Next Article in Journal
Reelin Functions, Mechanisms of Action and Signaling Pathways During Brain Development and Maturation
Previous Article in Journal
Prolyl Endopeptidase-Like Facilitates the α-Synuclein Aggregation Seeding, and This Effect Is Reverted by Serine Peptidase Inhibitor PMSF
Previous Article in Special Issue
Investigation of Volatiles in Cork Samples Using Chromatographic Data and the Superposing Significant Interaction Rules (SSIR) Chemometric Tool
Open AccessArticle

Concise Polygenic Models for Cancer-Specific Identification of Drug-Sensitive Tumors from Their Multi-Omics Profiles

by Stefan Naulaerts 1,2,3,4,5, Michael P. Menden 6,7,8 and Pedro J. Ballester 1,2,3,4,*
1
Cancer Research Center of Marseille, INSERM U1068, F-13009 Marseille, France
2
Institut Paoli-Calmettes, F-13009 Marseille, France
3
Aix-Marseille Université, F-13284 Marseille, France
4
CNRS UMR7258, F-13009 Marseille, France
5
Ludwig Institute for Cancer Research, de Duve Institute, Université catholique de Louvain, 1200 Brussels, Belgium
6
Institute of Computational Biology, Helmholtz Zentrum München—German Research Center for Environmental Health, 85764 Neuherberg, Germany
7
Department of Biology, Ludwig-Maximilians University Munich, 82152 Planegg-Martinsried, Germany
8
German Centre for Diabetes Research (DZD e.V.), 85764 Neuherberg, Germany
*
Author to whom correspondence should be addressed.
Biomolecules 2020, 10(6), 963; https://doi.org/10.3390/biom10060963
Received: 31 May 2020 / Revised: 20 June 2020 / Accepted: 22 June 2020 / Published: 26 June 2020
In silico models to predict which tumors will respond to a given drug are necessary for Precision Oncology. However, predictive models are only available for a handful of cases (each case being a given drug acting on tumors of a specific cancer type). A way to generate predictive models for the remaining cases is with suitable machine learning algorithms that are yet to be applied to existing in vitro pharmacogenomics datasets. Here, we apply XGBoost integrated with a stringent feature selection approach, which is an algorithm that is advantageous for these high-dimensional problems. Thus, we identified and validated 118 predictive models for 62 drugs across five cancer types by exploiting four molecular profiles (sequence mutations, copy-number alterations, gene expression, and DNA methylation). Predictive models were found in each cancer type and with every molecular profile. On average, no omics profile or cancer type obtained models with higher predictive accuracy than the rest. However, within a given cancer type, some molecular profiles were overrepresented among predictive models. For instance, CNA profiles were predictive in breast invasive carcinoma (BRCA) cell lines, but not in small cell lung cancer (SCLC) cell lines where gene expression (GEX) and DNA methylation profiles were the most predictive. Lastly, we identified the best XGBoost model per cancer type and analyzed their selected features. For each model, some of the genes in the selected list had already been found to be individually linked to the response to that drug, providing additional evidence of the usefulness of these models and the merits of the feature selection scheme. View Full-Text
Keywords: cancer pharmacogenomics; machine learning; feature selection; model interpretability; drug resistance cancer pharmacogenomics; machine learning; feature selection; model interpretability; drug resistance
Show Figures

Figure 1

MDPI and ACS Style

Naulaerts, S.; Menden, M.P.; Ballester, P.J. Concise Polygenic Models for Cancer-Specific Identification of Drug-Sensitive Tumors from Their Multi-Omics Profiles. Biomolecules 2020, 10, 963.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop