A survey on adverse drug reaction studies: Data, tasks and machine learning methods

Duc Anh Nguyen; Canh Hao Nguyen; Hiroshi Mamitsuka

doi:10.1093/bib/bbz140

A survey on adverse drug reaction studies: Data, tasks and machine learning methods

Duc Anh Nguyen^*
, Canh Hao Nguyen
, Hiroshi Mamitsuka

^*Tämän työn vastaava kirjoittaja

University of Kyoto

Tutkimustuotos: Lehtiartikkeli › Article › Scientific › vertaisarvioitu

41 Sitaatiot (Scopus)

262 Lataukset (Pure)

Abstrakti

Motivation: Adverse drug reaction (ADR) or drug side effect studies play a crucial role in drug discovery. Recently, with the rapid increase of both clinical and non-clinical data, machine learning methods have emerged as prominent tools to support analyzing and predicting ADRs. Nonetheless, there are still remaining challenges in ADR studies. Results: In this paper, we summarized ADR data sources and review ADR studies in three tasks: Drug-ADR benchmark data creation, drug-ADR prediction and ADR mechanism analysis. We focused on machine learning methods used in each task and then compare performances of the methods on the drug-ADR prediction task. Finally, we discussed open problems for further ADR studies. Availability: Data and code are available at https://github.com/anhnda/ADRPModels.

Alkuperäiskieli	Englanti
Sivut	164-177
Sivumäärä	14
Julkaisu	Briefings in Bioinformatics
Vuosikerta	22
Numero	1
Varhainen verkossa julkaisun päivämäärä	2019
DOI - pysyväislinkit	https://doi.org/10.1093/bib/bbz140
Tila	Julkaistu - tammik. 2021
OKM-julkaisutyyppi	A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä

Pääsy asiakirjaan

10.1093/bib/bbz140

Survey _ Final SubmissionAccepted author manuscript, 1,4 MB

Muut tiedostot ja linkit

Linkki julkaisuun Scopuksessa

1 Päättynyt

FiDiPro - Machine Learning for Augmented Science and Knowledge Work
Kaski, S. (Vastuullinen johtaja), Rezaeiyousefi, Z. (Projektin jäsen), Gillberg, L. (Projektin jäsen), Kaplan, S. (Projektin jäsen), Gisbrecht, A. (Projektin jäsen), Güvenç Paltun, B. (Projektin jäsen), Mamitsuka, H. (Projektin jäsen), Strahl, J. (Projektin jäsen), Peltonen, J. (Projektin jäsen) & Eranti, P. (Projektin jäsen)
01/01/2015 → 31/12/2018
Projekti: Business Finland: Other research funding

Siteeraa tätä

@article{f07191953c8d461294cdaadaa06c10c4,

title = "A survey on adverse drug reaction studies: Data, tasks and machine learning methods",

abstract = "Motivation: Adverse drug reaction (ADR) or drug side effect studies play a crucial role in drug discovery. Recently, with the rapid increase of both clinical and non-clinical data, machine learning methods have emerged as prominent tools to support analyzing and predicting ADRs. Nonetheless, there are still remaining challenges in ADR studies. Results: In this paper, we summarized ADR data sources and review ADR studies in three tasks: Drug-ADR benchmark data creation, drug-ADR prediction and ADR mechanism analysis. We focused on machine learning methods used in each task and then compare performances of the methods on the drug-ADR prediction task. Finally, we discussed open problems for further ADR studies. Availability: Data and code are available at https://github.com/anhnda/ADRPModels. ",

keywords = "ADR mechanism, ADR prediction, adverse drug reaction, machine learning methods",

author = "Nguyen, \{Duc Anh\} and Nguyen, \{Canh Hao\} and Hiroshi Mamitsuka",

year = "2021",

month = jan,

doi = "10.1093/bib/bbz140",

language = "English",

volume = "22",

pages = "164--177",

journal = "Briefings in Bioinformatics",

issn = "1467-5463",

publisher = "Oxford University Press",

number = "1",

}

TY - JOUR

T1 - A survey on adverse drug reaction studies

T2 - Data, tasks and machine learning methods

AU - Nguyen, Duc Anh

AU - Nguyen, Canh Hao

AU - Mamitsuka, Hiroshi

PY - 2021/1

Y1 - 2021/1

N2 - Motivation: Adverse drug reaction (ADR) or drug side effect studies play a crucial role in drug discovery. Recently, with the rapid increase of both clinical and non-clinical data, machine learning methods have emerged as prominent tools to support analyzing and predicting ADRs. Nonetheless, there are still remaining challenges in ADR studies. Results: In this paper, we summarized ADR data sources and review ADR studies in three tasks: Drug-ADR benchmark data creation, drug-ADR prediction and ADR mechanism analysis. We focused on machine learning methods used in each task and then compare performances of the methods on the drug-ADR prediction task. Finally, we discussed open problems for further ADR studies. Availability: Data and code are available at https://github.com/anhnda/ADRPModels.

AB - Motivation: Adverse drug reaction (ADR) or drug side effect studies play a crucial role in drug discovery. Recently, with the rapid increase of both clinical and non-clinical data, machine learning methods have emerged as prominent tools to support analyzing and predicting ADRs. Nonetheless, there are still remaining challenges in ADR studies. Results: In this paper, we summarized ADR data sources and review ADR studies in three tasks: Drug-ADR benchmark data creation, drug-ADR prediction and ADR mechanism analysis. We focused on machine learning methods used in each task and then compare performances of the methods on the drug-ADR prediction task. Finally, we discussed open problems for further ADR studies. Availability: Data and code are available at https://github.com/anhnda/ADRPModels.

KW - ADR mechanism

KW - ADR prediction

KW - adverse drug reaction

KW - machine learning methods

UR - https://www.scopus.com/pages/publications/85088011167

U2 - 10.1093/bib/bbz140

DO - 10.1093/bib/bbz140

M3 - Article

C2 - 31838499

AN - SCOPUS:85088011167

SN - 1467-5463

VL - 22

SP - 164

EP - 177

JO - Briefings in Bioinformatics

JF - Briefings in Bioinformatics

IS - 1

ER -

A survey on adverse drug reaction studies: Data, tasks and machine learning methods

Abstrakti

Pääsy asiakirjaan

Muut tiedostot ja linkit

Sormenjälki

Projektit

FiDiPro - Machine Learning for Augmented Science and Knowledge Work

Siteeraa tätä