MicotoXilico: An Interactive Database to Predict Mutagenicity, Genotoxicity, and Carcinogenicity of Mycotoxins

Abstract

Mycotoxins are secondary metabolites produced by certain filamentous fungi. They are common contaminants found in a wide variety of food matrices, thus representing a threat to public health, as they can be carcinogenic, mutagenic, or teratogenic, among other toxic effects. Several hundreds of mycotoxins have been reported, but only a few of them are regulated, due to the lack of data regarding their toxicity and mechanisms of action. Thus, a more comprehensive evaluation of the toxicity of mycotoxins found in foodstuffs is required. In silico toxicology approaches, such as Quantitative Structure-Activity Relationship (QSAR) models, can be used to rapidly assess chemical hazards by predicting different toxicological endpoints. In this work, for the first time, a comprehensive database containing 4360 mycotoxins classified in 170 categories was constructed. Then, specific robust QSAR models for the prediction of mutagenicity, genotoxicity, and carcinogenicity were generated, showing good accuracy, precision, sensitivity, and specificity. It must be highlighted that the developed QSAR models are compliant with the OECD regulatory criteria, and they can be used for regulatory purposes. Finally, all data were integrated into a web server that allows the exploration of the mycotoxin database and toxicity prediction. In conclusion, the developed tool is a valuable resource for scientists, industry, and regulatory agencies to screen the mutagenicity, genotoxicity, and carcinogenicity of non-regulated mycotoxins.

Keywords: QSAR; carcinogenicity; genotoxicity; mutagenicity; mycotoxins.

Figure 1

TMAP clustering graph of the database containing 4360 mycotoxins. The most important categories are labelled in different colors. For an interactive exploration of all categories, please visit MicotoXilico (https://chemopredictionsuite.com/MicotoXilico, accessed on 20 May 2023).

Figure 2

Metrics for QSAR models of (a) mutagenicity model A, (b) mutagenicity model B, (c) in vitro genotoxicity, (d) in vivo genotoxicity, and (e) carcinogenicity. ACC: accuracy; PREC: precision; SENS: sensitivity; AUC: area under the curve; SPEC: specificity; LGBM: Light Gradient Boosting Machine Classifier; LR: logistic regression; RFE: recursive feature elimination; SVC: Support Vector Machine Classifier (SVC).

Figure 3

Matrix confusion for the external validation of (a) the mutagenicity QSAR model A applied to 24 mycotoxins, (b) the in vitro genotoxicity QSAR model applied to 15 mycotoxins, (c) the in vivo genotoxicity QSAR model applied to 72 mycotoxins, and (d) the carcinogenicity QSAR model applied to 75 mycotoxins. SPEC: specificity; SENS: sensitivity; ACC: accuracy; pred NEG: predicted negatives; pred POS: predicted positives.

Figure 4

Global overview of genotoxicity, mutagenicity, and carcinogenicity predictions of the whole database of mycotoxins. Clustering was performed with the TMAP package. Blue = non-toxic; red = toxic. For more details, please visit MicotoXilico (https://chemopredictionsuite.com/MicotoXilico accessed on 20 May 2023).

Figure 5

Graphical representation of the percentage of genotoxic, carcinogenic, and mutagenic mycotoxins from the major categories obtained after prediction with the corresponding QSAR models.

Figure 6

Workflow diagram for QSAR model building.

Figure 7

In vitro and in vivo assays consulted for model development and their corresponding OECD test guideline.