Dmitrij Rappoport

Euclidean Embedding of Reaction Networks for Dimensionality Reduction of Chemical Spaces.

This work introduces a distance-preserving encoder that combines LMDS initialization with neural network refinement and achieves mMDS-level accuracy at a computational cost comparable to LMDS, and establishes low-dimensional Euclidean embeddings of RNs as a compact and searchable representation of chemical reaction spa...