Advertisement

Structural Chemistry

, Volume 30, Issue 6, pp 2429–2445 | Cite as

Application of multilayered strategy for variable selection in QSAR modeling of PET and SPECT imaging agents as diagnostic agents for Alzheimer’s disease

  • Priyanka De
  • Dhananjay Bhattacharyya
  • Kunal RoyEmail author
Original Research

Abstract

Non-invasive imaging of amyloid beta (Aβ) and tau fibrils in the brain may support an early and precise diagnosis of Alzheimer’s disease. Molecular imaging technologies involving radionuclides such as positron emission tomography (PET) and single-photon emission computed tomography (SPECT) against beta amyloid plaques and tau fibrils are among emerging research areas in the field of medicinal chemistry. In the current study, we have developed partial least square (PLS) regression-based two-dimensional quantitative structure-activity relationship (2D-QSAR) models using datasets of 38 PET and 73 SPECT imaging agents targeted against Aβ protein and 31 imaging agents (both PET and SPECT) targeted against tau protein. Following the strict Organization for Economic Co-operation and Development (OECD) guidelines, we have strived to select significant descriptors from the large initial pool of descriptors using multilayered variable selection strategy using the double cross-validation (DCV) method followed by the best subset selection (BSS) method prior to the development of the final PLS models. The developed models showed significant statistical performance and reliability. Molecular docking studies have been performed to understand the molecular interactions between the ligand and receptor, and the results are then correlated with the structural features obtained from the QSAR models. Furthermore, we have also designed some imaging agents based on the information provided by the models developed and some of them are predicted to be similar to or more active than the most active imaging agents present in the original dataset.

Keywords

Alzheimer’s disease Imaging agents Double cross-validation QSAR PLS 

Notes

Funding information

PD received financial assistance from the Department of Atomic Energy—Board of Research in Nuclear Sciences (DAE-BRNS).

Compliance with ethical standards

Conflict of interest

The authors declare that they have no conflict of interest.

Supplementary material

11224_2019_1376_MOESM1_ESM.docx (10 mb)
ESM 1 (DOCX 10268 kb)
11224_2019_1376_MOESM2_ESM.xlsx (21 kb)
ESM 2 (XLSX 20 kb)

