prediction of fine mineral tailings using a hybrid machine learning approach
Qi, C., Ly, H., Chen, Q., Le, T.-T., Le, M. V., & Pham, B. T. (2019) · Chemosphere · doi:10.1016/j.chemosphere.2019.125450 · Cited by 63
Singlet oxygen generation by porphyrins and metalloporphyrins revisited: A quantitative structure-property relationship (QSPR) study
Buglak, A. A., Filatov, M. A., Hussain, M. A., & Sugimoto, M. (2020) · Journal of Photochemistry and Photobiology A Chemistry · doi:10.1016/j.jphotochem.2020.112833 · Cited by 65
Predicting Marshall parameters of flexible pavement using support vector machine and genetic programming
Zhang, W., Khan, A. M., Huyan, J., Zhong, J., Peng, T., & Cheng, H. (2021) · Construction and Building Materials · doi:10.1016/j.conbuildmat.2021.124924 · Cited by 63
Integrated unsupervised–supervised modeling and prediction of protein–peptide affinities at structural level
Zhou, P., Li, W., Lin, J., Mei, L., Liu, Q., Shang, S., Li, J., & Shu, J. (2022) · Briefings in Bioinformatics · doi:10.1093/bib/bbac097 · Cited by 63
Insight into TLR4 receptor inhibitory activity via QSAR for the treatment of Mycoplasma pneumonia disease
Zhu, Z., Rahman, Z.-U., Aamir, M., Shah, S. Z. A., Hamid, S., Bilawal, A., Li, S., & Ishfaq, M. (2023) · RSC Advances · doi:10.1039/d2ra06178c · Cited by 63
Kinome-wide interaction modelling using alignment-based and alignment-independent approaches for kinase description and linear and non-linear data analysis techniques
Lapins, M., & Wikberg, J. E. S. (2010) · BMC Bioinformatics · doi:10.1186/1471-2105-11-339 · Cited by 66
“However, some studies have pointed out that Q2 may give an overly optimistic assessment of model performance in the case that the crossvalidation results are used to optimize model parameters or to select the best among many alternative models [49,50].”
Background
Application of genetic algorithm-kernel partial least square as a novel nonlinear feature selection method: Activity of carbonic anhydrase II inhibitors
Jalali‐Heravi, M., & Kyani, A. (2007) · European Journal of Medicinal Chemistry · doi:10.1016/j.ejmech.2006.12.020 · Cited by 63
Quantitative online prediction of peptide binding to the major histocompatibility complex
Hattotuwagama, C. K., Guan, P., Doytchinova, I. A., Zygouri, C., & Flower, D. R. (2003) · Journal of Molecular Graphics and Modelling · doi:10.1016/s1093-3263(03)00160-8 · Cited by 63
A novel descriptor of amino acids and its application in peptide QSAR
Tong, J., Liu, S., Zhou, P., Wu, B., & Li, Z. (2008) · Journal of Theoretical Biology · doi:10.1016/j.jtbi.2008.02.030 · Cited by 63
Molecular docking, molecular dynamics simulations and QSAR studies on some of 2-arylethenylquinoline derivatives for inhibition of Alzheimer's amyloid-beta aggregation: Insight into mechanism of interactions and parameters for design of new inhibitors
Safarizadeh, H., & Garkani‐Nejad, Z. (2018) · Journal of Molecular Graphics and Modelling · doi:10.1016/j.jmgm.2018.11.019 · Cited by 61
Prediction of compressive strength of high-volume fly ash self-compacting concrete with silica fume using machine learning techniques
Kumar, S., Kumar, R., Rai, B., & Samui, P. (2024) · Construction and Building Materials · doi:10.1016/j.conbuildmat.2024.136933 · Cited by 69
Gene expression programming as a basis for new generation of electricity demand prediction models
Mousavi, S. M., Mostafavi, E. S., & Hosseinpour, F. (2014) · Computers & Industrial Engineering · doi:10.1016/j.cie.2014.05.010 · Cited by 62
“Besides, new criteria recommended by Golbraikh and Tropsha (2002) were checked for external validation of the models on the validation data sets.”
