Machine learning and materials modelling interpretation of: In vivo toxicological response to TiO2nanoparticles library (UV and non-UV exposure)

Susana I.L. Gomes; Mónica J.B. Amorim; Suman Pokhrel; Lutz Mädler; Matteo Fasano; Eliodoro Chiavazzo; Pietro Asinari; Jaak Jänes; Kaido Tämm; Jaanus Burk; Janeck J. Scott-Fordsmand

doi:10.1039/d1nr03231c

Machine learning and materials modelling interpretation of: In vivo toxicological response to TiO₂nanoparticles library (UV and non-UV exposure)

Susana I.L. Gomes, Mónica J.B. Amorim^*, Suman Pokhrel, Lutz Mädler, Matteo Fasano, Eliodoro Chiavazzo, Pietro Asinari, Jaak Jänes, Kaido Tämm, Jaanus Burk, Janeck J. Scott-Fordsmand

^*Corresponding author for this work

Research output: Contribution to journal/Conference contribution in journal/Contribution to newspaper › Journal article › Research › peer-review

14 Citations (Scopus)

64 Downloads (Pure)

Abstract

Assessing the risks of nanomaterials/nanoparticles (NMs/NPs) under various environmental conditions requires a more systematic approach, including the comparison of effects across many NMs with identified different but related characters/descriptors. Hence, there is an urgent need to provide coherent (eco)toxicological datasets containing comprehensive toxicity information relating to a diverse spectra of NPs characters. These datasets are test benches for developing holistic methodologies with broader applicability. In the present study we assessed the effects of a custom design Fe-doped TiO2 NPs library, using the soil invertebrate Enchytraeus crypticus (Oligochaeta), via a 5-day pulse via aqueous exposure followed by a 21-days recovery period in soil (survival, reproduction assessment). Obviously, when testing TiO2, realistic conditions should include UV exposure. The 11 Fe-TiO2 library contains NPs of size range between 5-27 nm with varying %Fe (enabling the photoactivation of TiO2 at energy wavelengths in the visible-light range). The NPs were each described by 122 descriptors, being a mixture of measured and atomistic model descriptors. The data were explored using single and univariate statistical methods, combined with machine learning and multiscale modelling techniques. An iterative pruning process was adopted for identifying automatically the most significant descriptors. TiO2 NPs toxicity decreased when combined with UV. Notably, the short-term water exposure induced lasting biological responses even after longer-term recovery in clean exposure. The correspondence with Fe-content correlated with the band-gap hence the reduction of UV oxidative stress. The inclusion of both measured and modelled materials data benefitted the explanation of the results, when combined with machine learning. This journal is

Original language	English
Journal	Nanoscale
Volume	13
Issue	35
Pages (from-to)	14666-14678
ISSN	2040-3364
DOIs	https://doi.org/10.1039/d1nr03231c
Publication status	Published - Sept 2021

Access to Document

10.1039/d1nr03231c

d1nr03231cFinal published version, 4.53 MBLicence: CC BY-NC

Cite this

Gomes, S. I. L., Amorim, M. J. B., Pokhrel, S., Mädler, L., Fasano, M., Chiavazzo, E., Asinari, P., Jänes, J., Tämm, K., Burk, J., & Scott-Fordsmand, J. J. (2021). Machine learning and materials modelling interpretation of: In vivo toxicological response to TiO₂nanoparticles library (UV and non-UV exposure). Nanoscale, 13(35), 14666-14678. https://doi.org/10.1039/d1nr03231c

@article{b5451a5aa9d64dc0a354104a4c9559b7,

title = "Machine learning and materials modelling interpretation of: In vivo toxicological response to TiO2nanoparticles library (UV and non-UV exposure)",

abstract = "Assessing the risks of nanomaterials/nanoparticles (NMs/NPs) under various environmental conditions requires a more systematic approach, including the comparison of effects across many NMs with identified different but related characters/descriptors. Hence, there is an urgent need to provide coherent (eco)toxicological datasets containing comprehensive toxicity information relating to a diverse spectra of NPs characters. These datasets are test benches for developing holistic methodologies with broader applicability. In the present study we assessed the effects of a custom design Fe-doped TiO2 NPs library, using the soil invertebrate Enchytraeus crypticus (Oligochaeta), via a 5-day pulse via aqueous exposure followed by a 21-days recovery period in soil (survival, reproduction assessment). Obviously, when testing TiO2, realistic conditions should include UV exposure. The 11 Fe-TiO2 library contains NPs of size range between 5-27 nm with varying %Fe (enabling the photoactivation of TiO2 at energy wavelengths in the visible-light range). The NPs were each described by 122 descriptors, being a mixture of measured and atomistic model descriptors. The data were explored using single and univariate statistical methods, combined with machine learning and multiscale modelling techniques. An iterative pruning process was adopted for identifying automatically the most significant descriptors. TiO2 NPs toxicity decreased when combined with UV. Notably, the short-term water exposure induced lasting biological responses even after longer-term recovery in clean exposure. The correspondence with Fe-content correlated with the band-gap hence the reduction of UV oxidative stress. The inclusion of both measured and modelled materials data benefitted the explanation of the results, when combined with machine learning. This journal is ",

author = "Gomes, {Susana I.L.} and Amorim, {M{\'o}nica J.B.} and Suman Pokhrel and Lutz M{\"a}dler and Matteo Fasano and Eliodoro Chiavazzo and Pietro Asinari and Jaak J{\"a}nes and Kaido T{\"a}mm and Jaanus Burk and Scott-Fordsmand, {Janeck J.}",