References

  1. 1.
    Schilling LP, Zimmer ER, Shin M, Leuzy A, Pascoal TA, Benedet AL, Borelli WV, Palmini A, Gauthier S, Rosa-Neto P (2016) Imaging Alzheimer’s disease pathophysiology with PET. Dement Neuropsychol 10:79–90PubMedPubMedCentralGoogle Scholar
  2. 2.
    Klunk WE (1998) Biological markers of Alzheimer’s disease. Neurobiol Aging 2:145–147Google Scholar
  3. 3.
    Selkoe DJ (2001) Alzheimer’s disease: genes, proteins, and therapy. Physiol Rev 81:741–766PubMedGoogle Scholar
  4. 4.
    Wimo A, Winblad B, Aguero-Torres H, von Strauss E (2003) The magnitude of dementia occurrence in the world. Alzheimer Dis Assoc Disord 17:63–67PubMedGoogle Scholar
  5. 5.
    Alzheimer Association. Alzheimer’s and dementia facts and figures https://www.alz.org/alzheimers-dementia/facts-figures. Accessed on 20 Nov 2018
  6. 6.
    Okamura N, Furumoto S, Harada R, Tago T, Yoshikawa T, Fodero-Tavoletti M, Mulligan RS, Villemagne VL, Akatsu H, Yamamoto T (2013) Novel 18F-labeled arylquinoline derivatives for noninvasive imaging of tau pathology in Alzheimer disease. J Nucl Med 54:1420–1427PubMedGoogle Scholar
  7. 7.
    Duyckaerts C, Clavaguera F, Potier M-C (2019) The prion-like propagation hypothesis in Alzheimer’s and Parkinson’s disease. Curr Opin Neurol 32:266–271PubMedGoogle Scholar
  8. 8.
    Hamley IW (2012) The amyloid beta peptide: a chemist’s perspective. Role in Alzheimer’s and fibrillization. Chem Rev 112:5147–5192PubMedGoogle Scholar
  9. 9.
    Lichtenberg B, Mandelkow EM, Hagestedt T, Mandelkow E (1988) Structure and elasticity of microtubule-associated protein tau. Nature 334:359PubMedGoogle Scholar
  10. 10.
    Barghorn S, Davies P, Mandelkow E (2004) Tau paired helical filaments from Alzheimer’s disease brain and assembled in vitro are based on β-structure in the core domain. Biochemistry 43:1694–1703PubMedGoogle Scholar
  11. 11.
    Bondareff W, Mountjoy CQ, Roth M, Hauser DL (1989) Neurofibrillary degeneration and neuronal loss in Alzheimer’s disease. Neurobiol Aging 10:709–715PubMedGoogle Scholar
  12. 12.
    Bobinski M, Wegiel J, Wisniewski HM, Tarnawski M, Bobinski M, Reisberg B, De Leon MJ, Miller DC (1996) Neurofibrillary pathology—correlation with hippocampal formation atrophy in Alzheimer disease. Neurobiol Aging 17:909–919PubMedGoogle Scholar
  13. 13.
    Ono M, Hayashi S, Matsumura K, Kimura H, Okamoto Y, Ihara M, Takahashi R, Mori H, Saji H (2011) Rhodanine and thiohydantoin derivatives for detecting tau pathology in Alzheimer’s brains. ACS Chem Neurosci 2:269–275PubMedPubMedCentralGoogle Scholar
  14. 14.
    Wang Y, Klunk WE, Debnath ML, Huang G-F, Holt DP, Shao L, Mathis CA (2004) Development of a PET/SPECT agent for amyloid imaging in Alzheimer’s disease. J Mol Neurosci 24:55–62PubMedGoogle Scholar
  15. 15.
    Yang Y, Cui M, Jin B, Wang X, Li Z, Yu P, Jia J, Fu H, Jia H, Liu B (2013) 99mTc-labeled dibenzylideneacetone derivatives as potential SPECT probes for in vivo imaging of β-amyloid plaque. Eur J Med Chem 64:90–98PubMedGoogle Scholar
  16. 16.
    Kung HF, Choi SR, Qu W, Zhang W, Skovronsky D (2009) 18F stilbenes and styrylpyridines for PET imaging of Aβ plaques in Alzheimer’s disease: a miniperspective. J Med Chem 53:933–941Google Scholar
  17. 17.
    Rojo LE, Alzate-Morales J, Saavedra IN, Davies P, Maccioni RB (2010) Selective interaction of lansoprazole and astemizole with tau polymers: potential new clinical use in diagnosis of Alzheimer’s disease. J Alzheimers Dis 19:573–589PubMedPubMedCentralGoogle Scholar
