feat: initial support for data-platform

.github/workflows/level_1.yml

@@ -17,7 +17,7 @@ jobs:
     runs-on: ubuntu-latest
     environment: ${{ matrix.env }}
     strategy:
-      fail-fast: true
+      fail-fast: false
       matrix:
         python-version: ["3.13"]
         env: ${{ fromJSON( ((github.event_name == 'workflow_call' || github.event_name == 'release') && inputs.env != '') && format('["{0}"]', inputs.env) || '["dev","staging","prod"]' ) }}

.vscode/settings.json

@@ -37,18 +37,26 @@
         "drugability",
         "dtos",
         "emeq",
+        "ensembl",
+        "fasta",
         "finalizer",
         "FMCS",
+        "hbond",
+        "herg",
         "HETATM",
         "inchi",
+        "interpro",
         "isin",
         "isoparse",
         "kabsch",
         "Kekulization",
         "Kekulize",
         "Konnektor",
         "kwargs",
+        "ligandability",
         "ligandset",
+        "logd",
+        "logp",
         "marimo",
         "mbar",
         "molblock",
@@ -70,6 +78,7 @@
         "rcsbapi",
         "rdchem",
         "rdkit",
+        "refseq",
         "replex",
         "resnames",
         "retryable",
@@ -78,7 +87,10 @@
         "SASA",
         "softcore",
         "Substruct",
+        "subtable",
         "textea",
+        "tpsa",
+        "uniprot",
         "venv"
     ]
 }

docs/dd/how-to/proteins.md

@@ -37,6 +37,37 @@ from deeporigin.drug_discovery import Protein
 protein = Protein.from_name("insulin")
 ```
 
+### From a Deep Origin Data Platform ID
+
+You can create a Protein instance directly from a Deep Origin Data Platform ID. This method fetches the protein data from the platform, downloads the structure file, and creates a Protein instance with metadata from the platform:
+
+```python
+from deeporigin.drug_discovery import Protein
+
+protein = Protein.from_id("08AD337N5YV4Y")
+```
+
+The method automatically:
+- Downloads the structure file from the Deep Origin Data Platform
+- Sets the protein's ID, name, and PDB ID (if available) from the platform metadata
+- Creates a Protein instance from the downloaded file
+
+You can optionally provide a custom `DeepOriginClient` instance:
+
+```python
+from deeporigin.drug_discovery import Protein
+from deeporigin.platform.client import DeepOriginClient
+
+client = DeepOriginClient()
+protein = Protein.from_id("08AD337N5YV4Y", client=client)
+```
+
+!!! warning "Requires file_path"
+    The protein data in the platform must contain a `file_path` field. If the protein data does not have a file_path, a `ValueError` will be raised.
+
+!!! note "Automatic metadata"
+    The method automatically populates the protein's `name` field from the platform data, preferring `protein_name`, then `pdb_id`, then `gene_symbol` (in that order).
+
 
 ## Inspecting the Protein
 

docs/notebooks/clean/docking-single-ligand.ipynb

@@ -94,6 +94,16 @@
     "sim"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2d8bfa9a-c142-4deb-ac3d-d2a4f581df55",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "protein._remote_path"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "e2aa58aa",
@@ -115,6 +125,16 @@
     "ligands"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "95f716a7-4a4c-4c23-9d61-130fc3e9a72f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ligands.to_smiles()"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "94e19bec-6bee-4dbf-9c47-1490c41fdbd0",

docs/platform/ref/data.md

@@ -0,0 +1,71 @@
+# Data Platform API.
+
+The DeepOriginClient can be used to access the data platform API using:
+
+```{.python notest}
+from deeporigin.platform.client import DeepOriginClient
+
+client = DeepOriginClient()
+```
+
+Then, the following methods can be used, for example:
+
+```{.python notest}
+# Check the health status of the data platform
+health_status = client.data.health()
+
+# Search ligands joined with tool results
+results = client.data.search_ligands_with_results(
+    limit=10,
+    experiments=[{"toolId": "deeporigin.docking"}],
+)
+
+# Search an entity (e.g., ligands)
+results = client.data.search("ligands")
+
+# Search ligands using convenience method
+results = client.data.search_ligands(limit=10)
+
+# Search proteins using convenience method
+results = client.data.search_proteins(limit=10)
+
+# Create a new ligand
+ligand = client.data.create_ligand(
+    project_id="\\x0011223344556677",
+    canonical_smiles="CCOc1ccc2nc(S(=O)(=O)N3CCN(CC3)C)c(N)c2c1",
+    inchi_key="BSYNRYMUTXBXSQ-UHFFFAOYSA-N",
+    inchi="InChI=1S/C20H24N4O4S/.../h1-4,6-9H,5,10-14H2,(H,22,23)",
+    smiles="CCOc1ccc2nc(S(=O)(=O)N3CCN(CC3)C)c(N)c2c1",
+    name="Compound-12345",
+    formal_charge=0,
+    hbond_donor_count=1,
+    hbond_acceptor_count=6,
+    rotatable_bond_count=5,
+    tpsa=85.12,
+    molecular_weight=447.5,
+)
+
+# List projects
+projects = client.data.list_projects()
+
+# List public models
+models = client.data.list_models()
+```
+
+
+::: src.platform.data.Data
+    options:
+      heading_level: 2
+      docstring_style: google
+      show_root_heading: true
+      show_category_heading: true
+      show_object_full_path: false
+      show_root_toc_entry: false
+      inherited_members: true
+      members_order: alphabetical
+      filters:
+        - "!^_"  # Exclude private members (names starting with "_")
+      show_signature: true
+      show_signature_annotations: true
+      show_if_no_docstring: true
+      group_by_category: true

mkdocs.yaml

@@ -87,6 +87,7 @@ nav:
   - functions: platform/ref/functions.md
   - organizations: platform/ref/organizations.md
   - billing: platform/ref/billing.md
+  - data: platform/ref/data.md
 - Developing: 
   - Installing: dev/install.md
   - Clients: dev/clients.md

src/drug_discovery/structures/entity.py

@@ -5,7 +5,7 @@
 """
 
 from abc import ABC, abstractmethod
-from dataclasses import dataclass
+from dataclasses import dataclass, field
 from pathlib import Path
 from typing import Optional
 
@@ -20,6 +20,8 @@ class Entity(ABC):
     This class manages the remote path and provides an upload method to ensure that the entity's file is uploaded to the remote storage if it does not already exist there. It uses the DeepOrigin FilesClient for remote file operations.
     """
 
+    id: str | None = field(default=None, kw_only=True)
+
     @abstractmethod
     def to_hash(self) -> str:
         """computes a hash of the entity"""