Imran Shah1, Tia Tate1, Grace Patlewicz1. 1. Center for Computational Toxicology and Exposure, Office of Research and Development, United States Environmental Protection Agency.
Abstract
MOTIVATION: Generalised Read-Across (GenRA) is a data-driven approach to estimate physico-chemical, biological, or eco-toxicological properties of chemicals by inference from analogues. GenRA attempts to mimic a human expert's manual read-across reasoning for filling data gaps about new chemicals from known chemicals with an interpretable and automated approach based on nearest-neighbours. A key objective of GenRA is to systematically explore different choices of input data selection and neighbourhood definition to objectively evaluate predictive performance of automated read-across estimates of chemical properties. RESULTS: We have implemented genra-py as a python package that can be freely used for chemical safety analysis and risk assessment applications. Automated read-across prediction in genra-py conforms to the scikit-learn machine learning library's estimator design pattern, making it easy to use and integrate in computational pipelines. We demonstrate the data-driven application of genra-py to address two key human health risk assessment problems namely: hazard identification and point of departure estimation. AVAILABILITY: The package is available from github.com/i-shah/genra-py. Published by Oxford University Press 2021.
MOTIVATION: Generalised Read-Across (GenRA) is a data-driven approach to estimate physico-chemical, biological, or eco-toxicological properties of chemicals by inference from analogues. GenRA attempts to mimic a human expert's manual read-across reasoning for filling data gaps about new chemicals from known chemicals with an interpretable and automated approach based on nearest-neighbours. A key objective of GenRA is to systematically explore different choices of input data selection and neighbourhood definition to objectively evaluate predictive performance of automated read-across estimates of chemical properties. RESULTS: We have implemented genra-py as a python package that can be freely used for chemical safety analysis and risk assessment applications. Automated read-across prediction in genra-py conforms to the scikit-learn machine learning library's estimator design pattern, making it easy to use and integrate in computational pipelines. We demonstrate the data-driven application of genra-py to address two key human health risk assessment problems namely: hazard identification and point of departure estimation. AVAILABILITY: The package is available from github.com/i-shah/genra-py. Published by Oxford University Press 2021.
Authors: Imran Shah; Jie Liu; Richard S Judson; Russell S Thomas; Grace Patlewicz Journal: Regul Toxicol Pharmacol Date: 2016-05-09 Impact factor: 3.271
Authors: Yen Low; Alexander Sedykh; Denis Fourches; Alexander Golbraikh; Maurice Whelan; Ivan Rusyn; Alexander Tropsha Journal: Chem Res Toxicol Date: 2013-08-05 Impact factor: 3.739
Authors: A Patrícia Bento; Anne Hersey; Eloy Félix; Greg Landrum; Anna Gaulton; Francis Atkinson; Louisa J Bellis; Marleen De Veij; Andrew R Leach Journal: J Cheminform Date: 2020-09-01 Impact factor: 5.514
Authors: Antonio F Hernandez-Jerez; Paulien Adriaanse; Annette Aldrich; Philippe Berny; Tamara Coja; Sabine Duquesne; Andreas Focks; Marina Marinovich; Maurice Millet; Olavi Pelkonen; Silvia Pieper; Aaldrik Tiktak; Christopher J Topping; Anneli Widenfalk; Martin Wilks; Gerrit Wolterink; Ursula Gundert-Remy; Jochem Louisse; Serge Rudaz; Emanuela Testai; Alfonso Lostia; Jean-Lou Dorne; Juan Manuel Parra Morte Journal: EFSA J Date: 2021-12-23
Authors: Kyle Roell; Lauren E Koval; Rebecca Boyles; Grace Patlewicz; Caroline Ring; Cynthia V Rider; Cavin Ward-Caviness; David M Reif; Ilona Jaspers; Rebecca C Fry; Julia E Rager Journal: Front Toxicol Date: 2022-06-22