Predicting clinical drug response from model systems by non-linear subspace-based transfer learning

bioRxiv (Cold Spring Harbor Laboratory)

Abstract

Abstract Pre-clinical models have been the workhorse of cancer research for decades. While powerful, these models do not fully recapitulate the complexity of human tumors. Consequently, translating biomarkers of drug response from pre-clinical models to human tumors has been particularly challenging. To explicitly take these differences into account and enable an efficient exploitation of the vast pre-clinical drug response resources, we developed TRANSACT, a novel computational framework for clinical drug response prediction. First, TRANSACT employs non-linear manifold learning to capture biological processes active in pre-clinical models and human tumors. Then, TRANSACT builds predictors on cell line response only and transfers these to Patient-Derived Xenografts (PDXs) and human tumors. TRANSACT outperforms four competing approaches, including Deep Learning approaches, for a set of 15 drugs on PDXs, TCGA cohorts and 226 metastatic tumors from the Hartwig Medical Foundation data. For only four drugs Deep Learning outperforms TRANSACT. We further derived an algorithmic approach to interpret TRANSACT and used it to validate the approach by identifying known biomarkers to targeted therapies and we propose novel putative biomarkers of resistance to Paclitaxel and Gemcitabine.

Authors 8

1. Soufiane M. C. Mourragui

   The Netherlands Cancer Institute · Oncode Institute · Delft University of Technology

   Affiliation as printed

   Department of EEMCS, Delft University of Technology, Delft, The Netherlands

   Division of Molecular Carcinogenesis, Oncode Institute, The Netherlands Cancer Institute, Amsterdam, The Netherlands

2. Marco Loog

   University of Copenhagen · Delft University of Technology

   Affiliation as printed

   Department of Computer Science, University of Copenhagen, Copenhagen, Denmark

   Department of EEMCS, Delft University of Technology, Delft, The Netherlands

3. Daniël J. Vis

   The Netherlands Cancer Institute · Oncode Institute

   Affiliation as printed

   Division of Molecular Carcinogenesis, Oncode Institute, The Netherlands Cancer Institute, Amsterdam, The Netherlands

4. Kat S Moore

   The Netherlands Cancer Institute · Oncode Institute

   Affiliation as printed

   Division of Molecular Carcinogenesis, Oncode Institute, The Netherlands Cancer Institute, Amsterdam, The Netherlands

5. Anna G. Manjón

   The Netherlands Cancer Institute · Oncode Institute

   Affiliation as printed

   Division of Cell Biology, Oncode Institute, The Netherlands Cancer Institute, Amsterdam, The Netherlands

6. Mark A. van de Wiel

   University of Cambridge · MRC Biostatistics Unit · Amsterdam University Medical Centers

   Affiliation as printed

   Epidemiology and Biostatistics, Amsterdam University Medical Center, Amsterdam, The Netherlands

   MRC Biostatistics Unit, Cambridge University, Cambridge, United Kingdom

7. Marcel J. T. Reinders corresponding Aachen Leiden Computational Biology Center

   Leiden University Medical Center · Delft University of Technology

   Affiliation as printed

   Department of EEMCS, Delft University of Technology, Delft, The Netherlands

   Leiden Computational Biology Center, Leiden University Medical Center, Leiden, The Netherlands

8. Lodewyk F.A. Wessels corresponding

   The Netherlands Cancer Institute · Oncode Institute · Delft University of Technology

   Affiliation as printed

   Department of EEMCS, Delft University of Technology, Delft, The Netherlands

   Division of Molecular Carcinogenesis, Oncode Institute, The Netherlands Cancer Institute, Amsterdam, The Netherlands