Skip to main content

Advertisement

Springer Nature Link
Log in

On the interpretation and interpretability of quantitative structure–activity relationship models

  • Published:
Journal of Computer-Aided Molecular Design Aims and scope Submit manuscript

Abstract

The goal of a quantitative structure–activity relationship (QSAR) model is to encode the relationship between molecular structure and biological activity or physical property. Based on this encoding, such models can be used for predictive purposes. Assuming the use of relevant and meaningful descriptors, and a statistically significant model, extraction of the encoded structure–activity relationships (SARs) can provide insight into what makes a molecule active or inactive. Such analyses by QSAR models are useful in a number of scenarios, such as suggesting structural modifications to enhance activity, explanation of outliers and exploratory analysis of novel SARs. In this paper we discuss the need for interpretation and an overview of the factors that affect interpretability of QSAR models. We then describe interpretation protocols for different types of models, highlighting the different types of interpretations, ranging from very broad, global, trends to very specific, case-by-case, descriptions of the SAR, using examples from the training set. Finally, we discuss a number of case studies where workers have provide some form of interpretation of a QSAR model.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3

Similar content being viewed by others

Notes

  1. It should be noted that even though the problem may be understood from a mechanistic point of view, it is still possible for one to derive poor QSAR models, since the numerical characterization of the mechanistic features responsible for the property might be inaccurate or incomplete.

References

  1. Agrafiotis DK, Cedeño W (2002) Feature selection for structure-activity correlation using binary particle swarms. J Med Chem 45:1098–1107

    CAS  Google Scholar 

  2. Agrawal V, Sharma R, Khadikar P (2002) QSAR studies on antimalarial substituted phenyl analogues and their nω oxides. Bioorg Med Chem 10(5):1361–1366

    CAS  Google Scholar 

  3. Arakawa M, Hasegawa K, Funatsu K (2006) QSAR study of anti-HIV HEPT analogues based on multiobjective genetic programming and counter-propagation neural network. Chemom Intel Lab Syst 83:91–98

    CAS  Google Scholar 

  4. Banks J (1985) Nomograms. In: Encyclopedia of statistical sciences, vol 6. Wiley, New York

  5. Bender A, Mussa H, Glen R, Reiling S (2004) Similarity searching of chemical databases using atom environment descriptors (MOLPRINT 2D): evaluation of performance. J Chem Inf Comput Sci 44(5):1708–1718

    CAS  Google Scholar 

  6. Besalu E, Gallegos A, Carbo-Dorca R (2001) Topological quantum similarity indices and their use in QSAR: application to several families of antimalarial compounds. Commun Math Comp Chem 44:41–64

    CAS  Google Scholar 

  7. Breiman L (2001) Statistical modeling: two cultures. Stat Sci 16:199–231

    Google Scholar 

  8. Breiman L, Friedman J, Olshen R, Stone C (1984) Classification and regression trees. Chapman & Hall/CRC, Boca Raton, FL

    Google Scholar 

  9. Bremser W (1978) HOSE—a novel substructure code. Anal Chim Acta 103:355–365

    CAS  Google Scholar 

  10. Brown N, McKay B, Gasteiger J (2006) A novel workflow for the inverse QSPR problem using multiobjective optimization. J Comput Aided Mol Des 20:333–341

    CAS  Google Scholar 

  11. Burden F (1989) Molecular identification number for substructure searches. J Chem Inf Comput Sci 29:225–227

    CAS  Google Scholar 

  12. Byvatov E, Baringhaus KH, Schneider G, Matter H (2007) A virtual screening filter for identification of cytochrome P450 2C9 (CYP2C9) inhibitors. QSAR Comb Sci 26:618–628

    CAS  Google Scholar 

  13. Carbo-Dorca R, Leyda L, Arnau M (1980) How similar is a molecule to another? An electron density measure of similarity between two molecular structures. Int J Quantum Chem 17(6):1185–1189

    Google Scholar 

  14. Chastrette M, Zakarya D, Peyraud J (1994) Structure-musk odor relationships for tetralins and indans using neural networks (on the contribution of descriptors to the classification). Eur J Med Chem 29:343–348

