Computational Models Using Multiple Machine Learning Algorithms for Predicting Drug Hepatotoxicity with the DILIrank Dataset

Autor: Florentina Furtunescu, Carolina Constantin, Monica Neagu, Robert Ancuceanu, Mihaela Dinu, Adriana Iuliana Anghel, Marilena Viorica Hovanet
Jazyk: angličtina
Rok vydání: 2020
Předmět:
Drug
Quantitative structure–activity relationship
Databases
Factual
Drug-Related Side Effects and Adverse Reactions
Computer science
media_common.quotation_subject
nested cross-validation
Quantitative Structure-Activity Relationship
Feature selection
Machine learning
computer.software_genre
drug hepatotoxicity
Article
Catalysis
Task (project management)
pharmacology_toxicology
Machine Learning
Inorganic Chemistry
lcsh:Chemistry
Software
Molecular descriptor
Humans
Computer Simulation
Physical and Theoretical Chemistry
Molecular Biology
lcsh:QH301-705.5
Spectroscopy
media_common
Computational model
Virtual screening
business.industry
QSAR
DILIrank
Organic Chemistry
General Medicine
Models
Theoretical
Prognosis
virtual screening
Computer Science Applications
lcsh:Biology (General)
lcsh:QD1-999
in silico
DILI
Artificial intelligence
Chemical and Drug Induced Liver Injury
business
Algorithm
computer
Algorithms
Zdroj: International Journal of Molecular Sciences
Volume 21
Issue 6
International Journal of Molecular Sciences, Vol 21, Iss 6, p 2114 (2020)
ISSN: 1422-0067
DOI: 10.3390/ijms21062114
Popis: Drug-induced liver injury (DILI) remains one of the challenges in the safety profile of both authorized and candidate drugs, and predicting hepatotoxicity from the chemical structure of a substance remains a task worth pursuing. Such an approach is coherent with the current tendency for replacing non-clinical tests with in vitro or in silico alternatives. In 2016, a group of researchers from the FDA published an improved annotated list of drugs with respect to their DILI risk, constituting &ldquo
the largest reference drug list ranked by the risk for developing drug-induced liver injury in humans&rdquo
(DILIrank). This paper is one of the few attempting to predict liver toxicity using the DILIrank dataset. Molecular descriptors were computed with the Dragon 7.0 software, and a variety of feature selection and machine learning algorithms were implemented in the R computing environment. Nested (double) cross-validation was used to externally validate the models selected. A total of 78 models with reasonable performance were selected and stacked through several approaches, including the building of multiple meta-models. The performance of the stacked models was slightly superior to other models published. The models were applied in a virtual screening exercise on over 100,000 compounds from the ZINC database and about 20% of them were predicted to be non-hepatotoxic.
Databáze: OpenAIRE
Externí odkaz:
Nepřihlášeným uživatelům se plný text nezobrazuje