Predict drug sensitivity of cancer cells with pathway activity inference

Xuewei Wang, Zhifu D Sun, Michael T. Zimmermann, Andrej Bugrim, Jean-Pierre Kocher

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Background: Predicting cellular responses to drugs has been a major challenge for personalized drug therapy regimen. Recent pharmacogenomic studies measured the sensitivities of heterogeneous cell lines to numerous drugs, and provided valuable data resources to develop and validate computational approaches for the prediction of drug responses. Most of current approaches predict drug sensitivity by building prediction models with individual genes, which suffer from low reproducibility due to biologic variability and difficulty to interpret biological relevance of novel gene-drug associations. As an alternative, pathway activity scores derived from gene expression could predict drug response of cancer cells. Method: In this study, pathway-based prediction models were built with four approaches inferring pathway activity in unsupervised manner, including competitive scoring approaches (DiffRank and GSVA) and self-contained scoring approaches (PLAGE and Z-score). These unsupervised pathway activity inference approaches were applied to predict drug responses of cancer cells using data from Cancer Cell Line Encyclopedia (CCLE). Results: Our analysis on all the 24 drugs from CCLE demonstrated that pathway-based models achieved better predictions for 14 out of the 24 drugs, while taking fewer features as inputs. Further investigation on indicated that pathway-based models indeed captured pathways involving drug-related genes (targets, transporters and metabolic enzymes) for majority of drugs, whereas gene-models failed to identify these drug-related genes, in most cases. Among the four approaches, competitive scoring (DiffRank and GSVA) provided more accurate predictions and captured more pathways involving drug-related genes than self-contained scoring (PLAGE and Z-Score). Detailed interpretation of top pathways from the top method (DiffRank) highlights the merit of pathway-based approaches to predict drug response by identifying pathways relevant to drug mechanisms. Conclusion: Taken together, pathway-based modeling with inferred pathway activity is a promising alternative to predict drug response, with the ability to easily interpret results and provide biological insights into the mechanisms of drug actions.

Original languageEnglish (US)
Article number15
JournalBMC Medical Genomics
Volume12
DOIs
StatePublished - Jan 31 2019

Fingerprint

Pharmaceutical Preparations
Neoplasms
Encyclopedias
Genes
Cell Line
Gene Expression
Drug Therapy
Enzymes

Keywords

  • Cancer
  • Drug sensitivity
  • Machine learning
  • Pathway activity
  • Pharmacogenomics
  • Precision therapy

ASJC Scopus subject areas

  • Genetics
  • Genetics(clinical)

Cite this

Predict drug sensitivity of cancer cells with pathway activity inference. / Wang, Xuewei; Sun, Zhifu D; Zimmermann, Michael T.; Bugrim, Andrej; Kocher, Jean-Pierre.

In: BMC Medical Genomics, Vol. 12, 15, 31.01.2019.

Research output: Contribution to journalArticle

@article{959ae9cdbe3e4fb6a03f7877e1731398,
title = "Predict drug sensitivity of cancer cells with pathway activity inference",
abstract = "Background: Predicting cellular responses to drugs has been a major challenge for personalized drug therapy regimen. Recent pharmacogenomic studies measured the sensitivities of heterogeneous cell lines to numerous drugs, and provided valuable data resources to develop and validate computational approaches for the prediction of drug responses. Most of current approaches predict drug sensitivity by building prediction models with individual genes, which suffer from low reproducibility due to biologic variability and difficulty to interpret biological relevance of novel gene-drug associations. As an alternative, pathway activity scores derived from gene expression could predict drug response of cancer cells. Method: In this study, pathway-based prediction models were built with four approaches inferring pathway activity in unsupervised manner, including competitive scoring approaches (DiffRank and GSVA) and self-contained scoring approaches (PLAGE and Z-score). These unsupervised pathway activity inference approaches were applied to predict drug responses of cancer cells using data from Cancer Cell Line Encyclopedia (CCLE). Results: Our analysis on all the 24 drugs from CCLE demonstrated that pathway-based models achieved better predictions for 14 out of the 24 drugs, while taking fewer features as inputs. Further investigation on indicated that pathway-based models indeed captured pathways involving drug-related genes (targets, transporters and metabolic enzymes) for majority of drugs, whereas gene-models failed to identify these drug-related genes, in most cases. Among the four approaches, competitive scoring (DiffRank and GSVA) provided more accurate predictions and captured more pathways involving drug-related genes than self-contained scoring (PLAGE and Z-Score). Detailed interpretation of top pathways from the top method (DiffRank) highlights the merit of pathway-based approaches to predict drug response by identifying pathways relevant to drug mechanisms. Conclusion: Taken together, pathway-based modeling with inferred pathway activity is a promising alternative to predict drug response, with the ability to easily interpret results and provide biological insights into the mechanisms of drug actions.",
keywords = "Cancer, Drug sensitivity, Machine learning, Pathway activity, Pharmacogenomics, Precision therapy",
author = "Xuewei Wang and Sun, {Zhifu D} and Zimmermann, {Michael T.} and Andrej Bugrim and Jean-Pierre Kocher",
year = "2019",
month = "1",
day = "31",
doi = "10.1186/s12920-018-0449-4",
language = "English (US)",
volume = "12",
journal = "BMC Medical Genomics",
issn = "1755-8794",
publisher = "BioMed Central",

}

TY - JOUR

T1 - Predict drug sensitivity of cancer cells with pathway activity inference

AU - Wang, Xuewei

AU - Sun, Zhifu D

AU - Zimmermann, Michael T.

AU - Bugrim, Andrej

AU - Kocher, Jean-Pierre

PY - 2019/1/31

Y1 - 2019/1/31

N2 - Background: Predicting cellular responses to drugs has been a major challenge for personalized drug therapy regimen. Recent pharmacogenomic studies measured the sensitivities of heterogeneous cell lines to numerous drugs, and provided valuable data resources to develop and validate computational approaches for the prediction of drug responses. Most of current approaches predict drug sensitivity by building prediction models with individual genes, which suffer from low reproducibility due to biologic variability and difficulty to interpret biological relevance of novel gene-drug associations. As an alternative, pathway activity scores derived from gene expression could predict drug response of cancer cells. Method: In this study, pathway-based prediction models were built with four approaches inferring pathway activity in unsupervised manner, including competitive scoring approaches (DiffRank and GSVA) and self-contained scoring approaches (PLAGE and Z-score). These unsupervised pathway activity inference approaches were applied to predict drug responses of cancer cells using data from Cancer Cell Line Encyclopedia (CCLE). Results: Our analysis on all the 24 drugs from CCLE demonstrated that pathway-based models achieved better predictions for 14 out of the 24 drugs, while taking fewer features as inputs. Further investigation on indicated that pathway-based models indeed captured pathways involving drug-related genes (targets, transporters and metabolic enzymes) for majority of drugs, whereas gene-models failed to identify these drug-related genes, in most cases. Among the four approaches, competitive scoring (DiffRank and GSVA) provided more accurate predictions and captured more pathways involving drug-related genes than self-contained scoring (PLAGE and Z-Score). Detailed interpretation of top pathways from the top method (DiffRank) highlights the merit of pathway-based approaches to predict drug response by identifying pathways relevant to drug mechanisms. Conclusion: Taken together, pathway-based modeling with inferred pathway activity is a promising alternative to predict drug response, with the ability to easily interpret results and provide biological insights into the mechanisms of drug actions.

AB - Background: Predicting cellular responses to drugs has been a major challenge for personalized drug therapy regimen. Recent pharmacogenomic studies measured the sensitivities of heterogeneous cell lines to numerous drugs, and provided valuable data resources to develop and validate computational approaches for the prediction of drug responses. Most of current approaches predict drug sensitivity by building prediction models with individual genes, which suffer from low reproducibility due to biologic variability and difficulty to interpret biological relevance of novel gene-drug associations. As an alternative, pathway activity scores derived from gene expression could predict drug response of cancer cells. Method: In this study, pathway-based prediction models were built with four approaches inferring pathway activity in unsupervised manner, including competitive scoring approaches (DiffRank and GSVA) and self-contained scoring approaches (PLAGE and Z-score). These unsupervised pathway activity inference approaches were applied to predict drug responses of cancer cells using data from Cancer Cell Line Encyclopedia (CCLE). Results: Our analysis on all the 24 drugs from CCLE demonstrated that pathway-based models achieved better predictions for 14 out of the 24 drugs, while taking fewer features as inputs. Further investigation on indicated that pathway-based models indeed captured pathways involving drug-related genes (targets, transporters and metabolic enzymes) for majority of drugs, whereas gene-models failed to identify these drug-related genes, in most cases. Among the four approaches, competitive scoring (DiffRank and GSVA) provided more accurate predictions and captured more pathways involving drug-related genes than self-contained scoring (PLAGE and Z-Score). Detailed interpretation of top pathways from the top method (DiffRank) highlights the merit of pathway-based approaches to predict drug response by identifying pathways relevant to drug mechanisms. Conclusion: Taken together, pathway-based modeling with inferred pathway activity is a promising alternative to predict drug response, with the ability to easily interpret results and provide biological insights into the mechanisms of drug actions.

KW - Cancer

KW - Drug sensitivity

KW - Machine learning

KW - Pathway activity

KW - Pharmacogenomics

KW - Precision therapy

UR - http://www.scopus.com/inward/record.url?scp=85060845256&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85060845256&partnerID=8YFLogxK

U2 - 10.1186/s12920-018-0449-4

DO - 10.1186/s12920-018-0449-4

M3 - Article

VL - 12

JO - BMC Medical Genomics

JF - BMC Medical Genomics

SN - 1755-8794

M1 - 15

ER -