  18. 18.
    Jensen JR, Cisek K, Funk KE, Naphade S, Schafer KN, Kuret J (2011) Research towards tau imaging. J Alzheimers Dis 26:147–115PubMedGoogle Scholar
  19. 19.
    Fodero-Tavoletti MT, Okamura N, Furumoto S, Mulligan RS, Connor AR, McLean CA, Cao D, Rigopoulos A, Cartwright GA, O’keefe G (2011) 18F-THK523: a novel in vivo tau imaging ligand for Alzheimer’s disease. Brain 134:1089–1100PubMedGoogle Scholar
  20. 20.
    Villemagne VL, Furumoto S, Fodero-Tavoletti M, Harada R, Mulligan RS, Kudo Y, Masters CL, Yanai K, Rowe CC, Okamura N (2012) The challenges of tau imaging. Future Neurol 7:409–421Google Scholar
  21. 21.
    Ono M, Saji H (2011) SPECT imaging agents for detecting cerebral β-amyloid plaques. Int J Mol Imaging 2011.  https://doi.org/10.1155/2011/543267 Google Scholar
  22. 22.
    Small GW, Agdeppa ED, Kepe V, Satyamurthy N, Huang S-C, Barrio JR (2002) In vivo brain imaging of tangle burden in humans. J Mol Neurosci 19:321–327Google Scholar
  23. 23.
    Shoghi-Jadid K, Small GW, Agdeppa ED, Kepe V, Ercoli LM, Siddarth P, Read S, Satyamurthy N, Petric A, Huang S-C (2002) Localization of neurofibrillary tangles and beta-amyloid plaques in the brains of living patients with Alzheimer disease. Am J Geriatr Psychiatry 10:24–35PubMedGoogle Scholar
  24. 24.
    Hansch C, Leo A, Hoekman DH (1995) Exploring QSAR: fundamentals and applications in chemistry and biology. American Chemical Society, Washington, DCGoogle Scholar
  25. 25.
    Hansch C, Leo A, Mekapati SB, Kurup A (2004) Qsar and Adme. Bioorg Med Chem 12:3391–3400PubMedGoogle Scholar
  26. 26.
    Klein C, Kaiser D, Kopp S, Chiba P, Ecker GF (2002) Similarity based SAR (SIBAR) as tool for early ADME profiling. J Comput Aided Mol Des 16:785–793PubMedGoogle Scholar
  27. 27.
    Toropova MA (2017) Drug metabolism as an object of computational analysis by the Monte Carlo method. Curr Drug Metab 18:1123–1131PubMedGoogle Scholar
  28. 28.
    Toropova AP, Toropov AA (2018) CORAL: Monte Carlo method to predict endpoints for medical chemistry. Mini Rev Med Chem 18:382–391PubMedGoogle Scholar
  29. 29.
    Toropova AP, Toropov AA, Begum S, Achary PGR (2018) Blood brain barrier and Alzheimer’s disease: similarity and dissimilarity of molecular alerts. Curr Neuropharmacol 16:769–785PubMedPubMedCentralGoogle Scholar
  30. 30.
    Toropova MA, Toropov AA, Raška Jr I, Rašková M (2015) Searching therapeutic agents for treatment of Alzheimer disease using the Monte Carlo method. Comput Biol Med 64:148–154PubMedGoogle Scholar
  31. 31.
    Roy K, Ambure P (2016) The “double cross-validation” software tool for MLR QSAR model development. Chemom Intell Lab Syst 159:108–126Google Scholar
  32. 32.
    Herholz K, Ebmeier K (2011) Clinical amyloid imaging in Alzheimer’s disease. Lancet Neurol 10:667–670PubMedGoogle Scholar
  33. 33.
    Cohen AD, Rabinovici GD, Mathis CA, Jagust WJ, Klunk WE, Ikonomovic MD (2012) Using Pittsburgh compound B for in vivo PET imaging of fibrillar amyloid-beta. Adv Pharmacol 64:27–81PubMedPubMedCentralGoogle Scholar
  34. 34.
    Zhu L, Ploessl K, Kung HF (2014) PET/SPECT imaging agents for neurodegenerative diseases. Chem Soc Rev 43:6683–6691PubMedPubMedCentralGoogle Scholar
  35. 35.
    Mathis CA, Wang Y, Holt DP, Huang G-F, Debnath ML, Klunk WE (2003) Synthesis and evaluation of 11C-labeled 6-substituted 2-arylbenzothiazoles as amyloid imaging agents. J Med Chem 46:2740–2754PubMedGoogle Scholar
  36. 36.
    Ono M, Kawashima H, Nonaka A, Kawai T, Haratake M, Mori H, Kung M-P, Kung HF, Saji H, Nakayama M (2006) Novel benzofuran derivatives for PET imaging of β-amyloid plaques in Alzheimer’s disease brains. J Med Chem 49:2725–2730PubMedGoogle Scholar
  37. 37.
    Qu W, Kung M-P, Hou C, Jin L-W, Kung HF (2007) Radioiodinated aza-diphenylacetylenes as potential SPECT imaging agents for β-amyloid plaque detection. Bioorg Med Chem Lett 17:3581–3584PubMedPubMedCentralGoogle Scholar
  38. 38.
    Ono M, Cheng Y, Kimura H, Watanabe H, Matsumura K, Yoshimura M, Iikuni S, Okamoto Y, Ihara M, Takahashi R (2013) Development of novel 123I-labeled pyridyl benzofuran derivatives for SPECT imaging of β-amyloid plaques in Alzheimer’s disease. PLoS One 8:e74104PubMedPubMedCentralGoogle Scholar
  39. 39.
    Fuchigami T, Yamashita Y, Kawasaki M, Ogawa A, Haratake M, Atarashi R, Sano K, Nakagaki T, Ubagai K, Ono M (2016) Characterisation of radioiodinated flavonoid derivatives for SPECT imaging of cerebral prion deposits. Sci Rep 5:18440Google Scholar
  40. 40.
    Maya Y, Ono M, Watanabe H, Haratake M, Saji H, Nakayama M (2008) Novel radioiodinated aurones as probes for SPECT imaging of β-amyloid plaques in the brain. Bioconjug Chem 20:95–101Google Scholar
  41. 41.
    Alagille D, DaCosta H, Baldwin RM, Tamagnan GD (2011) 2-Arylimidazo [2, 1-b] benzothiazoles: a new family of amyloid binding agents with potential for PET and SPECT imaging of Alzheimer’s brain. Bioorg Med Chem Lett 21:2966–2968PubMedGoogle Scholar
  42. 42.
    Maya Y, Okumura Y, Kobayashi R, Onishi T, Shoyama Y, Barret O, Alagille D, Jennings D, Marek K, Seibyl J (2015) Preclinical properties and human in vivo assessment of 123 I-ABC577 as a novel SPECT agent for imaging amyloid-β. Brain 139:193–203PubMedPubMedCentralGoogle Scholar
  43. 43.
    Kung M-P, Hou C, Zhuang Z-P, Skovronsky DM, Zhang B, Gur TL, Trojanowski JQ, Lee VMY, Kung HF (2002) Radioiodinated styrylbenzene derivatives as potential SPECT imaging agents for amyloid plaque detection in Alzheimer’s disease. J Mol Neurosci 19:7–10PubMedGoogle Scholar
  44. 44.
    Pan J, Mason NS, Debnath ML, Mathis CA, Klunk WE, Lin K-S (2013) Design, synthesis and structure–activity relationship of rhenium 2-arylbenzothiazoles as β-amyloid plaque binding agents. Bioorg Med Chem Lett 23:1720–1726PubMedPubMedCentralGoogle Scholar
  45. 45.
    Okamura N, Suemoto T, Furumoto S, Suzuki M, Shimadzu H, Akatsu H, Yamamoto T, Fujiwara H, Nemoto M, Maruyama M (2005) Quinoline and benzimidazole derivatives: candidate probes for in vivo imaging of tau pathology in Alzheimer’s disease. J Neurosci 25:10857–10862PubMedPubMedCentralGoogle Scholar
  46. 46.
    Declercq L, Celen S, Lecina J, Ahamed M, Tousseyn T, Moechars D, Alcazar J, Ariza M, Fierens K, Bottelbergs A (2016) Comparison of new tau PET-tracer candidates with [18F] T808 and [18F] T807. Mol Imaging 15:1536012115624920PubMedPubMedCentralGoogle Scholar
  47. 47.
    Tago T, Furumoto S, Okamura N, Harada R, Adachi H, Ishikawa Y, Yanai K, Iwata R, Kudo Y (2016) Structure–activity relationship of 2-arylquinolines as PET imaging tracers for tau pathology in Alzheimer disease. J Nucl Med 57:608–614PubMedGoogle Scholar
  48. 48.
