Developing Predictive Models by Sharing Predictions – An Investigation of a Federated Learning Approach for ADMET Predictions

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.

Authors

Institutions

Publication Details

Journal
Journal of Medicinal Chemistry
Published
2026-05-29
DOI
https://doi.org/10.1021/acs.jmedchem.5c03681
Primary Topic
Privacy-Preserving Technologies in Data
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Developing Predictive Models by Sharing Predictions – An Investigation of a Federated Learning Approach for ADMET Predictions

Susanne Winiwarter, Majdi Hassan, Edward Price, Christopher D. Edwards et al.
Journal of Medicinal Chemistry
Privacy-Preserving Technologies in Data
article

Developing Predictive Models by Sharing Predictions – An Investigation of a Federated Learning Approach for ADMET Predictions

Susanne Winiwarter, Majdi Hassan, Edward Price, Christopher D. Edwards, Barun Bhhatarai, Darren V. S. Green, Fabio Broccatelli, Rajarshi Guha, Ling He, Yohei Kosugi, Harutoshi Kato, Nathaniel Woody, Prashant Desai, Wenyi Wang, Anthony DiFranzo, Christopher Keefer
article en

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.

Journal of Medicinal Chemistry
Novartis (Switzerland) (CH), Merck & Co., Inc., Rahway, NJ, USA (United States) (US), Pfizer (United States) (US), Age UK (GB), AbbVie (United States) (US), Systems Analytics (United States) (US), Quantitative BioSciences (US), EP Analytics (United States) (US), AstraZeneca (Brazil) (BR), System Simulation (United Kingdom) (GB), Daiichi Sankyo (United States) (US), Mitsubishi Tanabe Pharma Corporation, Novartis Institutes for BioMedical Research, Takeda (Japan) (JP), Vertex Pharmaceuticals (United States) (US)
Openalex Percentile: Top 4%
Privacy-Preserving Technologies in Data
DOISourceOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.