Predicting drug-target interactions from chemical and genomic kernels using Bayesian matrix factorization

Research output: Contribution to journalArticle

171 Citations (Scopus)

Abstract

Motivation: Identifying interactions between drug compounds and target proteins has a great practical importance in the drug discovery process for known diseases. Existing databases contain very few experimentally validated drug-target interactions and formulating successful computational methods for predicting interactions remains challenging. Results: In this study, we consider four different drug-target interaction networks from humans involving enzymes, ion channels, G-protein-coupled receptors and nuclear receptors. We then propose a novel Bayesian formulation that combines dimensionality reduction, matrix factorization and binary classification for predicting drug-target interaction networks using only chemical similarity between drug compounds and genomic similarity between target proteins. The novelty of our approach comes from the joint Bayesian formulation of projecting drug compounds and target proteins into a unified subspace using the similarities and estimating the interaction network in that subspace. We propose using a variational approximation in order to obtain an efficient inference scheme and give its detailed derivations. Finally, we demonstrate the performance of our proposed method in three different scenarios: (i) exploratory data analysis using low-dimensional projections, (ii) predicting interactions for the out-of-sample drug compounds and (iii) predicting unknown interactions of the given network.

Original languageEnglish (US)
Article numberbts360
Pages (from-to)2304-2310
Number of pages7
JournalBioinformatics
Volume28
Issue number18
DOIs
StatePublished - Sep 2012
Externally publishedYes

Fingerprint

Matrix Factorization
Factorization
Drug Interactions
Genomics
Drugs
kernel
Proteins
Target
Interaction
Pharmaceutical Preparations
Drug interactions
Drug Compounding
Drug Discovery
Cytoplasmic and Nuclear Receptors
G-Protein-Coupled Receptors
Computational methods
Protein
Ion Channels
Receptor
Enzymes

ASJC Scopus subject areas

  • Biochemistry
  • Molecular Biology
  • Computational Theory and Mathematics
  • Computer Science Applications
  • Computational Mathematics
  • Statistics and Probability
  • Medicine(all)

Cite this

Predicting drug-target interactions from chemical and genomic kernels using Bayesian matrix factorization. / Gonen, Mehmet.

In: Bioinformatics, Vol. 28, No. 18, bts360, 09.2012, p. 2304-2310.

Research output: Contribution to journalArticle

@article{015640aaf57d42038f3e057649ebdbe7,
title = "Predicting drug-target interactions from chemical and genomic kernels using Bayesian matrix factorization",
abstract = "Motivation: Identifying interactions between drug compounds and target proteins has a great practical importance in the drug discovery process for known diseases. Existing databases contain very few experimentally validated drug-target interactions and formulating successful computational methods for predicting interactions remains challenging. Results: In this study, we consider four different drug-target interaction networks from humans involving enzymes, ion channels, G-protein-coupled receptors and nuclear receptors. We then propose a novel Bayesian formulation that combines dimensionality reduction, matrix factorization and binary classification for predicting drug-target interaction networks using only chemical similarity between drug compounds and genomic similarity between target proteins. The novelty of our approach comes from the joint Bayesian formulation of projecting drug compounds and target proteins into a unified subspace using the similarities and estimating the interaction network in that subspace. We propose using a variational approximation in order to obtain an efficient inference scheme and give its detailed derivations. Finally, we demonstrate the performance of our proposed method in three different scenarios: (i) exploratory data analysis using low-dimensional projections, (ii) predicting interactions for the out-of-sample drug compounds and (iii) predicting unknown interactions of the given network.",
author = "Mehmet Gonen",
year = "2012",
month = "9",
doi = "10.1093/bioinformatics/bts360",
language = "English (US)",
volume = "28",
pages = "2304--2310",
journal = "Bioinformatics",
issn = "1367-4803",
publisher = "Oxford University Press",
number = "18",

}

TY - JOUR

T1 - Predicting drug-target interactions from chemical and genomic kernels using Bayesian matrix factorization

AU - Gonen, Mehmet

PY - 2012/9

Y1 - 2012/9

N2 - Motivation: Identifying interactions between drug compounds and target proteins has a great practical importance in the drug discovery process for known diseases. Existing databases contain very few experimentally validated drug-target interactions and formulating successful computational methods for predicting interactions remains challenging. Results: In this study, we consider four different drug-target interaction networks from humans involving enzymes, ion channels, G-protein-coupled receptors and nuclear receptors. We then propose a novel Bayesian formulation that combines dimensionality reduction, matrix factorization and binary classification for predicting drug-target interaction networks using only chemical similarity between drug compounds and genomic similarity between target proteins. The novelty of our approach comes from the joint Bayesian formulation of projecting drug compounds and target proteins into a unified subspace using the similarities and estimating the interaction network in that subspace. We propose using a variational approximation in order to obtain an efficient inference scheme and give its detailed derivations. Finally, we demonstrate the performance of our proposed method in three different scenarios: (i) exploratory data analysis using low-dimensional projections, (ii) predicting interactions for the out-of-sample drug compounds and (iii) predicting unknown interactions of the given network.

AB - Motivation: Identifying interactions between drug compounds and target proteins has a great practical importance in the drug discovery process for known diseases. Existing databases contain very few experimentally validated drug-target interactions and formulating successful computational methods for predicting interactions remains challenging. Results: In this study, we consider four different drug-target interaction networks from humans involving enzymes, ion channels, G-protein-coupled receptors and nuclear receptors. We then propose a novel Bayesian formulation that combines dimensionality reduction, matrix factorization and binary classification for predicting drug-target interaction networks using only chemical similarity between drug compounds and genomic similarity between target proteins. The novelty of our approach comes from the joint Bayesian formulation of projecting drug compounds and target proteins into a unified subspace using the similarities and estimating the interaction network in that subspace. We propose using a variational approximation in order to obtain an efficient inference scheme and give its detailed derivations. Finally, we demonstrate the performance of our proposed method in three different scenarios: (i) exploratory data analysis using low-dimensional projections, (ii) predicting interactions for the out-of-sample drug compounds and (iii) predicting unknown interactions of the given network.

UR - http://www.scopus.com/inward/record.url?scp=84866459051&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84866459051&partnerID=8YFLogxK

U2 - 10.1093/bioinformatics/bts360

DO - 10.1093/bioinformatics/bts360

M3 - Article

C2 - 22730431

AN - SCOPUS:84866459051

VL - 28

SP - 2304

EP - 2310

JO - Bioinformatics

JF - Bioinformatics

SN - 1367-4803

IS - 18

M1 - bts360

ER -