Method
A Large‐Scale Empirical Evaluation of Cross‐Validation and External Test Set Validation in (Q)SAR
Gütlein, M., Helma, C., Karwath, A., & Krämer, S. (2013) · Molecular Informatics · doi:10.1002/minf.201200134 · Cited by 63
Modeling and prediction of binding affinities between the human amphiphysin SH3 domain and its peptide ligands using genetic algorithm‐Gaussian processes
Zhou, P., Tian, F., Chen, X., & Shang, Z. (2008) · Biopolymers · doi:10.1002/bip.21091 · Cited by 63
Novel sulfone derivatives containing a 1,3,4‐oxadiazole moiety: design and synthesis based on the 3D‐QSAR model as potential antibacterial agent
Chen, J., Luo, Y., Wei, C., Wu, S., Wu, R., Wang, S., Hu, D., & Song, B. (2020) · Pest Management Science · doi:10.1002/ps.5873 · Cited by 62
Machine learning-based constitutive models for cement-grouted coal specimens under shearing
Li, G., Sun, Y., & Qi, C. (2021) · International Journal of Mining Science and Technology · doi:10.1016/j.ijmst.2021.08.005 · Cited by 61
Advanced Machine Learning Modeling Approach for Prediction of Compressive Strength of FRP Confined Concrete Using Multiphysics Genetic Expression Programming
Ilyas, I., Zafar, A., Afzal, M., Javed, M. F., Alrowais, R., Althoey, F., Mohamed, A. M., Mohamed, A., & Vatin, N. I. (2022) · Polymers · doi:10.3390/polym14091789 · Cited by 61
“934 (Golbraikh and Tropsha, 2002) [88] MLR 0.”
QSAR models for prediction study of HIV protease inhibitors using support vector machines, neural networks and multiple linear regression
Darnag, R., Minaoui, B., & Fakir, M. (2012) · Arabian Journal of Chemistry · doi:10.1016/j.arabjc.2012.10.021 · Cited by 61
“Though there is no rigorous rule to rely on (Golbraikh and Tropsha, 2002), a practical way is to use a ratio, q, to determine the number of hidden units (Andrea and Kalayeh, 1991). q is defined as the following: q ¼ number of compounds presented to the network number of connections in the network…”
BackgroundMethod
An investigation of structurally diverse carbamates for acetylcholinesterase (AChE) inhibition using 3D-QSAR analysis
Roy, K. K., Dixit, A., & Saxena, A. K. (2008) · Journal of Molecular Graphics and Modelling · doi:10.1016/j.jmgm.2008.04.006 · Cited by 61
Prediction of Anti-inflammatory Plants and Discovery of Their Biomarkers by Machine Learning Algorithms and Metabolomic Studies
Chagas‐Paula, D. A., Oliveira, T. B., Zhang, T., Edrada‐Ebel, R., & Costa, F. B. D. (2015) · Planta Medica · doi:10.1055/s-0034-1396206 · Cited by 61
QSAR study of anthranilic acid sulfonamides as inhibitors of methionine aminopeptidase-2 using LS-SVM and GRNN based on principal components
Shahlaei, M., Sabet, R., Ziari, M. B., Moeinifard, B., Fassihi, A., & Karbakhsh, R. (2010) · European Journal of Medicinal Chemistry · doi:10.1016/j.ejmech.2010.07.010 · Cited by 61
SMILES-based QSAR model for arylpiperazines as high-affinity 5-HT1A receptor ligands using CORAL
Veselinović, A. M., Milosavljević, J. B., Toropov, A. A., & Nikolić, G. M. (2012) · European Journal of Pharmaceutical Sciences · doi:10.1016/j.ejps.2012.12.021 · Cited by 61
The applications of PCA in QSAR studies: A case study on CCR5 antagonists
Yoo, C., & Shahlaei, M. (2017) · Chemical Biology & Drug Design · doi:10.1111/cbdd.13064 · Cited by 61
A Novel Formulation for the Compressive Strength of IBP-Based Geopolymer Stabilized Clayey Soils Using ANN and GMDH-NN Approaches
