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 101–200 of 1,004

Development and Validation of k-Nearest-Neighbor QSPR Models of Metabolic Stability of Drug Candidates
Shen, M., Xiao, Y.-D., Golbraikh, A., Gombar, V. K., & Tropsha, A. (2003) · Journal of Medicinal Chemistry · doi:10.1021/jm020491t · Cited by 183
Self-citation
Application of Random Forest Approach to QSAR Prediction of Aquatic Toxicity
Полищук, П. Г., Muratov, E. N., Artemenko, A. G., Kolumbin, O. G., MURATOV, N. N., & Kuz’min, V. Е. (2009) · Journal of Chemical Information and Modeling · doi:10.1021/ci900203n · Cited by 182
Degree of deacetylation of chitosan by infrared spectroscopy and partial least squares
Dimzon, I. K. D., & Knepper, T. P. (2014) · International Journal of Biological Macromolecules · doi:10.1016/j.ijbiomac.2014.09.050 · Cited by 180
Detecting “bad” regression models: multicriteria fitness functions in regression analysis
Todeschini, R., Consonni, V., Mauri, A., & Pavan, M. (2004) · Analytica Chimica Acta · doi:10.1016/j.aca.2003.12.010 · Cited by 179
Binding affinity in drug design: experimental and computational techniques
Kairys, V., Baranauskienė, L., Kazlauskiene, M., Matulis, D., & Kazlauskas, E. (2019) · Expert Opinion on Drug Discovery · doi:10.1080/17460441.2019.1623202 · Cited by 184
Proteochemometric modeling as a tool to design selective compounds and for extrapolating to novel targets
van Westen, G. J. P., Wegner, J. K., IJzerman, A. P., van Vlijmen, H. W. T., & Bender, A. (2011) · MedChemComm · doi:10.1039/c0md00165a · Cited by 176
Surface functional groups determine adsorption of pharmaceuticals and personal care products on polypropylene microplastics
Yao, J., Wen, J., Li, H., & Yang, Y. (2021) · Journal of Hazardous Materials · doi:10.1016/j.jhazmat.2021.127131 · Cited by 171
Evaluation of water quality indexes with novel machine learning and SHapley Additive ExPlanation (SHAP) approaches
Aldrees, A., Khan, M., Taha, A. T. B., & Ali, M. (2024) · Journal of Water Process Engineering · doi:10.1016/j.jwpe.2024.104789 · Cited by 180
Structure-Thermodynamics-Antioxidant Activity Relationships of Selected Natural Phenolic Acids and Derivatives: An Experimental and Theoretical Evaluation
Chen, Y., Xiao, H., Zheng, J., & Liang, G. (2015) · PLoS ONE · doi:10.1371/journal.pone.0121276 · Cited by 172
“600 [45], respectively.”
Applications of Gene Expression Programming and Regression Techniques for Estimating Compressive Strength of Bagasse Ash based Concrete
Javed, M. F., Amin, M. N., Shah, M. I., Khan, K., Iftikhar, B., Farooq, F., Aslam, F., Alyousef, R., & Alabduljabbar, H. (2020) · Crystals · doi:10.3390/cryst10090737 · Cited by 170
“Furthermore, other criteria for external verification of the models proposed by Golbraikh and Tropsha [74] suggested that the slope of the regression line should be approximately near to 1.”
Background
Reliable estimation of prediction errors for QSAR models under model uncertainty using double cross-validation
Baumann, D., & Baumann, K. (2014) · Journal of Cheminformatics · doi:10.1186/s13321-014-0047-1 · Cited by 178
“Simulated Annealing in combination with k nearest neighbour (SAkNN) was employed as nonlinear modelling technique [64].”