note = "Publisher Copyright: {\textcopyright} The Royal Society of Chemistry.",

year = "2021",

month = sep,

doi = "10.1039/d1nr03231c",

language = "English",

volume = "13",

pages = "14666--14678",

journal = "Nanoscale",

issn = "2040-3364",

publisher = "Royal Society of Chemistry",

number = "35",

}

Gomes, SIL, Amorim, MJB, Pokhrel, S, Mädler, L, Fasano, M, Chiavazzo, E, Asinari, P, Jänes, J, Tämm, K, Burk, J & Scott-Fordsmand, JJ 2021, 'Machine learning and materials modelling interpretation of: In vivo toxicological response to TiO₂nanoparticles library (UV and non-UV exposure)', Nanoscale, vol. 13, no. 35, pp. 14666-14678. https://doi.org/10.1039/d1nr03231c

Machine learning and materials modelling interpretation of: In vivo toxicological response to TiO₂nanoparticles library (UV and non-UV exposure). / Gomes, Susana I.L.; Amorim, Mónica J.B.; Pokhrel, Suman et al.
In: Nanoscale, Vol. 13, No. 35, 09.2021, p. 14666-14678.

Research output: Contribution to journal/Conference contribution in journal/Contribution to newspaper › Journal article › Research › peer-review

TY - JOUR

T1 - Machine learning and materials modelling interpretation of

T2 - In vivo toxicological response to TiO2nanoparticles library (UV and non-UV exposure)

AU - Gomes, Susana I.L.

AU - Amorim, Mónica J.B.

AU - Pokhrel, Suman

AU - Mädler, Lutz

AU - Fasano, Matteo

AU - Chiavazzo, Eliodoro

AU - Asinari, Pietro

AU - Jänes, Jaak

AU - Tämm, Kaido

AU - Burk, Jaanus

AU - Scott-Fordsmand, Janeck J.

PY - 2021/9

Y1 - 2021/9

N2 - Assessing the risks of nanomaterials/nanoparticles (NMs/NPs) under various environmental conditions requires a more systematic approach, including the comparison of effects across many NMs with identified different but related characters/descriptors. Hence, there is an urgent need to provide coherent (eco)toxicological datasets containing comprehensive toxicity information relating to a diverse spectra of NPs characters. These datasets are test benches for developing holistic methodologies with broader applicability. In the present study we assessed the effects of a custom design Fe-doped TiO2 NPs library, using the soil invertebrate Enchytraeus crypticus (Oligochaeta), via a 5-day pulse via aqueous exposure followed by a 21-days recovery period in soil (survival, reproduction assessment). Obviously, when testing TiO2, realistic conditions should include UV exposure. The 11 Fe-TiO2 library contains NPs of size range between 5-27 nm with varying %Fe (enabling the photoactivation of TiO2 at energy wavelengths in the visible-light range). The NPs were each described by 122 descriptors, being a mixture of measured and atomistic model descriptors. The data were explored using single and univariate statistical methods, combined with machine learning and multiscale modelling techniques. An iterative pruning process was adopted for identifying automatically the most significant descriptors. TiO2 NPs toxicity decreased when combined with UV. Notably, the short-term water exposure induced lasting biological responses even after longer-term recovery in clean exposure. The correspondence with Fe-content correlated with the band-gap hence the reduction of UV oxidative stress. The inclusion of both measured and modelled materials data benefitted the explanation of the results, when combined with machine learning. This journal is

AB - Assessing the risks of nanomaterials/nanoparticles (NMs/NPs) under various environmental conditions requires a more systematic approach, including the comparison of effects across many NMs with identified different but related characters/descriptors. Hence, there is an urgent need to provide coherent (eco)toxicological datasets containing comprehensive toxicity information relating to a diverse spectra of NPs characters. These datasets are test benches for developing holistic methodologies with broader applicability. In the present study we assessed the effects of a custom design Fe-doped TiO2 NPs library, using the soil invertebrate Enchytraeus crypticus (Oligochaeta), via a 5-day pulse via aqueous exposure followed by a 21-days recovery period in soil (survival, reproduction assessment). Obviously, when testing TiO2, realistic conditions should include UV exposure. The 11 Fe-TiO2 library contains NPs of size range between 5-27 nm with varying %Fe (enabling the photoactivation of TiO2 at energy wavelengths in the visible-light range). The NPs were each described by 122 descriptors, being a mixture of measured and atomistic model descriptors. The data were explored using single and univariate statistical methods, combined with machine learning and multiscale modelling techniques. An iterative pruning process was adopted for identifying automatically the most significant descriptors. TiO2 NPs toxicity decreased when combined with UV. Notably, the short-term water exposure induced lasting biological responses even after longer-term recovery in clean exposure. The correspondence with Fe-content correlated with the band-gap hence the reduction of UV oxidative stress. The inclusion of both measured and modelled materials data benefitted the explanation of the results, when combined with machine learning. This journal is

UR - http://www.scopus.com/inward/record.url?scp=85115629259&partnerID=8YFLogxK

U2 - 10.1039/d1nr03231c

DO - 10.1039/d1nr03231c

M3 - Journal article

C2 - 34533558

AN - SCOPUS:85115629259

SN - 2040-3364

VL - 13

SP - 14666

EP - 14678

JO - Nanoscale

JF - Nanoscale

IS - 35

ER -

Machine learning and materials modelling interpretation of: In vivo toxicological response to TiO₂nanoparticles library (UV and non-UV exposure)

Abstract

Access to Document

Other files and links

Fingerprint

Cite this