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

17.11.2023

In the context of pharmaceutical research, privacy-preserving decentralized approaches are crucial since they would allow for the enrichment of chemical and biological space for predictive modeling. When applied to collaborative activities, traditional and central ML techniques exhibited shortcomings.

Aljoša Smajić, Melanie Grandits, Gerhard F. Ecker, Privacy-preserving techniques for decentralized and secure machine learning in drug discovery, Drug Discovery Today, Volume 28, Issue 12, 2023 

DOI

https://doi.org/10.1016/j.drudis.2023.103820

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.

Funding

The Pharmacoinformatics Research Group (Ecker lab) acknowledges funding provided by the Austrian Science Fund FWF AW012321 MolTag.

Rights & permissions

This is an open access article distributed under the terms of the Creative Commons CC-BY license, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Figure 3. Simplified depiction of a fully homomorphic encryption.

 More News

News
 

We warmly welcome Sharath to the Pharminfo group! His expertise includes AI-assisted drug discovery and cheminformatics. We look forward to working...

Project
 

We are excited that our project AI4Health - Using AI for detecting drug-drug interactions - was recently granted by the Vienna Business Agency.

Publication
 

In the past years the interest in Solute Carrier Transporters (SLC) has increased due to their potential as drug targets. At the same time,...