4.7 Article

Predicting chemicals' toxicity pathway of female reproductive disorders using AOP7 and deep neural networks

Related references

Note: Only part of the references are listed.
Article Environmental Sciences

Identification of neurotoxic compounds in cyanobacteria exudate mixtures

Yuanyan Zi et al.

Summary: The release of toxic cyanobacterial secondary metabolites poses threats to biosecurity, food webs, and public health. Through machine learning and molecular docking, this study identified neurotoxicity mechanisms and neurotoxins in Microcystis aeruginosa exudates, which are important for understanding cyanobacteria management.

SCIENCE OF THE TOTAL ENVIRONMENT (2023)

Article Environmental Sciences

Predicting chemical hazard across taxa through machine learning

Jimeng Wu et al.

Summary: Machine learning methods were used to predict chemical hazards for fish acute toxicity across different taxa. The relevance of taxonomy and experimental setup was analyzed, indicating that considering these factors can significantly improve the classification performance. By incorporating taxonomic and experimental information, better accuracy was achieved compared to classification based solely on chemical information.

ENVIRONMENT INTERNATIONAL (2022)

Article Engineering, Environmental

High throughput data-based, toxicity pathway-oriented development of a quantitative adverse outcome pathway network linking AHR activation to lung damages

Yuan Jin et al.

Summary: This study developed a highly reliable AOP model concerning human health, validated and quantitatively evaluated it, and conducted targeted bioassays to further understand cellular responses. Through these research efforts, a comprehensive AOP network was established, providing valuable insights for risk assessment.

JOURNAL OF HAZARDOUS MATERIALS (2022)

Article Toxicology

Mapping DEHP to the adverse outcome pathway network for human female reproductive toxicity

Kristina Pogrmic-Majkic et al.

Summary: This study utilized AOPs and AOP networks to understand the impact of chemicals on human health. It derived the HFRT-AOP network and mapped DEHP to this network, providing insights into the toxic mechanism of DEHP-induced human female reproductive toxicity.

ARCHIVES OF TOXICOLOGY (2022)

Article Engineering, Environmental

Artificial Intelligence-Based Toxicity Prediction of Environmental Chemicals: Future Directions for Chemical Management Applications

Jaeseong Jeong et al.

Summary: In recent years, the rapid development of computer technology has led to the emergence of artificial intelligence (AI) -based computational toxicology models that can predict toxicity without animal testing. Various computational toxicology techniques are being used to predict toxicity based on the structure of chemical substances, including quantitative structure-activity relationship. This study analyzed databases, molecular descriptors, fingerprints, and algorithms used in recent studies to understand the development of these models. The findings reveal that AI models have been developed to predict approximately 30 different toxicity endpoints using more than 20 toxicity databases. Molecular access system and extended-connectivity fingerprints are commonly used molecular descriptors, while random forest is the most used algorithm among machine learning techniques and deep neural network is the most used algorithm among deep learning techniques. The use of AI technology in the development of toxicity prediction models is a new concept that can help achieve scientific consensus and meet regulatory applications.

ENVIRONMENTAL SCIENCE & TECHNOLOGY (2022)

Article Toxicology

A development of a graph-based ensemble machine learning model for skin sensitization hazard and potency assessment

Byoungjun Jeon et al.

Summary: This study developed an ensemble prediction model using a graph convolutional network and machine learning approach to assess skin sensitization. The model integrates in silico parameters and data from alternatives to animal testing to improve the predictive ability of skin sensitization hazard and potency assessment.

JOURNAL OF APPLIED TOXICOLOGY (2022)

Article Environmental Sciences

Identification of toxicity pathway of diesel particulate matter using AOP of PPARγ inactivation leading to pulmonary fibrosis

Jaeseong Jeong et al.

Summary: Diesel particulate matter (DPM) is a major subset of urban fine particulate matter (PM2.5) and has been classified as a group 1 carcinogen due to its complex mixture of various chemicals. Using the Adverse Outcome Pathway (AOP) approach, we identified the toxicity pathway of DPM and demonstrated the usefulness of ToxCast and deep learning models in determining potential toxicity pathways of chemical mixtures like DPM.

ENVIRONMENT INTERNATIONAL (2021)

Review Environmental Sciences

Female Fertility and Environmental Pollution

Rita Canipari et al.

INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH (2020)

Article Chemistry, Multidisciplinary

Could deep learning in neural networks improve the QSAR models?

G. Gini et al.

SAR AND QSAR IN ENVIRONMENTAL RESEARCH (2019)

Article Computer Science, Artificial Intelligence

SMOTE for Learning from Imbalanced Data: Progress and Challenges, Marking the 15-year Anniversary

Alberto Fernandez et al.

JOURNAL OF ARTIFICIAL INTELLIGENCE RESEARCH (2018)

Review Environmental Sciences

Harvesting the promise of AOPs: An assessment and recommendations

Annamaria Carusi et al.

SCIENCE OF THE TOTAL ENVIRONMENT (2018)

Review Environmental Sciences

Human exposure to endocrine disrupting chemicals: effects on the male and female reproductive systems

Stavros Sifakis et al.

ENVIRONMENTAL TOXICOLOGY AND PHARMACOLOGY (2017)

Article Toxicology

Adverse outcome pathways: opportunities, limitations and open questions

Marcel Leist et al.

ARCHIVES OF TOXICOLOGY (2017)

Review Pharmacology & Pharmacy

The adverse outcome pathway concept: A pragmatic tool in toxicology

Mathieu Vinken

TOXICOLOGY (2013)

Article Chemistry, Medicinal

Extended-Connectivity Fingerprints

David Rogers et al.

JOURNAL OF CHEMICAL INFORMATION AND MODELING (2010)

Article Endocrinology & Metabolism

Direct rosiglitazone action on steroidogenesis and proinflammatory factor production in human granulosa-lutein cells

Qiuju Chen et al.

REPRODUCTIVE BIOLOGY AND ENDOCRINOLOGY (2009)

Article Cell Biology

Dual activation of PPARα and PPARγ by mono-(2-ethylhexyl) phthalate in rat ovarian granulosa cells

T Lovekamp-Swan et al.

MOLECULAR AND CELLULAR ENDOCRINOLOGY (2003)

Review Biochemical Research Methods

Molecular descriptors in chemoinformatics, computational combinatorial chemistry, and virtual screening

L Xue et al.

COMBINATORIAL CHEMISTRY & HIGH THROUGHPUT SCREENING (2000)