Sustainable utilization of foundry waste: Forecasting mechanical properties of foundry sand based concrete using multi-expression programming
Iqbal, M. F., Javed, M. F., Rauf, M., Azim, I., Ashraf, M., Yang, J., & Liu, Q. (2021) · The Science of The Total Environment · doi:10.1016/j.scitotenv.2021.146524 · Cited by 166
Cytotoxicity of selected imidazolium-derived ionic liquids in the human Caco-2 cell line. Sub-structural toxicological interpretation through a QSAR study
García-Lorenzo, A., Tojo, E., Tojo, J., Teijeira, M., Rodrı́guez-Berrocal, F. J., González, M. P., & Martínez-Zorzano, V. S. (2008) · Green Chemistry · doi:10.1039/b718860a · Cited by 160
A novel variable selection approach that iteratively optimizes variable space using weighted binary matrix sampling
Deng, B., Yun, Y., Liang, Y., & Yi, L. (2014) · The Analyst · doi:10.1039/c4an00730a · Cited by 160
Novel Approach to Strength Modeling of Concrete under Triaxial Compression
Gandomi, A. H., Babanajad, S. K., Alavi, A. H., & Farnam, Y. A. (2012) · Journal of Materials in Civil Engineering · doi:10.1061/(asce)mt.1943-5533.0000494 · Cited by 160
DeepDSC: A Deep Learning Method to Predict Drug Sensitivity of Cancer Cell Lines
Li, M., Wang, Y., Zheng, R., Shi, X. M., Li, Y., Wu, F., & Wang, J. (2019) · IEEE Transactions on Computational Biology and Bioinformatics · doi:10.1109/tcbb.2019.2919581 · Cited by 162
“We also choose coefﬁcient of determination R 2 [50] described in (6) to measure the predictive performance of our deep learning models. where N is the size of the test data, y i and ~ y i are the target drug sensitivity data and the predicted counterpart of i th input data, and (cid:2) y is the…”
Method
Quantitative Structure-Permeation Relationships (QSPeRs) to Predict Skin Permeation: A Critical Evaluation
Geinoz, S., Guy, R. H., Testa, B., & Carrupt, P. (2004) · Pharmaceutical Research · doi:10.1023/b:pham.0000012155.27488.2b · Cited by 164
How drugs get into cells: tested and testable predictions to help discriminate between transporter-mediated uptake and lipoidal bilayer diffusion
Kell, D. B., & Oliver, S. G. (2014) · Frontiers in Pharmacology · doi:10.3389/fphar.2014.00231 · Cited by 158
“However, this approach to QSAR/QSPR has since been questioned seriously (e.g., Golbraikh and Tropsha, 2002; Cronin and Schultz, 2003; Eriksson et al., www.frontiersin.org October 2014 | Volume 5 | Article 231 | 5 2003; Golbraikh et al., 2003; Tropsha et al., 2003; Broadhurst and Kell, 2006;…”
Method
Towards artificial intelligence-enabled extracellular vesicle precision drug delivery
Greenberg, Z., Graim, K. S., & He, M. (2023) · Advanced Drug Delivery Reviews · doi:10.1016/j.addr.2023.114974 · Cited by 166
Synthesis, biological evaluation and molecular modeling study of pyrazole and pyrazoline derivatives as selective COX-2 inhibitors and anti-inflammatory agents. Part 2
El‐Sayed, M. A. ‐., Abdel-Aziz, N. I., Abdel‐Aziz, A. A. ‐., El‐Azab, A. S., & ElTahir, K. E. H. (2012) · Bioorganic & Medicinal Chemistry · doi:10.1016/j.bmc.2012.03.044 · Cited by 155
In Silico Absorption, Distribution, Metabolism, Excretion, and Pharmacokinetics (ADME-PK): Utility and Best Practices. An Industry Perspective from the International Consortium for Innovation through Quality in Pharmaceutical Development
Lombardo, F., Desai, P. V., Arimoto, R., Desino, K. E., Fischer, H., Keefer, C. E., Petersson, C., Winiwarter, S., & Broccatelli, F. (2017) · Journal of Medicinal Chemistry · doi:10.1021/acs.jmedchem.7b00487 · Cited by 161
Prediction model for compressive arch action capacity of RC frame structures under column removal scenario using gene expression programming
Azim, I., Yang, J., Javed, M. F., Iqbal, M. F., Mahmood, Z., Wang, F., & Liu, Q. (2020) · Structures · doi:10.1016/j.istruc.2020.02.028 · Cited by 155
Practical Aspects of Computational Chemistry
Leszczyński, J., & Shukla, M. K. (2009) · Springer eBooks · doi:10.1007/978-90-481-2687-3 · Cited by 163
Application of Predictive QSAR Models to Database Mining: Identification and Experimental Validation of Novel Anticonvulsant Compounds
Shen, M., Béguin, C., Golbraikh, A., Stables, J. P., Kohn, H., & Tropsha, A. (2004) · Journal of Medicinal Chemistry · doi:10.1021/jm030584q · Cited by 150
Self-citation
How important is to detect systematic error in predictions and understand statistical applicability domain of QSAR models?
Roy, K., Ambure, P. S., & Aher, R. B. (2017) · Chemometrics and Intelligent Laboratory Systems · doi:10.1016/j.chemolab.2017.01.010 · Cited by 146
Compressive strength of Foamed Cellular Lightweight Concrete simulation: New development of hybrid artificial intelligence model
Ashrafian, A., Shokri, F., Amiri, M. J. T., Yaseen‬‬‬‬‬‬‬‬‬‬‬‬‬‬‬‬, Z. M., & Rezaie-Balf, M. (2019) · Construction and Building Materials · doi:10.1016/j.conbuildmat.2019.117048 · Cited by 151
New machine learning-based prediction models for fracture energy of asphalt mixtures
Majidifard, H., Jahangiri, B., Buttlar, W. G., & Alavi, A. H. (2018) · Measurement · doi:10.1016/j.measurement.2018.11.081 · Cited by 145
“Besides, Table 6 shows some criteria suggested by Golbraikh and Tropsha [35] and Roy and Roy [73] for the external validation of the models.”
Method
Quantitative Structure−Activity Relationship Analysis of Functionalized Amino Acid Anticonvulsant Agents Using k Nearest Neighbor and Simulated Annealing PLS Methods
Shen, M., LeTiran, A., Xiao, Y.-D., Golbraikh, A., Kohn, H., & Tropsha, A. (2002) · Journal of Medicinal Chemistry · doi:10.1021/jm010488u · Cited by 145
Self-citation
General Melting Point Prediction Based on a Diverse Compound Data Set and Artificial Neural Networks
Karthikeyan, M., Glen, R. C., & Bender, A. (2005) · Journal of Chemical Information and Modeling · doi:10.1021/ci0500132 · Cited by 146
“21 Thus we employ a two-step validation protocol.”
Method
Beware of machine learning-based scoring functions-on the danger of developing black boxes.
Gabel, J., Desaphy, J., & Rognan, D. (2014) · Journal of Chemical Information and Modeling · doi:10.1021/ci500406k · Cited by 143
Camptothecins: A SAR/QSAR Study
Verma, R. P., & Hansch, C. H. (2008) · Chemical Reviews · doi:10.1021/cr0780210 · Cited by 142
Statistical Methods in QSAR/QSPR
Roy, K., Kar, S., & Das, R. N. (2015) · Springer briefs in molecular science · doi:10.1007/978-3-319-17281-1_2 · Cited by 140
Applicability Domain: A Step Toward Confident Predictions and Decidability for QSAR Modeling
Kar, S., Roy, K., & Leszczyński, J. (2018) · Methods in molecular biology · doi:10.1007/978-1-4939-7899-1_6 · Cited by 140
Combinatorial QSAR Modeling of P-Glycoprotein Substrates
Lima, P. D. C., Golbraikh, A., Oloff, S., Xiao, Y.-D., & Tropsha, A. (2006) · Journal of Chemical Information and Modeling · doi:10.1021/ci0504317 · Cited by 138
Self-citation
Consensus QSAR modeling of toxicity of pharmaceuticals to different aquatic organisms: Ranking and prioritization of the DrugBank database compounds
Khan, K., Benfenati, E., & Roy, K. (2018) · Ecotoxicology and Environmental Safety · doi:10.1016/j.ecoenv.2018.10.060 · Cited by 138
New public QSAR model for carcinogenicity
Fjodorova, N., Vračko, M., Novič, M., Roncaglioni, A., & Benfenati, E. (2010) · Chemistry Central Journal · doi:10.1186/1752-153x-4-s1-s3 · Cited by 137
“External validation is commonly used for the predictivity and reliability of QSAR model [71,72].”
Method
3D-QSAR illusions
Doweyko, A. M. (2004) · Journal of Computer-Aided Molecular Design · doi:10.1007/s10822-004-4068-0 · Cited by 135
QSAR: dead or alive?
