AOP-Based Machine Learning for Toxicity Prediction

Shi, Wei; Zhang, Rong; Tan, Haoyue

doi:10.1007/978-3-031-20730-3_5

Cited by 2 publications

(2 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The AOP framework represents knowledge of causal relationships between molecular initiating events (MIEs) and key events (KEs) at the subcellular, cellular, tissue, and organ levels, which lead to specific adverse outcomes (AOs) at the individual or population level. , AOP-driven ML is promising, because it enables the integration of computational modeling with biological perturbation pathways. However, to date, only a few studies have combined AOP with IVIVE.…”

Section: In Vivo Toxicity Prediction With ML Model-based Ivivementioning

confidence: 99%

Advancing Toxicity Predictions: A Review on in Vitro to in Vivo Extrapolation in Next-Generation Risk Assessment

Han,

Li,

Yang

et al. 2024

Environ. Health

View full text Add to dashboard Cite

As a key step in next-generation risk assessment (NGRA), in vitro to in vivo extrapolation (IVIVE) aims to mobilize a mechanism-based understanding of toxicology to translate bioactive chemical concentrations obtained from in vitro assays to corresponding exposures likely to induce bioactivity in vivo. This conversion can be achieved via physiologically-based toxicokinetic (PBTK) models and machine learning (ML) algorithms. The last 5 years have witnessed a period of rapid development in IVIVE, with the number of IVIVE-related publications increasing annually. This Review aims to (1) provide a comprehensive overview of the origin of IVIVE and initiatives undertaken by multiple national agencies to promote its development; (2) compile and sort out IVIVE-related publications and perform a clustering analysis of their high-frequency keywords to capture key research hotspots; (3) comprehensively review PBTK and ML model-based IVIVE studies published in the last 5 years to understand the research directions and methodology developments; and (4) propose future perspectives for IVIVE from two aspects: expanding the scope of application and integrating new technologies. The former includes focusing on metabolite toxicity, conducting IVIVE studies on susceptible populations, advancing ML-based quantitative IVIVE models, and extending research to ecological effects. The latter includes combining systems biology, multiomics, and adverse outcome networks with IVIVE, aiming at a more microscopic, mechanistic, and comprehensive toxicity prediction. This Review highlights the important value of IVIVE in NGRA, with the goal of providing confidence for its routine use in chemical prioritization, hazard assessment, and regulatory decision making.

show abstract

Section: In Vivo Toxicity Prediction With ML Model-based Ivivementioning

confidence: 99%

Advancing Toxicity Predictions: A Review on in Vitro to in Vivo Extrapolation in Next-Generation Risk Assessment

Han,

Li,

Yang

et al. 2024

Environ. Health

View full text Add to dashboard Cite

show abstract

“…Likewise, Support Vector Machines (SVMs) represent a ML technique that can solve both regression and classification tasks. SVMs have been applied to a variety of tasks to identify molecular adverse outcomes (e.g., carcinogenicity, hepatotoxicity) with promising results ( Shi et al, 2023 ). Such models, leverage the features or molecular fingerprints extracted from the molecular structure and their corresponding measured values or classes to make predictions based on the learnt pattern in the data representation.…”

Section: Background On Cell Painting Molecular Representations and Ar...mentioning

confidence: 99%

Unleashing the potential of cell painting assays for compound activities and hazards prediction

Odje,

Meijer,

von Coburg

et al. 2024

Front. Toxicol.

View full text Add to dashboard Cite

The cell painting (CP) assay has emerged as a potent imaging-based high-throughput phenotypic profiling (HTPP) tool that provides comprehensive input data for in silico prediction of compound activities and potential hazards in drug discovery and toxicology. CP enables the rapid, multiplexed investigation of various molecular mechanisms for thousands of compounds at the single-cell level. The resulting large volumes of image data provide great opportunities but also pose challenges to image and data analysis routines as well as property prediction models. This review addresses the integration of CP-based phenotypic data together with or in substitute of structural information from compounds into machine (ML) and deep learning (DL) models to predict compound activities for various human-relevant disease endpoints and to identify the underlying modes-of-action (MoA) while avoiding unnecessary animal testing. The successful application of CP in combination with powerful ML/DL models promises further advances in understanding compound responses of cells guiding therapeutic development and risk assessment. Therefore, this review highlights the importance of unlocking the potential of CP assays when combined with molecular fingerprints for compound evaluation and discusses the current challenges that are associated with this approach.

show abstract

AOP-Based Machine Learning for Toxicity Prediction

Cited by 2 publications

References 58 publications

Advancing Toxicity Predictions: A Review on in Vitro to in Vivo Extrapolation in Next-Generation Risk Assessment

Advancing Toxicity Predictions: A Review on in Vitro to in Vivo Extrapolation in Next-Generation Risk Assessment

Unleashing the potential of cell painting assays for compound activities and hazards prediction

Contact Info

Product

Resources

About