Eidgahee, D. R., Rafiean, A. H., & Haddad, A. (2019) · Iranian Journal of Science and Technology Transactions of Civil Engineering · doi:10.1007/s40996-019-00263-1 · Cited by 61
CORAL: QSAR models of CB1 cannabinoid receptor inhibitors based on local and global SMILES attributes with the index of ideality of correlation and the correlation contradiction index
Kumar, P. P., & Kumar, A. (2020) · Chemometrics and Intelligent Laboratory Systems · doi:10.1016/j.chemolab.2020.103982 · Cited by 61
Boosted leave-many-out cross-validation: the effect of training and test set diversity on PLS statistics
Clark, R. D. (2003) · Journal of Computer-Aided Molecular Design · doi:10.1023/a:1025366721142 · Cited by 61
Predicting the Biological Activities Through QSAR Analysis and Docking-Based Scoring
Vilar, S., & Costanzi, S. (2012) · Methods in molecular biology · doi:10.1007/978-1-62703-023-6_16 · Cited by 60
QSAR studies about cytotoxicity of benzophenazines with dual inhibition toward both topoisomerases I and II: 3D-MoRSE descriptors and statistical considerations about variable selection
Saı́z-Urra, L., González, M. P., & Teijeira, M. (2006) · Bioorganic & Medicinal Chemistry · doi:10.1016/j.bmc.2006.05.081 · Cited by 59
QSAR analysis on tacrine-related acetylcholinesterase inhibitors
Wong, K. Y., Mercader, A. G., Saavedra, L. M., Honarparvar, B., Romanelli, G. P., & Duchowicz, P. R. (2014) · Journal of Biomedical Science · doi:10.1186/s12929-014-0084-0 · Cited by 60
“50 for obtaining a validated model [54].”
Synthesis, antimicrobial, anticancer, antiviral evaluation and QSAR studies of 4-(1-aryl-2-oxo-1,2-dihydro-indol-3-ylideneamino)-N-substituted benzene sulfonamides
Kumar, M. C., Ramasamy, K., Mani, V., Mishra, R. K., Majeed, A. B. A., Clercq, E. D., & Narasimhan, B. (2012) · Arabian Journal of Chemistry · doi:10.1016/j.arabjc.2012.12.005 · Cited by 60
“The value of q2 greater than 0.5 is the basic requirement for qualifying aQSARmodel to be valid (Golbraikh and Tropsha, 2002).”
BackgroundInfluential
Support vector regression and least squares support vector regression for hormetic dose–response curves fitting
Qin, L., Liu, S., Liu, H., & Zhang, Y. (2009) · Chemosphere · doi:10.1016/j.chemosphere.2009.10.029 · Cited by 60
Factor Analysis Scale of Generalized Amino Acid Information as the Source of a New Set of Descriptors for Elucidating the Structure and Activity Relationships of Cationic Antimicrobial Peptides
Liang, G., & Li, Z. (2007) · QSAR & Combinatorial Science · doi:10.1002/qsar.200630145 · Cited by 60
Prediction of the self-accelerating decomposition temperature of organic peroxides using QSPR models
Wang, B., Yi, H., Xu, K., & Wang, Q. (2016) · Journal of Thermal Analysis and Calorimetry · doi:10.1007/s10973-016-5922-8 · Cited by 60
Exploring pyrazolo[3,4-d]pyrimidine phosphodiesterase 1 (PDE1) inhibitors: a predictive approach combining comparative validated multiple molecular modelling techniques
Amin, S. A., Bhargava, S., Adhikari, N., Gayen, S., & Jha, T. (2017) · Journal of Biomolecular Structure and Dynamics · doi:10.1080/07391102.2017.1288659 · Cited by 59
“By carrying out the whole process of Monte Carlo optimization, one can get a suitable model and the best model was selected on the basis of Golbraikh and Tropsha criterion (Golbraikh & Tropsha, 2002).”
Method
Synthesis, antimicrobial, anticancer evaluation and QSAR studies of 6-methyl-4-[1-(2-substituted-phenylamino-acetyl)-1H-indol-3-yl]-2-oxo/thioxo-1,2,3,4-tetrahydropyrimidine-5-carboxylic acid ethyl esters
Sharma, S. K., Kumar, P., Narasimhan, B., Ramasamy, K., Mani, V., Mishra, R. K., & Majeed, A. B. A. (2011) · European Journal of Medicinal Chemistry · doi:10.1016/j.ejmech.2011.11.028 · Cited by 59
A comparative QSAR on 1,2,5-thiadiazolidin-3-one 1,1-dioxide compounds as selective inhibitors of human serine proteinases
García, J., Duchowicz, P. R., Rozas, M. F., Caram, J. A., Mirífico, M. V., Fernández, F. M., & Castro, E. A. (2011) · Journal of Molecular Graphics and Modelling · doi:10.1016/j.jmgm.2011.07.007 · Cited by 59
Technique for Energy Decomposition in the Study of “Receptor-Ligand” Complexes
Potemkin, V., Pogrebnoy, A. A., & Grishina, M. (2009) · Journal of Chemical Information and Modeling · doi:10.1021/ci800405n · Cited by 59
Virtual Screening for R-Groups, including Predicted pIC50 Contributions, within Large Structural Databases, Using Topomer CoMFA
CRAMER, R. D. I., Cruz, P., Stahl, G., Curtiss, W. C., Campbell, B., Masek, B. B., & Soltanshahi, F. (2008) · Journal of Chemical Information and Modeling · doi:10.1021/ci8001556 · Cited by 59
Predictive QSAR workflow for the in silico identification and screening of novel HDAC inhibitors
Melagraki, G., Afantitis, A., Sarimveis, H., Koutentis, P. A., Kollias, G. A., & Igglessi‐Markopoulou, O. (2009) · Molecular Diversity · doi:10.1007/s11030-009-9115-2 · Cited by 60
“To illustrate this, the following evaluation techniques were used: the leave-one-out (LOO) cross-validation procedure, validation through an external test set and Y-randomization [49–53].”
Method
Robust design of some selective matrix metalloproteinase-2 inhibitors over matrix metalloproteinase-9 through in silico/fragment-based lead identification and de novo lead modification: Syntheses and biological assays
Adhikari, N., Halder, A. K., Mallick, S., Saha, A., Saha, K. D., & Jha, T. (2016) · Bioorganic & Medicinal Chemistry · doi:10.1016/j.bmc.2016.07.023 · Cited by 59
Studies on diagnostic biomarkers and therapeutic mechanism of Alzheimer's disease through metabolomics and hippocampal proteomics
Lin, W., Zhang, J., Liu, Y., Wu, R., Yang, H., Hu, X., & Ling, X. (2017) · European Journal of Pharmaceutical Sciences · doi:10.1016/j.ejps.2017.05.003 · Cited by 59
“Besides, permutation testing was performed to validate the classification models (Golbraikh and Tropsha, 2002).”
QSPR Modeling of the Refractive Index for Diverse Polymers Using 2D Descriptors
Khan, P. M., Rasulev, B., & Roy, K. (2018) · ACS Omega · doi:10.1021/acsomega.8b01834 · Cited by 59
“The ﬁ nally selected models were satisfactory in terms of all of the internal as well as external validation metrics including mean absolute error (MAE)-based criteria 51 and Golbraikh and Tropsha ’ s criteria, 52 proving the signi ﬁ cance of the models.”
Hybrid ANN and Artificial Cooperative Search Algorithm to Forecast Short-Term Electricity Price in De-Regulated Electricity Market
Pourdaryaei, A., Mokhlis, H., Illias, H. A., Kaboli, S. H. A., Ahmad, S., & Ang, S. P. (2019) · IEEE Access · doi:10.1109/access.2019.2938842 · Cited by 59
“To evaluate the performance of the developed model, following attributes are recommended [36-39]: I.”