    CAS  Google Scholar 

  15. Chatterjee S, Hadi A (1986) Influential observations, high leverage points, and outliers in linear regression. Stat Sci 1(3):379–416

    Google Scholar 

  16. Chin T, So S (2004) Development of neural network QSPR models for Hansch substituent constants. 2. Applications in QSAR studies of HIV-1 reverse transcriptase and dihydrofolate reductase inhibitors. J Chem Inf Comput Sci 44:154–160

    Google Scholar 

  17. Cho BH, Yu H, Lee J, Chee YJ, Kim IY, Kim SI (2008) Nonlinear support vector machine visualization for risk factor analysis using nomograms and localized radial basis function kernels. IEEE Trans Inf Technol Biomed 12:247–256

    Google Scholar 

  18. Chohan K, Paine S, Mistry J, Barton P, Davis A (2005) A rapid computational filter for cytochrome P450 1A2 inhibition potential of compound libraries. J Med Chem 48:5154–5161

    CAS  Google Scholar 

  19. Colmenarejo G, Pedraglio A, Lavandera J (2001) Cheminformatic models to predict binding affinities to human serum albumin. J Med Chem 44(25):4370–4378

    CAS  Google Scholar 

  20. Consonni V, Todeschini R, Pavan M, Gramatica P (2002) Structure/response correlations and similarity/diversity analysis by GETAWAY descriptors. Part 2. Application of the novel 3D molecular descriptors to QSAR/QSPR studies. J Chem Inf Comput Sci 42(3):693–705

    Google Scholar 

  21. Cruz-Monteagudo M, Borges F, Perez Gonzalez M, Dias Soeiro Cordeiro MN (2007) Computational modeling tools for the design of potent antimalarial bisbenzamidines: overcoming the antimalarial potential of pentamidine. Bioorg Med Chem 15:5322–5339

    CAS  Google Scholar 

  22. De Lucca G, Liang J, De Lucca I (1999) Stereospecific synthesis, structure-activity relationship, and oral bioavailability of tetrahydropyrimidin-2-one HIV protease inhibitors. J Med Chem 42(1):135–152

    CAS  Google Scholar 

  23. Dias Selassie C, Li Rl, Poe M, Hansch C (1991) Optimization of hydrophobic and hydrophilic substituent interactions of 2,4-diamino-5-(substituted-benzyl)pyrimidines with dihydrofolate reductase. J Med Chem 34(1):46–54

    CAS  Google Scholar 

  24. Dietrich SW, Blaney JM, Reynolds MA, Jow PYC, Hansch C (1980) Quantitative structure-selectivity relationships. Comparison of the inhibition of Escherichia coli and bovine liver dihydrofolate reductase by 5-(substituted benzyl)-2,4-diaminopyrimidines. J Med Chem 23(11):1205–1212

    CAS  Google Scholar 

  25. Diller DJ, Hobbs DW (2007) Understanding hERG inhibition with QSAR models based on a one dimensional molecular representation. J Comput Aided Mol Des 21:379–393

    CAS  Google Scholar 

  26. Diudea M (1997) Cluj matrix invariants. J Chem Inf Comput Sci 37:300–305

    CAS  Google Scholar 

  27. Doweyko A (2008) QSAR: dead or alive? J Comput Aided Mol Des 22:81–89

    CAS  Google Scholar 

  28. Durant J, Leland B, Henry D, Nourse J (2002) Reoptimization of MDL keys for use in drug discovery. J Chem Inf Comput Sci 42(6):1273–1280

    CAS  Google Scholar 

  29. Dutta D, Guha R, Chen T, Wild D (2007) Ensemble feature selection: consistent descriptor subsets for multiple QSAR models. J Chem Inf Model 47(3):989–997

    CAS  Google Scholar 

  30. Eriksson L, Johansson E, Lindgren F, Sjostrom M, Wold S (2002) Megavariate analysis of hierarchical QSAR data. J Comput Aided Mol Des 16:711–726

