AutoWeka: Toward an Automated Data Mining Software for QSAR and QSPR Studies

  • Chanin Nantasenamat
  • Apilak Worachartcheewan
  • Saksiri Jamsak
  • Likit Preeyanon
  • Watshara Shoombuatong
  • Saw Simeon
  • Prasit Mandi
  • Chartchalerm Isarankura-Na-Ayudhya
  • Virapong Prachayasittikul
Protocol
Part of the Methods in Molecular Biology book series (MIMB, volume 1260)

Abstract

In biology and chemistry, a key goal is to discover novel compounds affording potent biological activity or chemical properties. This could be achieved through a chemical intuition-driven trial-and-error process or via data-driven predictive modeling. The latter is based on the concept of quantitative structure-activity/property relationship (QSAR/QSPR) when applied in modeling the biological activity and chemical properties, respectively, of compounds. Data mining is a powerful technology underlying QSAR/QSPR as it harnesses knowledge from large volumes of high-dimensional data via multivariate analysis. Although extremely useful, the technicalities of data mining may overwhelm potential users, especially those in the life sciences. Herein, we aim to lower the barriers to access and utilization of data mining software for QSAR/QSPR studies. AutoWeka is an automated data mining software tool that is powered by the widely used machine learning package Weka. The software provides a user-friendly graphical interface along with an automated parameter search capability. It employs two robust and popular machine learning methods: artificial neural networks and support vector machines. This chapter describes the practical usage of AutoWeka and relevant tools in the development of predictive QSAR/QSPR models. Availability: The software is freely available at http://www.mt.mahidol.ac.th/autoweka.

Key words

Quantitative structure-activity relationship Quantitative structure-property relationship QSAR QSPR Data mining 

Notes

Acknowledgments

This work was supported by Mahidol University via the Goal-Oriented Research Grant to C.N.; postdoctoral fellowship to W.S.; research assistantships to P.M., S.J., and L.P.; and partial financial support to S.S.

References

  1. 1.
    Brodin A (1858) On the analogy of arsenic and phosphoric acid with respect to chemical and toxicology. Medico-Surgical Academy, St. Petersburg, RussiaGoogle Scholar
  2. 2.
    Cros A (1863) Action de l’alcool amylique sur l’organisme. University of Strasbourg, StrasbourgGoogle Scholar
  3. 3.
    Kekulé A (1865) Sur la constitution des substances aromatiques. Bull Soc Chim Fr 3:98Google Scholar
  4. 4.
    Richardson B (1869) Physiological research on alcohols. Med Times Gaz 2:703–706Google Scholar
  5. 5.
    Richet C (1893) On the relationship between the toxicity and the physical properties of substances. Compt Rendus Seances Soc Biol 9:775–776Google Scholar
  6. 6.
    Overton E (1897) Osmotic properties of cells in the bearing on toxicology and pharmacology. Z Phys Chem 22:189–209Google Scholar
  7. 7.
    Meyer H (1899) On the theory of alcohol narcosis. Arch Exp Pathol Pharmacol 42:109–118CrossRefGoogle Scholar
  8. 8.
    Moore W (1917) Volatility of organic compounds as an index of the toxicity of their vapors to insects. J Agric Res 10(7):365Google Scholar
  9. 9.
    Hammett LP (1937) The effect of structure upon the reactions of organic compounds. Benzene derivatives. J Am Chem Soc 59(1):96–103CrossRefGoogle Scholar
  10. 10.
    Taft RW (1952) Polar and steric substituent constants for aliphatic and o-benzoate groups from rates of esterification and hydrolysis of esters1. J Am Chem Soc 74(12):3120–3128CrossRefGoogle Scholar
  11. 11.
    Hansch C, Maloney PP, Fujita T et al (1962) Correlation of biological activity of phenoxyacetic acids with Hammett substituent constants and partition coefficients. Nature 194:178–180Google Scholar
  12. 12.
    Hansch C, Muir RM, Fujita T et al (1963) The correlation of biological activity of plant growth regulators and chloromycetin derivatives with Hammett constants and partition coefficients. J Am Chem Soc 85(18):2817–2824CrossRefGoogle Scholar
  13. 13.
    Hansch C, Muir RM (1950) The ortho effect in plant growth-regulators. Plant Physiol 25(3):389PubMedCentralPubMedCrossRefGoogle Scholar
  14. 14.
    Hansch C, Fujita T (1964) p-σ-π analysis. A method for the correlation of biological activity and chemical structure. J Am Chem Soc 86(8):1616–1626CrossRefGoogle Scholar
  15. 15.
    Free SM Jr, Wilson JW (1964) A mathematical contribution to structure-activity studies. J Med Chem 7:395–399PubMedCrossRefGoogle Scholar
  16. 16.
    Hansch C (1969) Quantitative approach to biochemical structure-activity relationships. Acc Chem Res 2(8):232–239CrossRefGoogle Scholar
  17. 17.
    Nantasenamat C, Isarankura-Na-Ayudhya C, Naenna T et al (2009) A practical overview of quantitative structure-activity relationship. Excli J 8:74–88Google Scholar
  18. 18.
    Nantasenamat C, Isarankura-Na-Ayudhya C, Prachayasittikul V (2010) Advances in computational methods to predict the biological activity of compounds. Expert Opin Drug Discov 5(7):633–654PubMedCrossRefGoogle Scholar
  19. 19.
    Medina-Franco JL, Martinez-Mayorga K, Bender A et al (2009) Characterization of activity landscapes using 2D and 3D similarity methods: consensus activity cliffs. J Chem Inf Model 49(2):477–491PubMedCrossRefGoogle Scholar
  20. 20.
    Bajorath J (2012) Modeling of activity landscapes for drug discovery. Expert Opin Drug Discov 7(6):463–473PubMedCrossRefGoogle Scholar
  21. 21.
    Doweyko AM (2008) QSAR: dead or alive? J Comput Aided Mol Des 22(2):81–89PubMedCrossRefGoogle Scholar
  22. 22.
    Doweyko AM (2008) Is QSAR relevant to drug discovery? IDrugs 11(12):894–899PubMedGoogle Scholar
  23. 23.
    Tropsha A, Golbraikh A (2007) Predictive QSAR modeling workflow, model applicability domains, and virtual screening. Curr Pharm Des 13(34):3494–3504PubMedCrossRefGoogle Scholar
  24. 24.
    Golbraikh A, Tropsha A (2002) Beware of q2! J Mol Graph Model 20(4):269–276PubMedCrossRefGoogle Scholar
  25. 25.
    Huang J, Fan X (2011) Why QSAR fails: an empirical evaluation using conventional computational approach. Mol Pharm 8(2):600–608PubMedCrossRefGoogle Scholar
  26. 26.
    Tropsha A, Gramatica P, Gombar VK (2003) The importance of being earnest: validation is the absolute essential for successful application and interpretation of QSPR models. QSAR Comb Sci 22(1):69–77CrossRefGoogle Scholar
  27. 27.
    Tropsha A (2010) Best practices for QSAR model development, validation, and exploitation. Mol Inf 29(6–7):476–488CrossRefGoogle Scholar
  28. 28.
    Fourches D, Muratov E, Tropsha A (2010) Trust, but verify: on the importance of chemical structure curation in cheminformatics and QSAR modeling research. J Chem Inf Model 50(7):1189–1204PubMedCentralPubMedCrossRefGoogle Scholar
