update of the readme

Author: antonkulaga

README.md

@@ -8,20 +8,12 @@
 [BioThings.io](https://biothings.io/) is a platform that provides a network of high-performance biomedical APIs and tools for building FAIR (Findable, Accessible, Interoperable, and Reusable) data services. The platform includes several key components:
 
 - **Core BioThings APIs**:
-  - MyGene.info - Gene Annotation Service
-  - MyVariant.info - Variant Annotation Service
-  - MyChem.info - Chemical and Drug Annotation Service
-  - MyDisease.info - Disease Annotation Service
+  - [MyGene.info](https://mygene.info/) - Gene Annotation Service
+  - [MyVariant.info](https://myvariant.info/) - Variant Annotation Service
+  - [MyChem.info](https://mychem.info/) - Chemical and Drug Annotation Service
+  - [MyDisease.info](http://mydisease.info/) - Disease Annotation Service
   - Taxonomy API - For querying taxonomic information
 
-- **Development Tools**:
-  - BioThings SDK - A Python-based toolkit for building high-performance data APIs
-  - BioThings Studio - A pre-configured environment for building and administering BioThings APIs
-
-- **Discovery and Integration Tools**:
-  - SmartAPI - A registry for semantically annotated APIs
-  - BioThings Explorer - A tool for exploring biological data through linked API services
-
 This typed client library is built on top of the BioThings ecosystem, providing type-safe access to these services through Python.
 
 ## Project Description
@@ -30,11 +22,10 @@ A strongly-typed Python wrapper around the [BioThings Client](https://github.com
 
 ## Features
 
-- **Type Safety**: Strongly typed models for all BioThings data using Pydantic
-- **IDE Support**: Full autocompletion and type checking in modern IDEs
+- **Type Safety & Validation**: Leverages Pydantic models for runtime data validation and type checking.
+- **Enhanced IDE Support**: Full autocompletion and static analysis in modern IDEs
 - **Synchronous & Asynchronous**: Support for both sync and async operations
 - **Helper Methods**: Additional utility methods for common operations
-- **Validation**: Runtime type checking and data validation
 - **Compatibility**: Maintains full compatibility with the original BioThings client
 
