Impact Factor 3.517 | CiteScore 3.60
More on impact ›

Original Research ARTICLE Provisionally accepted The full-text will be published soon. Notify me

Front. Genet. | doi: 10.3389/fgene.2019.01041

Paclitaxel response can be predicted with interpretable multi-variate classifiers exploiting DNA-methylation and miRNA data

 Alexandra Bomane1, Anthony Gonçalves2 and  Pedro Ballester1*
  • 1INSERM U1068 Centre de Recherche en Cancérologie de Marseille, France
  • 2Institut Paoli-Calmettes (IPC), France

To address the problem of resistance to paclitaxel, we have investigated to which extent is possible to predict the response to this drug of Breast Cancer (BC) patients. We constructed a large-scale molecular analysis using the US National Cancer Institute’s Genomic Data Commons, comprising the responses of BC patients to paclitaxel along with six types of their tumours’ profiles. We assessed seven Machine Learning (ML) algorithms on each of these profiles and evaluated the resulting 42 classifiers on the same BC patients.
DNA methylation and miRNA profiles were the most informative overall. In combination with these two profiles, ML algorithms selecting the smallest subset of molecular features generated the most predictive classifiers: a complexity-optimized XGBoost classifier based on CpG island methylation extracted a subset of molecular factors relevant to predict paclitaxel response (AUC = 0.74). A CpG site methylation-based Decision Tree (DT) combining only 2 of the 22,941 considered CpG sites (AUC = 0.89) and a miRNA expression-based DT employing just 4 of the 337 analysed mature miRNAs (AUC = 0.72) reveal the molecular types associated to paclitaxel sensitive and resistant BC tumours. A literature review shows that features selected by these three classifiers have been individually linked to the cytotoxic-drug sensitivities and prognosis of BC patients.
Our work leads to some molecular signatures, unearthed from methylome and miRNome, which can anticipate which BC tumours can respond or not to paclitaxel. These results may provide insights to optimize paclitaxel-therapies in clinical practice.

Keywords: Biomarker Discovery, machine learning, precision oncology, Tumour profiling, bioinformatics

Received: 18 Jun 2019; Accepted: 30 Sep 2019.

Copyright: © 2019 Bomane, Gonçalves and Ballester. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

* Correspondence: Dr. Pedro Ballester, INSERM U1068 Centre de Recherche en Cancérologie de Marseille, Marseille, 13273, Provence-Alpes-Côte d'Azur, France, pedro.ballester@inserm.fr