BIOMAT Database Logo BIOMAT Database Logo

Machine learning models for predicting endocrine disruption potential of environmental chemicals. 2018

Marco Chierici, and Marco Giulini, and Nicole Bussola, and Giuseppe Jurman, and Cesare Furlanello
a Fondazione Bruno Kessler , Trento , Italy.

We introduce here ML4Tox, a framework offering Deep Learning and Support Vector Machine models to predict agonist, antagonist, and binding activities of chemical compounds, in this case for the estrogen receptor ligand-binding domain. The ML4Tox models have been developed with a 10 × 5-fold cross-validation schema on the training portion of the CERAPP ToxCast dataset, formed by 1677 chemicals, each described by 777 molecular features. On the CERAPP "All Literature" evaluation set (agonist: 6319 compounds; antagonist 6539; binding 7283), ML4Tox significantly improved sensitivity over published results on all three tasks, with agonist: 0.78 vs 0.56; antagonist: 0.69 vs 0.11; binding: 0.66 vs 0.26.

UI MeSH Term Description Entries
D011485 Protein Binding The process in which substances, either endogenous or exogenous, bind to proteins, peptides, enzymes, protein precursors, or allied compounds. Specific protein-binding measures are often used as assays in diagnostic assessments. Plasma Protein Binding Capacity,Binding, Protein
D011960 Receptors, Estrogen Cytoplasmic proteins that bind estrogens and migrate to the nucleus where they regulate DNA transcription. Evaluation of the state of estrogen receptors in breast cancer patients has become clinically important. Estrogen Receptor,Estrogen Receptors,Estrogen Nuclear Receptor,Estrogen Receptor Type I,Estrogen Receptor Type II,Estrogen Receptors Type I,Estrogen Receptors Type II,Receptor, Estrogen Nuclear,Receptors, Estrogen, Type I,Receptors, Estrogen, Type II,Nuclear Receptor, Estrogen,Receptor, Estrogen
D003198 Computer Simulation Computer-based representation of physical systems and phenomena such as chemical processes. Computational Modeling,Computational Modelling,Computer Models,In silico Modeling,In silico Models,In silico Simulation,Models, Computer,Computerized Models,Computer Model,Computer Simulations,Computerized Model,In silico Model,Model, Computer,Model, Computerized,Model, In silico,Modeling, Computational,Modeling, In silico,Modelling, Computational,Simulation, Computer,Simulation, In silico,Simulations, Computer
D004785 Environmental Pollutants Substances or energies, for example heat or light, which when introduced into the air, water, or land threaten life or health of individuals or ECOSYSTEMS. Environmental Pollutant,Pollutant,Pollutants,Pollutants, Environmental,Pollutant, Environmental
D000069550 Machine Learning A type of ARTIFICIAL INTELLIGENCE that enable COMPUTERS to independently initiate and execute LEARNING when exposed to new data. Transfer Learning,Learning, Machine,Learning, Transfer
D052244 Endocrine Disruptors Exogenous agents, synthetic and naturally occurring, which are capable of disrupting the functions of the ENDOCRINE SYSTEM including the maintenance of HOMEOSTASIS and the regulation of developmental processes. Endocrine disruptors are compounds that can mimic HORMONES, or enhance or block the binding of hormones to their receptors, or otherwise lead to activating or inhibiting the endocrine signaling pathways and hormone metabolism. Endocrine Disrupting Chemical,Endocrine Disrupting Chemicals,Endocrine Disruptor,Endocrine Disruptor Effect,Endocrine Disruptor Effects,Chemical, Endocrine Disrupting,Chemicals, Endocrine Disrupting,Disrupting Chemical, Endocrine,Disruptor Effect, Endocrine,Disruptor Effects, Endocrine,Disruptor, Endocrine,Disruptors, Endocrine,Effect, Endocrine Disruptor,Effects, Endocrine Disruptor
D060388 Support Vector Machine SUPERVISED MACHINE LEARNING algorithm which learns to assign labels to objects from a set of training examples. Examples are learning to recognize fraudulent credit card activity by examining hundreds or thousands of fraudulent and non-fraudulent credit card activity, or learning to make disease diagnosis or prognosis based on automatic classification of microarray gene expression profiles drawn from hundreds or thousands of samples. Support Vector Network,Machine, Support Vector,Machines, Support Vector,Network, Support Vector,Networks, Support Vector,Support Vector Machines,Support Vector Networks,Vector Machine, Support,Vector Machines, Support,Vector Network, Support,Vector Networks, Support
D018675 Toxicity Tests An array of tests used to determine the toxicity of a substance to living systems. These include tests on clinical drugs, foods, and environmental pollutants. Tests, Toxicity,Test, Toxicity,Toxicity Test
D021281 Quantitative Structure-Activity Relationship A quantitative prediction of the biological, ecotoxicological or pharmaceutical activity of a molecule. It is based upon structure and activity information gathered from a series of similar compounds. Structure Activity Relationship, Quantitative,3D-QSAR,QSAR,QSPR Modeling,Quantitative Structure Property Relationship,3D QSAR,3D-QSARs,Modeling, QSPR,Quantitative Structure Activity Relationship,Quantitative Structure-Activity Relationships,Relationship, Quantitative Structure-Activity,Relationships, Quantitative Structure-Activity,Structure-Activity Relationship, Quantitative,Structure-Activity Relationships, Quantitative

