Drug repositioning: a machine-learning approach through data integration

Francesco Napolitano, Yan Zhao, Vânia M Moreira, Roberto Tagliaferri, Juha Kere, Mauro D'Amato, Dario Greco

Research output: Contribution to journalArticle

104 Citations (Scopus)

Abstract

Existing computational methods for drug repositioning either rely only on the gene expression response of cell lines after treatment, or on drug-to-disease relationships, merging several information levels. However, the noisy nature of the gene expression and the scarcity of genomic data for many diseases are important limitations to such approaches. Here we focused on a drug-centered approach by predicting the therapeutic class of FDA-approved compounds, not considering data concerning the diseases. We propose a novel computational approach to predict drug repositioning based on state-of-the-art machine-learning algorithms. We have integrated multiple layers of information: i) on the distances of the drugs based on how similar are their chemical structures, ii) on how close are their targets within the protein-protein interaction network, and iii) on how correlated are the gene expression patterns after treatment. Our classifier reaches high accuracy levels (78%), allowing us to re-interpret the top misclassifications as re-classifications, after rigorous statistical evaluation. Efficient drug repurposing has the potential to significantly impact the whole field of drug development. The results presented here can significantly accelerate the translation into the clinics of known compounds for novel therapeutic uses.

LanguageEnglish
Article number30
Number of pages9
JournalJournal of Cheminformatics
Volume5
Issue number1
DOIs
Publication statusPublished - 22 Jun 2013

Fingerprint

data integration
machine learning
Data integration
Gene expression
Learning systems
drugs
drug
gene expression
Pharmaceutical Preparations
learning
Proteins
Computational methods
Merging
Learning algorithms
Disease
Classifiers
Cells
proteins
classifiers
cultured cells

Keywords

  • drug repositioning
  • connectivity map
  • CMap
  • integrative genomics

Cite this

Napolitano, F., Zhao, Y., Moreira, V. M., Tagliaferri, R., Kere, J., D'Amato, M., & Greco, D. (2013). Drug repositioning: a machine-learning approach through data integration. Journal of Cheminformatics, 5(1), [30]. https://doi.org/10.1186/1758-2946-5-30
Napolitano, Francesco ; Zhao, Yan ; Moreira, Vânia M ; Tagliaferri, Roberto ; Kere, Juha ; D'Amato, Mauro ; Greco, Dario. / Drug repositioning : a machine-learning approach through data integration. In: Journal of Cheminformatics. 2013 ; Vol. 5, No. 1.
@article{95c018ee898c4ab6b7e44d49c1752974,
title = "Drug repositioning: a machine-learning approach through data integration",
abstract = "Existing computational methods for drug repositioning either rely only on the gene expression response of cell lines after treatment, or on drug-to-disease relationships, merging several information levels. However, the noisy nature of the gene expression and the scarcity of genomic data for many diseases are important limitations to such approaches. Here we focused on a drug-centered approach by predicting the therapeutic class of FDA-approved compounds, not considering data concerning the diseases. We propose a novel computational approach to predict drug repositioning based on state-of-the-art machine-learning algorithms. We have integrated multiple layers of information: i) on the distances of the drugs based on how similar are their chemical structures, ii) on how close are their targets within the protein-protein interaction network, and iii) on how correlated are the gene expression patterns after treatment. Our classifier reaches high accuracy levels (78{\%}), allowing us to re-interpret the top misclassifications as re-classifications, after rigorous statistical evaluation. Efficient drug repurposing has the potential to significantly impact the whole field of drug development. The results presented here can significantly accelerate the translation into the clinics of known compounds for novel therapeutic uses.",
keywords = "drug repositioning, connectivity map, CMap, integrative genomics",
author = "Francesco Napolitano and Yan Zhao and Moreira, {V{\^a}nia M} and Roberto Tagliaferri and Juha Kere and Mauro D'Amato and Dario Greco",
year = "2013",
month = "6",
day = "22",
doi = "10.1186/1758-2946-5-30",
language = "English",
volume = "5",
journal = "Journal of Cheminformatics",
issn = "1758-2946",
number = "1",

}

Napolitano, F, Zhao, Y, Moreira, VM, Tagliaferri, R, Kere, J, D'Amato, M & Greco, D 2013, 'Drug repositioning: a machine-learning approach through data integration' Journal of Cheminformatics, vol. 5, no. 1, 30. https://doi.org/10.1186/1758-2946-5-30

Drug repositioning : a machine-learning approach through data integration. / Napolitano, Francesco; Zhao, Yan; Moreira, Vânia M; Tagliaferri, Roberto; Kere, Juha; D'Amato, Mauro; Greco, Dario.

In: Journal of Cheminformatics, Vol. 5, No. 1, 30, 22.06.2013.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Drug repositioning

T2 - Journal of Cheminformatics

AU - Napolitano, Francesco

AU - Zhao, Yan

AU - Moreira, Vânia M

AU - Tagliaferri, Roberto

AU - Kere, Juha

AU - D'Amato, Mauro

AU - Greco, Dario

PY - 2013/6/22

Y1 - 2013/6/22

N2 - Existing computational methods for drug repositioning either rely only on the gene expression response of cell lines after treatment, or on drug-to-disease relationships, merging several information levels. However, the noisy nature of the gene expression and the scarcity of genomic data for many diseases are important limitations to such approaches. Here we focused on a drug-centered approach by predicting the therapeutic class of FDA-approved compounds, not considering data concerning the diseases. We propose a novel computational approach to predict drug repositioning based on state-of-the-art machine-learning algorithms. We have integrated multiple layers of information: i) on the distances of the drugs based on how similar are their chemical structures, ii) on how close are their targets within the protein-protein interaction network, and iii) on how correlated are the gene expression patterns after treatment. Our classifier reaches high accuracy levels (78%), allowing us to re-interpret the top misclassifications as re-classifications, after rigorous statistical evaluation. Efficient drug repurposing has the potential to significantly impact the whole field of drug development. The results presented here can significantly accelerate the translation into the clinics of known compounds for novel therapeutic uses.

AB - Existing computational methods for drug repositioning either rely only on the gene expression response of cell lines after treatment, or on drug-to-disease relationships, merging several information levels. However, the noisy nature of the gene expression and the scarcity of genomic data for many diseases are important limitations to such approaches. Here we focused on a drug-centered approach by predicting the therapeutic class of FDA-approved compounds, not considering data concerning the diseases. We propose a novel computational approach to predict drug repositioning based on state-of-the-art machine-learning algorithms. We have integrated multiple layers of information: i) on the distances of the drugs based on how similar are their chemical structures, ii) on how close are their targets within the protein-protein interaction network, and iii) on how correlated are the gene expression patterns after treatment. Our classifier reaches high accuracy levels (78%), allowing us to re-interpret the top misclassifications as re-classifications, after rigorous statistical evaluation. Efficient drug repurposing has the potential to significantly impact the whole field of drug development. The results presented here can significantly accelerate the translation into the clinics of known compounds for novel therapeutic uses.

KW - drug repositioning

KW - connectivity map

KW - CMap

KW - integrative genomics

UR - https://jcheminf.springeropen.com/articles/10.1186/1758-2946-5-30

U2 - 10.1186/1758-2946-5-30

DO - 10.1186/1758-2946-5-30

M3 - Article

VL - 5

JO - Journal of Cheminformatics

JF - Journal of Cheminformatics

SN - 1758-2946

IS - 1

M1 - 30

ER -