The SELFIES paper might be of interest for the organization, it comes with code :). As far as I understand, the trade-off is that the SELFIES representation is always a valid molecule but is less human readable, which does not matter much for the use case of exploring the molecule space programmatically with generation models. Not my area though, I just attended a nice talk by that research group.
Related topics
Topic | Replies | Views | Activity | |
---|---|---|---|---|
[ANN] Lints.jl - easy, high performance integrals for quantum chemistry | 2 | 921 | August 15, 2020 | |
[ANN] Chemistry.jl | 5 | 1166 | June 26, 2021 | |
Interest in chemistry-focused BoF? | 56 | 4749 | July 27, 2021 | |
[ANN] PeriodicTable.jl : A small julia library for getting periodic table elements and their data | 7 | 1918 | March 15, 2018 | |
[ANN] ProtoSyn.jl v1.1: Molecular manipulation and simulation | 2 | 464 | July 13, 2022 |