    CAS  Google Scholar 

  31. Estrada E (2002) Physicochemical interpretation of molecular connectivity indices. J Phys Chem A 106:9085–9091

    CAS  Google Scholar 

  32. Fernandez M, Caballero J (2006) Modeling of activity of cyclic urea HIV-1 protease inhibitors using regularized-artificial neural networks. Bioorg Med Chem 14:280–294

    CAS  Google Scholar 

  33. Franke L, Schwarz O, Muller-Kuhrt L, Hoernig C, Fischer L, George S, Tanrikulu Y, Schneider P, Werz O, Steinhilber D, Schneider G (2007) Identification of natural-product-derived inhibitors of 5-lipoxygenase activity by ligand-based virtual screening. J Med Chem 50(11):2640–2646

    CAS  Google Scholar 

  34. Gangjee A, Yu J, McGuire J, Cody V, Galitsky N, Kisliuk R, Queener S (2000) Design, synthesis, and X-ray crystal structure of a potent dual inhibitor of thymidylate synthase and dihydrofolate reductase as an antitumor agent. J Med Chem 43:3837–3851

    CAS  Google Scholar 

  35. Garcia-Domenech R, Galvez J, de Julian-Ortiz J, Pogliani L (2008) Some new trends in chemical graph theory. Chem Rev 108(3):1127–1169

    CAS  Google Scholar 

  36. Garg R, Bhhatarai B (2004) A mechanistic study of 3-aminoindazole cyclic urea HIV-1 protease inhibitors using comparative QSAR. Bioorg Med Chem 12(22):5819–5831

    CAS  Google Scholar 

  37. Garson D (1991) Interpreting neural network connection strengths. AI Expert 6(7):47–51

    Google Scholar 

  38. Gavaghan CL, Arnby CH, Blomberg N, Strandlund G, Boyer S (2007) Development, interpretation and temporal evaluation of a global QSAR of hERG electrophysiology screening data. J Comput Aided Mol Des 21:189–206

    CAS  Google Scholar 

  39. Girones X, Gallegos A, Carbo-Dorca R (2001) Antimalarial activity of synthetic 1,2,4-trioxanes and cyclic peroxy ketals, a quantum similarity study. J Comput Aided Mol Des 15:1053–1063

    CAS  Google Scholar 

  40. Gleeson MP, Davis AM, Chohan KK, Paine SW, Boyer S, Gavaghan CL, Arnby CH, Kankkonen C, Albertson N (2007) Generation of in-silico cytochrome P450 1A2, 2C9, 2C19, 2D6, and 3A4 inhibition QSAR models. J Comput Aided Mol Des 21:559–573

    CAS  Google Scholar 

  41. Gramatica P (2007) Principles of QSAR models validation: internal and external. QSAR Comb Sci 26(5):694–701

    CAS  Google Scholar 

  42. Guha R, Jurs P (2004) Development of linear, ensemble, and nonlinear models for the prediction and interpretation of the biological activity of a set of PDGFR inhibitors. J Chem Inf Comput Sci 44(6):2179–2189

    CAS  Google Scholar 

  43. Guha R, Jurs P (2004) The development of QSAR models to predict and interpret the biological activity of artemisinin analogues. J Chem Inf Comput Sci 44:1440–1449

    CAS  Google Scholar 

  44. Guha R, Jurs P (2005) Interpreting computational neural network QSAR models: a measure of descriptor importance. J Chem Inf Model 45:800–806

    CAS  Google Scholar 

  45. Guha R, Schürer S (2008) Utilizing high throughput screening data for predictive toxicology models: protocols and application to MLSCN assays. J Comput Aided Mol Des 22(6–7):367–384

    CAS  Google Scholar 

  46. Guha R, Stanton D, Jurs P (2005) Interpreting computational neural network QSAR models: a detailed interpretation of the weights and biases. J Chem Inf Model 45:1109–1121

    CAS  Google Scholar 

  47. Gunturi S, Narayanan R, Khandelwal A (2006) In silico ADME modelling 2: computational models to predict human serum albumin binding affinity using ant colony systems. Bioorg Med Chem 14:4118–4129