Doweyko, A. M. (2008) · Journal of Computer-Aided Molecular Design · doi:10.1007/s10822-007-9162-7 · Cited by 134
A hybrid computational approach to derive new ground-motion prediction equations
Gandomi, A. H., Alavi, A. H., Mousavi, M., & Tabatabaei, S. M. (2011) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2011.01.005 · Cited by 134
Statistical variation in progressive scrambling
Clark, R. D., & Fox, P. C. (2004) · Journal of Computer-Aided Molecular Design · doi:10.1007/s10822-004-4077-z · Cited by 132
QSAR Prediction of Estrogen Activity for a Large Set of Diverse Chemicals under the Guidance of OECD Principles
Liu, H., Papa, E., & Gramatica, P. (2006) · Chemical Research in Toxicology · doi:10.1021/tx0601509 · Cited by 133
Synthesis and QSAR of Quinazoline Sulfonamides As Highly Potent Human Histamine H 4 Receptor Inverse Agonists
Smits, R. A., Adami, M., Istyastono, E. P., Zuiderveld, O. P., van Dam, C. M. E., de Kanter, F. J. J., Jongejan, A., Coruzzi, G., Leurs, R., & de Esch, I. J. P. (2010) · Journal of Medicinal Chemistry · doi:10.1021/jm901379s · Cited by 133
Existing and Developing Approaches for QSAR Analysis of Mixtures
Muratov, E. N., Varlamova, E. V., Artemenko, A. G., Полищук, П. Г., & Kuz’min, V. Е. (2012) · Molecular Informatics · doi:10.1002/minf.201100129 · Cited by 139
QSAR, molecular docking and ADMET properties in silico studies of novel 4,5,6,7-tetrahydrobenzo[D]-thiazol-2-Yl derivatives derived from dimedone as potent anti-tumor agents through inhibition of C-Met receptor tyrosine kinase
Daouı, O., Elkhattabi, S., Chtita, S., Elkhalabi, R., Zgou, H., & Benjelloun, A. T. (2021) · Heliyon · doi:10.1016/j.heliyon.2021.e07463 · Cited by 135
Predicting pKa
Lee, A. C., & Crippen, G. M. (2009) · Journal of Chemical Information and Modeling · doi:10.1021/ci900209w · Cited by 134
Model population analysis for variable selection
Li, H., Liang, Y., Xu, Q., & Cao, D. (2010) · Journal of Chemometrics · doi:10.1002/cem.1300 · Cited by 130
“What is the philosophy of the classification? Is it a pitfall or is there anything we did not paymuch attention to [6,7]? Is there anything connecting with the overfitting, since, in his example, the number of variables (200) is much larger than that of samples (100).”
Background
Chemo- and bioinformatics resources for in silico drug discovery from medicinal plants beyond their traditional use: a critical review
Lagunin, A. A., Goel, R. K., Gawande, D. Y., Pahwa, P., Gloriozova, T. A., Dmitriev, A. V., Ivanov, S. M., Rudik, A. V., Konova, V., Pogodin, P. V., et al. (2014) · Natural Product Reports · doi:10.1039/c4np00068d · Cited by 133
Development of quantitative structure activity relationship (QSAR) model for disinfection byproduct (DBP) research: A review of methods and resources
Chen, B., Zhang, T., Bond, T., & Gan, Y. (2015) · Journal of Hazardous Materials · doi:10.1016/j.jhazmat.2015.06.054 · Cited by 130
“[92,165,166] Data analysis Outlier and AD Indicators R2, Q2, SD, RMSE, F-test, h”
Method
The Better Predictive Model: High q2 for the Training Set or Low Root Mean Square Error of Prediction for the Test Set?
Aptula, A. O., Jeliazkova, N., Schultz, T. W., & Cronin, M. (2005) · QSAR & Combinatorial Science · doi:10.1002/qsar.200430909 · Cited by 129
Improved large-scale prediction of growth inhibition patterns using the NCI60 cancer cell line panel
Cortés‐Ciriano, I., van Westen, G. J. P., Bouvier, G., Nilges, M., Overington, J. P., Bender, A., & Malliavin, T. E. (2015) · Bioinformatics · doi:10.1093/bioinformatics/btv529 · Cited by 123
“6 Model validation The predictive power of the models was assessed on the test set according to the RMSEtest and R 2 0 test values (Golbraikh and Tropsha, 2002):”
MethodInfluential
Prediction of the five-day biochemical oxygen demand and chemical oxygen demand in natural streams using machine learning methods
Najafzadeh, M., & Ghaemi, A. (2019) · Environmental Monitoring and Assessment · doi:10.1007/s10661-019-7446-8 · Cited by 128
“Performance of external validation is evaluated by means of the testing datasets and then several criteria are computed (Golbraikh and Tropsha 2002; Sattar 2014).”
