Advanced search
Publication Cover
Nanotoxicology Volume 12, 2018 - Issue 1
Submit an article Journal homepage
3,108
Views
50
CrossRef citations to date
0
Altmetric
Article

Decision tree models to classify nanomaterials according to the DF4nanoGrouping scheme

Agnieszka GajewiczLaboratory of Environmental Chemometrics, Faculty of Chemistry, University of Gdansk, Gdansk, Poland; View further author information
,
Tomasz PuzynLaboratory of Environmental Chemometrics, Faculty of Chemistry, University of Gdansk, Gdansk, Poland; View further author information
,
Katarzyna OdziomekLaboratory of Environmental Chemometrics, Faculty of Chemistry, University of Gdansk, Gdansk, Poland; View further author information
,
Piotr UrbaszekLaboratory of Environmental Chemometrics, Faculty of Chemistry, University of Gdansk, Gdansk, Poland; View further author information
,
Andrea HaaseGerman Federal Institute for Risk Assessment (BfR), Department of Chemical and Product Safety, Berlin, Germany; View further author information
,
Christian RiebelingGerman Federal Institute for Risk Assessment (BfR), Department of Chemical and Product Safety, Berlin, Germany; View further author information
,
Andreas LuchGerman Federal Institute for Risk Assessment (BfR), Department of Chemical and Product Safety, Berlin, Germany; View further author information
,
Muhammad A. IrfanDepartment of Experimental Toxicology and Ecology, BASF SE, Ludwigshafen, Germany; View further author information
,
Robert LandsiedelDepartment of Experimental Toxicology and Ecology, BASF SE, Ludwigshafen, Germany; View further author information
,
Meike van der ZandeRIKILT – Wageningen University and Research, Wageningen, The NetherlandsView further author information
&
Hans BouwmeesterRIKILT – Wageningen University and Research, Wageningen, The NetherlandsCorrespondence[email protected]
View further author information
 show all
Pages 1-17 | Received 30 May 2017, Accepted 05 Dec 2017, Published online: 18 Dec 2017

Figures & data

Table 1. Experimentally determined physicochemical properties.

Figure 1. Confusion matrix describing the performance of a classification model (or ‘classifier’) on a set of test data for which the true values are known.

Figure 1. Confusion matrix describing the performance of a classification model (or ‘classifier’) on a set of test data for which the true values are known.

Table 2. Nanomaterial surface coatings.

Table 3. Summary of the nanomaterial intrinsic oxidative potential, protein carbonylation, and NOAECs derived from short-term inhalation studies (STIS).

Table 4. Activity in protein carbonylation assay.

Figure 2. Classification tree for the protein carbonylation assay. Active nanomaterials are indicated with red; inactive with green color. Please note that the classification tree uses the auto scaled values of the descriptors. Thus, size≥ −0.41 corresponds to 12.5 nm and SSA≥ −1.4 corresponds to 47.9 m2/g.

Figure 2. Classification tree for the protein carbonylation assay. Active nanomaterials are indicated with red; inactive with green color. Please note that the classification tree uses the auto scaled values of the descriptors. Thus, size≥ −0.41 corresponds to 12.5 nm and SSA≥ −1.4 corresponds to 47.9 m2/g.

Table 5. Validation of the model robustness (protein carbonylation assay).

Table 6. Original and consensus fuzzy predictions of protein carbonylation for untested nanomaterials.

Figure 3. Classification tree for nanomaterial intrinsic oxidative potential. Active nanomaterials are indicated with red; inactive with green color. Please note that the classification tree uses the auto scaled values of the descriptors. Thus, size≥ −0.41 corresponds to 23.83 nm.

Figure 3. Classification tree for nanomaterial intrinsic oxidative potential. Active nanomaterials are indicated with red; inactive with green color. Please note that the classification tree uses the auto scaled values of the descriptors. Thus, size≥ −0.41 corresponds to 23.83 nm.

Table 7. Nanomaterial intrinsic oxidative potential.

Table 8. Validation of model robustness (nanomaterial intrinsic oxidative potential).

Table 9. Original and consensus fuzzy predictions of nanomaterial intrinsic oxidative potential for untested nanomaterials.

Figure 4. Classification tree for a short-term inhalation study in rats. Active nanomaterials are indicated with red; inactive with green color. Please note that the classification tree uses the auto scaled values of the descriptors. Thus, LUMO_C< −0.61 corresponds to −2.40 eV; SSA ≥0.99 corresponds to 158.48 m2/g, and Shelpres <0.05 to the value of 0.5.

Figure 4. Classification tree for a short-term inhalation study in rats. Active nanomaterials are indicated with red; inactive with green color. Please note that the classification tree uses the auto scaled values of the descriptors. Thus, LUMO_C< −0.61 corresponds to −2.40 eV; SSA ≥0.99 corresponds to 158.48 m2/g, and Shelpres <0.05 to the value of 0.5.

Table 10. Activity in a short-term inhalation study in rats.

Table 11. Validation of model robustness (a short-term inhalation study in rats).

Table 12. Original and consensus fuzzy predictions of activity in a short-term inhalation study in rats for untested nanomaterials.

Supplemental material

A._GAJEWICZ_ET_AL_Supplementary_content.zip

Download Zip (85.5 KB)

Related Research Data

Decision tree models to classify nanomaterials according to the DF4nanoGrouping scheme
Source: Figshare
Decision tree models to classify nanomaterials according to the DF4nanoGrouping scheme
Source: Figshare

Linking provided by 

Related research

People also read lists articles that other readers of this article have read.

Recommended articles lists articles that we recommend and is powered by our AI driven recommendation engine.

Cited by lists all citing articles based on Crossref citations.
Articles with the Crossref icon will open in a new tab.