Abstract: A method and system are disclosed for providing an aggregated trained machine learning model for performing a prediction task. A main processing device obtains from a first processing device at least a portion of a first trained model having been generated by training an initial model on a first training dataset, and a first training parameter indicative of a level of predictive uncertainty thereof. The main processing device obtains from a second processing device at least a portion of a second trained model having been generated by training the initial model on a second training dataset, and a second training parameter indicative of a level of predictive uncertainty thereof. The main processing device combines, using the first and second training parameters, at least the portion of the first and second trained models to thereby obtain the aggregated trained model. The main processing device provides the aggregated trained model.
Type:
Application
Filed:
January 19, 2022
Publication date:
April 18, 2024
Applicants:
IMAGIA CYBERNETICS INC., CONCORDIA UNIVERSITY INC.
Inventors:
Jonatan REYES, Marta KERSTEN-OERTEL, Cecile LOW-KAM, Lisa DI JORIO, Philippe LACAILLE, Florent CHANDELIER
Abstract: Disclosed are methods and compositions which may be used in human cytochrome P450 (CYP450) enzyme phenotyping. The methods and compositions typically utilize substrate for CYP3A5 comprising eplerenone which may be administered orally to a subject. Subsequently, metabolites of eplereone may be detected in the subject's saliva as well as any non- metabolized eplerenone to calculate a metabolic ratio for CYP3A5 enzyme in order to generate a phenytopic CYP3A5 enzyme profile for the subject.
Abstract: Disclosed are methods and compositions which may be used in human cytochrome P450 (CYP450) enzyme phenotyping. The methods and compositions typically utilize a mélange of substrates for different CYP450 enzymes which may be administered orally to a patient. Subsequently, the metabolites of the substrates may be detected in the patient's saliva as well as any non-metabolized substrates to calculate a metabolic ratio for any given CYP450 enzyme in order to generate a phenotypic CYP450 enzyme profile for the patient.
Abstract: Disclosed are substituted (4?-hydroxylphenyl)cycloalkane compounds and there use as selective agonists of the estrogen receptor beta isoform (ER?). The disclosed compounds may be formulated as pharmaceutical compositions and administered to treat diseases associated with ER activity, such as proliferative diseases and disorders and/or psychiatric diseases or disorders.
Type:
Grant
Filed:
May 23, 2016
Date of Patent:
February 25, 2020
Assignees:
Marquette University, Concordia University Inc.
Inventors:
William A. Donaldson, Daniel S. Sem, Terrence S. Neumann
Abstract: Disclosed are methods and compositions which may be used in human cytochrome P450 (CYP450) enzyme phenotyping. The methods and compositions typically utilize a mélange of substrates for different CYP450 enzymes which may be administered orally to a patient. Subsequently, the metabolites of the substrates may be detected in the patient's saliva as well as any non-metabolized substrates to calculate a metabolic ratio for any given CYP450 enzyme in order to generate a phenotypic CYP450 enzyme profile for the patient.