Predicting neurological Adverse Drug Reactions based on biological, chemical and phenotypic properties of drugs using machine learning models

Abstract Adverse drug reactions (ADRs) have become one of the primary reasons for the failure of drugs and a leading cause of deaths. Owing to the severe effects of ADRs, there is an urgent need for the generation of effective models which can accurately predict ADRs during early stages of drug deve...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Salma Jamal, Sukriti Goyal, Asheesh Shanker, Abhinav Grover
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2017
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/97625a901dae49729c73b6ab9cd8dca1
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:97625a901dae49729c73b6ab9cd8dca1
record_format	dspace
spelling	oai:doaj.org-article:97625a901dae49729c73b6ab9cd8dca12021-12-02T16:06:18ZPredicting neurological Adverse Drug Reactions based on biological, chemical and phenotypic properties of drugs using machine learning models10.1038/s41598-017-00908-z2045-2322https://doaj.org/article/97625a901dae49729c73b6ab9cd8dca12017-04-01T00:00:00Zhttps://doi.org/10.1038/s41598-017-00908-zhttps://doaj.org/toc/2045-2322Abstract Adverse drug reactions (ADRs) have become one of the primary reasons for the failure of drugs and a leading cause of deaths. Owing to the severe effects of ADRs, there is an urgent need for the generation of effective models which can accurately predict ADRs during early stages of drug development based on integration of various features of drugs. In the current study, we have focused on neurological ADRs and have used various properties of drugs that include biological properties (targets, transporters and enzymes), chemical properties (substructure fingerprints), phenotypic properties (side effects (SE) and therapeutic indications) and a combinations of the two and three levels of features. We employed relief-based feature selection technique to identify relevant properties and used machine learning approach to generated learned model systems which would predict neurological ADRs prior to preclinical testing. Additionally, in order to explain the efficiency and applicability of the models, we tested them to predict the ADRs for already existing anti-Alzheimer drugs and uncharacterized drugs, respectively in side effect resource (SIDER) database. The generated models were highly accurate and our results showed that the models based on chemical (accuracy 93.20%), phenotypic (accuracy 92.41%) and combination of three properties (accuracy 94.18%) were highly accurate while the models based on biological properties (accuracy 82.11%) were highly informative.Salma JamalSukriti GoyalAsheesh ShankerAbhinav GroverNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 7, Iss 1, Pp 1-12 (2017)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Salma Jamal Sukriti Goyal Asheesh Shanker Abhinav Grover Predicting neurological Adverse Drug Reactions based on biological, chemical and phenotypic properties of drugs using machine learning models
description	Abstract Adverse drug reactions (ADRs) have become one of the primary reasons for the failure of drugs and a leading cause of deaths. Owing to the severe effects of ADRs, there is an urgent need for the generation of effective models which can accurately predict ADRs during early stages of drug development based on integration of various features of drugs. In the current study, we have focused on neurological ADRs and have used various properties of drugs that include biological properties (targets, transporters and enzymes), chemical properties (substructure fingerprints), phenotypic properties (side effects (SE) and therapeutic indications) and a combinations of the two and three levels of features. We employed relief-based feature selection technique to identify relevant properties and used machine learning approach to generated learned model systems which would predict neurological ADRs prior to preclinical testing. Additionally, in order to explain the efficiency and applicability of the models, we tested them to predict the ADRs for already existing anti-Alzheimer drugs and uncharacterized drugs, respectively in side effect resource (SIDER) database. The generated models were highly accurate and our results showed that the models based on chemical (accuracy 93.20%), phenotypic (accuracy 92.41%) and combination of three properties (accuracy 94.18%) were highly accurate while the models based on biological properties (accuracy 82.11%) were highly informative.
format	article
author	Salma Jamal Sukriti Goyal Asheesh Shanker Abhinav Grover
author_facet	Salma Jamal Sukriti Goyal Asheesh Shanker Abhinav Grover
author_sort	Salma Jamal
title	Predicting neurological Adverse Drug Reactions based on biological, chemical and phenotypic properties of drugs using machine learning models
title_short	Predicting neurological Adverse Drug Reactions based on biological, chemical and phenotypic properties of drugs using machine learning models
title_full	Predicting neurological Adverse Drug Reactions based on biological, chemical and phenotypic properties of drugs using machine learning models
title_fullStr	Predicting neurological Adverse Drug Reactions based on biological, chemical and phenotypic properties of drugs using machine learning models
title_full_unstemmed	Predicting neurological Adverse Drug Reactions based on biological, chemical and phenotypic properties of drugs using machine learning models
title_sort	predicting neurological adverse drug reactions based on biological, chemical and phenotypic properties of drugs using machine learning models
publisher	Nature Portfolio
publishDate	2017
url	https://doaj.org/article/97625a901dae49729c73b6ab9cd8dca1
work_keys_str_mv	AT salmajamal predictingneurologicaladversedrugreactionsbasedonbiologicalchemicalandphenotypicpropertiesofdrugsusingmachinelearningmodels AT sukritigoyal predictingneurologicaladversedrugreactionsbasedonbiologicalchemicalandphenotypicpropertiesofdrugsusingmachinelearningmodels AT asheeshshanker predictingneurologicaladversedrugreactionsbasedonbiologicalchemicalandphenotypicpropertiesofdrugsusingmachinelearningmodels AT abhinavgrover predictingneurologicaladversedrugreactionsbasedonbiologicalchemicalandphenotypicpropertiesofdrugsusingmachinelearningmodels
_version_	1718385039751774208

Predicting neurological Adverse Drug Reactions based on biological, chemical and phenotypic properties of drugs using machine learning models

Ejemplares similares