Ligand Biological Activity Predictions Using Fingerprint-Based Artificial Neural Networks (FANN-QSAR)

  • Kyaw Z. MyintEmail author
  • Xiang-Qun XieEmail author
Part of the Methods in Molecular Biology book series (MIMB, volume 1260)


This chapter focuses on the fingerprint-based artificial neural networks QSAR (FANN-QSAR) approach to predict biological activities of structurally diverse compounds. Three types of fingerprints, namely ECFP6, FP2, and MACCS, were used as inputs to train the FANN-QSAR models. The results were benchmarked against known 2D and 3D QSAR methods, and the derived models were used to predict cannabinoid (CB) ligand binding activities as a case study. In addition, the FANN-QSAR model was used as a virtual screening tool to search a large NCI compound database for lead cannabinoid compounds. We discovered several compounds with good CB2 binding affinities ranging from 6.70 nM to 3.75 μM. The studies proved that the FANN-QSAR method is a useful approach to predict bioactivities or properties of ligands and to find novel lead compounds for drug discovery research.

Key words

Quantitative structure-activity relationship (QSAR) Fingerprint Artificial neural networks (ANN) Biological activity Cannabinoid 


  1. 1.
    Myint KZ, Xie X-Q (2010) Recent advances in fragment-based QSAR and multi-dimensional QSAR methods. Int J Mol Sci 11(10):3846–3866PubMedCentralPubMedCrossRefGoogle Scholar
  2. 2.
    Perkins R, Fang H, Tong W et al (2003) Quantitative structure-activity relationship methods: perspectives on drug discovery and toxicology. Environ Toxicol Chem 22(8):1666–1679PubMedCrossRefGoogle Scholar
  3. 3.
    Salum L, Andricopulo A (2009) Fragment-based QSAR: perspectives in drug design. Mol Divers 13(3):277PubMedCrossRefGoogle Scholar
  4. 4.
    Chen JZ, Wang J, Xie XQ (2007) GPCR structure-based virtual screening approach for CB2 antagonist search. J Chem Inf Model 47(4):1626–1637. doi: 10.1021/ci7000814 PubMedCrossRefGoogle Scholar
  5. 5.
    Wang L, Ma C, Wipf P et al (2013) TargetHunter: an in silico target identification tool for predicting therapeutic potential of small organic molecules based on chemogenomic database. AAPS J 15:395–406, PMID: 23292636PubMedCentralPubMedCrossRefGoogle Scholar
  6. 6.
    Tandon M, Wang L, Xu Q et al (2012) A targeted library screen reveals a new inhibitor scaffold for protein kinase D. PLoS One 7(9):e44653. doi: 10.1371/journal.pone.0044653, PMID: 23028574PubMedCentralPubMedCrossRefGoogle Scholar
  7. 7.
    Ma C, Wang L, Yang P et al (2013) LiCABEDS II. Modeling of ligand selectivity for G-protein coupled cannabinoid receptors. J Chem Inf Model 53(1):11–26. doi: 10.1021/ci3003914 PubMedCentralPubMedCrossRefGoogle Scholar
  8. 8.
    Wang L, Ma C, Wipf P et al (2012) Linear and nonlinear support vector machine for the classification of human 5-HT1A ligand functionality. Mol Inf 31(1):85–95. doi: 10.1002/minf.201100126 CrossRefGoogle Scholar
  9. 9.
    Myint K, Xie X-Q (2011) Fragment-based QSAR algorithm development for compound bioactivity prediction. SAR QSAR Environ Res 22(3):385–410PubMedCrossRefGoogle Scholar
  10. 10.
    Chen JZ, Myint KZ, Xie X-Q (2011) New QSAR prediction models derived from GPCR CB2-antagonistic triaryl bis-sulfone analogues by a combined molecular morphological and pharmacophoric approach. SAR QSAR Environ Res 22(5–6):525–544. doi: 10.1080/1062936x.2011.569948 PubMedCrossRefGoogle Scholar
  11. 11.
