Privacy-preserving techniques for decentralized and secure machine learning in drug discovery

Author(s)
Aljoša Smajić, Melanie Grandits, Gerhard F Ecker
Abstract

Data availability, data security, and privacy concerns often hamper optimal performance efficiency of machine learning (ML) techniques. Therefore, novel techniques for the utilization of private/sensitive data in the field of drug discovery have been proposed for ML model-building tasks. Some examples of the different techniques are secure multiparty computation, distributed deep learning, homomorphic encryption, blockchain-based peer-to-peer networking, differential privacy, and federated learning, as well as combinations of such techniques. In this paper, we present an overview of these techniques for decentralized ML to illustrate its benefits and drawbacks in the field of drug discovery.

Organisation(s)
Department of Pharmaceutical Sciences
Journal
Drug Discovery Today
Volume
28
Pages
1-8
No. of pages
8
ISSN
1359-6446
DOI
https://doi.org/10.1016/j.drudis.2023.103820
Publication date
11-2023
Peer reviewed
Yes
Austrian Fields of Science 2012
301207 Pharmaceutical chemistry
ASJC Scopus subject areas
Drug Discovery, Pharmacology
Portal url
https://ucrisportal.univie.ac.at/en/publications/privacypreserving-techniques-for-decentralized-and-secure-machine-learning-in-drug-discovery(3e7235f5-c322-44a7-a598-e3d0ad4d1f85).html