Large-scale integration of heterogeneous pharmacogenomic data for identifying drug mechanism of action

Yunan Luo, Sheng Wang, Jinfeng Xiao, Jian Peng

Research output: Contribution to journalConference article

Abstract

A variety of large-scale pharmacogenomic data, such as perturbation experiments and sensitivity profiles, enable the systematical identification of drug mechanism of actions (MoAs), which is a crucial task in the era of precision medicine. However, integrating these complementary pharmacogenomic datasets is inherently challenging due to the wild heterogeneity, high-dimensionality and noisy nature of these datasets. In this work, we develop Mania, a novel method for the scalable integration of large-scale pharmacogenomic data. Mania first constructs a drug-drug similarity network through integrating multiple heterogeneous data sources, including drug sensitivity, drug chemical structure, and perturbation assays. It then learns a compact vector representation for each drug to simultaneously encode its structural and pharmacogenomic properties. Extensive experiments demonstrate that Mania achieves substantially improved performance in both MoAs and targets prediction, compared to predictions based on individual data sources as well as a state-of-the-art integrative method. Moreover, Mania identifies drugs that target frequently mutated cancer genes, which provides novel insights into drug repurposing.

Original languageEnglish (US)
Pages (from-to)44-55
Number of pages12
JournalPacific Symposium on Biocomputing
Volume0
Issue number212669
DOIs
StatePublished - Jan 1 2018
Event23rd Pacific Symposium on Biocomputing, PSB 2018 - Kohala Coast, United States
Duration: Jan 3 2018Jan 7 2018

Fingerprint

LSI circuits
Pharmacogenetics
Bipolar Disorder
Pharmaceutical Preparations
Information Storage and Retrieval
Medicine
Drug Repositioning
Assays
Genes
Experiments
Precision Medicine
Neoplasm Genes

Keywords

  • Data integration
  • Dimensionality reduction
  • Drug mechanisms of action
  • Drug similarity network
  • Drug target

ASJC Scopus subject areas

  • Biomedical Engineering
  • Computational Theory and Mathematics

Cite this

Large-scale integration of heterogeneous pharmacogenomic data for identifying drug mechanism of action. / Luo, Yunan; Wang, Sheng; Xiao, Jinfeng; Peng, Jian.

In: Pacific Symposium on Biocomputing, Vol. 0, No. 212669, 01.01.2018, p. 44-55.

Research output: Contribution to journalConference article

@article{795f56035a1a482a8fa17da8fbb72662,
title = "Large-scale integration of heterogeneous pharmacogenomic data for identifying drug mechanism of action",
abstract = "A variety of large-scale pharmacogenomic data, such as perturbation experiments and sensitivity profiles, enable the systematical identification of drug mechanism of actions (MoAs), which is a crucial task in the era of precision medicine. However, integrating these complementary pharmacogenomic datasets is inherently challenging due to the wild heterogeneity, high-dimensionality and noisy nature of these datasets. In this work, we develop Mania, a novel method for the scalable integration of large-scale pharmacogenomic data. Mania first constructs a drug-drug similarity network through integrating multiple heterogeneous data sources, including drug sensitivity, drug chemical structure, and perturbation assays. It then learns a compact vector representation for each drug to simultaneously encode its structural and pharmacogenomic properties. Extensive experiments demonstrate that Mania achieves substantially improved performance in both MoAs and targets prediction, compared to predictions based on individual data sources as well as a state-of-the-art integrative method. Moreover, Mania identifies drugs that target frequently mutated cancer genes, which provides novel insights into drug repurposing.",
keywords = "Data integration, Dimensionality reduction, Drug mechanisms of action, Drug similarity network, Drug target",
author = "Yunan Luo and Sheng Wang and Jinfeng Xiao and Jian Peng",
year = "2018",
month = "1",
day = "1",
doi = "10.1142/9789813235533_0005",
language = "English (US)",
volume = "0",
pages = "44--55",
journal = "Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing",
issn = "2335-6936",
number = "212669",

}

TY - JOUR

T1 - Large-scale integration of heterogeneous pharmacogenomic data for identifying drug mechanism of action

AU - Luo, Yunan

AU - Wang, Sheng

AU - Xiao, Jinfeng

AU - Peng, Jian

PY - 2018/1/1

Y1 - 2018/1/1

N2 - A variety of large-scale pharmacogenomic data, such as perturbation experiments and sensitivity profiles, enable the systematical identification of drug mechanism of actions (MoAs), which is a crucial task in the era of precision medicine. However, integrating these complementary pharmacogenomic datasets is inherently challenging due to the wild heterogeneity, high-dimensionality and noisy nature of these datasets. In this work, we develop Mania, a novel method for the scalable integration of large-scale pharmacogenomic data. Mania first constructs a drug-drug similarity network through integrating multiple heterogeneous data sources, including drug sensitivity, drug chemical structure, and perturbation assays. It then learns a compact vector representation for each drug to simultaneously encode its structural and pharmacogenomic properties. Extensive experiments demonstrate that Mania achieves substantially improved performance in both MoAs and targets prediction, compared to predictions based on individual data sources as well as a state-of-the-art integrative method. Moreover, Mania identifies drugs that target frequently mutated cancer genes, which provides novel insights into drug repurposing.

AB - A variety of large-scale pharmacogenomic data, such as perturbation experiments and sensitivity profiles, enable the systematical identification of drug mechanism of actions (MoAs), which is a crucial task in the era of precision medicine. However, integrating these complementary pharmacogenomic datasets is inherently challenging due to the wild heterogeneity, high-dimensionality and noisy nature of these datasets. In this work, we develop Mania, a novel method for the scalable integration of large-scale pharmacogenomic data. Mania first constructs a drug-drug similarity network through integrating multiple heterogeneous data sources, including drug sensitivity, drug chemical structure, and perturbation assays. It then learns a compact vector representation for each drug to simultaneously encode its structural and pharmacogenomic properties. Extensive experiments demonstrate that Mania achieves substantially improved performance in both MoAs and targets prediction, compared to predictions based on individual data sources as well as a state-of-the-art integrative method. Moreover, Mania identifies drugs that target frequently mutated cancer genes, which provides novel insights into drug repurposing.

KW - Data integration

KW - Dimensionality reduction

KW - Drug mechanisms of action

KW - Drug similarity network

KW - Drug target

UR - http://www.scopus.com/inward/record.url?scp=85048511776&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85048511776&partnerID=8YFLogxK

U2 - 10.1142/9789813235533_0005

DO - 10.1142/9789813235533_0005

M3 - Conference article

C2 - 29218868

AN - SCOPUS:85048511776

VL - 0

SP - 44

EP - 55

JO - Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing

JF - Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing

SN - 2335-6936

IS - 212669

ER -