AI in Predictive Toxicology DOI
Bancha Yingngam

Advances in medical technologies and clinical practice book series, Journal Year: 2024, Volume and Issue: unknown, P. 79 - 134

Published: Sept. 14, 2024

The field of toxicology is undergoing a significant transformation due to the integration artificial intelligence (AI). In addition traditional reliance on empirical studies and animal testing, AI-powered predictive now used predict toxic effects chemicals drugs. This chapter examines role AI in enhancing accuracy, efficiency, breadth toxicological assessments by bridging gap between approaches advanced techniques. It explores various methodologies, such as machine learning, deep neural networks, focusing their application toxicity prediction. Furthermore, this investigates with databases development validation models. also addresses challenges associated toxicology, including data quality, model interpretability, scalability. concludes that despite facing challenges, powerful tool modern analysis.

Language: Английский

Predictive Tox-21 Methods for Assessing Emerging Pollutants in the Marine Environment DOI
Yusra Sajid Kiani

Published: Jan. 1, 2025

Language: Английский

Citations

0

A combination of high-throughput in vitro and in silico new approach methods (NAMs) for ecotoxicology hazard assessment for fish DOI Creative Commons
Johanna Nyffeler, Felix R. Harris, Clinton Willis

et al.

Environmental Toxicology and Chemistry, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 6, 2025

Fish acute toxicity testing is used to inform environmental hazard assessment of chemicals. In silico and in vitro approaches have the potential reduce number fish increase efficiency generating data for assessing ecological hazards. Here, two bioactivity assays were adapted use high-throughput chemical screening. First, a miniaturized version Organisation Economic Co-operation Development (OECD) test guideline 249 plate reader-based assay RTgill-W1 cells was developed. Second, Cell Painting (CP) along with an imaging-based cell viability assay. Then, 225 chemicals tested each Potencies calls from reader comparable. The CP more sensitive than either that it detected larger as bioactive, phenotype altering concentrations (PACs) lower decreased viability. An disposition (IVD) model accounted sorption plastic over time applied predict freely dissolved PACs compared vivo data. Adjustment using IVD modeling improved concordance For 65 where comparison values possible, 59% adjusted within one order magnitude lethal 50% organisms. protective 73% This combination has or replace testing.

Language: Английский

Citations

0

Extrapolation factors for calculating ecotoxicity effects in LCA DOI Creative Commons
Rahul Aggarwal, Mikael Gustavsson, Gregory Peters

et al.

The International Journal of Life Cycle Assessment, Journal Year: 2024, Volume and Issue: unknown

Published: Sept. 10, 2024

Abstract Purpose This study focuses on updating, improving, and expanding the extrapolation factors needed to convert various acute or chronic effect concentration indicators into consistent EC10eq (effect inducing a 10% response over background) for use in life cycle assessment (LCA). Our main objectives include (1) present detailed approach harmonization of ecotoxicity data, with focus deriving factors, (2) estimate both generic species group-specific facilitating conversion indicator groups (EC10eq EC50eq) EC10eq. Methods Experimental data were sourced from CompTox Version 2.1.1, which integrates toxicity information ToxValDB v9.1.1, REACH registration dossiers. We developed framework harmonizing ensuring uniformity high quality aquatic these sources. Through linear regression analysis, then derived. Results discussion Harmonization yielded streamlined dataset 339,729 datapoints 10,668 chemicals, reflecting 54% reduction raw datapoints. The geometric mean-based aggregation process produced 79,001 aggregated at level, 41,303 group 23,215 level chemicals. facilitated derivation 3 24 allowing across two exposure classes (acute vs. chronic) groups, as defined US EPA ECOTOX knowledgebase, including algae, amphibians, fish, crustaceans, insects/spiders, invertebrates, molluscs, worms. Conclusions derived permit integration diverse varying durations USEtox characterization factors. has potential enhance substance coverage characterizing effects chemicals LCA frameworks by permitting wider coverage. More generally, this is part global efforts extend quantitative environmental impacts an framework.

Language: Английский

Citations

2

AI in Predictive Toxicology DOI
Bancha Yingngam

Advances in medical technologies and clinical practice book series, Journal Year: 2024, Volume and Issue: unknown, P. 79 - 134

Published: Sept. 14, 2024

The field of toxicology is undergoing a significant transformation due to the integration artificial intelligence (AI). In addition traditional reliance on empirical studies and animal testing, AI-powered predictive now used predict toxic effects chemicals drugs. This chapter examines role AI in enhancing accuracy, efficiency, breadth toxicological assessments by bridging gap between approaches advanced techniques. It explores various methodologies, such as machine learning, deep neural networks, focusing their application toxicity prediction. Furthermore, this investigates with databases development validation models. also addresses challenges associated toxicology, including data quality, model interpretability, scalability. concludes that despite facing challenges, powerful tool modern analysis.

Language: Английский

Citations

0