Lhasa Limited shared knowledge shared progress

Using privacy-preserving federated learning to enable pre-competitive cross-industry knowledge sharing and improve QSAR models

pdf fileHanser T; Bastogne D; Basu A; Davies R; Delaunois A; Fowkes A; Harding A; Johnston LA; Korlowski C; Kotsampasakou E; Plante J; Rosenbrier-Ribeiro L; Rowell P; Sabnis Y; Sartini A; Sibony A; Werner AL; White A; Yukawa T;

Secondary pharmacology profiling using quantitative structure-activity relationship (QSAR) models offer an efficient way to provide insight into biological properties during compound optimisation and prioritisation. The performance of these models is highly dependent on the quality and the quantity of the data available to train them, particularly when investigating new areas of chemical space.

A wealth of knowledge is locked in high-quality proprietary data silos and allowing QSAR models to access this knowledge would lead to unprecedented performances and decision support. Federated learning can overcome the confidentiality through using a privacy-preserving approach to extract knowledge from proprietary data and facilitate pre-competitive collaboration.


Additional Documents

    © 2023 Lhasa Limited | Registered office: Granary Wharf House, 2 Canal Wharf, Leeds, LS11 5PS, UK Tel: +44 (0)113 394 6020
    VAT number 396 8737 77 | Lhasa Limited is registered as a charity (290866)| Company Registration Number 01765239 (England and Wales).