Translational systems pharmacology-based predictive assessment of drug-induced cardiomyopathy

DImitris E. Messinis, Ioannis N. Melas, Junguk Hur, Navya Varshney, Leonidas G. Alexopoulos, Jane P.F. Bai

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Drug-induced cardiomyopathy contributes to drug attrition. We compared two pipelines of predictive modeling: (1) applying elastic net (EN) to differentially expressed genes (DEGs) of drugs; (2) applying integer linear programming (ILP) to construct each drug's signaling pathway starting from its targets to downstream proteins, to transcription factors, and to its DEGs in human cardiomyocytes, and then subjecting the genes/proteins in the drugs' signaling networks to EN regression. We classified 31 drugs with availability of DEGs into 13 toxic and 18 nontoxic drugs based on a clinical cardiomyopathy incidence cutoff of 0.1%. The ILP-augmented modeling increased prediction accuracy from 79% to 88% (sensitivity: 88%; specificity: 89%) under leave-one-out cross validation. The ILP-constructed signaling networks of drugs were better predictors than DEGs. Per literature, the microRNAs that reportedly regulate expression of our six top predictors are of diagnostic value for natural heart failure or doxorubicin-induced cardiomyopathy. This translational predictive modeling might uncover potential biomarkers.

Original languageEnglish (US)
Pages (from-to)166-174
Number of pages9
JournalCPT: Pharmacometrics and Systems Pharmacology
Volume7
Issue number3
DOIs
StatePublished - Mar 1 2018
Externally publishedYes

Fingerprint

Cardiomyopathy
Pharmacology
Cardiomyopathies
Drugs
Genes
Linear programming
Linear Programming
Pharmaceutical Preparations
Integer Linear Programming
Gene
Elastic Net
Predictive Modeling
Proteins
Transcription factors
Biomarkers
Predictors
Protein
Heart Failure
Attrition
Pipelines

ASJC Scopus subject areas

  • Modeling and Simulation
  • Pharmacology (medical)

Cite this

Translational systems pharmacology-based predictive assessment of drug-induced cardiomyopathy. / Messinis, DImitris E.; Melas, Ioannis N.; Hur, Junguk; Varshney, Navya; Alexopoulos, Leonidas G.; Bai, Jane P.F.

In: CPT: Pharmacometrics and Systems Pharmacology, Vol. 7, No. 3, 01.03.2018, p. 166-174.

Research output: Contribution to journalArticle

Messinis, DImitris E. ; Melas, Ioannis N. ; Hur, Junguk ; Varshney, Navya ; Alexopoulos, Leonidas G. ; Bai, Jane P.F. / Translational systems pharmacology-based predictive assessment of drug-induced cardiomyopathy. In: CPT: Pharmacometrics and Systems Pharmacology. 2018 ; Vol. 7, No. 3. pp. 166-174.
@article{3b2b66f0c4da40e58e7144f2e0061abc,
title = "Translational systems pharmacology-based predictive assessment of drug-induced cardiomyopathy",
abstract = "Drug-induced cardiomyopathy contributes to drug attrition. We compared two pipelines of predictive modeling: (1) applying elastic net (EN) to differentially expressed genes (DEGs) of drugs; (2) applying integer linear programming (ILP) to construct each drug's signaling pathway starting from its targets to downstream proteins, to transcription factors, and to its DEGs in human cardiomyocytes, and then subjecting the genes/proteins in the drugs' signaling networks to EN regression. We classified 31 drugs with availability of DEGs into 13 toxic and 18 nontoxic drugs based on a clinical cardiomyopathy incidence cutoff of 0.1{\%}. The ILP-augmented modeling increased prediction accuracy from 79{\%} to 88{\%} (sensitivity: 88{\%}; specificity: 89{\%}) under leave-one-out cross validation. The ILP-constructed signaling networks of drugs were better predictors than DEGs. Per literature, the microRNAs that reportedly regulate expression of our six top predictors are of diagnostic value for natural heart failure or doxorubicin-induced cardiomyopathy. This translational predictive modeling might uncover potential biomarkers.",
author = "Messinis, {DImitris E.} and Melas, {Ioannis N.} and Junguk Hur and Navya Varshney and Alexopoulos, {Leonidas G.} and Bai, {Jane P.F.}",
year = "2018",
month = "3",
day = "1",
doi = "10.1002/psp4.12272",
language = "English (US)",
volume = "7",
pages = "166--174",
journal = "CPT: Pharmacometrics and Systems Pharmacology",
issn = "2163-8306",
publisher = "Nature Publishing Group",
number = "3",

}

TY - JOUR

T1 - Translational systems pharmacology-based predictive assessment of drug-induced cardiomyopathy

AU - Messinis, DImitris E.

AU - Melas, Ioannis N.

AU - Hur, Junguk

AU - Varshney, Navya

AU - Alexopoulos, Leonidas G.

AU - Bai, Jane P.F.

PY - 2018/3/1

Y1 - 2018/3/1

N2 - Drug-induced cardiomyopathy contributes to drug attrition. We compared two pipelines of predictive modeling: (1) applying elastic net (EN) to differentially expressed genes (DEGs) of drugs; (2) applying integer linear programming (ILP) to construct each drug's signaling pathway starting from its targets to downstream proteins, to transcription factors, and to its DEGs in human cardiomyocytes, and then subjecting the genes/proteins in the drugs' signaling networks to EN regression. We classified 31 drugs with availability of DEGs into 13 toxic and 18 nontoxic drugs based on a clinical cardiomyopathy incidence cutoff of 0.1%. The ILP-augmented modeling increased prediction accuracy from 79% to 88% (sensitivity: 88%; specificity: 89%) under leave-one-out cross validation. The ILP-constructed signaling networks of drugs were better predictors than DEGs. Per literature, the microRNAs that reportedly regulate expression of our six top predictors are of diagnostic value for natural heart failure or doxorubicin-induced cardiomyopathy. This translational predictive modeling might uncover potential biomarkers.

AB - Drug-induced cardiomyopathy contributes to drug attrition. We compared two pipelines of predictive modeling: (1) applying elastic net (EN) to differentially expressed genes (DEGs) of drugs; (2) applying integer linear programming (ILP) to construct each drug's signaling pathway starting from its targets to downstream proteins, to transcription factors, and to its DEGs in human cardiomyocytes, and then subjecting the genes/proteins in the drugs' signaling networks to EN regression. We classified 31 drugs with availability of DEGs into 13 toxic and 18 nontoxic drugs based on a clinical cardiomyopathy incidence cutoff of 0.1%. The ILP-augmented modeling increased prediction accuracy from 79% to 88% (sensitivity: 88%; specificity: 89%) under leave-one-out cross validation. The ILP-constructed signaling networks of drugs were better predictors than DEGs. Per literature, the microRNAs that reportedly regulate expression of our six top predictors are of diagnostic value for natural heart failure or doxorubicin-induced cardiomyopathy. This translational predictive modeling might uncover potential biomarkers.

UR - http://www.scopus.com/inward/record.url?scp=85044463879&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85044463879&partnerID=8YFLogxK

U2 - 10.1002/psp4.12272

DO - 10.1002/psp4.12272

M3 - Article

VL - 7

SP - 166

EP - 174

JO - CPT: Pharmacometrics and Systems Pharmacology

JF - CPT: Pharmacometrics and Systems Pharmacology

SN - 2163-8306

IS - 3

ER -