Got to Write a Classic: Classical and Perturbation-Based QSAR Methods, Machine Learning, and the Monitoring of Nanoparticle Ecotoxicity

  • Ana S. Moura
  • M. Natália D. S. CordeiroEmail author
Part of the Methods in Pharmacology and Toxicology book series (MIPT)


Machine learning has become a central feature in the development or refinement of in silico methodologies and techniques. Quantitative structure-activity relationship (QSAR) models are no exception. In fact, one can consider there is a renaissance of QSAR techniques and respective reliability as there is a greater synergy between the two of them. Further, this new wave of QSAR + machine learning (ML) techniques allows new avenues in several fields of application, namely, when regarding cytotoxicity and/or ecotoxicity monitoring of nanoparticles (NPs). The latter is of major importance, as the challenges brought by environment management and the increasing concern it has on the food chain are met with expensive and overall slow experimental answers. Within this context, and alongside classical QSAR + machine learning techniques, recent QSAR perturbation-based models join methods with ML as well. The QSAR perturbation models feature the possibility of simultaneous modeling multi bio-targets versus NPs in different experimental conditions, thus offering practical solutions to classical QSAR + ML limitations. The use of in silico models could be the most feasible answer to the present and future scenarios of mandatory ecotoxicity monitorization for nanotechnology by-products. This chapter approaches the methodologies and fundamentals of classical and perturbation-based QSAR models within the environmental risk assessment framework, as scaffold to develop novel in silico techniques.

Key words

QSAR QSTR Machine learning Ecotoxicity Environmental monitorization Nanoparticles Hybrid in silico models 



This work was supported by UID/QUI/50006/2019, contract IF CEECIND/03631/2017, and project PTDC/QUI-QIN/30649/2017 with funding from FCT/MCTES through national funds.


  1. 1.
    Crum-Brown A, Fraser TR (1865) The connection of chemical constitution and physiological action. Trans R Soc Edinb 25(1968–1969):257Google Scholar
  2. 2.
    Crum-Brown A, Fraser TR (1868) On the connection between chemical constitution and physiological action; with special reference to the physiological action of the salts of the ammonium bases derived from strychnia, brucia, thebaia, codeia, morphia, and nicotia. J Anat Physiol 2(2):224–242Google Scholar
  3. 3.
    Hansch C (1969) A quantitative approach to biochemical structure-activity relationships. Acc Chem Res 2:232–239CrossRefGoogle Scholar
  4. 4.
    Devinyak OT, Lesyk RB (2016) 5-year trends in QSAR and its machine learning methods. Curr Comput Aided Drug Des 12(4):265–271PubMedCrossRefGoogle Scholar
  5. 5.
    Mitchell TM (1997) Machine learning, vol 45. McGraw Hill, Ridge, pp 870–877Google Scholar
  6. 6.
    Kim BJ, Ko Y, Cho JH (2013) Organic field-effect transistor memory devices using discrete ferritin nanoparticle-based gate dielectrics. Small 9(22):3784–3791PubMedCrossRefGoogle Scholar
  7. 7.
    Liz-Marzán LM, Kamat PV (2004) Nanoscale materials. Kluwer Academic Publishers, New YorkCrossRefGoogle Scholar
  8. 8.
    Chen CY, Retamal JR, Wu IW et al (2012) Probing surface band bending of surface-engineered metal oxide nanowires. ACS Nano 6(11):9366–9372PubMedCrossRefGoogle Scholar
  9. 9.
    Biffis A, Králik M (2001) Catalysis by metal nanoparticles supported on functional organic polymers. J Mol Catal A 177(1):113–138CrossRefGoogle Scholar
  10. 10.
    Chan NY, Zhao M, Wang N et al (2013) Palladium nanoparticle enhanced giant photoresponse at LaAlO/SrTiO two-dimensional electron gas heterostructures. ACS Nano 7(10):8673–8679PubMedCrossRefGoogle Scholar
  11. 11.
    Lu P, Campbell CT, Xia Y (2013) A sinter-resistant catalytic system fabricated by maneuvering the selectivity of SiO2 deposition onto TiO2 surface versus Pt nanoparticle surface. Nano Lett 13(10):4957–4962PubMedCrossRefGoogle Scholar
  12. 12.
    Yang B, Zhao C, Xiao M et al (2013) Loading metal nanostructures on cotton fabrics as recyclable catalysts. Small 9(7):1003–1007PubMedCrossRefGoogle Scholar
  13. 13.
    Moseler M, Walter M, Yoon B et al (2012) Oxidation state and symmetry of magnesia-supported Pd13O(x) nanocatalysts influence activation barriers of CO oxidation. J Am Chem Soc 134(18):7690–7699PubMedCrossRefGoogle Scholar
  14. 14.
    Corchero JL, Villaverde A (2009) Biomedical applications of distally controlled magnetic nanoparticles. Trends Biotechnol 27(8):468–476PubMedCrossRefGoogle Scholar
  15. 15.
    Zhang Z, Wang J, Chen C (2013) Near-infrared light-mediated nanoplatforms for cancer thermo-chemotherapy and optical imaging. Adv Mater 25(28):3869–3880PubMedCrossRefGoogle Scholar
  16. 16.
    Schoen DT, Coenen T, Garcia de Abajo FJ et al (2013) The planar parabolic optical antenna. Nano Lett 13(1):188–193PubMedCrossRefPubMedCentralGoogle Scholar
  17. 17.
    Liao L, Liu J, Dreaden EC et al (2014) A convergent synthetic platform for single-nanoparticle combination cancer therapy: ratiometric loading and controlled release of cisplatin, doxorubicin, and camptothecin. J Am Chem Soc 136(16):5896–5899PubMedPubMedCentralCrossRefGoogle Scholar
  18. 18.
    Lu CH, Willner B, Willner I (2013) DNA nanotechnology: from sensing and DNA machines to drug-delivery systems. ACS Nano 7(10):8320–8332PubMedCrossRefPubMedCentralGoogle Scholar
  19. 19.
    Brigger I, Dubernet C, Couvreur P (2002) Nanoparticles in cancer therapy and diagnosis. Adv Drug Deliv Rev 54(5):631–651PubMedCrossRefPubMedCentralGoogle Scholar
  20. 20.
    Todeschini R, Consonni V (2000) Handbook of molecular descriptors, vol 11. Wiley VCH, WeinheimCrossRefGoogle Scholar
  21. 21.
    Halder AK, Moura AS, Cordeiro MNDS (2018) Advanced chemometric modeling approaches for the design of multitarget drugs against neurodegenerative diseases. In: Roy K (ed) Multi-target drug design using chem-bioinformatic approaches. Methods in pharmacology and toxicology. Humana Press, New YorkGoogle Scholar
  22. 22.
    Hsu DD, Chemicool Periodic Table,, Accessed April 4, 2019
  23. 23.
    Simulations Plus, Inc [US]. Accessed 10 Apr 2019
  24. 24.
    Rana S, Kalaichelvan PT (2013) Ecotoxicity of nanoparticles. ISRN Toxicology 2013:1. Scholar
  25. 25.
    Ostiguy C, Lapointe G, Ménard L, et al. (2006) Les nanoparticules:´Etat des connaissances sur les risques en santé et sécurité du travail, Rapport IRSST Soumis, IRSST, MontréalGoogle Scholar
  26. 26.
    Gimbert LJ, Hamon RE, Casey PS, Worsfold PJ (2007) Partitioning and stability of engineered ZnO nanoparticles in soil suspensions using flow field-flow fractionation. Environ Chem 4(1):8–10CrossRefGoogle Scholar
  27. 27.
    Borm PJA (2003) Toxicology of ultrafine particles. Rapport d’un atelier du BIA sur ultrafine aerosols at workplaces. BIA Report, Berufsgenossenschaftliches Institut für ArbeitsschutzGoogle Scholar
  28. 28.
    Guzman KAD, Finnegan MP, Banfield JF (2006) Influence of surface potential on aggregation and transport of titania nanoparticles. Environ Sci Technol 40(24):7688–7693PubMedCrossRefGoogle Scholar
  29. 29.
    Yan X, Sedykh A, Wang W et al (2019) In silico profiling nanoparticles: predictive nanomodeling using universal nanodescriptors and various machine learning approaches. Nanoscale 11:8352–8362. Scholar
  30. 30.
    Delaunay M (1924) Sur la sphère vide. Congrès International des Mathématiciens, Toronto, Canada pp 695–700Google Scholar
  31. 31.
    Wang W, Sedykh A, Sun H et al (2017) Predicting nano-bio interactions by integrating nanoparticle libraries and quantitative nanostructure activity relationship modeling. ACS Nano 11:12641–12649PubMedPubMedCentralCrossRefGoogle Scholar
  32. 32.
    Quintero FA, Patel SJ, Munõz F et al (2012) Review of existing QSAR/QSPR models developed for properties used in hazardous chemicals classification system. Ind Eng Chem Res 51(49):16101–16115CrossRefGoogle Scholar
  33. 33.
    Lewis RA, Wood D (2014) Modern 2D QSAR for drug discovery. Wiley Interdiscip Rev Comput Mol Sci 4(6):505–522CrossRefGoogle Scholar
  34. 34.
    Ghanem OB, Mutalib MIA, Lévêque J-M et al (2017) Development of QSAR model to predict the ecotoxicity of Vibrio fischeri using COSMO-RS descriptors. Chemosphere 170:242–250PubMedPubMedCentralCrossRefGoogle Scholar
  35. 35.
    Husowitz B, Sanchez-Arias R (2017) A machine learning approach to designing guidelines for acute aquatic toxicity. J Biom Biostat 8:385. Scholar
  36. 36.
    Kausar S, Falcao AO (2018) An automated framework for QSAR model building. J Cheminform 10(1).
  37. 37.
    Kulacki KJ, Lamberti GA (2008) Toxicity of imidazolium ionic liquids to fresh water algae. Green Chem 10:104–110CrossRefGoogle Scholar
  38. 38.
    Latala A, Nedzi M, Stepnowski P (2009) Toxicity of imidazolium and pyridinium based ionic liquids towards algae, Chlorella vulgaris, Oocystis submarina (green algae) and Cyclotella meneghiniana, Skeletonema marinoi (diatoms). Green Chem 11:580–588CrossRefGoogle Scholar
  39. 39.
    Pretti C, Chiappe C, Baldetti L et al (2009) Acute toxicity of ionic liquids for three freshwater organisms: pseudokirchneriella subcapitata, Daphnia magna and Dario rerio. Ecotoxicol Environ Saf 72:1170–1176PubMedCrossRefPubMedCentralGoogle Scholar
  40. 40.
    Costa SP, Justina VD, Bica K et al (2014) Automated evaluation of pharmaceutically active ionic liquids’(eco) toxicity through inhibition of human carboxylesterase and Vibrio fischeri. J Hazard Mater 265:133–141PubMedCrossRefGoogle Scholar
  41. 41.
    Viboud S, Papaiconomou N, Cortsei A et al (2012) Correlating the structure and composition of ionic liquids with their toxicity in Vibrio fischeri: a systematic study. J Hazard Mater 215:40–48PubMedCrossRefGoogle Scholar
  42. 42.
    Stolte S, Matzke M, Arning J et al (2007) Effects of different head groups and functionalized side chains on the aquatic toxicity of ionic liquids. Green Chem 9:1170–1179CrossRefGoogle Scholar
  43. 43.
    Radosevic K, Cvjetko M, Kopjar M et al (2013) In vitro cytotoxicity assessment of imidazolium ionic liquids: biological effects in fish channel catfish ovary (CCO) cell line. Ecotoxicol Environ Saf 92:112–118PubMedCrossRefGoogle Scholar
  44. 44.
    Dong M, Zhu S, Wang J et al (2013) Toxic effects of 1-decyl-3-methylimidazolium bromide ionic liquid on the antioxidantenzyme system and DNA in zebrafish (Danio rerio) livers. Chemosphere 91:1107–1112PubMedCrossRefGoogle Scholar
  45. 45.
    Holden PA, Nisbet RM, Lenihan HS et al (2013) Ecological nanotoxicology: integrating nanomaterial hazard considerations across the subcellular, population, community, and ecosystems levels. Acc Chem Res 46:813–822PubMedCrossRefGoogle Scholar
  46. 46.
    Gonzalez-Diaz H, Arrasate S, Gomez-SanJuan A et al (2013) General theory for multiple input-output perturbations in complex molecular systems. 1. Linear QSPR electronegativity models in physical, organic, and medicinal chemistry. Curr Top Med Chem 13:1713–1741PubMedCrossRefGoogle Scholar
  47. 47.
    Kleandrova VV, Luan F, Gonzalez-Diaz H et al (2014) Computational ecotoxicology: simultaneous prediction of Ecotoxic effects of nanoparticles under different experimental conditions. Environ Int 73C:288–294CrossRefGoogle Scholar
  48. 48.
    Kleandrova VV, Luan F, Gonzalez-Diaz H et al (2014) Computational tool for risk assessment of nanomaterials: novel QSTR-perturbation model for simultaneous prediction of Ecotoxicity and cytotoxicity of uncoated and coated nanoparticles under multiple experimental conditions. Environ Sci Technol 48:14686–14694PubMedCrossRefGoogle Scholar
  49. 49.
    Luan F, Kleandrova VV, Gonzalez-Diaz H et al (2014) Computer-aided nanotoxicology: assessing cytotoxicity of nanoparticles under diverse experimental conditions by using a novel QSTR-perturbation approach. Nanoscale 6:10623–10630PubMedCrossRefGoogle Scholar
  50. 50.
    Concu R, Kleandrova VV, Speck-Planche A et al (2017) Probing the toxicity of nanoparticles: a unified in silico machine learning model based on perturbation theory. Nanotoxicology 11(7):891–906PubMedCrossRefGoogle Scholar
  51. 51.
    Kato T (1995) Perturbation theory in a finite-dimensional space. In: Perturbation theory for linear operators, (Reprint of the 1980 edn). Springer, BerlinGoogle Scholar
  52. 52.
    Concu R, Dea-Ayuela MA, Perez-Montoto LG et al (2009) 3D entropy and moments prediction of enzyme classes and experimental – theoretic study of peptide fingerprints in Leishmania parasites. Biochim Biophys Acta 1794:1784–1794PubMedCrossRefGoogle Scholar
  53. 53.
    Concu R, Podda G, Uriarte E et al (2009) Computational chemistry study of 3Dstructure–function relationships for enzymes based on Markov models for protein electrostatic, HINT, and van der Waals potentials. J Comput Chem 30:1510–1520PubMedCrossRefGoogle Scholar
  54. 54.
    García A, Espinosa R, Delgado L et al (2011) Acute toxicity of cerium oxide, titanium oxide and iron oxide nanoparticles using standardized tests. Desalination 269:136–141CrossRefGoogle Scholar
  55. 55.
    Hill T, Lewicki P (2006) Statistics methods and applications. A comprehensive reference for science, industry and data mining. StatSoft, TulsaGoogle Scholar
  56. 56.
    Tenorio-Borroto E, Garcia-Mera X, Penuelas-Rivas CG et al (2013) Entropy model for multiplex drug-target interaction endpoints of drug immunotoxicity. Curr Top Med Chem 13:1636–1649PubMedCrossRefGoogle Scholar
  57. 57.
    Statsoft-Team (2001) Statistica. Data analysis software system. v6.0. TulsaGoogle Scholar
  58. 58.
    González-Díaz H, Pérez-Bello A, Cruz-Monteagudo M et al (2007) Chemometrics for QSAR with low sequence homology: mycobacterial promoter sequences recognition with 2DRNA entropies. Chemom Intell Lab Syst 85:20–26CrossRefGoogle Scholar
  59. 59.
    Hanczar B, Hua J, Sima C et al (2010) Small-sample precision of ROC-related estimates. Bioinformatics 26:822–830PubMedCrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2020

Authors and Affiliations

  1. 1.LAQV-REQUIMTE, Department of Chemistry and Biochemistry, Faculdade de CiênciasUniversidade do PortoPortoPortugal

Personalised recommendations