Aggregating pharmaceutical data in the drug-target interaction (DTI) domain can potentially deliver life-saving breakthroughs. It is, however, notoriously difficult due to regulatory constraints and commercial interests. This work proposes the application of federated learning, which is reconcilable with the industry's constraints. It does not require sharing any information that would reveal the entities' data or any other high-level summary. When used on a representative GraphDTA model and the KIBA dataset, it achieves up to 15\% improved performance relative to the best available non-privacy preserving alternative. Our extensive battery of experiments shows that, unlike in other domains, the non-IID data distribution in the DTI datasets does not deteriorate FL performance. Additionally, we identify a material trade-off between the benefits of adding new data and the cost of adding more clients.

A Federated Learning Benchmark for Drug-Target Interaction

Gianluca Mittone
Co-first
;
Marco Aldinucci;Pietro Lio
Last
2023-01-01

Abstract

Aggregating pharmaceutical data in the drug-target interaction (DTI) domain can potentially deliver life-saving breakthroughs. It is, however, notoriously difficult due to regulatory constraints and commercial interests. This work proposes the application of federated learning, which is reconcilable with the industry's constraints. It does not require sharing any information that would reveal the entities' data or any other high-level summary. When used on a representative GraphDTA model and the KIBA dataset, it achieves up to 15\% improved performance relative to the best available non-privacy preserving alternative. Our extensive battery of experiments shows that, unlike in other domains, the non-IID data distribution in the DTI datasets does not deteriorate FL performance. Additionally, we identify a material trade-off between the benefits of adding new data and the cost of adding more clients.
2023
International World Wide Web Conference 2023
Austin
30/04/2023
Companion Proceedings of the ACM Web Conference 2023
ACM
1177
1181
9781450394192
https://dl.acm.org/doi/abs/10.1145/3543873.3587687
Gianluca Mittone, Filip Svoboda, Marco Aldinucci, Nicholas D. Lane, Pietro Lio
File in questo prodotto:
File Dimensione Formato  
3543873.3587687.pdf

Accesso aperto

Descrizione: Open-Access paper
Tipo di file: PDF EDITORIALE
Dimensione 501.41 kB
Formato Adobe PDF
501.41 kB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/2318/1898472
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 1
  • ???jsp.display-item.citation.isi??? 0
social impact