PRECISE: A domain adaptation approach to transfer predictors of drug response from pre-clinical models to tumors

Soufiane Mourragui, Marco Loog, Mark A. van de Wiel, Marcel J. T. Reinders, Lodewyk F. A. Wessels

Research output: Contribution to journalArticleAcademicpeer-review

Abstract

Motivation: Cell lines and patient-derived xenografts (PDXs) have been used extensively to understand the molecular underpinnings of cancer. While core biological processes are typically conserved, these models also show important differences compared to human tumors, hampering the translation of findings from pre-clinical models to the human setting. In particular, employing drug response predictors generated on data derived from pre-clinical models to predict patient response remains a challenging task. As very large drug response datasets have been collected for pre-clinical models, and patient drug response data are often lacking, there is an urgent need for methods that efficiently transfer drug response predictors from pre-clinical models to the human setting. Results: We show that cell lines and PDXs share common characteristics and processes with human tumors. We quantify this similarity and show that a regression model cannot simply be trained on cell lines or PDXs and then applied on tumors. We developed PRECISE, a novel methodology based on domain adaptation that captures the common information shared amongst pre-clinical models and human tumors in a consensus representation. Employing this representation, we train predictors of drug response on pre-clinical data and apply these predictors to stratify human tumors. We show that the resulting domain-invariant predictors show a small reduction in predictive performance in the pre-clinical domain but, importantly, reliably recover known associations between independent biomarkers and their companion drugs on human tumors.
Original languageEnglish
Pages (from-to)i510-i519
JournalBioinformatics
Volume35
Issue number14
DOIs
Publication statusPublished - 15 Jul 2019
Externally publishedYes

Cite this

@article{dd6b5a5ece2d4ecfae95294fa5f48a8f,
title = "PRECISE: A domain adaptation approach to transfer predictors of drug response from pre-clinical models to tumors",
abstract = "Motivation: Cell lines and patient-derived xenografts (PDXs) have been used extensively to understand the molecular underpinnings of cancer. While core biological processes are typically conserved, these models also show important differences compared to human tumors, hampering the translation of findings from pre-clinical models to the human setting. In particular, employing drug response predictors generated on data derived from pre-clinical models to predict patient response remains a challenging task. As very large drug response datasets have been collected for pre-clinical models, and patient drug response data are often lacking, there is an urgent need for methods that efficiently transfer drug response predictors from pre-clinical models to the human setting. Results: We show that cell lines and PDXs share common characteristics and processes with human tumors. We quantify this similarity and show that a regression model cannot simply be trained on cell lines or PDXs and then applied on tumors. We developed PRECISE, a novel methodology based on domain adaptation that captures the common information shared amongst pre-clinical models and human tumors in a consensus representation. Employing this representation, we train predictors of drug response on pre-clinical data and apply these predictors to stratify human tumors. We show that the resulting domain-invariant predictors show a small reduction in predictive performance in the pre-clinical domain but, importantly, reliably recover known associations between independent biomarkers and their companion drugs on human tumors.",
author = "Soufiane Mourragui and Marco Loog and {van de Wiel}, {Mark A.} and Reinders, {Marcel J. T.} and Wessels, {Lodewyk F. A.}",
year = "2019",
month = "7",
day = "15",
doi = "10.1093/bioinformatics/btz372",
language = "English",
volume = "35",
pages = "i510--i519",
journal = "Bioinformatics",
issn = "1367-4803",
publisher = "Oxford University Press",
number = "14",

}

PRECISE: A domain adaptation approach to transfer predictors of drug response from pre-clinical models to tumors. / Mourragui, Soufiane; Loog, Marco; van de Wiel, Mark A.; Reinders, Marcel J. T.; Wessels, Lodewyk F. A.

In: Bioinformatics, Vol. 35, No. 14, 15.07.2019, p. i510-i519.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - PRECISE: A domain adaptation approach to transfer predictors of drug response from pre-clinical models to tumors

AU - Mourragui, Soufiane

AU - Loog, Marco

AU - van de Wiel, Mark A.

AU - Reinders, Marcel J. T.

AU - Wessels, Lodewyk F. A.

PY - 2019/7/15

Y1 - 2019/7/15

N2 - Motivation: Cell lines and patient-derived xenografts (PDXs) have been used extensively to understand the molecular underpinnings of cancer. While core biological processes are typically conserved, these models also show important differences compared to human tumors, hampering the translation of findings from pre-clinical models to the human setting. In particular, employing drug response predictors generated on data derived from pre-clinical models to predict patient response remains a challenging task. As very large drug response datasets have been collected for pre-clinical models, and patient drug response data are often lacking, there is an urgent need for methods that efficiently transfer drug response predictors from pre-clinical models to the human setting. Results: We show that cell lines and PDXs share common characteristics and processes with human tumors. We quantify this similarity and show that a regression model cannot simply be trained on cell lines or PDXs and then applied on tumors. We developed PRECISE, a novel methodology based on domain adaptation that captures the common information shared amongst pre-clinical models and human tumors in a consensus representation. Employing this representation, we train predictors of drug response on pre-clinical data and apply these predictors to stratify human tumors. We show that the resulting domain-invariant predictors show a small reduction in predictive performance in the pre-clinical domain but, importantly, reliably recover known associations between independent biomarkers and their companion drugs on human tumors.

AB - Motivation: Cell lines and patient-derived xenografts (PDXs) have been used extensively to understand the molecular underpinnings of cancer. While core biological processes are typically conserved, these models also show important differences compared to human tumors, hampering the translation of findings from pre-clinical models to the human setting. In particular, employing drug response predictors generated on data derived from pre-clinical models to predict patient response remains a challenging task. As very large drug response datasets have been collected for pre-clinical models, and patient drug response data are often lacking, there is an urgent need for methods that efficiently transfer drug response predictors from pre-clinical models to the human setting. Results: We show that cell lines and PDXs share common characteristics and processes with human tumors. We quantify this similarity and show that a regression model cannot simply be trained on cell lines or PDXs and then applied on tumors. We developed PRECISE, a novel methodology based on domain adaptation that captures the common information shared amongst pre-clinical models and human tumors in a consensus representation. Employing this representation, we train predictors of drug response on pre-clinical data and apply these predictors to stratify human tumors. We show that the resulting domain-invariant predictors show a small reduction in predictive performance in the pre-clinical domain but, importantly, reliably recover known associations between independent biomarkers and their companion drugs on human tumors.

UR - https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85068898672&origin=inward

UR - https://www.ncbi.nlm.nih.gov/pubmed/31510654

U2 - 10.1093/bioinformatics/btz372

DO - 10.1093/bioinformatics/btz372

M3 - Article

VL - 35

SP - i510-i519

JO - Bioinformatics

JF - Bioinformatics

SN - 1367-4803

IS - 14

ER -