MemBack: An Equivariant Graph Neural Network for Backmapping Lipid Membranes
Abstract Backmapping coarse-grained (CG) simulations to atomistic resolution is central to multiscale molecular simulation but remains challenging for chemically complex lipid membranes. We introduce MemBack, an SE(3)-equivariant graph neural network (GNN) that reconstructs CHARMM36 lipid structures from Martini 3 configurations by single-pass heavy-atom prediction followed by automated postprocessing. Across chemically diverse systems, MemBack achieved a mean superposition-free per-lipid heavy-atom RMSD of 0.65 Å while retaining comparable accuracy for membrane systems and lipid species excluded from training. At the membrane scale, MemBack preserved structural organization across resolutions: in a 16-component red-blood-cell (RBC) membrane model excluded from training, bilayer thickness, area per lipid (APL), and acyl-chain order closely matched the atomistic reference after only restrained minimization; in a native phase-separated Martini 3 membrane, the lateral organization of ordered and disordered domains was likewise retained directly after backmapping, without atomistic equilibration. Native Martini 3 systems containing up to 1.4 million reconstructed atoms remained consistent with their parent coarse-grained configurations and could be propagated in atomistic simulations, providing an efficient interface between Martini 3 and CHARMM36 membrane simulations.
Authors
- Rainer A. Böckmann (ORCID: https://orcid.org/0000-0002-9325-5162)
- Y. Eren Tunç (ORCID: https://orcid.org/0009-0001-5384-5918)
Institutions
- Friedrich-Alexander-Universität Erlangen-Nürnberg (DE)
Publication Details
- Journal
- Journal of Chemical Theory and Computation
- Published
- 2026-11-14
- DOI
- https://doi.org/10.1021/acs.jctc.6c01711
- Citations
- 1
- Primary Topic
- Lipid Membrane Structure and Behavior
- Type
- article
- Field-Weighted Citation Impact
- 1.27