small fixes

.gitignore

@@ -0,0 +1,129 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+pip-wheel-metadata/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/

cprt/data/cprt_datamodule.py

@@ -85,9 +85,8 @@ def __init__(
         super().__init__()
         self.batch_size = batch_size
 
-        self.protein_tokenizer = AutoTokenizer.from_pretrained(
-            f"facebook/{esm_model}", model_max_length=max_protein_length
-        )
+        self.protein_tokenizer = AutoTokenizer.from_pretrained(f"facebook/{esm_model}")
+        self.protein_tokenizer.model_max_length = max_protein_length
         self.text_tokenizer = GPT2Tokenizer.from_pretrained(language_model)
         self.text_tokenizer.pad_token = self.text_tokenizer.eos_token
         self.placeholder_length = len(
@@ -114,6 +113,7 @@ def train_dataloader(self) -> DataLoader:  # type: ignore[type-arg]
             batch_size=self.batch_size,
             shuffle=True,
             collate_fn=self.collate_fn,
+            num_workers=4,
         )
 
     def val_dataloader(self) -> DataLoader:  # type: ignore[type-arg]
@@ -123,6 +123,7 @@ def val_dataloader(self) -> DataLoader:  # type: ignore[type-arg]
             batch_size=self.batch_size,
             shuffle=False,
             collate_fn=self.collate_fn,
+            num_workers=4,
         )
 
     def test_dataloader(self) -> DataLoader:  # type: ignore[type-arg]
@@ -132,6 +133,7 @@ def test_dataloader(self) -> DataLoader:  # type: ignore[type-arg]
             batch_size=self.batch_size,
             shuffle=False,
             collate_fn=self.collate_fn,
+            num_workers=4,
         )
 
     def collate_fn(self, batch: List[Tuple[str, str]]) -> CprtData:

cprt/data/data_utils.py

@@ -190,9 +190,11 @@ def get_uniref_cluster_data(
         gzip_info = len(gzip.compress(text_data.encode()))
 
         # keep all fields for final data_dict (set to remove duplications)
-        data_dic = {k: list(set(info_dict[k])) for k in info_fields}
+        data_dic: Dict[str, List[str] | str] = {
+            k: list(set(info_dict[k])) for k in info_fields
+        }
         data_dic |= {k: info_dict[k] for k in BASE_FIELDS}
-        data_dic["sequence"] = info_dict["sequence"]
+        data_dic["sequence"] = info_dict["sequence"][0]
 
         data_rows.append(
             (