Extrapolation of drug induced liver injury responses from cancer cell lines using machine learning approaches

Research output: Contribution to journal › Journal article › Research › peer-review

Standard

Extrapolation of drug induced liver injury responses from cancer cell lines using machine learning approaches. / Aguayo-Orozco, Alejandro; Brunak, Søren; Taboureau, Olivier.

In: Computational Toxicology, Vol. 17, 100147, 2021.

Research output: Contribution to journal › Journal article › Research › peer-review

Harvard

Aguayo-Orozco, A, Brunak, S & Taboureau, O 2021, 'Extrapolation of drug induced liver injury responses from cancer cell lines using machine learning approaches', Computational Toxicology, vol. 17, 100147. https://doi.org/10.1016/j.comtox.2020.100147

APA

Aguayo-Orozco, A., Brunak, S., & Taboureau, O. (2021). Extrapolation of drug induced liver injury responses from cancer cell lines using machine learning approaches. Computational Toxicology, 17, [100147]. https://doi.org/10.1016/j.comtox.2020.100147

Vancouver

Aguayo-Orozco A, Brunak S, Taboureau O. Extrapolation of drug induced liver injury responses from cancer cell lines using machine learning approaches. Computational Toxicology. 2021;17. 100147. https://doi.org/10.1016/j.comtox.2020.100147

Author

Aguayo-Orozco, Alejandro ; Brunak, Søren ; Taboureau, Olivier. / Extrapolation of drug induced liver injury responses from cancer cell lines using machine learning approaches. In: Computational Toxicology. 2021 ; Vol. 17.

Bibtex

@article{6218acd5d27444cbb17bd63a7528a847,
title = "Extrapolation of drug induced liver injury responses from cancer cell lines using machine learning approaches",
abstract = "Currently, computational tools able to predict drug-induced liver injury (DILI) based on gene expression data from in vitro assays remain a challenge. Here we introduce a Qualitative Gene expression Activity Relationship (QGexAR) approach to assess the risk of DILI for any chemical. Using gene expression profiles of 276 chemicals tested on breast cancer cell line (MCF7) and prostate cancer cell line (PC3), we developed classification models based on Support Vector Machine (SVM) and Random Forest (RF) aiming at predicting the risk of DILI. With the combination of tissue expression filtering and a pathway enrichment fingerprint approach, a classification model with an accuracy reaching 0.72 in the training set and 0.95 in a validation set was obtained. Genes and pathways involved in liver metabolism contributed the most to the performance of the models. Notably, FoxO signalling pathway, alanine, aspartate and glutamate metabolism, drug metabolism and cytochrome P450 are highlighted, giving some indication to the mechanisms of action leading to DILI.",
keywords = "Chemical risk assessment, Drug-induced-liver injury, Liver toxicity, QGexAR, Support Vector Machine, Toxicogenomics",
author = "Alejandro Aguayo-Orozco and S{\o}ren Brunak and Olivier Taboureau",
note = "Publisher Copyright: {\textcopyright} 2020 The Author(s)",
year = "2021",
doi = "10.1016/j.comtox.2020.100147",
language = "English",
volume = "17",
journal = "Computational Toxicology",
issn = "2468-1113",
publisher = "Elsevier",

}

RIS

TY - JOUR

T1 - Extrapolation of drug induced liver injury responses from cancer cell lines using machine learning approaches

AU - Aguayo-Orozco, Alejandro

AU - Brunak, Søren

AU - Taboureau, Olivier

N1 - Publisher Copyright: © 2020 The Author(s)

PY - 2021

Y1 - 2021

N2 - Currently, computational tools able to predict drug-induced liver injury (DILI) based on gene expression data from in vitro assays remain a challenge. Here we introduce a Qualitative Gene expression Activity Relationship (QGexAR) approach to assess the risk of DILI for any chemical. Using gene expression profiles of 276 chemicals tested on breast cancer cell line (MCF7) and prostate cancer cell line (PC3), we developed classification models based on Support Vector Machine (SVM) and Random Forest (RF) aiming at predicting the risk of DILI. With the combination of tissue expression filtering and a pathway enrichment fingerprint approach, a classification model with an accuracy reaching 0.72 in the training set and 0.95 in a validation set was obtained. Genes and pathways involved in liver metabolism contributed the most to the performance of the models. Notably, FoxO signalling pathway, alanine, aspartate and glutamate metabolism, drug metabolism and cytochrome P450 are highlighted, giving some indication to the mechanisms of action leading to DILI.

AB - Currently, computational tools able to predict drug-induced liver injury (DILI) based on gene expression data from in vitro assays remain a challenge. Here we introduce a Qualitative Gene expression Activity Relationship (QGexAR) approach to assess the risk of DILI for any chemical. Using gene expression profiles of 276 chemicals tested on breast cancer cell line (MCF7) and prostate cancer cell line (PC3), we developed classification models based on Support Vector Machine (SVM) and Random Forest (RF) aiming at predicting the risk of DILI. With the combination of tissue expression filtering and a pathway enrichment fingerprint approach, a classification model with an accuracy reaching 0.72 in the training set and 0.95 in a validation set was obtained. Genes and pathways involved in liver metabolism contributed the most to the performance of the models. Notably, FoxO signalling pathway, alanine, aspartate and glutamate metabolism, drug metabolism and cytochrome P450 are highlighted, giving some indication to the mechanisms of action leading to DILI.

KW - Chemical risk assessment

KW - Drug-induced-liver injury

KW - Liver toxicity

KW - QGexAR

KW - Support Vector Machine

KW - Toxicogenomics

U2 - 10.1016/j.comtox.2020.100147

DO - 10.1016/j.comtox.2020.100147

M3 - Journal article

AN - SCOPUS:85096872082

VL - 17

JO - Computational Toxicology

JF - Computational Toxicology

SN - 2468-1113

M1 - 100147

ER -

ID: 275889297