MethodInfluential
Design, synthesis and biological evaluation of novel isoniazid derivatives with potent antitubercular activity
Martins, F. E. L., Santos, S., Ventura, C. M., Elvas‐Leitão, R., Santos, L., Vitorino, S., Reis, M. A. M., Miranda, V. P. B., Correia, H. F., Aires‐de‐Sousa, J., et al. (2014) · European Journal of Medicinal Chemistry · doi:10.1016/j.ejmech.2014.04.077 · Cited by 127
“6 is usually taken as a good measure of the robustness of the model [35,63,72].”
Background
QSPR prediction of the hydroxyl radical rate constant of water contaminants
Borhani, T. N. G., Saniedanesh, M., Bagheri, M., & Lim, J. S. (2016) · Water Research · doi:10.1016/j.watres.2016.04.038 · Cited by 127
The index of ideality of correlation: A criterion of predictive potential of QSPR/QSAR models?
Toropov, A. A., & Toropova, A. P. (2017) · Mutation Research/Genetic Toxicology and Environmental Mutagenesis · doi:10.1016/j.mrgentox.2017.05.008 · Cited by 127
Ground Motion Prediction Model Using Artificial Neural Network
Dhanya, J., & Raghukanth, S. T. G. (2017) · Pure and Applied Geophysics · doi:10.1007/s00024-017-1751-3 · Cited by 127
“Additionally, the model is tested with the set of new evaluation criteria given by Golbraikh and Tropsha (2002) and is summarized in Table 6.”
Method
SS-XGBoost: A Machine Learning Framework for Predicting Newmark Sliding Displacements of Slopes
Wang, M., Huang, D., Wang, G., & Li, D. Q. (2020) · Journal of Geotechnical and Geoenvironmental Engineering · doi:10.1061/(asce)gt.1943-5606.0002297 · Cited by 127
New Prediction Model for the Ultimate Axial Capacity of Concrete-Filled Steel Tubes: An Evolutionary Approach
Javed, M. F., Farooq, F., Memon, S. A., Akbar, A., Khan, M. A., Aslam, F., Alyousef, R., Alabduljabbar, H., & Rehman, S. K. U. (2020) · Crystals · doi:10.3390/cryst10090741 · Cited by 127
“Furthermore, external verification is also suggested by researcher [75].”
Background
Data Science Meets Physical Organic Chemistry
Crawford, J. M., Kingston, C., Toste, F. D., & Sigman, M. S. (2021) · Accounts of Chemical Research · doi:10.1021/acs.accounts.1c00285 · Cited by 123
Investigating the influence of data splitting on the predictive ability of QSAR/QSPR models
Puzyn, T., Mostrąg, A., Gajewicz, A., Skrzyński, M., & Worth, A. P. (2011) · Structural Chemistry · doi:10.1007/s11224-011-9757-4 · Cited by 122
“Only properly trained and validated models are able to provide reliable predictions for novel compounds [1–5].”
Background
Periodic table-based descriptors to encode cytotoxicity profile of metal oxide nanoparticles: A mechanistic QSTR approach
Kar, S., Gajewicz, A., Puzyn, T., Roy, K., & Leszczyński, J. (2014) · Ecotoxicology and Environmental Safety · doi:10.1016/j.ecoenv.2014.05.026 · Cited by 123
Quantitative Structure–Retention Relationship Models To Support Nontarget High-Resolution Mass Spectrometric Screening of Emerging Contaminants in Environmental Samples
Aalizadeh, R., Τhomaidis, Ν. S., Bletsou, A. A., & Gago-Ferrero, P. (2016) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.5b00752 · Cited by 128
DrugScore Meets CoMFA: Adaptation of Fields for Molecular Comparison (AFMoC) or How to Tailor Knowledge-Based Pair-Potentials to a Particular Protein
Gohlke, H., & Klebe, G. (2002) · Journal of Medicinal Chemistry · doi:10.1021/jm020808p · Cited by 122
Endocrine-disrupting activity of per- and polyfluoroalkyl substances: Exploring combined approaches of ligand and structure based modeling
Kar, S., Sepúlveda, M. S., Roy, K., & Leszczyński, J. (2017) · Chemosphere · doi:10.1016/j.chemosphere.2017.06.024 · Cited by 120
History of Quantitative Structure–Activity Relationships
Selassie, C. R. D., & Verma, R. P. (2010) · Wiley eBooks · doi:10.1002/0471266949.bmc001.pub2 · Cited by 121
Empirical modeling of plate load test moduli of soil via gene expression programming
Mollahasani, A., Alavi, A. H., & Gandomi, A. H. (2011) · Computers and Geotechnics · doi:10.1016/j.compgeo.2010.11.008 · Cited by 118
Prediction of the potency of mammalian cyclooxygenase inhibitors with ensemble proteochemometric modeling
Cortés‐Ciriano, I., Murrell, D. S., van Westen, G. J. P., Bender, A., & Malliavin, T. E. (2015) · Journal of Cheminformatics · doi:10.1186/s13321-014-0049-z · Cited by 117
“[54-56], and to the RMSE values (Equation 1).”