Related Publications

Marco Chierici, and Marco Giulini, and Nicole Bussola, and Giuseppe Jurman, and Cesare Furlanello
Improved Machine Learning Models by Data Processing for Predicting Life-Cycle Environmental Impacts of Chemicals.
February 2023, Environmental science & technology,
Marco Chierici, and Marco Giulini, and Nicole Bussola, and Giuseppe Jurman, and Cesare Furlanello
Machine Learning Models for Estrogen Receptor Bioactivity and Endocrine Disruption Prediction.
October 2020, Environmental science & technology,
Marco Chierici, and Marco Giulini, and Nicole Bussola, and Giuseppe Jurman, and Cesare Furlanello
Novel machine learning models to predict endocrine disruption activity for high-throughput chemical screening.
January 2022, Frontiers in toxicology,
Marco Chierici, and Marco Giulini, and Nicole Bussola, and Giuseppe Jurman, and Cesare Furlanello
Machine Learning Models for Predicting Liver Toxicity.
January 2022, Methods in molecular biology (Clifton, N.J.),
Marco Chierici, and Marco Giulini, and Nicole Bussola, and Giuseppe Jurman, and Cesare Furlanello
Machine Learning Models for Predicting Cytotoxicity of Nanomaterials.
February 2022, Chemical research in toxicology,
Marco Chierici, and Marco Giulini, and Nicole Bussola, and Giuseppe Jurman, and Cesare Furlanello
Machine learning for interatomic potential models.
February 2020, The Journal of chemical physics,
Marco Chierici, and Marco Giulini, and Nicole Bussola, and Giuseppe Jurman, and Cesare Furlanello
Computational prediction models for assessing endocrine disrupting potential of chemicals.
January 2018, Journal of environmental science and health. Part C, Environmental carcinogenesis & ecotoxicology reviews,
Marco Chierici, and Marco Giulini, and Nicole Bussola, and Giuseppe Jurman, and Cesare Furlanello
Improved machine learning models for predicting selective compounds.
January 2012, Journal of chemical information and modeling,
Marco Chierici, and Marco Giulini, and Nicole Bussola, and Giuseppe Jurman, and Cesare Furlanello
Machine learning for predicting halogen radical reactivity toward aqueous organic chemicals.
July 2024, Journal of hazardous materials,
Marco Chierici, and Marco Giulini, and Nicole Bussola, and Giuseppe Jurman, and Cesare Furlanello
Transferability of Machine Learning Models for Predicting Raman Spectra.
March 2024, The journal of physical chemistry. A,
Copied contents to your clipboard!