    Hashimoto H, Kawamura K, Takei M, Igarashi N, Fujishiro T, Shiomi S, Watanabe R, Muto M, Furutsuka K, Ito T (2015) Identification of a major radiometabolite of [11C] PBB3. Nucl Med Biol 42:905–910PubMedGoogle Scholar
  49. 49.
    Tago T, Furumoto S, Okamura N, Harada R, Ishikawa Y, Arai H, Yanai K, Iwata R, Kudo Y (2014) Synthesis and preliminary evaluation of 2-arylhydroxyquinoline derivatives for tau imaging. J Label Compd Radiopharm 57:18–24Google Scholar
  50. 50.
    Matsumura K, Ono M, Hayashi S, Kimura H, Okamoto Y, Ihara M, Takahashi R, Mori H, Saji H (2011) Phenyldiazenyl benzothiazole derivatives as probes for in vivo imaging of neurofibrillary tangles in Alzheimer’s disease brains. MedChemComm 2:596–600Google Scholar
  51. 51.
    MarvinSketch software, https://www.chemaxon.com. Accessed 28 Dec 2018
  52. 52.
    Dragon version 7, Kodesrl, Milan, Italy, 2016; software available at http://www.talete.mi.it/index.htm. Accessed 03 Jan 2019
  53. 53.
    Golbraikh A, Shen M, Xiao Z, Xiao Y-D, Lee K-H, Tropsha A (2003) Rational selection of training and test sets for the development of validated QSAR models. J Comput Aided Mol Des 17:241–253PubMedGoogle Scholar
  54. 54.
    Golmohammadi H, Dashtbozorgi Z, Acree Jr WE (2012) Quantitative structure–activity relationship prediction of blood-to-brain partitioning behavior using support vector machine. Eur J Pharm Sci 47:421–429PubMedGoogle Scholar
  55. 55.
    Park H-S, Jun C-H (2009) A simple and fast algorithm for K-medoids clustering. Expert Syst Appl 36:3336–3341Google Scholar
  56. 56.
    Khan PM, Roy K (2018) Current approaches for choosing feature selection and learning algorithms in quantitative structure-activity relationships (QSAR). Expert Opin Drug Discov 13:1075–1089PubMedGoogle Scholar
  57. 57.
    Pope PT, Webster JT (1972) The use of an F-statistic in stepwise regression procedures. Technometrics 14:327–340Google Scholar
  58. 58.
    Wold S, Sjöström M, Eriksson L (2001) PLS-regression: a basic tool of chemometrics. Chemom Intell Lab Syst 58:109–130Google Scholar
  59. 59.
    Baumann D, Baumann K (2014) Reliable estimation of prediction errors for QSAR models under model uncertainty using double cross-validation. J Cheminform 6:47PubMedPubMedCentralGoogle Scholar
  60. 60.
    Roy K, Kar S, Das RN (2015) Understanding the basics of QSAR for applications in pharmaceutical sciences and risk assessment. Academic Press, New YorkGoogle Scholar
  61. 61.
    Todeschini R, Ballabio D, Grisoni F (2016) Beware of unreliable Q2! A comparative study of regression metrics for predictivity assessment of QSAR models. J Chem Inf Model 56:1905–1913PubMedGoogle Scholar
  62. 62.
    Chirico N, Gramatica P (2012) Real external predictivity of QSAR models. Part 2. New intercomparable thresholds for different validation criteria and the need for scatter plot inspection. J Chem Inf Model 52:2044–2058PubMedGoogle Scholar
  63. 63.
    Roy K, Mitra I, Kar S, Ojha PK, Das RN, Kabir H (2012) Comparative studies on some metrics for external validation of QSPR models. J Chem Inf Model 52:396–408PubMedGoogle Scholar
  64. 64.
    Roy K, Das RN, Ambure P, Aher RB (2016) Be aware of error measures. Further studies on validation of predictive QSAR models. Chemom Intell Lab Syst 152:18–33Google Scholar
  65. 65.
    Paravastu AK, Leapman RD, Yau W-M, Tycko R (2008) Molecular structural basis for polymorphism in Alzheimer’s β-amyloid fibrils. Proc Natl Acad Sci 105:18349–18354PubMedGoogle Scholar