Method
New tyrosinase inhibitors selected by atomic linear indices-based classification models
Casañola‐Martín, G. M., Khan, M. T. H., Marrero‐Ponce, Y., Ather, A., Sultankhodzhaev, M. N., & Torrens, F. (2005) · Bioorganic & Medicinal Chemistry Letters · doi:10.1016/j.bmcl.2005.09.085 · Cited by 58
Development and validation of QSPR models for corrosion inhibition of carbon steel by some pyridazine derivatives in acidic medium
Assiri, E. H. E., Driouch, M., Lazrak, J., Bensouda, Z., Elhaloui, A., Sfaira, M., Saffaj, T., & Taleb, M. (2020) · Heliyon · doi:10.1016/j.heliyon.2020.e05067 · Cited by 58
3D-QSAR, ADME-Tox In Silico Prediction and Molecular Docking Studies for Modeling the Analgesic Activity against Neuropathic Pain of Novel NR2B-Selective NMDA Receptor Antagonists
fadili, M. E., Er-rajy, M., Imtara, H., Kara, M., Zarougui, S., Altwaijry, N., Kamaly, O. M. A., Alsfouk, A. A., & Elhallaoui, M. (2022) · Processes · doi:10.3390/pr10081462 · Cited by 60
Forecasting energy demand of PCM integrated residential buildings: A machine learning approach
Zhussupbekov, M., Memon, S. A., Khawaja, S. A., Nazir, K., & Kim, J. R. (2023) · Journal of Building Engineering · doi:10.1016/j.jobe.2023.106335 · Cited by 58
APPROPRIATE Life Cycle Assessment: A PRO cess-Specific, PR edictive I mpact A ssessmen T Method for Emerging Chemical Processes
Kleinekorte, J., Kleppich, J., Fleitmann, L., Beckert, V., Blodau, L., & Bardow, A. (2023) · ACS Sustainable Chemistry & Engineering · doi:10.1021/acssuschemeng.2c07682 · Cited by 64
Artificial Intelligence and Green Innovation in Small and Medium-Sized Enterprises and Competitive-Advantage Drive Toward Achieving Sustainable Development Goals
Farmanesh, P., Dehkordi, N. S., Vehbi, A., & Chavali, K. (2025) · Sustainability · doi:10.3390/su17052162 · Cited by 58
AI-Integrated QSAR Modeling for Enhanced Drug Discovery: From Classical Approaches to Deep Learning and Structural Insight
Koirala, M., Yan, L., Mohamed, Z., & DiPaola, M. (2025) · International Journal of Molecular Sciences · doi:10.3390/ijms26199384 · Cited by 78
The use of machine learning and nonlinear statistical tools for ADME prediction
Sakiyama, Y. (2009) · Expert Opinion on Drug Metabolism & Toxicology · doi:10.1517/17425250902753261 · Cited by 59
“So far, there have been several arguments regarding the mismatch between the predictive ability of cross validation versus external validation [56-58] .”
Background
Two New Parameters Based on Distances in a Receiver Operating Characteristic Chart for the Selection of Classification Models
Pérez, A., Helguera, A. M., Borges, F., Cordeiro, M. N. D. S., Rivero‐Buceta, V., & Escudero, A. G. (2011) · Journal of Chemical Information and Modeling · doi:10.1021/ci2003076 · Cited by 58
Is regression through origin useful in external validation of QSAR models?
Shayanfar, A., & Shayanfar, S. (2014) · European Journal of Pharmaceutical Sciences · doi:10.1016/j.ejps.2014.03.007 · Cited by 58
A novel simple QSAR model for the prediction of anti-HIV activity using multiple linear regression analysis
Afantitis, A., Melagraki, G., Sarimveis, H., Koutentis, P. A., Markopoulos, J., & Igglessi‐Markopoulou, O. (2006) · Molecular Diversity · doi:10.1007/s11030-005-9012-2 · Cited by 58
“[18, 19] considered a QSAR model predictive, if the following conditions are satisfied:”
Background
In silico screening of chemicals for bacterial mutagenicity using electrotopological E-state indices and MDL QSAR software
Contrera, J. F., Matthews, E. J., Kruhlak, N. L., & Benz, R. D. (2005) · Regulatory Toxicology and Pharmacology · doi:10.1016/j.yrtph.2005.09.001 · Cited by 58
“External validation is considered the best means for determining the predictive power and reliability of a QSAR model (Golbraikh and Tropsha, 2002; Perkins et al., 2003).”
Method
QSAR Models for CXCR2 Receptor Antagonists Based on the Genetic Algorithm for Data Preprocessing Prior to Application of the PLS Linear Regression Method and Design of the New Compounds Using In Silico Virtual Screening
Asadollahi, T., Dadfarnia, S., Shabani, A. M. H., Ghasemi, J. B., & Sarkhosh, M. (2011) · Molecules · doi:10.3390/molecules16031928 · Cited by 58
“It should be noted that even when there is no correlation between the LOO- cross-validated R(2) (Q(2)) and regression coefficient R(2) for a predictive set with known values of biological activities, the validated model can be used for predicting activities/ properties of new chemicals [33,36].”