    CAS  Google Scholar 

  48. Hansch C (1969) A quantitative approach to biochemical structure-activity relationships. Acc Chem Res 2:232–239

    CAS  Google Scholar 

  49. Hansch C, Fujita T (1964) ε−σ−π analysis. A method for the correlation of biological activity and chemical structure. J Am Chem Soc 86:1616–1626

    CAS  Google Scholar 

  50. Hansch C, Leo A, Hoekman D (1995) Exploring QSAR: hydrophobic, electronic, and steric constants. American Chemical Society, Washington, DC

    Google Scholar 

  51. Hassan M, Brown RD, Varma-O’Brien S, Rogers D (2006) Cheminformatics analysis and learning in a data pipelining environment. Mol Divers 10(3):283–299

    CAS  Google Scholar 

  52. Hemmer M, Gasteiger J (2000) Prediction of three-dimensional molecular structures using information from infrared spectra. Anal Chim Acta 420:145–154

    CAS  Google Scholar 

  53. Hemmer M, Steinhauer V, Gasteiger J (1999) Deriving the 3D structure of organic molecules from their infrared spectra. Vib Spectrosc 19:151–164

    CAS  Google Scholar 

  54. Hirst J (1996) Nonlinear quantitative structure-activity relationship for the inhibition of dihydrofolate reductase by pyrimidines. J Med Chem 39(18):3526–3532

    CAS  Google Scholar 

  55. Ivanciuc O, Braun W (2007) Robust quantitative modeling of peptide binding affinities for MHC molecules using physical-chemical descriptors. Protein Pept Lett 14:903–916

    CAS  Google Scholar 

  56. Johnson S (2008) The trouble with QSAR (or how I learned to stop worrying and embrace fallacy). J Chem Inf Model 48(1):25–26

    CAS  Google Scholar 

  57. Katritzky A, Petrukhin R, Tatham D, Basak S, Benfenati E, Karelson M, Maran U (2001) Interpretation of quantitative structure-property and -activity relationships. J Chem Inf Comput Sci 41:679–685

    CAS  Google Scholar 

  58. Katritzky A, Oliferenko A, Lomaka A, Karelson M (2002) Six-membered cyclic ureas as HIV-1 protease inhibitors: a QSAR study based on CODESSA PRO approach. Bioorg Med Chem Lett 12:3453–3457

    CAS  Google Scholar 

  59. Katritzky A, Kulshyn O, Stoyanova-Slavova I, Dobehev D, Kuanar M, Fara D, Karelson M (2006) Antimalarial activity: a QSAR modeling using CODESSA PRO software. Bioorg Med Chem 14:2333–2357

    CAS  Google Scholar 

  60. Kier L, Hall L (1986) Molecular connectivity in structure-activity analysis. Wiley, New York

    Google Scholar 

  61. Kier L, Hall L (1999) Molecular structure description: the electrotopological state. Academic Press, Burlington, MA

    Google Scholar 

  62. Kiralj R, Ferreira M (2003) A priori molecular descriptors in QSAR: a case of HIV-1 protease inhibitors. I. The chemometric approach. J Mol Graph Model 21:435–448

    CAS  Google Scholar 

  63. Klayman D (1985) Qinghaosu (artemisinin): an antimalarial drug from China. Science 228:1049

    CAS  Google Scholar 

  64. Klon A, Heroux A, Ross L, Pathak V, Johnson C, Piper J, Borhani D (2002) Atomic structures of human dihydrofolate reductase complexed with NADPH and two lipophilic antifolates at 1.09 Angstrom and 1.05 Angstrom resolution. J Mol Biol 320:677–693

    CAS  Google Scholar 

  65. Kramer C, Beck B, Kriegl JM, Clark T (2008) A composite model for hERG blockade. ChemMedChem 3:254–265

    CAS  Google Scholar 

  66. Leonard JT, Roy K (2007) Comparative classical QSAR modeling of anti-HIV thiocarbamates. QSAR Comb Sci 26:980–990

    CAS  Google Scholar 

  67. Lewis RA (2005) A general method for exploiting QSAR models in lead optimization. J Med Chem 48:1638–1648

    CAS  Google Scholar 

  68. Lin TS, Zhu LY, Xu SP, Divo AA, Sartorelli AC (1991) Synthesis and antimalarial activity of 2-aziridinyl- and 2,3-bis(aziridinyl)-1,4-naphthoquinonyl sulfonate and acylate derivatives. J Med Chem 34(5):1634–1639