 ## Installation
@@ -52,28 +43,34 @@ cd biothings-typed-client
 pip install biothings-typed-client
 ```
 
-### Using UV (Recommended)
+#### Setting Up for Development
+
+If you want to contribute to this repository:
 
-[UV](https://github.com/astral-sh/uv) is a fast Python package installer and resolver, written in Rust. It's designed to be a drop-in replacement for pip and pip-tools.
+1.  Clone the repository (if you haven't already):
+    ```bash
+    git clone https://github.com/longevity-genie/biothings-typed-client.git
+    cd biothings-typed-client
+    ```
 
-1. Install UV (if you haven't already):
-   ```bash
-   curl -LsSf https://astral.sh/uv/install.sh | sh
-   ```
+2.  Install UV:
+    ```bash
+    curl -LsSf https://astral.sh/uv/install.sh | sh
+    ```
 
-2. Install the package:
-   ```bash
-   uv sync
-   ```
+3.  Create and activate a virtual environment:
+    ```bash
+    uv venv
+    source .venv/bin/activate  # On Unix/macOS
+    # or
+    .venv\Scripts\activate  # On Windows
+    ```
 
-3. To create a virtual environment and install dependencies:
-   ```bash
-   uv venv
-   source .venv/bin/activate  # On Unix/macOS
-   # or
-   .venv\Scripts\activate  # On Windows
-   uv install biothings-typed-client
-   ```
+4.  Install all dependencies, including development tools:
+    ```bash
+    uv sync --all-extras
+    ```
+    This command reads the `pyproject.toml` file and installs the package in editable mode along with all its dependencies and optional dependencies (like those needed for testing and development).
 
 ## Quick Start
 
@@ -203,16 +200,15 @@ client = ChemClient()
 
 # Get a single chemical
 chem = client.getchem("ZRALSGWEFCBTJO-UHFFFAOYSA-N")  # Using InChI key
-if chem:
-    print(f"Chemical ID: {chem.id}")
-    print(f"Molecular Formula: {chem.pubchem.molecular_formula}")
-    print(f"SMILES: {chem.pubchem.smiles}")
-    print(f"Molecular Weight: {chem.pubchem.molecular_weight}")
-    print(f"XLogP: {chem.pubchem.xlogp}")
-    print(f"Hydrogen Bond Donors: {chem.pubchem.hydrogen_bond_donor_count}")
-    print(f"Hydrogen Bond Acceptors: {chem.pubchem.hydrogen_bond_acceptor_count}")
-    print(f"Rotatable Bonds: {chem.pubchem.rotatable_bond_count}")
-    print(f"Topological Polar Surface Area: {chem.pubchem.topological_polar_surface_area} Ų")
+print(f"Chemical ID: {chem.id}")
+print(f"Molecular Formula: {chem.pubchem.molecular_formula}")
+print(f"SMILES: {chem.pubchem.smiles}")
+print(f"Molecular Weight: {chem.pubchem.molecular_weight}")
+print(f"XLogP: {chem.pubchem.xlogp}")
+print(f"Hydrogen Bond Donors: {chem.pubchem.hydrogen_bond_donor_count}")
+print(f"Hydrogen Bond Acceptors: {chem.pubchem.hydrogen_bond_acceptor_count}")
+print(f"Rotatable Bonds: {chem.pubchem.rotatable_bond_count}")
+print(f"Topological Polar Surface Area: {chem.pubchem.topological_polar_surface_area} Ų")
 
 # Get multiple chemicals
 chems = client.getchems(["ZRALSGWEFCBTJO-UHFFFAOYSA-N", "RRUDCFGSUDOHDG-UHFFFAOYSA-N"])

pyproject.toml

@@ -1,7 +1,7 @@
 [project]
 name = "biothings-typed-client"
-version = "0.0.2"
-description = "Add your description here"
+version = "0.0.3"
+description = "A strongly-typed Python wrapper around the BioThings Client library, providing type safety and better IDE support through Python's type hints and Pydantic models."
 readme = "README.md"
 authors = [
     { name = "antonkulaga", email = "antonkulaga@gmail.com" }

src/biothings_typed_client/genes.py

@@ -7,12 +7,12 @@
 
 class RefSeq(BaseModel):
     """RefSeq information for a gene"""
-    genomic: Optional[List[str]] = Field(default=None, description="Genomic RefSeq IDs")
+    genomic: Optional[Union[str, List[str]]] = Field(default=None, description="Genomic RefSeq IDs")
     protein: Optional[Union[str, List[str]]] = Field(default=None, description="Protein RefSeq IDs")
     rna: Optional[Union[str, List[str]]] = Field(default=None, description="RNA RefSeq IDs")
     translation: Optional[Union[Dict[str, str], List[Dict[str, str]]]] = Field(default=None, description="Protein-RNA translation pairs")
 
-    @field_validator('protein', 'rna', mode='before')
+    @field_validator('genomic', 'protein', 'rna', mode='before')
     @classmethod
     def ensure_list(cls, v):
         if v is None:

tests/test_genes.py

@@ -69,3 +69,15 @@ def test_metadata_sync(sync_client: GeneClient):
     assert metadata is not None
     assert "stats" in metadata
     assert "total" in metadata["stats"]
+
+def test_getgene_sync_ensembl_string_refseq(sync_client: GeneClient):
+    """Test sync gene retrieval for Ensembl ID with single string RefSeq genomic ID."""
+    ensembl_id = "ENSECAG00000002212" # Known to return string for refseq.genomic
+    gene = sync_client.getgene(ensembl_id)
+    assert gene is not None
+    assert isinstance(gene, GeneResponse)
+    assert gene.id == "100050481" # MyGene resolves this Ensembl to Entrez ID
+    assert gene.taxid == 9796 # Cavia porcellus
+    assert gene.has_refseq()
+    assert isinstance(gene.refseq.genomic, list) # Validator should ensure it's a list
+    assert "NC_091700.1" in gene.refseq.genomic

tests/test_genes_async.py

@@ -66,3 +66,16 @@ async def test_metadata_async(async_client: GeneClientAsync):
     assert metadata is not None
     assert "stats" in metadata
     assert "total" in metadata["stats"]
+
+@pytest.mark.asyncio
+async def test_getgene_async_ensembl_string_refseq(async_client: GeneClientAsync):
+    """Test async gene retrieval for Ensembl ID with single string RefSeq genomic ID."""
+    ensembl_id = "ENSECAG00000002212" # Known to return string for refseq.genomic
+    gene = await async_client.getgene(ensembl_id)
+    assert gene is not None
+    assert isinstance(gene, GeneResponse)
+    assert gene.id == "100050481" # MyGene resolves this Ensembl to Entrez ID
+    assert gene.taxid == 9796 # Cavia porcellus
+    assert gene.has_refseq()
+    assert isinstance(gene.refseq.genomic, list) # Validator should ensure it's a list
+    assert "NC_091700.1" in gene.refseq.genomic