BackgroundMethod
Assessment of Additive/Nonadditive Effects in Structure−Activity Relationships: Implications for Iterative Drug Design
Patel, Y., Gillet, V. J., Howe, T. J., Pastor, J., Oyarzábal, J., & Willett, P. (2008) · Journal of Medicinal Chemistry · doi:10.1021/jm801070q · Cited by 58
Identification of ischemic heart disease via machine learning analysis on magnetocardiograms
Tantimongcolwat, T., Naenna, T., Isarankura-Na-Ayudhya, C., Embrechts, M. J., & Prachayasittikul, V. (2008) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2008.04.009 · Cited by 57
“The results are similar to the quality of classiﬁcation as achieved by the trained expert [38–40].”
Result
Identification of hydantoin based Decaprenylphosphoryl-β-d-Ribose Oxidase (DprE1) inhibitors as antimycobacterial agents using computational tools
Mali, S. N., Pandey, A., Bhandare, R. R., & SHAIK, A. B. (2022) · Scientific Reports · doi:10.1038/s41598-022-20325-1 · Cited by 58
Optimizing durability assessment: Machine learning models for depth of wear of environmentally-friendly concrete
Khan, M., Nassar, R., Khan, A. U., Houda, M., Hachem, C. E., Rasheed, M., & Anwar, W. (2023) · Results in Engineering · doi:10.1016/j.rineng.2023.101625 · Cited by 57
CoMFA and CoMSIA 3D-QSAR studies on quionolone caroxylic acid derivatives inhibitors of HIV-1 integrase
Lü, P., Wei, X., & Zhang, R. (2010) · European Journal of Medicinal Chemistry · doi:10.1016/j.ejmech.2010.04.030 · Cited by 57
Prediction of octanol-air partition coefficients for polychlorinated biphenyls (PCBs) using 3D-QSAR models
Chen, Y., Cai, X., Jiang, L. K., & Li, Y. (2015) · Ecotoxicology and Environmental Safety · doi:10.1016/j.ecoenv.2015.10.024 · Cited by 57
UPLC–MS retention time prediction: a machine learning approach to metabolite identification in untargeted profiling
Wolfer, A. M., Lozano, S., Umbdenstock, T., Croixmarie, V., Arrault, A., & Vayer, P. (2015) · Metabolomics · doi:10.1007/s11306-015-0888-2 · Cited by 57
Efficient Approximation of Ligand Rotational and Translational Entropy Changes upon Binding for Use in MM-PBSA Calculations
Ben‐Shalom, I., Pfeiffer‐Marek, S., Baringhaus, K. H., & Gohlke, H. (2016) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.6b00373 · Cited by 59
Chemometric modeling of aquatic toxicity of contaminants of emerging concern (CECs) in Dugesia japonica and its interspecies correlation with daphnia and fish: QSTR and QSTTR approaches
Hossain, K. A., & Roy, K. (2018) · Ecotoxicology and Environmental Safety · doi:10.1016/j.ecoenv.2018.09.068 · Cited by 57
Particle Swarm Optimization Based Approach for Estimation of Costs and Duration of Construction Projects
Khalaf, T. Z., Çağlar, H., Çağlar, A., & Hanoon, A. N. (2020) · Civil Engineering Journal · doi:10.28991/cej-2020-03091478 · Cited by 57
“The criteria suggested by Golbraikh et al. (2002) [28] were checked for the external verification of the proposed models on the testing datasets.”
