Transcriptomics in Toxicogenomics, Part III: Data Modelling for Risk Assessment

Abstract

Transcriptomics data are relevant to address a number of challenges in Toxicogenomics (TGx). After careful planning of exposure conditions and data preprocessing, the TGx data can be used in predictive toxicology, where more advanced modelling techniques are applied. The large volume of molecular profiles produced by omics-based technologies allows the development and application of artificial intelligence (AI) methods in TGx. Indeed, the publicly available omics datasets are constantly increasing together with a plethora of different methods that are made available to facilitate their analysis, interpretation and the generation of accurate and stable predictive models. In this review, we present the state-of-the-art of data modelling applied to transcriptomics data in TGx. We show how the benchmark dose (BMD) analysis can be applied to TGx data. We review read across and adverse outcome pathways (AOP) modelling methodologies. We discuss how network-based approaches can be successfully employed to clarify the mechanism of action (MOA) or specific biomarkers of exposure. We also describe the main AI methodologies applied to TGx data to create predictive classification and regression models and we address current challenges. Finally, we present a short description of deep learning (DL) and data integration methodologies applied in these contexts. Modelling of TGx data represents a valuable tool for more accurate chemical safety assessment. This review is the third part of a three-article series on Transcriptomics in Toxicogenomics.

Inhaled multi-walled carbon nanotubes differently modulate global gene and protein expression in rat lungs

“…To identify key transcription regulators of toxicological response, we implemented a computational approach based on reverse engineering techniques. These methods can identify mutual variation in expression levels among genes in different samples and represent these dependencies as a network (Serra et al 2020;Zhernovkov et al 2019). Using the GENIE3 algorithm (Huynh-Thu et al 2010) and transcriptomics data from NM-401 and NM-403 experiments, we identified coexpression scores for transcription factors (TFs) and their potential target genes.…”

Engineered Nanomaterials: The Challenges and Opportunities for Nanomedicines

“…In regulating the toxicity data of ENMs, various machine learning algorithms have been developed to better understand and evaluate the toxicity behavior of the ENMs. 125 These include linear and logistic models, support vector machines (SVM), random forests (RF), classification and regression trees (CART), partial least squares discriminant analysis (PLSDA), linear discriminant analysis (LDA), and artificial neural networks (ANNs). 126 These approaches are anticipated to produce toxicity prediction with greater accuracy.…”

Manually curated transcriptomics data collection for toxicogenomic assessment of engineered nanomaterials

“…Here we provide the biggest homogenized collection of transcriptomics data sets in the field of nanosafety supplemented with metadata and ENM physico-chemical characteristics. The collection offers a valuable source for multiple analysis and modeling approaches 33 . For instance, the mechanism of action of each ENM can be characterized by investigating the provided lists of differentially expressed genes, and may be linked to specific physico-chemical characteristics such as size, surface capping or coating which can guide redesign of ENMs that www.nature.com/scientificdata www.nature.com/scientificdata/ are safer and may support grouping into sets of nanoforms in accordance with REACH regulation (https://echa.…”

“…Our manually curated transcriptomics data collection with supporting ENM descriptions will have a high impact on the nanosafety community and can aid the development of new methodologies for nanomaterial safety assessment 2,8,30,33,43 .…”