Drug side-effect prediction based on the integration of chemical and biological spaces

Yoshihiro Yamanishi, Edouard Pauwels, Masaaki Kotera

Research output: Contribution to journalArticle

65 Citations (Scopus)

Abstract

Drug side-effects, or adverse drug reactions, have become a major public health concern and remain one of the main causes of drug failure and of drug withdrawal once they have reached the market. Therefore, the identification of potential severe side-effects is a challenging issue. In this paper, we develop a new method to predict potential side-effect profiles of drug candidate molecules based on their chemical structures and target protein information on a large scale. We propose several extensions of kernel regression model for multiple responses to deal with heterogeneous data sources. The originality lies in the integration of the chemical space of drug chemical structures and the biological space of drug target proteins in a unified framework. As a result, we demonstrate the usefulness of the proposed method on the simultaneous prediction of 969 side-effects for approved drugs from their chemical substructure and target protein profiles and show that the prediction accuracy consistently improves owing to the proposed regression model and integration of chemical and biological information. We also conduct a comprehensive side-effect prediction for uncharacterized drug molecules stored in DrugBank and confirm interesting predictions using independent information sources. The proposed method is expected to be useful at many stages of the drug development process.

Original languageEnglish
Pages (from-to)3284-3292
Number of pages9
JournalJournal of Chemical Information and Modeling
Volume52
Issue number12
DOIs
Publication statusPublished - Dec 21 2012

Fingerprint

drug
Proteins
Pharmaceutical Preparations
Molecules
Public health
regression
withdrawal
candidacy
public health
cause
market

All Science Journal Classification (ASJC) codes

  • Chemistry(all)
  • Chemical Engineering(all)
  • Computer Science Applications
  • Library and Information Sciences

Cite this

Drug side-effect prediction based on the integration of chemical and biological spaces. / Yamanishi, Yoshihiro; Pauwels, Edouard; Kotera, Masaaki.

In: Journal of Chemical Information and Modeling, Vol. 52, No. 12, 21.12.2012, p. 3284-3292.

Research output: Contribution to journalArticle

Yamanishi, Yoshihiro ; Pauwels, Edouard ; Kotera, Masaaki. / Drug side-effect prediction based on the integration of chemical and biological spaces. In: Journal of Chemical Information and Modeling. 2012 ; Vol. 52, No. 12. pp. 3284-3292.
@article{0c015fb586e745a8aae28d652c8a1dfb,
title = "Drug side-effect prediction based on the integration of chemical and biological spaces",
abstract = "Drug side-effects, or adverse drug reactions, have become a major public health concern and remain one of the main causes of drug failure and of drug withdrawal once they have reached the market. Therefore, the identification of potential severe side-effects is a challenging issue. In this paper, we develop a new method to predict potential side-effect profiles of drug candidate molecules based on their chemical structures and target protein information on a large scale. We propose several extensions of kernel regression model for multiple responses to deal with heterogeneous data sources. The originality lies in the integration of the chemical space of drug chemical structures and the biological space of drug target proteins in a unified framework. As a result, we demonstrate the usefulness of the proposed method on the simultaneous prediction of 969 side-effects for approved drugs from their chemical substructure and target protein profiles and show that the prediction accuracy consistently improves owing to the proposed regression model and integration of chemical and biological information. We also conduct a comprehensive side-effect prediction for uncharacterized drug molecules stored in DrugBank and confirm interesting predictions using independent information sources. The proposed method is expected to be useful at many stages of the drug development process.",
author = "Yoshihiro Yamanishi and Edouard Pauwels and Masaaki Kotera",
year = "2012",
month = "12",
day = "21",
doi = "10.1021/ci2005548",
language = "English",
volume = "52",
pages = "3284--3292",
journal = "Journal of Chemical Information and Modeling",
issn = "1549-9596",
publisher = "American Chemical Society",
number = "12",

}

TY - JOUR

T1 - Drug side-effect prediction based on the integration of chemical and biological spaces

AU - Yamanishi, Yoshihiro

AU - Pauwels, Edouard

AU - Kotera, Masaaki

PY - 2012/12/21

Y1 - 2012/12/21

N2 - Drug side-effects, or adverse drug reactions, have become a major public health concern and remain one of the main causes of drug failure and of drug withdrawal once they have reached the market. Therefore, the identification of potential severe side-effects is a challenging issue. In this paper, we develop a new method to predict potential side-effect profiles of drug candidate molecules based on their chemical structures and target protein information on a large scale. We propose several extensions of kernel regression model for multiple responses to deal with heterogeneous data sources. The originality lies in the integration of the chemical space of drug chemical structures and the biological space of drug target proteins in a unified framework. As a result, we demonstrate the usefulness of the proposed method on the simultaneous prediction of 969 side-effects for approved drugs from their chemical substructure and target protein profiles and show that the prediction accuracy consistently improves owing to the proposed regression model and integration of chemical and biological information. We also conduct a comprehensive side-effect prediction for uncharacterized drug molecules stored in DrugBank and confirm interesting predictions using independent information sources. The proposed method is expected to be useful at many stages of the drug development process.

AB - Drug side-effects, or adverse drug reactions, have become a major public health concern and remain one of the main causes of drug failure and of drug withdrawal once they have reached the market. Therefore, the identification of potential severe side-effects is a challenging issue. In this paper, we develop a new method to predict potential side-effect profiles of drug candidate molecules based on their chemical structures and target protein information on a large scale. We propose several extensions of kernel regression model for multiple responses to deal with heterogeneous data sources. The originality lies in the integration of the chemical space of drug chemical structures and the biological space of drug target proteins in a unified framework. As a result, we demonstrate the usefulness of the proposed method on the simultaneous prediction of 969 side-effects for approved drugs from their chemical substructure and target protein profiles and show that the prediction accuracy consistently improves owing to the proposed regression model and integration of chemical and biological information. We also conduct a comprehensive side-effect prediction for uncharacterized drug molecules stored in DrugBank and confirm interesting predictions using independent information sources. The proposed method is expected to be useful at many stages of the drug development process.

UR - http://www.scopus.com/inward/record.url?scp=84871595040&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84871595040&partnerID=8YFLogxK

U2 - 10.1021/ci2005548

DO - 10.1021/ci2005548

M3 - Article

C2 - 23157436

AN - SCOPUS:84871595040

VL - 52

SP - 3284

EP - 3292

JO - Journal of Chemical Information and Modeling

JF - Journal of Chemical Information and Modeling

SN - 1549-9596

IS - 12

ER -