Predicting full thickness skin sensitization using a support vector machine

Prediction of skin sensitization using machine learning

As global awareness of animal welfare spreads, the development of alternative animal test models is increasingly necessary. The purpose of this study was to develop a practical machine-learning model for skin sensitization using three physicochemical properties of the chemicals: surface tension, melting point, and molecular weight. In this study, a total of 482 chemicals with local lymph node assay results were collected, and 297 datasets with 6 physico-chemical properties were used to develop Random Forest (RF) model for skin sensitization. The developed model was validated with 45 fragrance allergens announced by European Commission. The validation results showed that RF achieved better or similar classification performance with f1-scores of 54% for penal, 82% for ternary, and 96% for binary compared with Support Vector Machine (SVM) (penal, 41%; ternary, 81%; binary, 93%), QSARs (ChemTunes, 72% for ternary; OECD Toolbox, 89% for binary), and a linear model (Kim et al., 2020) (41% for penal), and we recommend the ternary classification based on Global Harmonized System providing more detailed and precise information. In the further study, the proposed model results were experimentally validated with the Direct Peptide Reactivity Assay (DPRA, OECD TG 442C approved model), and the results showed a similar tendency. We anticipate that this study will help to easily and quickly screen chemical sensitization hazards.

The Overt and Hidden Use of Animal-Derived Products in Alternative Methods for Skin Sensitisation: A Systematic Review

In vitro methods that can replace animal testing in the identification of skin sensitisers are now a reality. However, as cell culture and related techniques usually rely on animal-derived products, these methods may be failing to address the complete replacement of animals in safety assessment. The objective of this study was to identify the animal-derived products that are used as part of in vitro methods for skin sensitisation testing. Thus, a systematic review of 156 articles featuring 83 different in vitro methods was carried out and, from this review, the use of several animal-derived products from different species was identified, with the use of fetal bovine serum being cited in most of the methods (78%). The use of sera from other animals, monoclonal antibodies and animal proteins were also variously mentioned. While non-animal alternatives are available and methods free of animal-derived products are emerging, most of the current methods reported used at least one animal-derived product, which raises ethical and technical concerns. Therefore, to deliver technically and ethically better in vitro methods for the safety assessment of chemicals, more effort should be made to replace products of animal origin in existing methods and to avoid their use in the development of new method protocols.

Characterization of a New Reconstructed Full Thickness Skin Model, T-Skin™, and its Application for Investigations of Anti-Aging Compounds

BACKGROUND

We have characterized a new reconstructed full-thickness skin model, T-Skin™, compared to normal human skin (NHS) and evaluated its use in testing anti-aging compounds.

METHODS

The structure and layer-specific markers were compared with NHS using histological and immunohistological staining. In anti-aging experiments, T-SkinTM was exposed to retinol (10 µM) or vitamin C (200 µM) for 5 days, followed by immunohistological staining evaluation.

RESULTS

T-Skin™ exhibits a well stratified, differentiated and self-renewing epidermis with a dermal compartment of functional fibroblasts. Epidermal (cytokeratin 10, transglutaminase 1), dermo-epidermal junction (DEJ) (laminin 5, collagen-IV, collagen VII) and dermally-located (fibrillin 1, procollagen I) biomarkers were similar to those in NHS. Treatment of T-Skin™ with retinol decreased the expression of differentiation markers, cytokeratin 10 and transglutaminase 1 and increased the proliferation marker, Ki67, in epidermis basal-layer cells. Vitamin C increased the expression of DEJ components, collagen IV and VII and dermal procollagen 1.

CONCLUSIONS

T-Skin™ exhibits structural and biomarker location characteristics similar to NHS. Responses of T-Skin™ to retinol and vitamin C treatment were consistent with those of their known anti-aging effects. T-Skin™ is a promising model to investigate responses of epidermal, DEJ and dermal regions to new skin anti-ageing compounds.

Tri-culture system for pro-hapten sensitizer identification and potency classification

Allergic contact dermatitis (ACD) is an inflammatory disease that impacts 15-20% of the general population and accurate screening methods for chemical risk assessment are needed. However, most approaches poorly predict pre- and pro-hapten sensitizers, which require abiotic or metabolic conversion prior to inducing sensitization. We developed a tri-culture system comprised of MUTZ-3-derived Langerhans cells, HaCaT keratinocytes, and primary dermal fibroblasts to mimic the cellular and metabolic environments of skin sensitization. A panel of non-sensitizers and sensitizers was tested and the secretome was evaluated. A support vector machine (SVM) was used to identify the most predictive sensitization signature and classification trees identified statistical thresholds to predict sensitizer potency. The SVM computed 91% tri-culture prediction accuracy using the top 3 ranking biomarkers (IL-8, MIP-1β, and GM-CSF) and improved the detection of pre- and pro-haptens. This in vitro assay combined with in silico data analysis presents a promising approach and offers the possibility of multi-metric analysis for enhanced ACD sensitizer screening.

Alternatives to animal testing in basic and preclinical research of atopic dermatitis

Atopic dermatitis (AD) is a chronic inflammatory skin disease of increasing prevalence, especially in industrialized countries. Roughly 25% of the children and 1%-3% of adults are affected. Although significant progress has been made in the understanding of the pathogenesis of AD, many aspects remain poorly understood. Moreover, there is a pressing need for improved therapeutic options. Studies to elucidate the pathophysiological pathways of AD and to identify novel therapeutic targets over the last few decades have been conducted almost exclusively in animal models. However, in vitro approaches such as 3D skin disease models have recently emerged due to an increasing awareness of distinct interspecies-related differences that hamper the effective translation of results from animal models to humans. In addition, there is growing political and social pressure to develop alternatives to animal models according to the 3Rs principle (reduction, refinement and replacement of animal models).

Characterization of reconstructed human skin containing Langerhans cells to monitor molecular events in skin sensitization

Human cell-based approaches to assess defined key events in allergic contact dermatitis (ACD) are well-established, but lack cutaneous penetration and biotransformation as well as cellular cross-talk. Herein, we integrated in vitro-generated immature MUTZ-3-derived Langerhans-like cells (MUTZ-LCs) or monocyte-derived LC-like cells (MoLCs) into reconstructed human skin (RHS), consistent of a stratified epidermis formed by primary keratinocytes on a dermal compartment with collagen-embedded primary fibroblasts. LC-like cells were mainly localized in the epidermal compartment and distributed homogenously in accordance with native human skin. Topical application of the strong contact sensitizer 2,4-dinitrochlorobenzene (DNCB) induced IL-6 and IL-8 secretion in RHS with LC-like cells, whereas no change was observed in reference models. Increased gene expression of CD83, PD-L1, and CXCR4 in the dermal compartment indicated LC maturation. Importantly, exposure to DNCB enhanced mobility of the LC-like cells from epidermal to dermal compartments. In response to the moderate sensitizer isoeugenol and irritant sodium dodecyl sulphate, the obtained response was less pronounced. In summary, we integrated immature and functional MUTZ-LCs and MoLCs into RHS and provide a unique comparative experimental setting to monitor early events during skin sensitization.