Background
Predicting the emission wavelength of organic molecules using a combinatorial QSAR and machine learning approach
Ye, Z.-R., Huang, I.-S., Chan, Y.-T., Li, Z.-J., Liao, C.-C., Tsai, H.-R., Hsieh, M.-C., Chang, C., & Tsai, M. (2020) · RSC Advances · doi:10.1039/d0ra05014h · Cited by 54
Quantitative structure–activity relationship studies of HIV-1 integrase inhibition. 1. GETAWAY descriptors
Saı́z-Urra, L., González, M. P., Fall, Y., & Gómez, G. (2006) · European Journal of Medicinal Chemistry · doi:10.1016/j.ejmech.2006.08.005 · Cited by 58
3D-QSAR and molecular docking studies of aminopyrimidine derivatives as novel three-targeted Lck/Src/KDR inhibitors
Xie, W., Liu, Z., Fang, D., Wu, W., Ma, S., Tan, S., & Zheng, K. (2019) · Journal of Molecular Structure · doi:10.1016/j.molstruc.2019.02.071 · Cited by 56
Predicting Marshall Flow and Marshall Stability of Asphalt Pavements Using Multi Expression Programming
Awan, H. H., Hussain, A., Javed, M. F., Qiu, Y., Alrowais, R., Mohamed, A. M., Fathi, D. M., & Alzahrani, A. M. Y. (2022) · Buildings · doi:10.3390/buildings12030314 · Cited by 56
“The slopes of the regression li es (k or k′) running from the origin have been suggested to be close to one [81].”
Background
Efficient predictions of cytotoxicity of TiO2-based multi-component nanoparticles using a machine learning-based q-RASAR approach
Banerjee, A., Kar, S., Pore, S., & Roy, K. (2023) · Nanotoxicology · doi:10.1080/17435390.2023.2186280 · Cited by 56
“It is essential to note that both models passed the prescribed limits of the Golbraikh and Tropsha ’ s criteria (Golbraikh and Tropsha 2002) (Table 4).”
MethodInfluential
Hybrid soft computing models for predicting unconfined compressive strength of lime stabilized soil using strength property of virgin cohesive soil
Bahmed, I. T., Khatti, J., & Grover, K. S. (2024) · Bulletin of Engineering Geology and the Environment · doi:10.1007/s10064-023-03537-1 · Cited by 56
“The Golbraikh and Tropsha (2002) theory, which was proposed, is an accurate model in this investigation.”
Correlation between the glass transition temperatures and multipole moments for polymers
Yu, X., Yi, B., Wang, X., & Xie, Z. (2006) · Chemical Physics · doi:10.1016/j.chemphys.2006.11.029 · Cited by 56
Prediction of drug intestinal absorption by new linear and non-linear QSPR
Talevi, A., Goodarzi, M., Ortiz, E. V., Duchowicz, P. R., Bellera, C. L., Pesce, G. O., Castro, E. A., & Bruno‐Blanch, L. E. (2010) · European Journal of Medicinal Chemistry · doi:10.1016/j.ejmech.2010.11.005 · Cited by 55
Dragon method for finding novel tyrosinase inhibitors: Biosilico identification and experimental in vitro assays
Casañola‐Martín, G. M., Marrero‐Ponce, Y., Khan, M. T. H., Ather, A., Khan, K. M., Torrens, F., & Rotondo, R. (2007) · European Journal of Medicinal Chemistry · doi:10.1016/j.ejmech.2007.01.026 · Cited by 56
Total and Local Quadratic Indices of the “Molecular Pseudograph’s Atom Adjacency Matrix”. Application to Prediction of Caco-2 Permeability of Drugs
Marrero‐Ponce, Y., Cabrera‐Pérez, M. Á., Zaldívar, V. R., Ofori, E., & Montero, L. A. (2003) · International Journal of Molecular Sciences · doi:10.3390/i4080512 · Cited by 56
Discovery of Marinoquinolines as Potent and Fast-ActingPlasmodium falciparumInhibitors with in Vivo Activity
Aguiar, A. C. C., Panciera, M., dos Santos, E. F. S., Singh, M. K., Garcia, M. L., de Souza, G., Nakabashi, M., Costa, J. L., Garcia, C. R. S., Oliva, G., et al. (2018) · Journal of Medicinal Chemistry · doi:10.1021/acs.jmedchem.8b00143 · Cited by 56
Prediction on the mutagenicity of nitroaromatic compounds using quantum chemistry descriptors based QSAR and machine learning derived classification methods
Hao, Y., Sun, G., Fan, T., Sun, X., Liu, Y., Zhang, N., Zhao, L., Zhong, R., & Peng, Y. (2019) · Ecotoxicology and Environmental Safety · doi:10.1016/j.ecoenv.2019.109822 · Cited by 58
In vivo toxicity of nitroaromatic compounds to rats: QSTR modelling and interspecies toxicity relationship with mouse
Hao, Y., Sun, G., Fan, T., Tang, X., Zhang, J., Liu, Y., Zhang, N., Zhao, L., Zhong, R., & Peng, Y. (2020) · Journal of Hazardous Materials · doi:10.1016/j.jhazmat.2020.122981 · Cited by 56
Rational Design of New Antituberculosis Agents: Receptor-Independent Four-Dimensional Quantitative Structure−Activity Relationship Analysis of a Set of Isoniazid Derivatives
Pasqualoto, K. F. M., Ferreira, E. I., Santos‐Filho, O. A., & Hopfinger, A. J. (2004) · Journal of Medicinal Chemistry · doi:10.1021/jm049913k · Cited by 56
Prediction of organic compounds adsorbed by polyethylene and chlorinated polyethylene microplastics in freshwater using QSAR
Gui, B., Xu, X., Zhang, S., Wang, Y., Li, C., Zhang, D., Su, L., & Zhao, Y. H. (2021) · Environmental Research · doi:10.1016/j.envres.2021.111001 · Cited by 55
A comparison between 2D and 3D descriptors in QSAR modeling based on bio‐active conformations
Bahia, M. S., Kaspi, O., Touitou, M., Binayev, I., Dhail, S., Spiegel, J. D., Khazanov, N., Yosipof, A., & Senderowitz, H. (2023) · Molecular Informatics · doi:10.1002/minf.202200186 · Cited by 61
Synthesis and Structure–Activity Analysis of New Phosphonium Salts with Potent Activity against African Trypanosomes
Taladriz‐Sender, A., Healy, A. R., Pérez, E. J. F., Herrero, V., Martínez, C. R., Alkhaldi, A. A. M., Eze, A. A., Kaiser, M., de Koning, H. P., Chana, A., et al. (2012) · Journal of Medicinal Chemistry · doi:10.1021/jm2014259 · Cited by 55
QSAR analysis of the toxicity of nitroaromatics inTetrahymena pyriformis: structural factors and possible modes of action
Artemenko, A. G., Muratov, E. N., Kuz’min, V. Е., MURATOV, N. N., Varlamova, E. V., Kuz’mina, A. V., Gorb, L., Golius, A., Hill, F. C., Leszczyński, J., et al. (2011) · SAR and QSAR in environmental research · doi:10.1080/1062936x.2011.569950 · Cited by 55
“This approach allows us to minimize the dependence of the predictivity estimation on the test set compounds selection, although subsequent external validation on an independent test set is still highly desirable [46,49,58,59].”
Self-citation
QSAR prediction of inhibition of aldose reductase for flavonoids
Mercader, A. G., Duchowicz, P. R., Fernández, F. M., Castro, E. A., Bennardi, D. O., Autino, J. C., & Romanelli, G. P. (2008) · Bioorganic & Medicinal Chemistry · doi:10.1016/j.bmc.2008.06.004 · Cited by 55
QSAR-like models: A potential tool for the selection of PhACs and EDCs for monitoring purposes in drinking water treatment systems – A review
Delgado, L. F., Charles, P., Glucina, K., & Morlay, C. (2012) · Water Research · doi:10.1016/j.watres.2012.08.016 · Cited by 55
A novel approach to predict aquatic toxicity from molecular structure
Castillo‐Garit, J. A., Marrero‐Ponce, Y., Escobar, J., Torrens, F., & Rotondo, R. (2008) · Chemosphere · doi:10.1016/j.chemosphere.2008.05.024 · Cited by 55
“Efforts should be made to have chemical diversity within the training set and the chemicals in the validation set similar to those in the training set (Golbraikh and Tropsha, 2002).”
BackgroundResult
Ontology of core data mining entities
Panov, P., Soldatova, L., & Džeroski, S. (2014) · Data Mining and Knowledge Discovery · doi:10.1007/s10618-014-0363-0 · Cited by 56
“Experimental validation of QSAR predictive models is very rare (Golbraikh and Tropsha 2002).”
BackgroundMethod

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