The review of the most used computational methods for studies of the relationships between molecular structure and biological activity




QSAR, drug development, molecular modeling, QSAR methods, mathematical models, variable selection methods, machine learning


Aim. To systematize the most used methods of “molecular structure-biological activity” relationship studies and to disclose their principles of application, strong and weak sides.

Methods. The review of modern scientific literature devoted to QSAR modeling was carried out. The most frequently used methods for “structure-activity” models development were selected for further description.

Results. The place of “molecular structure-activity” relationships analysis among computer assisted drug design methods is discussed in the current review and the most used algorithms of QSAR model development with emphasis on the mechanisms of their work are described. The approaches based on model ensembles become more and more popular, one of which is Random Forest.

Conclusions. The progress in machine learning methods development is the key to the further evolution of QSAR direction and to the discovering of new biologically active substances

Author Biography

Олег Теодозійович Девіняк, Uzhhorod National University 3 Narodna sq, Uzhhorod, Ukraine, 88000

Candidate of Pharmaceutical Sciences

Head of the Department of Pharmaceutical Disciplines


Dudek, A., Arodz, T., Galvez, J. (2006). Computational Methods in Developing Quantitative Structure-Activity Relationships (QSAR): A Review. Combinatorial Chemistry & High Throughput Screening, 9 (3), 213–228. doi: 10.2174/138620706776055539

Arakawa, M., Hasegawa, K., Funatsu, K. (2007). The Recent Trend in QSAR Modeling – Variable Selection and 3D-QSAR Methods. Current Computer Aided-Drug Design, 3 (4), 254–262. doi: 10.2174/1573409077827994177

Tropsha, A., Golbraikh, A. (2007). Predictive QSAR Modeling Workflow, Model Applicability Domains, and Virtual Screening. Current Pharmaceutical Design, 13 (34), 3494–3504. doi: 10.2174/138161207782794257

Cherkasov, A., Muratov, E. N., Fourches, D., Varnek, A., Baskin, I. I., Cronin, M. et. al (2014). QSAR Modeling: Where Have You Been? Where Are You Going To? Journal of Medicinal Chemistry, 57 (12), 4977–5010. doi: 10.1021/jm4004285

Devinyak, O. T., Slivka, M. V., Slivka, M. V., Vais, V. M., Lendel, V. G. (2011). Quantitative structure-activity relationship study and directed synthesis of Thieno[2,3-d]pyrimidine-2,4-diones as monocarboxylate transporter 1 inhibitors. Medicinal Chemistry Research, 21 (9), 2263–2272. doi: 10.1007/s00044-011-9748-4

Devinyak, O. T., Havrylyuk, D.Y., Zimenkovsky, B. S., Lesyk, R. B. (2011). QSAR analiz 2(4)-tiazolidynoniv iz pirazolinovym frahmentom v molekulakh, shcho proiavliaiut protypukhlynnu aktyvnist shchodo klityn nedribnoklitynnoho raku lehen in vitro [QSAR Study of 2(4)-Thiazolidinones with Pyrazoline Scaffold Possesing Antitumor Activity in vitro on Nonsmall Cell Lung Cancer Cells]. Clinical Pharmacy, Pharmacotherapy and Medical Standardization, 3-4, 163–168.

Li, Y.-W., Li, B., He, J., Qian, P. (2011). Structure-activity relationship study of antioxidative peptides by QSAR modeling: the amino acid next to C-terminus affects the activity. Journal of Peptide Science, 17 (6), 454–462. doi: 10.1002/psc.1345

Mazanetz, M. P., Ichihara, O., Law, R. J., Whittaker, M. (2011). Prediction of cyclin-dependent kinase 2 inhibitor potency using the fragment molecular orbital method. Journal of Cheminformatics, 3 (1), 2. doi: 10.1186/1758-2946-3-2

Suenderhauf, C., Hammann, F., Maunz, A., Helma, C., Huwyler, J. (2011). Combinatorial QSAR Modeling of Human Intestinal Absorption. Molecular Pharmaceutics, 8 (1), 213–224. doi: 10.1021/mp100279d