    Chen J-Z, Han X-W, Liu Q et al (2006) 3D-QSAR studies of arylpyrazole antagonists of cannabinoid receptor subtypes CB1 and CB2. A combined NMR and CoMFA approach. J Med Chem 49(2):625–636PubMedCrossRefGoogle Scholar
  12. 12.
    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(3):1118–1124. doi: 10.1021/jm050932j PubMedCrossRefGoogle Scholar
  13. 13.
    González-Díaz H, Bonet I, Terán C et al (2007) ANN-QSAR model for selection of anticancer leads from structurally heterogeneous series of compounds. Eur J Med Chem 42(5):580–585. doi: 10.1016/j.ejmech.2006.11.016 PubMedCrossRefGoogle Scholar
  14. 14.
    Patra JC, Chua BH (2011) Artificial neural network-based drug design for diabetes mellitus using flavonoids. J Comput Chem 32(4):555–567. doi: 10.1002/jcc.21641 PubMedCrossRefGoogle Scholar
  15. 15.
    Dimitrov I, Naneva L, Bangov I et al (2014) Allergenicity prediction by artificial neural networks. J Chemometrics. doi: 10.1002/cem.2597 Google Scholar
  16. 16.
    Vanyúr R, Héberger K, Kövesdi I et al (2002) Prediction of tumoricidal activity and accumulation of photosensitizers in photodynamic therapy using multiple linear regression and artificial neural networks. Photochem Photobiol 75(5):471–478. doi: 10.1562/0031-8655(2002)0750471potaaa2.0.co2 CrossRefGoogle Scholar
  17. 17.
    Myint K-Z, Wang L, Tong Q et al (2012) Molecular fingerprint-based artificial neural networks QSAR for ligand biological activity predictions. Mol Pharm 9(10):2912–2923. doi: 10.1021/mp300237z PubMedCentralPubMedCrossRefGoogle Scholar
  18. 18.
    Molnár L, Keserű GM (2002) A neural network based virtual screening of cytochrome P450 3A4 inhibitors. Bioorg Med Chem Lett 12(3):419–421. doi: 10.1016/s0960-894x(01)00771-5 PubMedCrossRefGoogle Scholar
  19. 19.
    Muresan S, Sadowski J (2005) “In-House Likeness”: comparison of large compound collections using artificial neural networks. J Chem Inf Model 45(4):888–893. doi: 10.1021/ci049702o PubMedCrossRefGoogle Scholar
  20. 20.
    Wang L, Xie XQ (2012) Cannabinoid Ligand Database. Accessed Nov 2011Google Scholar
  21. 21.
    Sutherland JJ, O’Brien LA, Weaver DF (2004) A comparison of methods for modeling quantitative structure–activity relationships. J Med Chem 47(22):5541–5554. doi: 10.1021/jm0497141 PubMedCrossRefGoogle Scholar
  22. 22.
    Greenidge PA, Carlsson B, Bladh L-G et al (1998) Pharmacophores incorporating numerous excluded volumes defined by x-ray crystallographic structure in three-dimensional database searching: application to the thyroid hormone receptor. J Med Chem 41(14):2503–2512PubMedCrossRefGoogle Scholar
  23. 23.
    Mathworks (2007) MATLAB. (R2007b) edn, Natick, MAGoogle Scholar
  24. 24.
    O’Boyle N, Banck M, James C et al (2011) Open Babel: an open chemical toolbox. J Cheminform 3:33PubMedCentralPubMedCrossRefGoogle Scholar
  25. 25.
    Durant JL, Leland BA, Henry DR et al (2002) Reoptimization of MDL keys for use in drug discovery. J Chem Inf Comput Sci 42(6):1273–1280. doi: 10.1021/ci010132r PubMedCrossRefGoogle Scholar
  26. 26.
    Rogers D, Hahn M (2010) Extended-connectivity fingerprints. J Chem Inf Model 50(5):742–754. doi: 10.1021/ci100050t PubMedCrossRefGoogle Scholar
  27. 27.
