A transcriptomics data-driven gene space accurately predicts liver cytopathology and drug-induced liver injury

Pekka Kohonen; Juuso A Parkkinen; Egon L Willighagen; Rebecca Ceder; Krister Wennerberg; Samuel Kaski; Roland C Grafström

doi:10.1038/ncomms15932

A transcriptomics data-driven gene space accurately predicts liver cytopathology and drug-induced liver injury

Pekka Kohonen, Juuso A Parkkinen, Egon L Willighagen, Rebecca Ceder, Krister Wennerberg, Samuel Kaski, Roland C Grafström

43 Citations (Scopus)

Abstract

Predicting unanticipated harmful effects of chemicals and drug molecules is a difficult and costly task. Here we utilize a 'big data compacting and data fusion'-concept to capture diverse adverse outcomes on cellular and organismal levels. The approach generates from transcriptomics data set a 'predictive toxicogenomics space' (PTGS) tool composed of 1,331 genes distributed over 14 overlapping cytotoxicity-related gene space components. Involving ∼2.5 × 108 data points and 1,300 compounds to construct and validate the PTGS, the tool serves to: explain dose-dependent cytotoxicity effects, provide a virtual cytotoxicity probability estimate intrinsic to omics data, predict chemically-induced pathological states in liver resulting from repeated dosing of rats, and furthermore, predict human drug-induced liver injury (DILI) from hepatocyte experiments. Analysing 68 DILI-annotated drugs, the PTGS tool outperforms and complements existing tests, leading to a hereto-unseen level of DILI prediction accuracy.

Original language	English
Journal	Nature Communications
Volume	8
Pages (from-to)	15932
ISSN	2041-1723
DOIs	https://doi.org/10.1038/ncomms15932
Publication status	Published - 3 Jul 2017
Externally published	Yes

Access to Document

10.1038/ncomms15932Licence: CC BY

pmc5500850?pdf=renderFinal published version, 2.05 MBLicence: CC BY

Cite this

@article{55f9db45607e4c3b8e26e99842c8cbe7,

title = "A transcriptomics data-driven gene space accurately predicts liver cytopathology and drug-induced liver injury",

abstract = "Predicting unanticipated harmful effects of chemicals and drug molecules is a difficult and costly task. Here we utilize a 'big data compacting and data fusion'-concept to capture diverse adverse outcomes on cellular and organismal levels. The approach generates from transcriptomics data set a 'predictive toxicogenomics space' (PTGS) tool composed of 1,331 genes distributed over 14 overlapping cytotoxicity-related gene space components. Involving ∼2.5 × 108 data points and 1,300 compounds to construct and validate the PTGS, the tool serves to: explain dose-dependent cytotoxicity effects, provide a virtual cytotoxicity probability estimate intrinsic to omics data, predict chemically-induced pathological states in liver resulting from repeated dosing of rats, and furthermore, predict human drug-induced liver injury (DILI) from hepatocyte experiments. Analysing 68 DILI-annotated drugs, the PTGS tool outperforms and complements existing tests, leading to a hereto-unseen level of DILI prediction accuracy.",

author = "Pekka Kohonen and Parkkinen, {Juuso A} and Willighagen, {Egon L} and Rebecca Ceder and Krister Wennerberg and Samuel Kaski and Grafstr{\"o}m, {Roland C}",

year = "2017",

month = jul,

day = "3",

doi = "10.1038/ncomms15932",

language = "English",

volume = "8",

pages = "15932",

journal = "Nature Communications",

issn = "2041-1723",

publisher = "nature publishing group",

}

TY - JOUR

T1 - A transcriptomics data-driven gene space accurately predicts liver cytopathology and drug-induced liver injury

AU - Kohonen, Pekka

AU - Parkkinen, Juuso A

AU - Willighagen, Egon L

AU - Ceder, Rebecca

AU - Wennerberg, Krister

AU - Kaski, Samuel

AU - Grafström, Roland C

PY - 2017/7/3

Y1 - 2017/7/3

N2 - Predicting unanticipated harmful effects of chemicals and drug molecules is a difficult and costly task. Here we utilize a 'big data compacting and data fusion'-concept to capture diverse adverse outcomes on cellular and organismal levels. The approach generates from transcriptomics data set a 'predictive toxicogenomics space' (PTGS) tool composed of 1,331 genes distributed over 14 overlapping cytotoxicity-related gene space components. Involving ∼2.5 × 108 data points and 1,300 compounds to construct and validate the PTGS, the tool serves to: explain dose-dependent cytotoxicity effects, provide a virtual cytotoxicity probability estimate intrinsic to omics data, predict chemically-induced pathological states in liver resulting from repeated dosing of rats, and furthermore, predict human drug-induced liver injury (DILI) from hepatocyte experiments. Analysing 68 DILI-annotated drugs, the PTGS tool outperforms and complements existing tests, leading to a hereto-unseen level of DILI prediction accuracy.

AB - Predicting unanticipated harmful effects of chemicals and drug molecules is a difficult and costly task. Here we utilize a 'big data compacting and data fusion'-concept to capture diverse adverse outcomes on cellular and organismal levels. The approach generates from transcriptomics data set a 'predictive toxicogenomics space' (PTGS) tool composed of 1,331 genes distributed over 14 overlapping cytotoxicity-related gene space components. Involving ∼2.5 × 108 data points and 1,300 compounds to construct and validate the PTGS, the tool serves to: explain dose-dependent cytotoxicity effects, provide a virtual cytotoxicity probability estimate intrinsic to omics data, predict chemically-induced pathological states in liver resulting from repeated dosing of rats, and furthermore, predict human drug-induced liver injury (DILI) from hepatocyte experiments. Analysing 68 DILI-annotated drugs, the PTGS tool outperforms and complements existing tests, leading to a hereto-unseen level of DILI prediction accuracy.

U2 - 10.1038/ncomms15932

DO - 10.1038/ncomms15932

M3 - Journal article

C2 - 28671182

SN - 2041-1723

VL - 8

SP - 15932

JO - Nature Communications

JF - Nature Communications

ER -

A transcriptomics data-driven gene space accurately predicts liver cytopathology and drug-induced liver injury

Abstract

Access to Document

Fingerprint

Cite this