Machine learning approaches to predict drug efficacy and toxicity in oncology

Bara A Badwan; Gerry Liaropoulos; Efthymios Kyrodimos; Dimitrios Skaltsas; Aristotelis Tsirigos; Vassilis G Gorgoulis

doi:10.1016/j.crmeth.2023.100413

Machine learning approaches to predict drug efficacy and toxicity in oncology

Cell Rep Methods. 2023 Feb 21;3(2):100413. doi: 10.1016/j.crmeth.2023.100413. eCollection 2023 Feb 27.

Authors

Bara A Badwan¹, Gerry Liaropoulos¹, Efthymios Kyrodimos², Dimitrios Skaltsas¹, Aristotelis Tsirigos^{3

4}, Vassilis G Gorgoulis^{1

5

6

7

8}

Affiliations

¹ Intelligencia Inc, New York, NY 10014, USA.
² First ENT Department, Hippocration Hospital, National Kapodistrian University of Athens, Athens, GR 11527, Greece.
³ Department of Medicine, New York University School of Medicine, New York, NY 10016, USA.
⁴ Department of Pathology, New York University School of Medicine, New York, NY 10016, USA.
⁵ Department of Histology and Embryology, Faculty of Medicine, School of Health Sciences, National Kapodistrian University of Athens, Athens 11527, Greece.
⁶ Ninewells Hospital and Medical School, University of Dundee, Dundee DD1 9SY, UK.
⁷ Biomedical Research Foundation, Academy of Athens, Athens 11527, Greece.
⁸ Molecular and Clinical Cancer Sciences, Manchester Cancer Research Centre, Manchester Academic Health Sciences Centre, University of Manchester, Manchester M20 4GJ, UK.

Abstract

In recent years, there has been a surge of interest in using machine learning algorithms (MLAs) in oncology, particularly for biomedical applications such as drug discovery, drug repurposing, diagnostics, clinical trial design, and pharmaceutical production. MLAs have the potential to provide valuable insights and predictions in these areas by representing both the disease state and the therapeutic agents used to treat it. To fully utilize the capabilities of MLAs in oncology, it is important to understand the fundamental concepts underlying these algorithms and how they can be applied to assess the efficacy and toxicity of therapeutics. In this perspective, we lay out approaches to represent both the disease state and the therapeutic agents used by MLAs to derive novel insights and make relevant predictions.

Keywords: artificial intelligence; drug discovery; drug response; machine learning.

Publication types

Review
Research Support, Non-U.S. Gov't

MeSH terms

Algorithms
Artificial Intelligence*
Drug Discovery
Machine Learning*
Medical Oncology