Automatic Inference of Graph Transformation Rules Using the Cyclic Nature of Chemical Reactions

TL;DR

This paper presents methods for automatically inferring chemical reaction rules from large datasets by computing atom-atom mappings using graph algorithms that leverage the cyclic nature of chemical reactions.

Contribution

It introduces novel algorithms for atom-atom mapping that incorporate cyclic structures, enabling large-scale extraction of reaction rules from chemical databases.

Findings

Feasible computation of atom-atom maps at large scale

Effective algorithms for small edit distances and general instances

Application to biochemical reaction networks

Abstract

Graph transformation systems have the potential to be realistic models of chemistry, provided a comprehensive collection of reaction rules can be extracted from the body of chemical knowledge. A first key step for rule learning is the computation of atom-atom mappings, i.e., the atom-wise correspondence between products and educts of all published chemical reactions. This can be phrased as a maximum common edge subgraph problem with the constraint that transition states must have cyclic structure. We describe a search tree method well suited for small edit distance and an integer linear program best suited for general instances and demonstrate that it is feasible to compute atom-atom maps at large scales using a manually curated database of biochemical reactions as an example. In this context we address the network completion problem.