graphium
graphium copied to clipboard
Re-order atoms and edges when matching molecules from different datasets
Changelogs
- [x] Find the canonical ordering of every molecule
- [x] Find a mapping between the order of the featurized molecule, and the molecule associated to the labels
- [x] Re-order the atoms for "node"-level tasks
- [ ] Re-order the atoms for "edge"-level tasks
- [ ] Re-order the atoms for "nodepair"-level tasks.
Checklist:
- [x] Closing #467
- [ ] Add tests to cover the fixed bug(s) or the new introduced feature(s) (if appropriate).
- [ ] Update the API documentation is a new function is added, or an existing one is deleted.
- [ ] Write concise and explanatory changelogs above.
- [ ] If possible, assign one of the following labels to the PR:
feature
,fix
ortest
(or ask a maintainer to do it for you).
This PR is related to issue #467. It haven't been tested or run yet, it's still in draft mode. The idea is to re-order the labels for molecules that have been merged during the featurization, but for which ordering is important, such as node-level and edge-level tasks.