    Cramer R, Patterson D, Bunce J (1988) Comparative molecular field analysis (CoMFA). 1. Effect of shape on binding of steroids to carrier proteins. J Am Chem Soc 110:5959–5967PubMedCrossRefGoogle Scholar
  28. 28.
    Klebe G (1998) Comparative molecular similarity indices analysis: CoMSIA. 3D QSAR in Drug Design. Three-Dimensional Quantitative Structure Activity Relationships 3:87–104Google Scholar
  29. 29.
    Lowis D (1997) HQSAR: a new, highly predictive QSAR technique. Tripos Technical Notes 1(5):17Google Scholar
  30. 30.
    Jain AN (2004) Ligand-based structural hypotheses for virtual screening. J Med Chem 47(4):947–961PubMedCrossRefGoogle Scholar
  31. 31.
    Ferguson AM, Heritage T, Jonathon P et al (1997) EVA: a new theoretically based molecular descriptor for use in QSAR/QSPR analysis. J Comput Aided Mol Des 11(2):143–152. doi: 10.1023/a:1008026308790 PubMedCrossRefGoogle Scholar
  32. 32.
    Agrafiotis DK, Cedeño W, Lobanov VS (2002) On the use of neural network ensembles in QSAR and QSPR. J Chem Inf Comput Sci 42(4):903–911. doi: 10.1021/ci0203702 PubMedCrossRefGoogle Scholar
  33. 33.
    Bender A, Jenkins JL, Scheiber J et al (2009) How similar are similarity searching methods? A principal component analysis of molecular descriptor space. J Chem Inf Model 49(1):108–119. doi: 10.1021/ci800249s PubMedCrossRefGoogle Scholar
  34. 34.
    Glem R, Bender A, Arnby C et al (2006) Circular fingerprints: flexible molecular descriptors with applications from physical chemistry to ADME. IDrugs 9(3):199–204PubMedGoogle Scholar
  35. 35.
    Bellis LJ, Akhtar R, Al-Lazikani B et al (2011) Collation and data-mining of literature bioactivity data for drug discovery. Biochem Soc Trans 39(5):1365–1370. doi: 10.1042/BST0391365, BST0391365 [pii]PubMedCrossRefGoogle Scholar
  36. 36.
    Collins J, Crowell J (2011) Drug Synthesis and Chemistry Branch, Developmental Therapeutics Program (DTP), Division of Cancer Treatment and Diagnosis, National Cancer Institute.
  37. 37.
    Tripos (2012) SYBYL-X 1.2. 1699 South Hanley Rd., St. Louis, Missouri, 63144, USAGoogle Scholar
  38. 38.
    Xie XQ, Chen JZ (2008) Data mining a small molecule drug screening representative subset from NIH PubChem. J Chem Inf Model 48(3):465–475. doi: 10.1021/ci700193u PubMedCrossRefGoogle Scholar
  39. 39.
    Huffman JW, Yu S, Showalter V et al (1996) Synthesis and pharmacology of a very potent cannabinoid lacking a phenolic hydroxyl with high affinity for the CB2 receptor. J Med Chem 39(20):3875–3877. doi: 10.1021/jm960394y PubMedCrossRefGoogle Scholar
  40. 40.
    Morgan HL (1965) The generation of a unique machine description for chemical structures—a technique developed at Chemical Abstracts Service. J Chem Doc 5(2):107–113. doi: 10.1021/c160017a018 CrossRefGoogle Scholar
  41. 41.
    Gertsch J, Leonti M, Raduner S et al (2008) Beta-caryophyllene is a dietary cannabinoid. Proc Natl Acad Sci 105(26):9099–9104. doi: 10.1073/pnas.0803601105 PubMedCentralPubMedCrossRefGoogle Scholar
  42. 42.
    Raduner S, Majewska A, Chen J-Z et al (2006) Alkylamides from Echinacea are a new class of cannabinomimetics: cannabinoid type 2 receptor-dependent and -independent immunomodulatory effects. J Biol Chem 281(20):14192–14206PubMedCrossRefGoogle Scholar
  43. 43.
