AllgemeinMemBack is now published in the Journal of Chemical Theory and Computation!
MemBack turns coarse-grained Martini3 membrane snapshots into all-atom CHARMM36 systems for GROMACS. An SE(3)-equivariant graph neural network predicts lipid heavy-atom coordinates in a single forward pass. The workflow adds hydrogens, converts water and ions, corrects stereochemistry, resolves steric clashes, and assembles the system topology.MemBack now ships with mappings for 150 lipid species and a tool […]MemBack turns coarse-grained Martini3 membrane snapshots into all-atom CHARMM36 systems for GROMACS. An SE(3)-equivariant graph neural network predicts lipid heavy-atom coordinates in a single forward pass. The workflow adds hydrogens, converts water and ions, corrects stereochemistry, resolves steric clashes, and assembles the system topology.MemBack now ships with mappings for 150 lipid species and a tool […]