| 1. |
- Johansson, Henrik, et al.
(författare)
-
Genomic Allergen Rapid Detection In-House Validation—A Proof of Concept
- 2014
-
Ingår i: Toxicological Sciences. - : Oxford University Press (OUP). - 1096-0929 .- 1096-6080. ; 139:2, s. 362-370
-
Tidskriftsartikel (refereegranskat)abstract
- Chemical sensitization is an adverse immunologic response to chemical substances, inducing hypersensitivity in exposed individuals. Identifying chemical sensitizers is of great importance for chemical, pharmaceutical and cosmetic industry, in order to prevent the use of sensitizers in consumer products. Historically, chemical sensitizers have been assessed mainly by in vivo methods, however, recently enforced European legislations urge and promote the development of animal-free test methods able to predict chemical sensitizers. Recently, we presented a predictive biomarker signature in the myeloid cell line MUTZ-3, for assessment of skin sensitizers. The identified genomic biomarkers were found to be involved in immunologically relevant pathways, induced by recognition of foreign substances and regulating dendritic cell maturation and cytoprotective mechanisms. We have developed the usage of this biomarker signature into a novel in vitro assay for assessment of chemical sensitizers, called Genomic Allergen Rapid Detection, GARD. The assay is based on chemical stimulation of MUTZ-3 cultures, using the compounds to be assayed as stimulatory agents. The readout of the assay is a transcriptional quantification of the genomic predictors, collectively termed the GARD Prediction Signature, using a complete genome expression array. Compounds are predicted as either sensitizers or non-sensitizers by a Support Vector Machine model. In this report, we provide a proof of concept for the functionality of the GARD assay by describing the classification of 26 blinded and 11 non-blinded chemicals as sensitizers or non-sensitizers. Based on these classifications, the accuracy, sensitivity and specificity of the assay was estimated to 89%, 89% and 88%, respectively.
|
|
| 2. |
- Wilm, Anke, et al.
(författare)
-
Predicting the Skin Sensitization Potential of Small Molecules with Machine Learning Models Trained on Biologically Meaningful Descriptors
- 2021
-
Ingår i: Pharmaceuticals. - : MDPI. - 1424-8247. ; 14:8
-
Tidskriftsartikel (refereegranskat)abstract
- In recent years, a number of machine learning models for the prediction of the skin sensitization potential of small organic molecules have been reported and become available. These models generally perform well within their applicability domains but, as a result of the use of molecular fingerprints and other non-intuitive descriptors, the interpretability of the existing models is limited. The aim of this work is to develop a strategy to replace the non-intuitive features by predicted outcomes of bioassays. We show that such replacement is indeed possible and that as few as ten interpretable, predicted bioactivities are sufficient to reach competitive performance. On a holdout data set of 257 compounds, the best model ("Skin Doctor CP:Bio") obtained an efficiency of 0.82 and an MCC of 0.52 (at the significance level of 0.20). Skin Doctor CP:Bio is available free of charge for academic research. The modeling strategies explored in this work are easily transferable and could be adopted for the development of more interpretable machine learning models for the prediction of the bioactivity and toxicity of small organic compounds.
|
|
| 3. |
- Wilm, Anke, et al.
(författare)
-
Skin Doctor CP : Conformal Prediction of the Skin Sensitization Potential of Small Organic Molecules
- 2021
-
Ingår i: Chemical Research in Toxicology. - : ACS Publications. - 0893-228X .- 1520-5010. ; 34:2, s. 330-344
-
Tidskriftsartikel (refereegranskat)abstract
- Skin sensitization potential or potency is an important end point in the safety assessment of new chemicals and new chemical mixtures. Formerly, animal experiments such as the local lymph node assay (LLNA) were the main form of assessment. Today, however, the focus lies on the development of nonanimal testing approaches (i.e., in vitro and in chemico assays) and computational models. In this work, we investigate, based on publicly available LLNA data, the ability of aggregated, Mondrian conformal prediction classifiers to differentiate between non- sensitizing and sensitizing compounds as well as between two levels of skin sensitization potential (weak to moderate sensitizers, and strong to extreme sensitizers). The advantage of the conformal prediction framework over other modeling approaches is that it assigns compounds to activity classes only if a defined minimum level of confidence is reached for the individual predictions. This eliminates the need for applicability domain criteria that often are arbitrary in their nature and less flexible. Our new binary classifier, named Skin Doctor CP, differentiates nonsensitizers from sensitizers with a higher reliability-to-efficiency ratio than the corresponding nonconformal prediction workflow that we presented earlier. When tested on a set of 257 compounds at the significance levels of 0.10 and 0.30, the model reached an efficiency of 0.49 and 0.92, and an accuracy of 0.83 and 0.75, respectively. In addition, we developed a ternary classification workflow to differentiate nonsensitizers, weak to moderate sensitizers, and strong to extreme sensitizers. Although this model achieved satisfactory overall performance (accuracies of 0.90 and 0.73, and efficiencies of 0.42 and 0.90, at significance levels 0.10 and 0.30, respectively), it did not obtain satisfying class-wise results (at a significance level of 0.30, the validities obtained for nonsensitizers, weak to moderate sensitizers, and strong to extreme sensitizers were 0.70, 0.58, and 0.63, respectively). We argue that the model is, in consequence, unable to reliably identify strong to extreme sensitizers and suggest that other ternary models derived from the currently accessible LLNA data might suffer from the same problem. Skin Doctor CP is available via a public web service at https://nerdd.zbh.uni-hamburg.de/skinDoctorII/.
|
|
