Developing Predictive Models by Sharing Predictions – An Investigation of a Federated Learning Approach for ADMET Predictions
- 29 May 2026
- journal article
- research article
- Published by American Chemical Society (ACS) in Journal of Medicinal Chemistry
- Vol. 69 (11) , 12973-12981
Abstract
Machine learning models for ADMET prediction benefit from large, diverse data sets, yet such data are typically siloed across organizations. Federated learning (FL) enables collaborative modeling while preserving data privacy. Here, we investigate a student–teacher model (STM) framework in which organizations train internal models on proprietary data and share predictions on a public data set to generate pseudolabels for a centralized student model. As a proof of concept, 11 pharmaceutical companies contributed predictions for rat steady-state volume of distribution, yielding a pseudolabeled data set of ∼133,000 compounds. The resulting student model achieved performance comparable to individual teacher models on an external test set (RMSE ≈ 0.51 vs 0.47–0.61). Compared with FL approaches such as MELLODY and Effiris, STM offers a simpler workflow that avoids direct data sharing or iterative collaboration, providing a practical and scalable framework for secure cross-company model development.Keywords
This publication has 27 references indexed in Scilit:
- Federated learning for molecular discoveryCurrent Opinion in Structural Biology, 2023
- Benchmarking Accuracy and Generalizability of Four Graph Neural Networks Using Large In Vitro ADME Datasets from Different Chemical SpacesMolecular Informatics, 2022
- Machine Learning for In Silico ADMET Prediction2021
- Developing more generalizable prediction models from pooled studies and large clustered data setsStatistics in Medicine, 2021
- A survey on federated learningKnowledge-Based Systems, 2021
- Federated Learning in Robotic and Autonomous SystemsProcedia Computer Science, 2021
- Bayer’s in silico ADMET platform: a journey of machine learning over the past two decadesDrug Discovery Today, 2020
- I Have a DREAM! (DiffeRentially privatE smArt Metering)2011
- The importance of the domain of applicability in QSAR modelingJournal of Molecular Graphics and Modelling, 2008
- Extremely randomized treesMachine Learning, 2006