BackgroundMethod
Machine learning interpretable-prediction models to evaluate the slump and strength of fly ash-based geopolymer
Nazar, S., Yang, J., Amin, M. N., Khan, K., Ashraf, M., Aslam, F., Javed, M. F., & Eldin, S. M. (2023) · Journal of Materials Research and Technology · doi:10.1016/j.jmrt.2023.02.180 · Cited by 118
SFCscore: Scoring functions for affinity prediction of protein–ligand complexes
Sotriffer, C., Sanschagrin, P. C., Matter, H., & Klebe, G. (2008) · Proteins Structure Function and Bioinformatics · doi:10.1002/prot.22058 · Cited by 121
In Silico Prediction of Caco‐2 Cell Permeability by a Classification QSAR Approach
Pham‐The, H., González‐Álvarez, I., Bermejo, M., Sanjuan, V. M., Centelles, I., Garrigues, T., & Cabrera‐Pérez, M. Á. (2011) · Molecular Informatics · doi:10.1002/minf.201000118 · Cited by 121
Synergistic and Antagonistic Drug Combinations against SARS-CoV-2
Bobrowski, T., Chen, L., Eastman, R. T., Itkin, Z., Shinn, P., Chen, C. Z., Guo, H., Zheng, W., Michael, S., Simeonov, A. M., et al. (2020) · Molecular Therapy · doi:10.1016/j.ymthe.2020.12.016 · Cited by 119
“All models were developed according to the best practices of QSAR modeling,(34,42,43) with special attention paid for data curation and rigorous external validation.(47) Mixture-specific descriptors and validation techniques(48) specially developed for modeling of drug combinations were utilized for modeling of drug-d…”
Method
A Systematic Investigation of Quaternary Ammonium Ions as Asymmetric Phase-Transfer Catalysts. Application of Quantitative Structure Activity/Selectivity Relationships
Denmark, S. E., Gould, N. D., & Wolf, L. M. (2011) · The Journal of Organic Chemistry · doi:10.1021/jo2005457 · Cited by 115
A new hybrid system of QSAR models for predicting bioconcentration factors (BCF)
Zhao, C., Boriani, E., Chana, A., Roncaglioni, A., & Benfenati, E. (2008) · Chemosphere · doi:10.1016/j.chemosphere.2008.09.033 · Cited by 116
Polypharmacology modelling using proteochemometrics (PCM): recent methodological developments, applications to target families, and future prospects
Cortés‐Ciriano, I., Ain, Q. U., Subramanian, V., Lenselink, E. B., Méndez‐Lucio, O., IJzerman, A. P., Wohlfahrt, G., Prūsis, P., Malliavin, T. E., van Westen, G. J. P., et al. (2014) · MedChemComm · doi:10.1039/c4md00216d · Cited by 119
A hybrid intelligent fuzzy predictive model with simulation for supplier evaluation and selection
Madjid Tavana, D., Fallahpour, A., Caprio, D. D., & Santos‐Arteaga, F. J. (2016) · Expert Systems with Applications · doi:10.1016/j.eswa.2016.05.027 · Cited by 116
“In particular, we have used the statistic indicators recommended by Golbraikh and Tropsha (2002) to perform an external validation of the proposed models on the testing data sets.”
Method
The index of ideality of correlation: A criterion of predictability of QSAR models for skin permeability?
Toropova, A. P., & Toropov, A. A. (2017) · The Science of The Total Environment · doi:10.1016/j.scitotenv.2017.01.198 · Cited by 116
External Evaluation of QSAR Models, in Addition to Cross‐Validation: Verification of Predictive Capability on Totally New Chemicals
Gramatica, P. (2014) · Molecular Informatics · doi:10.1002/minf.201400030 · Cited by 113
What are the ideal properties for functional food peptides with antihypertensive effect? A computational peptidology approach
Zhou, P., Yang, C., Ren, Y., Wang, C., & Tian, F. (2013) · Food Chemistry · doi:10.1016/j.foodchem.2013.05.140 · Cited by 115
Current approaches for choosing feature selection and learning algorithms in quantitative structure–activity relationships (QSAR)
Khan, P. M., & Roy, K. (2018) · Expert Opinion on Drug Discovery · doi:10.1080/17460441.2018.1542428 · Cited by 113
“Various validation metrics and rules are applied to examine the quality of predictions such as Q 2ext metrics, r m2 metrics [119], Tropsha ’ s criteria [120], and mean absolute error (MAE)-based criteria [121].”
Method
Identification of novel acetylcholinesterase inhibitors designed by pharmacophore-based virtual screening, molecular docking and bioassay
Jang, C., Yadav, D. K., Subedi, L., Venkatesan, R., Venkanna, A., Afzal, S., Lee, E.-H., Yoo, J.-W., Ji, E., Kim, S. Y., et al. (2018) · Scientific Reports · doi:10.1038/s41598-018-33354-6 · Cited by 114
In Silico Predictions of Blood-Brain Barrier Penetration: Considerations to “Keep in Mind”
Goodwin, J. T., & Clark, D. E. (2005) · Journal of Pharmacology and Experimental Therapeutics · doi:10.1124/jpet.104.075705 · Cited by 113
Predictive modeling in homogeneous catalysis: a tutorial
Maldonado, A. G., & Rothenberg, G. (2010) · Chemical Society Reviews · doi:10.1039/b921393g · Cited by 111
QSAR Modeling Using Chirality Descriptors Derived from Molecular Topology
Golbraikh, A., & Tropsha, A. (2002) · Journal of Chemical Information and Computer Sciences · doi:10.1021/ci025516b · Cited by 110
Self-citation
Genetic algorithm optimization in drug design QSAR: Bayesian-regularized genetic neural networks (BRGNN) and genetic algorithm-optimized support vectors machines (GA-SVM)
Fernández, M., Caballero, J., Fernández, L., & Sarai, A. (2010) · Molecular Diversity · doi:10.1007/s11030-010-9234-9 · Cited by 108
“In addition to assessment of statistical fit by crossvalidation, randomization of the modeled property (also known as Y-randomization) have also evaluated model robustness [21,24,27,65,66].”
BackgroundMethod
3D-QSAR and docking studies of flavonoids as potent Escherichia coli inhibitors
Fang, Y., Lu, Y., Zang, X., Wu, T., Qi, X., Pan, S., & Xu, X. (2016) · Scientific Reports · doi:10.1038/srep23634 · Cited by 109
New prediction models for unconfined compressive strength of geopolymer stabilized soil using multi-gen genetic programming
Soleimani, S., Rajaei, S., Jiao, P., Sabz, A., & Soheilinia, S. (2017) · Measurement · doi:10.1016/j.measurement.2017.08.043 · Cited by 109
Energy-based numerical models for assessment of soil liquefaction
Alavi, A. H., & Gandomi, A. H. (2011) · Geoscience Frontiers · doi:10.1016/j.gsf.2011.12.008 · Cited by 109
“Golbraikh and Tropsha (2002) suggested that at least one slope of regression lines (k or k0) through the origin should be close to 1.”
