Multi-aspect candidates for repositioning: Data fusion methods using heterogeneous information sources

Á Arany, B. Bolgár, B. Balogh, P. Antal, P. Mátyus

Research output: Contribution to journalArticle

13 Citations (Scopus)

Abstract

Drug repositioning, an innovative therapeutic application of an old drug, has received much attention as a particularly costeffective strategy in drug RandD. Recent work has indicated that repositioning can be promoted by utilizing a wide range of information sources, including medicinal chemical, target, mechanism, main and side-effect-related information, and also bibliometric and taxonomical fingerprints, signatures and knowledge bases. This article describes the adaptation of a conceptually novel, more efficient approach for the identification of new possible therapeutic applications of approved drugs and drug candidates, based on a kernel-based data fusion method. This strategy includes (1) the potentially multiple representation of information sources, (2) the automated weighting and statistically optimal combination of information sources, and (3) the automated weighting of parts of the query compounds. The performance was systematically evaluated by using Anatomical Therapeutic Chemical Classification System classes in a cross-validation framework. The results confirmed that kernel-based data fusion can integrate heterogeneous information sources significantly better than standard rank-based fusion can, and this method provides a unique solution for repositioning; it can also be utilized for de novo drug discovery. The advantages of kernel-based data fusion are illustrated with examples and open problems that are particularly relevant for pharmaceutical applications.

Original languageEnglish
Pages (from-to)95-107
Number of pages13
JournalCurrent Medicinal Chemistry
Volume20
Issue number1
DOIs
Publication statusPublished - Jan 2013

Fingerprint

Data fusion
Pharmaceutical Preparations
Drug Repositioning
Bibliometrics
Knowledge Bases
Dermatoglyphics
Drug Discovery
Therapeutics

Keywords

  • Data fusion
  • Drug repositioning
  • In silico drug discovery
  • Kernel fusion
  • Side-effect
  • Similarity search
  • Support vector machine

ASJC Scopus subject areas

  • Molecular Medicine
  • Pharmacology

Cite this

Multi-aspect candidates for repositioning : Data fusion methods using heterogeneous information sources. / Arany, Á; Bolgár, B.; Balogh, B.; Antal, P.; Mátyus, P.

In: Current Medicinal Chemistry, Vol. 20, No. 1, 01.2013, p. 95-107.

Research output: Contribution to journalArticle

@article{8276972fe98742e191e7dc871fdb7522,
title = "Multi-aspect candidates for repositioning: Data fusion methods using heterogeneous information sources",
abstract = "Drug repositioning, an innovative therapeutic application of an old drug, has received much attention as a particularly costeffective strategy in drug RandD. Recent work has indicated that repositioning can be promoted by utilizing a wide range of information sources, including medicinal chemical, target, mechanism, main and side-effect-related information, and also bibliometric and taxonomical fingerprints, signatures and knowledge bases. This article describes the adaptation of a conceptually novel, more efficient approach for the identification of new possible therapeutic applications of approved drugs and drug candidates, based on a kernel-based data fusion method. This strategy includes (1) the potentially multiple representation of information sources, (2) the automated weighting and statistically optimal combination of information sources, and (3) the automated weighting of parts of the query compounds. The performance was systematically evaluated by using Anatomical Therapeutic Chemical Classification System classes in a cross-validation framework. The results confirmed that kernel-based data fusion can integrate heterogeneous information sources significantly better than standard rank-based fusion can, and this method provides a unique solution for repositioning; it can also be utilized for de novo drug discovery. The advantages of kernel-based data fusion are illustrated with examples and open problems that are particularly relevant for pharmaceutical applications.",
keywords = "Data fusion, Drug repositioning, In silico drug discovery, Kernel fusion, Side-effect, Similarity search, Support vector machine",
author = "{\'A} Arany and B. Bolg{\'a}r and B. Balogh and P. Antal and P. M{\'a}tyus",
year = "2013",
month = "1",
doi = "10.2174/09298673130110",
language = "English",
volume = "20",
pages = "95--107",
journal = "Current Medicinal Chemistry",
issn = "0929-8673",
publisher = "Bentham Science Publishers B.V.",
number = "1",

}

TY - JOUR

T1 - Multi-aspect candidates for repositioning

T2 - Data fusion methods using heterogeneous information sources

AU - Arany, Á

AU - Bolgár, B.

AU - Balogh, B.

AU - Antal, P.

AU - Mátyus, P.

PY - 2013/1

Y1 - 2013/1

N2 - Drug repositioning, an innovative therapeutic application of an old drug, has received much attention as a particularly costeffective strategy in drug RandD. Recent work has indicated that repositioning can be promoted by utilizing a wide range of information sources, including medicinal chemical, target, mechanism, main and side-effect-related information, and also bibliometric and taxonomical fingerprints, signatures and knowledge bases. This article describes the adaptation of a conceptually novel, more efficient approach for the identification of new possible therapeutic applications of approved drugs and drug candidates, based on a kernel-based data fusion method. This strategy includes (1) the potentially multiple representation of information sources, (2) the automated weighting and statistically optimal combination of information sources, and (3) the automated weighting of parts of the query compounds. The performance was systematically evaluated by using Anatomical Therapeutic Chemical Classification System classes in a cross-validation framework. The results confirmed that kernel-based data fusion can integrate heterogeneous information sources significantly better than standard rank-based fusion can, and this method provides a unique solution for repositioning; it can also be utilized for de novo drug discovery. The advantages of kernel-based data fusion are illustrated with examples and open problems that are particularly relevant for pharmaceutical applications.

AB - Drug repositioning, an innovative therapeutic application of an old drug, has received much attention as a particularly costeffective strategy in drug RandD. Recent work has indicated that repositioning can be promoted by utilizing a wide range of information sources, including medicinal chemical, target, mechanism, main and side-effect-related information, and also bibliometric and taxonomical fingerprints, signatures and knowledge bases. This article describes the adaptation of a conceptually novel, more efficient approach for the identification of new possible therapeutic applications of approved drugs and drug candidates, based on a kernel-based data fusion method. This strategy includes (1) the potentially multiple representation of information sources, (2) the automated weighting and statistically optimal combination of information sources, and (3) the automated weighting of parts of the query compounds. The performance was systematically evaluated by using Anatomical Therapeutic Chemical Classification System classes in a cross-validation framework. The results confirmed that kernel-based data fusion can integrate heterogeneous information sources significantly better than standard rank-based fusion can, and this method provides a unique solution for repositioning; it can also be utilized for de novo drug discovery. The advantages of kernel-based data fusion are illustrated with examples and open problems that are particularly relevant for pharmaceutical applications.

KW - Data fusion

KW - Drug repositioning

KW - In silico drug discovery

KW - Kernel fusion

KW - Side-effect

KW - Similarity search

KW - Support vector machine

UR - http://www.scopus.com/inward/record.url?scp=84872958472&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84872958472&partnerID=8YFLogxK

U2 - 10.2174/09298673130110

DO - 10.2174/09298673130110

M3 - Article

C2 - 23210850

AN - SCOPUS:84872958472

VL - 20

SP - 95

EP - 107

JO - Current Medicinal Chemistry

JF - Current Medicinal Chemistry

SN - 0929-8673

IS - 1

ER -