MELLODDY: Cross-pharma Federated Learning at Unprecedented Scale Unlocks Benefits in QSAR without Compromising Proprietary Information
Top Cited Papers
Open Access
- 29 August 2023
- journal article
- research article
- Published by American Chemical Society (ACS) in Journal of Chemical Information and Modeling
- Vol. 64 (7) , 2331-2344
Abstract
Federated multipartner machine learning has been touted as an appealing and efficient method to increase the effective training data volume and thereby the predictivity of models, particularly when the generation of training data is resource-intensive. In the landmark MELLODDY project, indeed, each of ten pharmaceutical companies realized aggregated improvements on its own classification or regression models through federated learning. To this end, they leveraged a novel implementation extending multitask learning across partners, on a platform audited for privacy and security. The experiments involved an unprecedented cross-pharma data set of 2.6+ billion confidential experimental activity data points, documenting 21+ million physical small molecules and 40+ thousand assays in on-target and secondary pharmacodynamics and pharmacokinetics. Appropriate complementary metrics were developed to evaluate the predictive performance in the federated setting. In addition to predictive performance increases in labeled space, the results point toward an extended applicability domain in federated learning. Increases in collective training data volume, including by means of auxiliary data resulting from single concentration high-throughput and imaging assays, continued to boost predictive performance, albeit with a saturating return. Markedly higher improvements were observed for the pharmacokinetics and safety panel assay-based task subsets.Keywords
All Related Versions
Funding Information
- KU Leuven
- Innovative Medicines Initiative (831472)
- Horizon 2020 Framework Programme
- European Federation of Pharmaceutical Industries and Associations
This publication has 42 references indexed in Scilit:
- Time-Split Cross-Validation as a Method for Estimating the Goodness of Prospective Prediction.Journal of Chemical Information and Modeling, 2013
- Reducing safety-related drug attrition: the use of in vitro pharmacological profilingNature Reviews Drug Discovery, 2012
- Extended-Connectivity FingerprintsJournal of Chemical Information and Modeling, 2010
- Predicting the Predictability: A Unified Approach to the Applicability Domain Problem of QSAR ModelsJournal of Chemical Information and Modeling, 2009
- Unify QSAR approach to antimicrobials. Part 1: Predicting antifungal activity against different speciesBioorganic & Medicinal Chemistry, 2006
- QSAR/QSTR of fluoroquinolones: an example of simultaneous analysis of multiple biological activities using neural network methodEuropean Journal of Medicinal Chemistry, 1998
- Topological torsion: a new molecular descriptor for SAR applications. Comparison with other descriptorsJournal of Chemical Information and Computer Sciences, 1987
- Atom pairs as molecular features in structure-activity studies: definition and applicationsJournal of Chemical Information and Computer Sciences, 1985
- p-σ-π Analysis. A Method for the Correlation of Biological Activity and Chemical StructureJournal of the American Chemical Society, 1964
- Correlation of Biological Activity of Phenoxyacetic Acids with Hammett Substituent Constants and Partition CoefficientsNature, 1962