Background
Advantages of support vector machine in QSPR studies for predicting auto-ignition temperatures of organic compounds
Pan, Y., Jiang, J., Wang, R., & Cao, H. (2008) · Chemometrics and Intelligent Laboratory Systems · doi:10.1016/j.chemolab.2008.03.002 · Cited by 109
Best of Both Worlds: Combining Pharma Data and State of the Art Modeling Technology To Improve in Silico pKa Prediction
Fraczkiewicz, R., Lobell, M., Göller, A. H., Krenz, U., Schoenneis, R., Clark, R. D., & Hillisch, A. (2014) · Journal of Chemical Information and Modeling · doi:10.1021/ci500585w · Cited by 107
QSAR Modeling of Bioconcentration Factor by theoretical molecular descriptors
Gramatica, P., & Papa, E. (2003) · QSAR & Combinatorial Science · doi:10.1002/qsar.200390027 · Cited by 107
A new prediction model for the load capacity of castellated steel beams
Gandomi, A. H., Tabatabaei, S. M., Moradian, M. H., Radfar, A., & Alavi, A. H. (2011) · Journal of Constructional Steel Research · doi:10.1016/j.jcsr.2011.01.014 · Cited by 107
Design equations for prediction of pressuremeter soil deformation moduli utilizing expression programming systems
Alavi, A. H., Gandomi, A. H., Nejad, H. C., Mollahasani, A., & Rashed, A. (2012) · Neural Computing and Applications · doi:10.1007/s00521-012-1144-6 · Cited by 106
“Instead, new criteria recommended by Golbraikh and Tropsha [48] are checked for external validation of the models on the validation data sets.”
Method
Effects of Oligosaccharides From Morinda officinalis on Gut Microbiota and Metabolome of APP/PS1 Transgenic Mice
Yang, X., Diling, C., Yang, J. T., Ting, L., Guoyan, H., Hualun, L., Xiaocui, T., Lai, G., Shuai, O., Chaoqun, Z., et al. (2018) · Frontiers in Neurology · doi:10.3389/fneur.2018.00412 · Cited by 110
“Furthermore, the categorized models were confirmed with the response permutation test (RPT) (38).”
Method
Towards Intelligent Mining for Backfill: A genetic programming-based method for strength forecasting of cemented paste backfill
Qi, C., Tang, X., Dong, X., Chen, Q., Fourie, A. B., & Liu, E. (2019) · Minerals Engineering · doi:10.1016/j.mineng.2019.01.004 · Cited by 106
Quantitative Structure-Activity Relationship (QSAR): Modeling Approaches to Biological Applications
Peter, S. C., Dhanjal, J. K., Malik, V., Radhakrishnan, N., Mannu, J., & Sundar, D. (2018) · Elsevier eBooks · doi:10.1016/b978-0-12-809633-8.20197-0 · Cited by 115
Mixed learning algorithms and features ensemble in hepatotoxicity prediction
Liew, C. Y., Lim, Y. C., & Yap, C. W. (2011) · Journal of Computer-Aided Molecular Design · doi:10.1007/s10822-011-9468-3 · Cited by 109
Chemometric-assisted method development in hydrophilic interaction liquid chromatography: A review
Taraji, M., Haddad, P. R., Amos, R. I. J., Talebi, M., Szücs, R., Dolan, J. W., & Pohl, C. A. (2017) · Analytica Chimica Acta · doi:10.1016/j.aca.2017.09.041 · Cited by 104
Systematic Comparison and Comprehensive Evaluation of 80 Amino Acid Descriptors in Peptide QSAR Modeling
Zhou, P., Liu, Q., Wu, T., Miao, Q., Shang, S., Wang, H., Chen, Z., Wang, S., & Wang, H. (2021) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.0c01370 · Cited by 104
Assessment of the ground vibration during blasting in mining projects using different computational approaches
Hosseini, S., Khatti, J., Taiwo, B. O., Fissha, Y., Grover, K. S., Ikeda, H., Pushkarna, M., Tuka, M. B., & Ali, M. (2023) · Scientific Reports · doi:10.1038/s41598-023-46064-5 · Cited by 103
New QSPR study for the prediction of aqueous solubility of drug-like compounds
Duchowicz, P. R., Talevi, A., Bruno‐Blanch, L. E., & Castro, E. A. (2008) · Bioorganic & Medicinal Chemistry · doi:10.1016/j.bmc.2008.07.067 · Cited by 104
Comparative Study of Multitask Toxicity Modeling on a Broad Chemical Space
Sosnin, S., Karlov, D., Tetko, I. V., & Fedorov, M. V. (2019) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.8b00685 · Cited by 102
“56 To combat with this problem and estimate the statistical performance in a robust way a 5-fold cross-validation routine has been carried out for all models in this study.”
Method

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