Fig. 6: Architecture of MolGraph-xLSTM. | Communications Chemistry

Fig. 6: Architecture of MolGraph-xLSTM.

From: MolGraph-xLSTM as a graph-based dual-level xLSTM framework for enhanced molecular representation and interpretability

Fig. 6

The architecture consists of four main components: A motif graph construction. The atom-level graph is decomposed into motifs to form a motif-level graph. B Feature extraction on the atom-level graph. A GCN-based xLSTM framework with jumping knowledge extracts features, followed by pooling to generate the atom-level representation \({{{\bf{f}}}}_{{{\rm{atom}}}}^{{{\rm{xLSTM}}}}\). C Feature extraction on the motif-level graph. Using xLSTM blocks and pooling to produce the motif-level representation \({{{\bf{f}}}}_{{{\rm{motif}}}}^{{{\rm{xLSTM}}}}\). D MHMoE and property prediction. Features (\({{{\bf{f}}}}_{{{\rm{gcn}}}}\), \({{{\bf{f}}}}_{{{\rm{atom}}}}^{{{\rm{xLSTM}}}}\) and \({{{\bf{f}}}}_{{{\rm{motif}}}}^{{{\rm{xLSTM}}}}\)) are combined and refined through the MHMoE module for final property prediction.

Back to article page