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 [5, 18]. 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 / Mittone, G.; Svoboda, F.; Aldinucci, M.; Lane, N.; Lio, P.. - (2023), pp. 1177-1181. (Intervento presentato al convegno 2023 World Wide Web Conference, WWW 2023 tenutosi a Austin; usa) [10.1145/3543873.3587687].

A Federated Learning Benchmark for Drug-Target Interaction

Lio P.
2023

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 [5, 18]. 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
2023 World Wide Web Conference, WWW 2023
Benchmark; Drug-Target Interaction; Federated Learning; Graph Neural Networks
04 Pubblicazione in atti di convegno::04b Atto di convegno in volume
A Federated Learning Benchmark for Drug-Target Interaction / Mittone, G.; Svoboda, F.; Aldinucci, M.; Lane, N.; Lio, P.. - (2023), pp. 1177-1181. (Intervento presentato al convegno 2023 World Wide Web Conference, WWW 2023 tenutosi a Austin; usa) [10.1145/3543873.3587687].
File allegati a questo prodotto
File Dimensione Formato  
Mottone_A-Federated_2023.pdf

solo gestori archivio

Tipologia: Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 501.41 kB
Formato Adobe PDF
501.41 kB Adobe PDF   Contatta l'autore

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/11573/1726836
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 4
  • ???jsp.display-item.citation.isi??? 2
social impact