PatWalters / benchmark_map4

Benchmarking the MAP4 fingerprint in regression models
MIT License
4 stars 2 forks source link

unfolded counted fingerprints #1

Open UnixJunkie opened 1 month ago

UnixJunkie commented 1 month ago

Dear Patrick,

In this benchmark, since it is about regression modeling, it might be quite interesting to see at least one or two unfolded-counted fingerprints: e.g. ECFP or atom-pairs.

I might send a PR about this, if I manage to wrap my head around your piece of code.

Regards, F.

UnixJunkie commented 1 month ago

this issue could be assigned to me

UnixJunkie commented 1 month ago

In there: https://github.com/UnixJunkie/benchmark_map4/blob/unfolded_counted_fps/atom_pairs.py

I have a home made version of unfolded counted atom pairs.

The implementation is enough to be integrated into this benchmark. For a "real-world" implementation, only code for reusing an existing encoding dictionary is missing and a feature-full CLI.