From what I've seen, most use molecular fingerprints or cheminformatic descriptors such as RDKit provides. Google and Vijay Pande's group at Stanford had a recent publication on Molecular Graph Convolutions. I believe a lot of interesting research will come out in the area of molecular feature's over the next few years.
Where I work we refer to guidelines like this as code smell. These are cues that refactoring should be considered but not strict rules which would prevent a commit.
http://research.google.com/pubs/pub45548.html