    CAS  Google Scholar 

  69. Mackay A (1977) Scientific quotations: harvest of a quiet eye. Crane, Russak & Co, New York

    Google Scholar 

  70. Masek B, Shen L, Smith K, Pearlman R (2008) Sharing chemical information without sharing chemical structure. J Chem Inf Model 48(2):256–261

    CAS  Google Scholar 

  71. Miller A (2002) Subset selection in regression, 2nd edn. Chapman & Hall/CRC, Boca Raton, FL

    Google Scholar 

  72. Miller JF, Brieger M, Furfine ES, Hazen RJ, Kaldor I, Reynolds D, Sherrill RG, Spaltenstein A (2005) Novel P1 chain-extended HIV protease inhibitors possessing potent anti-HIV activity and remarkable inverse antiviral resistance profiles. Bioorg Med Chem Lett 15(15):3496–3500

    CAS  Google Scholar 

  73. Moreau G, Broto P (1980) Autocorrelation of molecular structures: application to SAR studies. Nouv J Chim 4:757–764

    CAS  Google Scholar 

  74. Navia-Vázquez A, Parrado-Hernández E (2006) Support vector machine interpretation. Neurocomputing 69:1754–1759

    Google Scholar 

  75. Ney H (1995) On the probabilistic interpretation of neural network classifiers and discriminative training criteria. IEEE Trans Pattern Anal Mach Intel 17:107–119

    Google Scholar 

  76. Nguyen-Cong V, Van Dang G, Rode B (1996) Using multivariate adaptive regression splines to QSAR studies of dihydroartemisinin derivatives. Eur J Med Chem 31:797–803

    CAS  Google Scholar 

  77. Otzen T, Wempe E, Kunz B, Bartels R, Lehwark-Yvetot G, Hansel W, Schaper K, Seydel J (2004) Folate-synthesizing enzyme system as target for development of inhibitors and inhibitor combinations against candida albicans-synthesis and biological activity of new 2,4-diaminopyrimidines and 4′-substituted 4-aminodiphenyl sulfones. J Med Chem 47:240–253

    CAS  Google Scholar 

  78. Pearlman RS, Smith KM (1999) Metric validation and the receptor-relevant subspace concept. J Chem Inf Comput Sci 39:28–35

    CAS  Google Scholar 

  79. Pinheiro J, Kiralj R, Ferreira M, Romero O (2003) Artemisinin derivatives with antimalarial activity against Plasmodium Falciparum designed with the aid of quantum chemical and partial least squares methods. QSAR Comb Sci 22:830–842

    CAS  Google Scholar 

  80. Polanski J, Zouhiri F, Jeanson L, Desmaele D, D’Angelo J, Mouscadet J, Gieleciak R, Gasteiger J, Le Bret M (2002) Use of the Kohonen neural network for rapid screening of ex vivo anti-HIV activity of styrylquinolines. J Med Chem 45:4647–4654

    CAS  Google Scholar 

  81. Purdy R (1996) A mechanism-mediated model for carcinogenicity: model content and prediction of the outcome of rodent carcinogenicity bioassays currently being conducted on 25 organic chemicals. Environ Health Perspect 104:1085–1094

    CAS  Google Scholar 

  82. Randic M (1978) Fragment search in acyclic structures. J Chem Inf Comput Sci 18(2):101–107

    CAS  Google Scholar 

  83. Randic M, Zupan J (2001) On interpretation of well-known topological indices. J Chem Inf Comput Sci 41: 550–560

    CAS  Google Scholar 

  84. Randic M, Balaban A, Basak S (2001) On structural interpretation of several distance related topological indices. J Chem Inf Comput Sci 41:593–601

    CAS  Google Scholar 

  85. Ravichandran V, Jain PK, Mourya VK, Agrawal RK (2007) QSAR study on some arylsulfonamides as anti-HIV agents. Med Chem Res 16:342–351

