Skip to main content
Fig. 1 | Journal of Cheminformatics

Fig. 1

From: Applying atomistic neural networks to bias conformer ensembles towards bioactive-like conformations

Fig. 1

Schematic representation of AtNNs architecture. A AtNNs take as input a conformation in the form of atomic numbers with corresponding atomic coordinates to output a single value for the conformation. B Architecture of an interaction block. A new atom embedding is produced by using an input atom embedding and basis functions (encoding the 3D structure) through a message passing paradigm performing convolutions between atoms in a neighbourhood subgraph defined by a distance cut-off

Back to article page