{"title":"整合网络分析和机器学习来阐明化学诱导的斑马鱼胚胎胰腺毒性。","authors":"Ashley V Schwartz, Karilyn E Sant, Uduak Z George","doi":"10.1093/toxsci/kfaf069","DOIUrl":null,"url":null,"abstract":"<p><p>Zebrafish (Danio rerio) are a popular vertebrate model for high-throughput toxicity testing, serving as a model for embryonic development and disease etiology. However, standardized protocols using zebrafish tend to explore pathologies and behaviors at the organism level, rather than at the organ-specific level. This study investigates the effects of chemical exposures on pancreatic function in whole-embryo zebrafish by integrating network analysis and machine learning, leveraging widely-available datasets to probe an organ-specific effect. We compiled transcriptomics data for zebrafish exposed to 53 exposures from 25 unique chemicals, including halogenated organic compounds, pesticides/herbicides, endocrine-disrupting chemicals, pharmaceuticals, parabens, and solvents. All raw sequencing data were processed through a uniform bioinformatics pipeline for re-analysis and quality control, identifying differentially expressed genes and altered pathways related to pancreatic function and development. Clustering analysis revealed five distinct clusters of chemical exposures with similar impacts on pancreatic pathways with gene co-expression network analysis identifying key driver genes within these clusters, providing insights into potential biomarkers of chemical-induced pancreatic toxicity. Machine learning was utilized to identify chemical properties that influence pancreatic pathway response, including average mass, biodegradation half-life. The random forest model achieved robust performance (4-fold cross-validation accuracy: 74%) over eXtreme Gradient Boosting, support vector machine, and multiclass logistic regression. This integrative approach enhances our understanding of the relationships between chemical properties and biological responses in a target organ, supporting the use of zebrafish whole-embryos as a high-throughput vertebrate model. This computational workflow can be leveraged to investigate the complex effects of other exposures on organ-specific development.</p>","PeriodicalId":23178,"journal":{"name":"Toxicological Sciences","volume":" ","pages":""},"PeriodicalIF":3.4000,"publicationDate":"2025-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Integrating Network Analysis and Machine Learning to Elucidate Chemical-Induced Pancreatic Toxicity in Zebrafish Embryos.\",\"authors\":\"Ashley V Schwartz, Karilyn E Sant, Uduak Z George\",\"doi\":\"10.1093/toxsci/kfaf069\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>Zebrafish (Danio rerio) are a popular vertebrate model for high-throughput toxicity testing, serving as a model for embryonic development and disease etiology. However, standardized protocols using zebrafish tend to explore pathologies and behaviors at the organism level, rather than at the organ-specific level. This study investigates the effects of chemical exposures on pancreatic function in whole-embryo zebrafish by integrating network analysis and machine learning, leveraging widely-available datasets to probe an organ-specific effect. We compiled transcriptomics data for zebrafish exposed to 53 exposures from 25 unique chemicals, including halogenated organic compounds, pesticides/herbicides, endocrine-disrupting chemicals, pharmaceuticals, parabens, and solvents. All raw sequencing data were processed through a uniform bioinformatics pipeline for re-analysis and quality control, identifying differentially expressed genes and altered pathways related to pancreatic function and development. Clustering analysis revealed five distinct clusters of chemical exposures with similar impacts on pancreatic pathways with gene co-expression network analysis identifying key driver genes within these clusters, providing insights into potential biomarkers of chemical-induced pancreatic toxicity. Machine learning was utilized to identify chemical properties that influence pancreatic pathway response, including average mass, biodegradation half-life. The random forest model achieved robust performance (4-fold cross-validation accuracy: 74%) over eXtreme Gradient Boosting, support vector machine, and multiclass logistic regression. This integrative approach enhances our understanding of the relationships between chemical properties and biological responses in a target organ, supporting the use of zebrafish whole-embryos as a high-throughput vertebrate model. This computational workflow can be leveraged to investigate the complex effects of other exposures on organ-specific development.</p>\",\"PeriodicalId\":23178,\"journal\":{\"name\":\"Toxicological Sciences\",\"volume\":\" \",\"pages\":\"\"},\"PeriodicalIF\":3.4000,\"publicationDate\":\"2025-05-15\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Toxicological Sciences\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1093/toxsci/kfaf069\",\"RegionNum\":3,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"TOXICOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Toxicological Sciences","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1093/toxsci/kfaf069","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"TOXICOLOGY","Score":null,"Total":0}
Integrating Network Analysis and Machine Learning to Elucidate Chemical-Induced Pancreatic Toxicity in Zebrafish Embryos.
Zebrafish (Danio rerio) are a popular vertebrate model for high-throughput toxicity testing, serving as a model for embryonic development and disease etiology. However, standardized protocols using zebrafish tend to explore pathologies and behaviors at the organism level, rather than at the organ-specific level. This study investigates the effects of chemical exposures on pancreatic function in whole-embryo zebrafish by integrating network analysis and machine learning, leveraging widely-available datasets to probe an organ-specific effect. We compiled transcriptomics data for zebrafish exposed to 53 exposures from 25 unique chemicals, including halogenated organic compounds, pesticides/herbicides, endocrine-disrupting chemicals, pharmaceuticals, parabens, and solvents. All raw sequencing data were processed through a uniform bioinformatics pipeline for re-analysis and quality control, identifying differentially expressed genes and altered pathways related to pancreatic function and development. Clustering analysis revealed five distinct clusters of chemical exposures with similar impacts on pancreatic pathways with gene co-expression network analysis identifying key driver genes within these clusters, providing insights into potential biomarkers of chemical-induced pancreatic toxicity. Machine learning was utilized to identify chemical properties that influence pancreatic pathway response, including average mass, biodegradation half-life. The random forest model achieved robust performance (4-fold cross-validation accuracy: 74%) over eXtreme Gradient Boosting, support vector machine, and multiclass logistic regression. This integrative approach enhances our understanding of the relationships between chemical properties and biological responses in a target organ, supporting the use of zebrafish whole-embryos as a high-throughput vertebrate model. This computational workflow can be leveraged to investigate the complex effects of other exposures on organ-specific development.
期刊介绍:
The mission of Toxicological Sciences, the official journal of the Society of Toxicology, is to publish a broad spectrum of impactful research in the field of toxicology.
The primary focus of Toxicological Sciences is on original research articles. The journal also provides expert insight via contemporary and systematic reviews, as well as forum articles and editorial content that addresses important topics in the field.
The scope of Toxicological Sciences is focused on a broad spectrum of impactful toxicological research that will advance the multidisciplinary field of toxicology ranging from basic research to model development and application, and decision making. Submissions will include diverse technologies and approaches including, but not limited to: bioinformatics and computational biology, biochemistry, exposure science, histopathology, mass spectrometry, molecular biology, population-based sciences, tissue and cell-based systems, and whole-animal studies. Integrative approaches that combine realistic exposure scenarios with impactful analyses that move the field forward are encouraged.