    CAS  Google Scholar 

  86. Renner S, Fechner U, Schneider G (2006) Pharmacophores and pharmacophore searches, methods and principles in medicinal chemistry, vol 32, chap Alignment-free pharmacophore patterns—a correlation vector approach. Wiley-VCH, Weinheim, Germany, pp 49–79

  87. Roche O, Schneider P, Zuegge J, Guba W, Kansy M, Alanine A, Bleicher K, Danel F, Gutknecht EM, Rogers-Evans M, Neidhart W, Stalder H, Dillon M, Sjogren E, Fotouhi N, Gillespie P, Goodnow R, Harris W, Jones P, Taniguchi M, Tsujii S, von der Saal W, Zimmermann G, Schneider G (2002) Development of a virtual screening method for identification of “frequent hitters” in compound libraries. J Med Chem 45(1):137–142

    CAS  Google Scholar 

  88. Rubner J, Schulten K, Tavan P (1990) A self organizing network for complete feature selection. In: International conference on parallel processing in neural systems and computers. Elsevier, Dusseldorf

  89. Sahu KK, Ravichandran V, Mourya VK, Agrawal K (2007) QSAR analysis of caffeoyl naphthalene sulfonamide derivatives as HIV-1 integrase inhibitors. Med Chem Res 15:418–430

    CAS  Google Scholar 

  90. Sato M, Tsukimoto H (2001) Rule extraction from neural networks via decision tree induction. In: Neural networks, proceedings international Joint conference, vol 3. IEEE Computer Society, Los Alamitos, CA, USA, pp 1870–1875

  91. Schölkopf B, Smola A (2002) Learning with Kernels. MIT Press, Cambridge, MA

    Google Scholar 

  92. Sheridan RP, Korzekwa KR, Torres RA, Walker MJ (2007) Empirical regioselectivity models for human cytochromes P450 3A4, 2D6, and 2C9. J Med Chem 50:3173–3184

    CAS  Google Scholar 

  93. Stanton D (2003) On the physical interpretation of QSAR models. J Chem Inf Comput Sci 43(5):1423–1433

    CAS  Google Scholar 

  94. Stanton D, Jurs P (1990) Development and use of charged partial surface area structural descriptors in computer assisted quantitative structure property relationship studies. Anal Chem 62:2323–2329

    CAS  Google Scholar 

  95. Stanton D, Mattioni BE, Knittel J, Jurs P (2004) Development and use of hydrophobic surface area (HSA) descriptors for computer assisted quantitative structure-activity and structure-property relationship studies. J Chem Inf Comput Sci 44:1010–1023

    CAS  Google Scholar 

  96. Summerfield R, Daigle D, Mayer S, Mallik D, Hughes D, Jackson S, Sulek M, Organ M, Brown E, Junop M (2006) A 2.13A structure of E. coli dihydrofolate reductase bound to a novel competitive inhibitor reveals a new binding surface involving the M20 loop region. J Med Chem 49(24):6977–6986

    CAS  Google Scholar 

  97. Sutter J, Dixon S, Jurs P (1995) Automated descriptor selection for quantitative structure-activity relationships using generalized simulated annealing. J Chem Inf Comput Sci 35:77–84

    CAS  Google Scholar 

  98. Taha I, Ghosh J (1999) Symbolic interpretation of artificial neural networks. IEEE Trans Knowl Data Eng 11:448–463

    Google Scholar 

  99. Takahashi T (1991) An information theoretical interpretation of neuronal activities. In: Neural networks, proceedings International Joint Conference, vol 2. IEEE Computer Society, Los Alamitos, CA, USA, pp 645–648

  100. Tang LJ, Zhou YP, Jiang JH, Zou HY, Wu HL, Shen GL, Yu RQ (2007) Radial basis function network-based transform for a nonlinear support vector machine as optimized by a particle swarm optimization algorithm with application to QSAR studies. J Chem Inf Model 47:1438–1445

    CAS  Google Scholar 

  101. Tian F, Zhou P, Lv F, Song R, Li Z (2007) Three-dimensional holograph vector of atomic interaction field (3D-HoVAIF): a novel rotation-translation invariant 3D structure descriptor and its applications to peptides. J Pept Sci 13:549–566