  66. 66.
    Andrei SA, Meijer FA, Neves JF, Brunsveld L, Landrieu I, Ottmann C, Milroy L-G (2018) Inhibition of 14-3-3/Tau by hybrid small-molecule peptides operating via two different binding modes. ACS Chem Neurosci 9:2639–2654PubMedPubMedCentralGoogle Scholar
  67. 67.
  68. 68.
    Wu G, Robertson DH, Brooks Iii CL, Vieth M (2003) Detailed analysis of grid-based molecular docking: a case study of CDOCKER—a CHARMm-based MD docking algorithm. J Comput Chem 24:1549–1562PubMedGoogle Scholar
  69. 69.
    Benfenati E (2011) Quantitative structure-activity relationships (QSAR) for pesticide regulatory purposes. Elsevier, AmsterdamGoogle Scholar
  70. 70.
    Chartrand G, Johns GL, Tian S (1993) Detour distance in graphs. Ann Discrete Math 55:127–136Google Scholar
  71. 71.
    Akarachantachote N, Chadcham S, Saithanu K (2014) Cutoff threshold of variable importance in projection for variable selection. Int J Pure Appl Math 94:307–322Google Scholar
  72. 72.
    Jackson JE (2005) A user’s guide to principal components. John Wiley & Sons, New JerseyGoogle Scholar
  73. 73.
    Gadaleta D, Mangiatordi GF, Catto M, Carotti A, Nicolotti O (2016) Applicability domain for QSAR models: where theory meets reality. IJQSPR 1:45–63Google Scholar
  74. 74.
    U. Simca-P, 10.0, info@umetrics.com, www.umetrics.com, Umea, Sweden, 2002. Accessed 22 Jan 2019
  75. 75.
    Rücker C, Rücker G, Meringer M (2007) Y-randomization and its variants in QSPR/QSAR. J Chem Inf Model 47:2345–2357PubMedGoogle Scholar
  76. 76.
    Alkorta I, Rozas I, Elguero J (1998) Non-conventional hydrogen bonds. Chem Soc Rev 27:163–170Google Scholar
  77. 77.
    Ribas J, Cubero E, Luque FJ, Orozco M (2002) Theoretical study of alkyl-π and aryl-π interactions. Reconciling theory and experiment. J Org Chem 67:7057–7065PubMedGoogle Scholar
  78. 78.
    Echeverría J (2017) Alkyl groups as electron density donors in π-hole bonding. CrystEngComm 19:6289–6296Google Scholar
  79. 79.
    Martinez CR, Iverson BL (2012) Rethinking the term “pi-stacking”. Chem Sci 3:2191–2201Google Scholar
  80. 80.
    Shiri F, Shahraki S, Baneshi S, Nejati-Yazdinejad M, Majd MH (2016) Synthesis, characterization, in vitro cytotoxicity, in silico ADMET analysis and interaction studies of 5-dithiocarbamato-1, 3, 4-thiadiazole-2-thiol and its zinc (ii) complex with human serum albumin: combined spectroscopy and molecular docking investigations. RSC Adv 6:106516–106526Google Scholar
  81. 81.
    Darras FH, Pang Y-P (2017) On the use of the experimentally determined enzyme inhibition constant as a measure of absolute binding affinity. Biochem Biophys Res Commun 489:451–454PubMedGoogle Scholar
  82. 82.
    De P, Roy K (2018) Greener chemicals for the future: QSAR modelling of the PBT index using ETA descriptors. SAR QSAR Environ Res 29:319–337PubMedGoogle Scholar
  83. 83.
    Khan K, Benfenati E, Roy K (2019) Consensus QSAR modeling of toxicity of pharmaceuticals to different aquatic organisms: ranking and prioritization of the DrugBank database compounds. Ecotoxicol Environ Saf 168:287–297PubMedGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2019

Authors and Affiliations

  1. 1.Drug Theoretics and Cheminformatics Laboratory, Department of Pharmaceutical TechnologyJadavpur UniversityKolkataIndia
  2. 2.Computational Science DivisionSaha Institute of Nuclear PhysicsKolkataIndia

Personalised recommendations