    Zhang Y, Xie Z, Wang L et al (2011) Mutagenesis and computer modeling studies of a GPCR conserved residue W5.43(194) in ligand recognition and signal transduction for CB2 receptor. Int Immunopharmacol 11(9):1303–1310. doi: 10.1016/j.intimp.2011.04.013 PubMedCentralPubMedCrossRefGoogle Scholar
  44. 44.
    Yang P, Wang L, Feng R et al (2013) Novel triaryl sulfonamide derivatives as selective cannabinoid receptor 2 inverse agonists and osteoclast inhibitors: discovery, optimization, and biological evaluation. J Med Chem 56(5):2045–2058. doi: 10.1021/jm3017464 PubMedCentralPubMedCrossRefGoogle Scholar
  45. 45.
    DePriest SA, Mayer D, Naylor CB et al (1993) 3D-QSAR of angiotensin-converting enzyme and thermolysin inhibitors: a comparison of CoMFA models based on deduced and experimentally determined active site geometries. J Am Chem Soc 115(13):5372–5384. doi: 10.1021/ja00066a004 CrossRefGoogle Scholar
  46. 46.
    Sugimoto H, Tsuchiya Y, Sugumi H et al (1992) Synthesis and structure-activity relationships of acetylcholinesterase inhibitors: 1-benzyl-4-(2-phthalimidoethyl)piperidine, and related derivatives. J Med Chem 35(24):4542–4548. doi: 10.1021/jm00102a005 PubMedCrossRefGoogle Scholar
  47. 47.
    Sugimoto H, Tsuchiya Y, Sugumi H et al (1990) Novel piperidine derivatives. Synthesis and anti-acetylcholinesterase activity of 1-benzyl-4-[2-(N-benzoylamino)ethyl]piperidine derivatives. J Med Chem 33(7):1880–1887. doi: 10.1021/jm00169a008 PubMedCrossRefGoogle Scholar
  48. 48.
    Haefely W, Kyburz E, Gerecke M et al (1985) Recent advances in the molecular pharmacology of benzodiazepine receptors and in the structure-activity relationships of their agonists and antagonists. Adv Drug Res 14:165–322Google Scholar
  49. 49.
    Chavatte P, Yous S, Marot C et al (2001) Three-dimensional quantitative structure–activity relationships of cyclo-oxygenase-2 (COX-2) inhibitors: a comparative molecular field analysis. J Med Chem 44(20):3223–3230. doi: 10.1021/jm0101343 PubMedCrossRefGoogle Scholar
  50. 50.
    Talley JJ, Brown DL, Carter JS et al (2000) 4-[5-Methyl-3-phenylisoxazol-4-yl]-benzenesulfonamide, Valdecoxib: a potent and selective inhibitor of COX-2. J Med Chem 43(5):775–777. doi: 10.1021/jm990577v PubMedCrossRefGoogle Scholar
  51. 51.
    Huang H-C, Li JJ, Garland DJ et al (1996) Diarylspiro[2.4]heptenes as orally active, highly selective cyclooxygenase-2 inhibitors: synthesis and structure–activity relationships. J Med Chem 39(1):253–266. doi: 10.1021/jm950664x PubMedCrossRefGoogle Scholar
  52. 52.
    Penning TD, Talley JJ, Bertenshaw SR et al (1997) Synthesis and biological evaluation of the 1,5-diarylpyrazole class of cyclooxygenase-2 inhibitors: identification of 4-[5-(4-Methylphenyl)-3-(trifluoromethyl)-1H-pyrazol-1-yl]benzenesulfonamide (SC-58635, Celecoxib). J Med Chem 40(9):1347–1365. doi: 10.1021/jm960803q PubMedCrossRefGoogle Scholar
  53. 53.