    CAS  Google Scholar 

  102. Todeschini R, Consonni V (2002) Handbook of molecular descriptors. Wiley-VCH, Berlin

    Google Scholar 

  103. Tropsha A, Gramatica P, Gombar V (2003) The importance of being earnest: validation is the absolute essential for successful application and interpretation of QSPR models. QSAR Comb Sci 22:69–77

    CAS  Google Scholar 

  104. Urbanek S (2006) Graphics of large datasets, chap Trees, pp. 177–2002. Statistics and Computing. Springer, Berlin Heidelberg

  105. Urbanek S, Unwin A (2002) Making trees interactive with KLIMT—a COSADA software project. Stat Comp Graph Newsl 13(1):13–16

    Google Scholar 

  106. Usdun B, Melssen WJ, Buydens LMC (2007) Visualisation and interpretation of support vector regression models. Anal Chim Acta 595:299–309

    Google Scholar 

  107. Vapnik V (1998) Statistical learning theory. Wiley, New York

    Google Scholar 

  108. Venkatraman V, Dalby AR, Yang ZR (2004) Evaluation of mutual information and genetic programming for feature selection in QSAR. J Chem Inf Comput Sci 44:1686–1692

    CAS  Google Scholar 

  109. Ventura C, Martins F (2008) Application of quantitative structure-activity relationships to the modeling of antitubercular compounds. 1. The hydrazide family. J Med Chem 51(3):612–624

    CAS  Google Scholar 

  110. Verma RP, Hansch C, Selassie CD (2007) Comparative QSAR studies on PAMPA/modified PAMPA for high throughput profiling of drug absorption potential with respect to Caco-2 cells and human intestinal absorption. J Comput Aided Mol Des 21:3–22

    CAS  Google Scholar 

  111. Vilar S, Santana L, Uriarte E (2006) Probabilistic neural network model for the in silico evaluation of anti-HIV activity and mechanism of action. J Med Chem 49:1118–1124

    CAS  Google Scholar 

  112. Visco D, Pophale R, Rintoul M, Faulon J (2002) Developing a methodology for an inverse quantitative structure-activity relationship using the signature molecular descriptor. J Mol Graph Model 20:429–438

    CAS  Google Scholar 

  113. Weininger D, Weininger A, Weininger J (1989) SMILES. 2. Algorithm for generation of unique SMILES notation. J Chem Inf Comput Sci 29:97–101

    CAS  Google Scholar 

  114. Yuan H, Parrill A (2002) QSAR studies of HIV-1 integrase inhibition. Bioorg Med Chem 10(12):4169–4183

    CAS  Google Scholar 

  115. Zahouily M, Lazar M, Elmakssoudi A, Rakik J, Elaychi S, Rayadh A (2006) QSAR for anti-malarial activity of 2-aziridinyl and 2,3-bis(aziridinyl)-1,4-naphthoquinonyl sulfonate and acylate derivatives. J Mol Model 12:398–405

    CAS  Google Scholar 

  116. Zhang H, Li H, Ma Q (2007) QSAR study of a large set of 3-pyridyl ethers as ligands of the a-4 b −2 nicotinic acetylcholine receptor. J Mol Graph Model 26:226–235

    CAS  Google Scholar 

  117. Zhou D, Alelyunas Y, Liu R (2008) Scores of extended connectivity fingerprint as descriptors in QSPR study of melting point and aqueous solubility. J Chem Inf Model 48(5):981–987

    CAS  Google Scholar 

Download references

Acknowledgments

I would like to thank Prof. Gerald Maggiora and Dr. David Stanton for useful comments on the issues underlying interpretability.

Author information

Authors and Affiliations

  1. School of Informatics, Indiana University, Bloomington, IN, 47408, USA

    Rajarshi Guha

Authors
  1. Rajarshi Guha
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Rajarshi Guha.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Guha, R. On the interpretation and interpretability of quantitative structure–activity relationship models. J Comput Aided Mol Des 22, 857–871 (2008). https://doi.org/10.1007/s10822-008-9240-5

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10822-008-9240-5

keywords