Feature/add mdposit scraper

README.md

@@ -171,6 +171,26 @@ This command will:
 5. Save the extracted metadata to Parquet files
 
 
+## Scrape MDposit
+
+Have a look to the notes regarding [MDposit](docs/mdposit.md) and its API.
+
+Scrape MDposit to collect molecular dynamics (MD) datasets and files:
+
+```bash
+uv run scrape-mdposit --output-dir data
+```
+
+This command will:
+
+1. Search for molecular dynamics entries and files through the MDposit API.
+2. Parse metadata and validate them using the Pydantic models
+   `DatasetMetadata` and `FileMetadata`.
+3. Save validated files and datasets metadata.
+
+The scraping takes about 13 minutes.
+
+
 ## Analyze Gromacs mdp and gro files
 
 ### Download files

pyproject.toml

@@ -72,3 +72,4 @@ scrape-zenodo = "mdverse_scrapers.scrapers.zenodo:main"
 scrape-figshare = "mdverse_scrapers.scrapers.figshare:main"
 scrape-nomad = "mdverse_scrapers.scrapers.nomad:main"
 scrape-atlas = "mdverse_scrapers.scrapers.atlas:main"
+scrape-mdposit = "mdverse_scrapers.scrapers.mdposit:main"

ruff.toml

@@ -41,6 +41,7 @@ extend-select = [
 ignore = [
     "COM812", # Redundant with ruff formatter. See: https://docs.astral.sh/ruff/rules/missing-trailing-comma/
     "G004", # f-strings are allowed with the loguru module. See https://docs.astral.sh/ruff/rules/logging-f-string/
+    "PERF401", # list.extend suggestion is not applicable when appending model instances.
 ]
 
 # Force numpy-style for docstrings

src/mdverse_scrapers/models/dataset.py

@@ -163,7 +163,7 @@ def format_dates(cls, value: datetime | str | None) -> str | None:
 
         Parameters
         ----------
-        cls : type[BaseDataset]
+        cls : type[DatasetMetadata]
             The Pydantic model class being validated.
         value : datetime | str | None
             The input value of the 'date' field to validate.

src/mdverse_scrapers/models/enums.py

@@ -20,3 +20,17 @@ class DatasetSourceName(StrEnum):
     ATLAS = "atlas"
     GPCRMD = "gpcrmd"
     NMRLIPIDS = "nmrlipids"
+    MDDB = "mddb"
+    MDPOSIT_INRIA_NODE = "mdposit_inria_node"
+    MDPOSIT_MMB_NODE = "mdposit_mmb_node"
+
+
+class MoleculeType(StrEnum):
+    """Common molecular types found in molecular dynamics simulations."""
+
+    PROTEIN = "protein"
+    NUCLEIC_ACID = "nucleic_acid"
+    ION = "ion"
+    LIPID = "lipid"
+    CARBOHYDRATE = "carbohydrate"
+    SOLVENT = "solvent"

src/mdverse_scrapers/models/simulation.py

@@ -5,6 +5,8 @@
 
 from pydantic import BaseModel, Field, StringConstraints, field_validator
 
+from .enums import MoleculeType
+
 DOI = Annotated[
     str,
     StringConstraints(pattern=r"^10\.\d{4,9}/[\w\-.]+$"),
@@ -15,6 +17,12 @@ class Molecule(BaseModel):
     """Molecule in a simulation."""
 
     name: str = Field(..., description="Name of the molecule.")
+    type: MoleculeType | None = Field(
+        None,
+        description="Type of the molecule."
+        "Allowed values in the MoleculeType enum. "
+        "Examples: PROTEIN, ION, LIPID...",
+    )
     number_of_atoms: int | None = Field(
         None, ge=0, description="Number of atoms in the molecule, if known."
     )