Sun, H. (2005). A Naive Bayes Classifier for Prediction of Multidrug Resistance Reversal Activity on the Basis of Atom Typing. Journal of Medicinal Chemistry, 48 (12), 4031–4039. doi: 10.1021/jm050180t

Prathipati, P., Ma, N. L., Keller, T. H. (2008). Global Bayesian Models for the Prioritization of Antitubercular Agents. Journal of Chemical Information and Modeling, 48 (12), 2362–2370. doi: 10.1021/ci800143n

Lv, W., Xue, Y. (2010). Prediction of acetylcholinesterase inhibitors and characterization of correlative molecular descriptors by machine learning methods. European Journal of Medicinal Chemistry, 45 (3), 1167–1172. doi: 10.1016/j.ejmech.2009.12.038

Yang, X.-G., Chen, D., Wang, M., Xue, Y., Chen, Y.-Z. (2009). Prediction of antibacterial compounds by machine learning approaches. Journal of Computational Chemistry, 30 (8), 1202–1211. doi: 10.1002/jcc.21148

Boiani, M., Cerecetto, H., González, M., Gasteiger, J. (2008). Modeling anti- Trypanosoma cruzi Activity of N -Oxide Containing Heterocycles. Journal of Chemical Information and Modeling, 48 (1), 213–219. doi: 10.1021/ci7002768

Saghaie, L., Shahlaei, M., Madadkar-Sobhani, A., Fassihi, A. (2010). Application of partial least squares and radial basis function neural networks in multivariate imaging analysis-quantitative structure activity relationship: Study of cyclin dependent kinase 4 inhibitors. Journal of Molecular Graphics and Modelling, 29 (4), 518–528. doi: 10.1016/j.jmgm.2010.10.001

Chen, H.-F. (2009). In Silico Log P Prediction for a Large Data Set with Support Vector Machines, Radial Basis Neural Networks and Multiple Linear Regression. Chemical Biology & Drug Design, 74 (2), 142–147. doi: 10.1111/j.1747-0285.2009.00840.x

Lü, W. J., Chen, Y. L., Ma, W. P., Zhang, X. Y., Luan, F., Liu, M. C., Chen, X. G., Hu, Z. D. (2008). QSAR study of neuraminidase inhibitors based on heuristic method and radial basis function network. European Journal of Medicinal Chemistry, 43 (3), 569–576. doi: 10.1016/j.ejmech.2007.04.011

Stempler, S., Levy-Sakin, M., Frydman-Marom, A., Amir, Y., Scherzer-Attali, R., Buzhansky, L., Gazit, E., Senderowitz, H. (2010). Quantitative structure–activity relationship analysis of β-amyloid aggregation inhibitors. Journal of Computer-Aided Molecular Design, 25 (2), 135–144. doi: 10.1007/s10822-010-9405-x

Schattel, V., Hinselmann, G., Jahn, A., Zell, A., Laufer, S. (2011). Modeling and Benchmark Data Set for the Inhibition of c-Jun N-terminal Kinase-3. J. Journal of Chemical Information and Modeling, 51 (3), 670–679. doi: 10.1021/ci100410h

Zimenkovsky, B. S., Devinyak, О. Т., Lesyk, R. B. (2012). Vyvchennia vzaiemozviazku «struktura–protypukhlynna aktyvnist» pokhidnykh 4-tiazolidynoniv metodamy rehresiinoho analizu ta klasyfikatsiinoho modeliuvannia [QSAR study of 4-thiazolidinones as anticancer agents using regression analysis and classification modeling]. Journal of organic and pharmaceutical chemistry, 10/2 (38), 43–49.

Bruce, C. L., Melville, J. L., Pickett, S. D., Hirst, J. D. (2007). Contemporary QSAR Classifiers Compared. Journal of Chemical Information and Modeling, 47 (1), 219–227. doi: 10.1021/ci600332j





Pharmaceutical Sciences