Geometric multi-color message passing graph neural networks for blood–brain barrier permeability prediction
We introduce GMC-MPNN, a novel 3D-aware graph neural network that models long-range geometric interactions to capture spatial atomic relationships, setting a new state-of-the-art performance for predicting blood–brain barrier permeability.
Authors
- Duc Duy Nguyen (ORCID: https://orcid.org/0000-0003-2215-0328)
- Farjana Tasnim Mukta
- Md Masud Rana (ORCID: https://orcid.org/0000-0001-8931-4329)
- Chang‐Guo Zhan (ORCID: https://orcid.org/0000-0002-4128-7269)
- Tiến Dũng Nguyễn (ORCID: https://orcid.org/0000-0003-0064-4044)
Institutions
- University of Kentucky (US)
- Kennesaw State University (US)
- University of Tennessee at Knoxville (US)
Publication Details
- Journal
- Molecular Systems Design & Engineering
- Published
- 2025-12-05
- DOI
- https://doi.org/10.1039/d5me00175g
- Citations
- 1
- Primary Topic
- Computational Drug Discovery Methods
- Type
- article
- Field-Weighted Citation Impact
- 1.50