    Li JJ, Norton MB, Reinhard EJ et al (1996) Novel terphenyls as selective cyclooxygenase-2 inhibitors and orally active anti-inflammatory agents. J Med Chem 39(9):1846–1856. doi: 10.1021/jm950878e PubMedCrossRefGoogle Scholar
  54. 54.
    Li JJ, Anderson GD, Burton EG et al (1995) 1,2-Diarylcyclopentenes as selective cyclooxygenase-2 inhibitors and orally active anti-inflammatory agents. J Med Chem 38(22):4570–4578. doi: 10.1021/jm00022a023 PubMedCrossRefGoogle Scholar
  55. 55.
    Reitz DB, Li JJ, Norton MB et al (1994) Selective cyclooxygenase inhibitors: novel 1,2-diarylcyclopentenes are potent and orally active COX-2 inhibitors. J Med Chem 37(23):3878–3881. doi: 10.1021/jm00049a005 PubMedCrossRefGoogle Scholar
  56. 56.
    Khanna IK, Yu Y, Huff RM et al (2000) Selective cyclooxygenase-2 inhibitors: heteroaryl modified 1,2-diarylimidazoles are potent, orally active antiinflammatory agents. J Med Chem 43(16):3168–3185. doi: 10.1021/jm0000719 PubMedCrossRefGoogle Scholar
  57. 57.
    Khanna IK, Weier RM, Yu Y et al (1997) 1,2-diarylimidazoles as potent, cyclooxygenase-2 selective, and orally active antiinflammatory agents. J Med Chem 40(11):1634–1647. doi: 10.1021/jm9700225 PubMedCrossRefGoogle Scholar
  58. 58.
    Khanna IK, Weier RM, Yu Y et al (1997) 1,2-Diarylpyrroles as potent and selective inhibitors of cyclooxygenase-2. J Med Chem 40(11):1619–1633. doi: 10.1021/jm970036a PubMedCrossRefGoogle Scholar
  59. 59.
    Gangjee A, Vidwans AP, Vasudevan A et al (1998) Structure-based design and synthesis of lipophilic 2,4-diamino-6-substituted quinazolines and their evaluation as inhibitors of dihydrofolate reductases and potential antitumor agents. J Med Chem 41(18):3426–3434. doi: 10.1021/jm980081y PubMedCrossRefGoogle Scholar
  60. 60.
    Rosowsky A, Mota CE, Wright JE et al (1994) 2,4-Diamino-5-chloroquinazoline analogs of trimetrexate and piritrexim: synthesis and antifolate activity. J Med Chem 37(26):4522–4528. doi: 10.1021/jm00052a011 PubMedCrossRefGoogle Scholar
  61. 61.
    Rosowsky A, Cody V, Galitsky N et al (1999) Structure-based design of selective inhibitors of dihydrofolate reductase: synthesis and antiparasitic activity of 2,4-diaminopteridine analogues with a bridged diarylamine side chain. J Med Chem 42(23):4853–4860. doi: 10.1021/jm990331q PubMedCrossRefGoogle Scholar
  62. 62.
    Graffner-Nordberg M, Kolmodin K, Åqvist J et al (2001) Design, synthesis, computational prediction, and biological evaluation of ester soft drugs as inhibitors of dihydrofolate reductase from Pneumocystis carinii. J Med Chem 44(15):2391–2402. doi: 10.1021/jm010856u PubMedCrossRefGoogle Scholar
  63. 63.
    Gangjee A, Elzein E, Queener SF et al (1998) Synthesis and biological activities of tricyclic conformationally restricted tetrahydropyrido annulated furo[2,3-d]pyrimidines as inhibitors of dihydrofolate reductases. J Med Chem 41(9):1409–1416. doi: 10.1021/jm9705420 PubMedCrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2015

Authors and Affiliations

  1. 1.NIDA Center of Excellence for Computational Chemogenomics Drug Abuse Research, Computational Chemical Genomics Screening CenterDepartment of Pharmaceutical Sciences, School of Pharmacy, University of PittsburghPittsburghUSA

Personalised recommendations