  29. 29.
    Scior T, Bender A, Tresadern G et al (2012) Recognizing pitfalls in virtual screening: a critical review. J Chem Inf Model 52(4):867–881PubMedCrossRefGoogle Scholar
  30. 30.
    Dearden JC, Cronin MT, Kaiser KL (2009) How not to develop a quantitative structure-activity or structure-property relationship (QSAR/QSPR). SAR QSAR Environ Res 20(3–4):241–266PubMedCrossRefGoogle Scholar
  31. 31.
    Jewell NE, Turner DB, Willett P et al (2001) Automatic generation of alignments for 3D QSAR analyses. J Mol Graph Model 20(2):111–121PubMedCrossRefGoogle Scholar
  32. 32.
    Tervo AJ, Nyronen TH, Ronkko T et al (2004) Comparing the quality and predictiveness between 3D QSAR models obtained from manual and automated alignment. J Chem Inf Comput Sci 44(3):807–816PubMedCrossRefGoogle Scholar
  33. 33.
    Olah M, Bologa C, Oprea TI (2004) An automated PLS search for biologically relevant QSAR descriptors. J Comput Aided Mol Des 18(7–9):437–449PubMedCrossRefGoogle Scholar
  34. 34.
    Bhonsle JB, Wang Z-X, Tamamura H et al (2005) A simple, automated quasi-4D-QSAR, quasi-multi way PLS approach to develop highly predictive QSAR models for highly flexible CXCR4 inhibitor cyclic pentapeptide ligands using scripted common molecular modeling tools. QSAR Comb Sci 24(5):620–630CrossRefGoogle Scholar
  35. 35.
    Cartmell J, Enoch S, Krstajic D et al (2005) Automated QSPR through competitive workflow. J Comput Aided Mol Des 19(11):821–833PubMedCrossRefGoogle Scholar
  36. 36.
    Zhang S, Golbraikh A, Oloff S et al (2006) A novel automated lazy learning QSAR (ALL-QSAR) approach: method development, applications, and virtual screening of chemical databases using validated ALL-QSAR models. J Chem Inf Model 46(5):1984–1995PubMedCentralPubMedCrossRefGoogle Scholar
  37. 37.
    Bhonsle JB, Bhattacharjee AK, Gupta RK (2007) Novel semi-automated methodology for developing highly predictive QSAR models: application for development of QSAR models for insect repellent amides. J Mol Model 13(1):179–208PubMedCrossRefGoogle Scholar
  38. 38.
    Obrezanova O, Csanyi G, Gola JM et al (2007) Gaussian processes: a method for automatic QSAR modeling of ADME properties. J Chem Inf Model 47(5):1847–1857PubMedCrossRefGoogle Scholar
  39. 39.
    Rodgers SL, Davis AM, Tomkinson NP et al (2007) QSAR modeling using automatically updating correction libraries: application to a human plasma protein binding model. J Chem Inf Model 47(6):2401–2407PubMedCrossRefGoogle Scholar
  40. 40.
    Ma CY, Buontempo FV, Wang XZ (2008) Inductive data mining: automatic generation of decision trees from data for QSAR modelling and process historical data analysis. Comput Aid Chem Eng 25:581–586CrossRefGoogle Scholar
  41. 41.
    Wood DJ, Buttar D, Cumming JG et al (2011) Automated QSAR with a hierarchy of global and local models. Mol Inf 30(11–12):960–972CrossRefGoogle Scholar
  42. 42.
    Perez-Castillo Y, Lazar C, Taminau J et al (2012) GA(M)E-QSAR: a novel, fully automatic genetic-algorithm-(meta)-ensembles approach for binary classification in ligand-based drug design. J Chem Inf Model 52(9):2366–2386PubMedCrossRefGoogle Scholar
  43. 43.
    Cox R, Green DV, Luscombe CN et al (2013) QSAR workbench: automating QSAR modeling to drive compound design. J Comput Aided Mol Des 27(4):321–336PubMedCentralPubMedCrossRefGoogle Scholar
  44. 44.
    Martins JPA, Ferreira MMC (2013) QSAR modeling: a new open source computational package to generate and validate QSAR models. Quim Nova 26:554–560CrossRefGoogle Scholar
  45. 45.
    Hall M, Frank E, Holmes G et al (2009) The WEKA data mining software: an update. SIGKDD Explorations 11 (1)Google Scholar
  46. 46.
    Venkateswarlu S, Ramachandra MS, Subbaraju GV (2005) Synthesis and biological evaluation of polyhydroxycurcuminoids. Bioorg Med Chem 13(23):6374–6380PubMedCrossRefGoogle Scholar
  47. 47.
    Worachartcheewan A, Nantasenamat C, Isarankura-Na-Ayudhya C et al (2011) Predicting the free radical scavenging activity of curcumin derivatives. Chemometr Intell Lab Syst 109(2):207–216CrossRefGoogle Scholar
  48. 48.
    Mandi P, Nantasenamat C, Srungboonmee K et al (2012) QSAR study of anti-prion activity of 2-aminothiazoles. Excli J 11:453–467Google Scholar
  49. 49.
    Nantasenamat C, Isarankura-Na-Ayudhya C, Naenna T et al (2008) Prediction of bond dissociation enthalpy of antioxidant phenols by support vector machine. J Mol Graph Model 27(2):188–196PubMedCrossRefGoogle Scholar
  50. 50.
    Nantasenamat C, Li H, Mandi P et al (2013) Exploring the chemical space of aromatase inhibitors. Mol Div. doi:10.1007/s11030-11013-19462-x Google Scholar
  51. 51.
    Nantasenamat C, Piacham T, Tantimongcolwat T et al (2008) QSAR model of the quorum-quenching N-acyl-homoserine lactone lactonase activity. J Biol Syst 16(2):279–293CrossRefGoogle Scholar
  52. 52.
    Pingaew R, Tongraung P, Worachartcheewan A et al (2012) Cytotoxicity and QSAR study of (thio)ureas derived from phenylalkylamines and pyridylalkylamines. Med Chem Res 22:4016-4029Google Scholar
  53. 53.
    Prachayasittikul S, Wongsawatkul O, Worachartcheewan A et al (2010) Elucidating the structure-activity relationships of the vasorelaxation and antioxidation properties of thionicotinic acid derivatives. Molecules 15(1):198–214PubMedCrossRefGoogle Scholar
  54. 54.
    Thippakorn C, Suksrichavalit T, Nantasenamat C et al (2009) Modeling the LPS neutralization activity of anti-endotoxins. Molecules 14(5):1869–1888PubMedCrossRefGoogle Scholar
  55. 55.
    Worachartcheewan A, Nantasenamat C, Isarankura-Na-Ayudhya C et al (2013) Predicting antimicrobial activities of benzimidazole derivatives. Med Chem Res 22:5418–5430Google Scholar
  56. 56.
    Worachartcheewan A, Nantasenamat C, Naenna T et al (2009) Modeling the activity of furin inhibitors using artificial neural network. Eur J Med Chem 44(4):1664–1673PubMedCrossRefGoogle Scholar
  57. 57.
    Nantasenamat C, Li H, Isarankura-Na-Ayudhya C et al (2012) Exploring the physicochemical properties of templates from molecular imprinting literature using interactive text mining approach. Chemometr Intell Lab Syst 116:128–136CrossRefGoogle Scholar
  58. 58.
    Nantasenamat C, Isarankura-Na-Ayudhya C, Tansila N et al (2007) Prediction of GFP spectral properties using artificial neural network. J Comput Chem 28(7):1275–1289PubMedCrossRefGoogle Scholar
  59. 59.
    Nantasenamat C, Naenna T, Isarankura N-AC et al (2005) Quantitative prediction of imprinting factor of molecularly imprinted polymers by artificial neural network. J Comput Aid Mol Des 19(7):509–524CrossRefGoogle Scholar
  60. 60.
    Nantasenamat C, Isarankura-Na-Ayudhya C, Naenna T et al (2007) Quantitative structure-imprinting factor relationship of molecularly imprinted polymers. Biosens Bioelectron 22(12):3309–3317PubMedCrossRefGoogle Scholar
  61. 61.
    Nantasenamat C, Srungboonmee K, Jamsak S et al (2013) Quantitative structure-property relationship study of spectral properties of green fluorescent protein with support vector machine. Chemometr Intell Lab Syst 120:42–52CrossRefGoogle Scholar
  62. 62.
    McCulloch WS, Pitts W (1943) A logical calculus of the ideas immanent in nervous activity. Bull Math Biophys 5(4):115–133CrossRefGoogle Scholar
  63. 63.
    Lawrence J (1993) Introduction to neural networks: design, theory, and applications, 6th edn. California Scientific Software, CaliforniaGoogle Scholar
  64. 64.
    Smith M (1993) Neural networks for statistical modeling. Van Nostrand Reinhold, New YorkGoogle Scholar
  65. 65.
    Bishop CM, Nasrabadi NM (2006) Pattern recognition and machine learning, vol 1. Springer, New YorkGoogle Scholar
  66. 66.
    Vapnik V (2000) The nature of statistical learning theory. Springer, New YorkCrossRefGoogle Scholar
  67. 67.
    Vapnik V (1998) Statistical learning theory. Wiley, New YorkGoogle Scholar
  68. 68.
    Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20(3):273–297Google Scholar
  69. 69.
    Cristianini N, Shawe-Taylor J (2000) An introduction to support vector machines and other kernel-based learning methods. Cambridge University Press, CambridgeCrossRefGoogle Scholar
  70. 70.
    Platt JC (1999) Fast training of support vector machines using sequential minimal optimization. In: Schoelkopf B, Burges C, Smola A (eds) Advances in kernel methods: support vector learning. MIT Press, Cambridge, USA, pp 185–208Google Scholar
  71. 71.
    Smola AJ, Schölkopf B (2004) A tutorial on support vector regression. Stat Comput 14(3):199–222CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2015

Authors and Affiliations

  • Chanin Nantasenamat
    • 1
  • Apilak Worachartcheewan
    • 1
  • Saksiri Jamsak
    • 1
  • Likit Preeyanon
    • 1
  • Watshara Shoombuatong
    • 1
  • Saw Simeon
    • 1
  • Prasit Mandi
    • 1
  • Chartchalerm Isarankura-Na-Ayudhya
    • 2
  • Virapong Prachayasittikul
    • 2
  1. 1.Center of Data Mining and Biomedical InformaticsFaculty of Medical Technology, Mahidol UniversityBangkokThailand
  2. 2.Department of Clinical Microbiology and Applied TechnologyFaculty of Medical Technology, Mahidol UniversityBangkokThailand

Personalised recommendations