Store temp x attr in FoldComp examples to ensure correct batching. (#319

)

* add PSW to nonstandard residues

* improve insertion and non-standard residue handling

* refactor chain selection

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* remove unused verbosity arg

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* fix chain selection in tests

* fix chain selection in tutorial notebook

* fix notebook chain selection

* fix chain selection typehint

* Update changelog

* Add NLW to non-standard residues

* add .ent support

* add entry for construction from dataframe

* add missing stage arg

* improve obsolete mapping retrieving to include entries with no replacement

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* update changelog

* add transforms to foldcomp datasets

* fix jaxtyping syntax

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Update changelog

* fix double application of transforms

* improve foldcomp data loading performance

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* remove unused imports

* linting

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Update changelog

* add B factors to FC parsing output

* bugfix to alpha & kappa angle embedding

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* update changelog

* handle selenocysteine in sidechain torsion angle computation

* fix protein data object initialisation #317

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* restore eq dunder

* update changelog

* add x to foldcomp examples for correct batching

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

graphein/ml/datasets/foldcomp_dataset.py

@@ -302,6 +302,7 @@ def fc_to_pyg(data: Dict[str, Any], name: Optional[str] = None) -> Protein:
             residue_type=residue_type.long(),
             b_factor=torch.from_numpy(b_factor).float(),
             id=name,
+            x=torch.zeros(len(res)),
         )
 
     def len(self) -> int: