Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Reorder atoms in label data (Fixes 502) + documenting C++ #521

Merged
merged 21 commits into from
Sep 23, 2024
Merged

Reorder atoms in label data (Fixes 502) + documenting C++ #521

merged 21 commits into from
Sep 23, 2024

Commits on Sep 23, 2024

  1. Reorder atoms in node-level and nodepair-level label data, when the s… 

    …ame molecule appears in multiple tasks with different atom orders, to be consistent with the first task's atom order
    @ndickson-nvidia
    ndickson-nvidia committed Sep 23, 2024
    Configuration menu
    Copy the full SHA
    1d7bfeb View commit details
    Browse the repository at this point in the history

  2. Merging of equivalent molecules is now optional, but still defaults t… 

    …o true.
    @ndickson-nvidia
    ndickson-nvidia committed Sep 23, 2024
    Configuration menu
    Copy the full SHA
    b7d9fe7 View commit details
    Browse the repository at this point in the history

  3. Fixed bug with recent change in smiles_to_brief_data

    @ndickson-nvidia
    ndickson-nvidia committed Sep 23, 2024
    Configuration menu
    Copy the full SHA
    5932fd8 View commit details
    Browse the repository at this point in the history

  4. Fix graphium_cpp.prepare_and_save_data call in test_dataset.py to inc… 

    …lude merge_equivalent_mols parameter
    @ndickson-nvidia
    ndickson-nvidia committed Sep 23, 2024
    Configuration menu
    Copy the full SHA
    020b08a View commit details
    Browse the repository at this point in the history

  5. In MultitaskFromSmilesDataModule.get_data_hash, include options used … 

    …during pre-processing
    @ndickson-nvidia
    ndickson-nvidia committed Sep 23, 2024
    Configuration menu
    Copy the full SHA
    6cd5e26 View commit details
    Browse the repository at this point in the history

  6. Linter fixes in python files already modified in this branch

    @ndickson-nvidia
    ndickson-nvidia committed Sep 23, 2024
    Configuration menu
    Copy the full SHA
    d1cad44 View commit details
    Browse the repository at this point in the history

  7. Split prepare_and_save_data into get_task_data, get_indices_and_strin… 

    …gs, compute_mol_keys, compute_stats, save_non_label_data, and save_label_data, to make the code more manageable.
    @ndickson-nvidia
    ndickson-nvidia committed Sep 23, 2024
    Configuration menu
    Copy the full SHA
    508abbd View commit details
    Browse the repository at this point in the history

  8. Added support for reordering edge label data if there are multiple ta… 

    …sks with the same molecule and one of them has edge-level label data. This should order bonds consistent with the first copy of the molecule.
    @ndickson-nvidia
    ndickson-nvidia committed Sep 23, 2024
    Configuration menu
    Copy the full SHA
    044cd47 View commit details
    Browse the repository at this point in the history

  9. Changed parse_mol in graphium_cpp.cpp to order based only on explicit… 

    … atom classes in the SMILES strings, and only if they represent a complete atom order, to fix the accidental removal of support for explcit ordering. The atom classes (atom map numbers) are then removed, so that they don't cause equivalent molecules to have different canonical atom orders. This allows the ordered parameter to default to true again. Some callers may want to set this to false, for performance.
    @ndickson-nvidia
    ndickson-nvidia committed Sep 23, 2024
    Configuration menu
    Copy the full SHA
    50adb1b View commit details
    Browse the repository at this point in the history

  10. The datasets use 0-based indexing for explicit ordering via atom clas… 

    …ses in SMILES strings, not 1-based
    @ndickson-nvidia
    ndickson-nvidia committed Sep 23, 2024
    Configuration menu
    Copy the full SHA
    c870af4 View commit details
    Browse the repository at this point in the history

  11. Started adding doxygen comments to the C++ code. Also changed compute… 

    …_laplacian_eigendecomp to accept `const int32_t*` instead of `const std::vector<int32_t>*`
    @ndickson-nvidia
    ndickson-nvidia committed Sep 23, 2024
    Configuration menu
    Copy the full SHA
    90f2403 View commit details
    Browse the repository at this point in the history

  12. Adding unit test for node ordering

    @WenkelF @ndickson-nvidia
    WenkelF authored and ndickson-nvidia committed Sep 23, 2024
    Configuration menu
    Copy the full SHA
    bafdfe8 View commit details
    Browse the repository at this point in the history

  13. Added doxygen comments for functions and enums related to one-hot fea… 

    …ture encoding
    @ndickson-nvidia
    ndickson-nvidia committed Sep 23, 2024
    Configuration menu
    Copy the full SHA
    7fd40e7 View commit details
    Browse the repository at this point in the history

  14. Added more doxygen comments

    @ndickson-nvidia
    ndickson-nvidia committed Sep 23, 2024
    Configuration menu
    Copy the full SHA
    06b12b2 View commit details
    Browse the repository at this point in the history

  15. Added and updated more comments

    @ndickson-nvidia
    ndickson-nvidia committed Sep 23, 2024
    Configuration menu
    Copy the full SHA
    5d798a5 View commit details
    Browse the repository at this point in the history

  16. Added comments to each function in features.cpp

    @ndickson-nvidia
    ndickson-nvidia committed Sep 23, 2024
    Configuration menu
    Copy the full SHA
    7261279 View commit details
    Browse the repository at this point in the history

  17. Investigating failing unit tests

    @WenkelF
    WenkelF committed Sep 23, 2024
    Configuration menu
    Copy the full SHA
    b82f582 View commit details
    Browse the repository at this point in the history

  18. Added more comments to labels.cpp

    @ndickson-nvidia
    ndickson-nvidia committed Sep 23, 2024
    Configuration menu
    Copy the full SHA
    4a152b2 View commit details
    Browse the repository at this point in the history

  19. Merge branch 'atom_order' of ssh://github.com/ndickson-nvidia/graphiu… 

    …m into atom_order
    @ndickson-nvidia
    ndickson-nvidia committed Sep 23, 2024
    Configuration menu
    Copy the full SHA
    618bbb1 View commit details
    Browse the repository at this point in the history

  20. Build fix in features.cpp

    @ndickson-nvidia
    ndickson-nvidia committed Sep 23, 2024
    Configuration menu
    Copy the full SHA
    92ab751 View commit details
    Browse the repository at this point in the history

  21. Skipping test_training.py for now

    @WenkelF
    WenkelF committed Sep 23, 2024
    Configuration menu
    Copy the full SHA
    f123565 View commit details
    Browse the repository at this point in the history