csa3d 0.2.1__tar.gz → 0.2.2__tar.gz

{csa3d-0.2.1 → csa3d-0.2.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: csa3d
-Version: 0.2.1
+Version: 0.2.2
 Summary: Extract and analyze enzyme catalytic sites in 3D from the Mechanism and Catalytic Site Atlas (M-CSA)
 Author-email: Ioannis Riziotis <riziotis@ebi.ac.uk>
 License: Apache-2.0
@@ -106,28 +106,43 @@ pip install -e ".[dev,docs]"
 
 ## Quick Start
 
-### 1. Configure Data Directory
+### 1. Automatic Data Setup (Recommended)
 
-First, you need to set up the M-CSA data files. You can either:
+Download and setup M-CSA data automatically:
 
-**Option A: Download automatically (recommended)**
 ```python
-from csa3d import config
-config.setup_data("/path/to/csa3d_data")  # Downloads ~50 GB
+from csa3d import setup_data
+
+# Downloads ~50 GB of data to ~/.csa3d/data
+# Set up specific location with:
+# setup_data("/path/to/csa3d_data")
+success = setup_data()
+
+if success:
+    print("✓ Data setup complete!")
 ```
 
-**Option B: Set environment variable**
+Or via command line:
+```bash
+python -m csa3d.data_setup /path/to/csa3d_data
+```
+
+### 2. Manual Data Configuration
+
+If you prefer to download data manually:
+
+**Option A: Environment variable**
 ```bash
 export CSA3D_DATA_DIR="/path/to/csa3d_data"
 ```
 
-**Option C: Set in code**
+**Option B: Set in code**
 ```python
-from csa3d import config
-config.set_data_dir("/path/to/csa3d_data")
+from csa3d import set_data_dir
+set_data_dir("/path/to/csa3d_data")
 ```
 
-### 2. Load and Inspect Active Sites
+### 3. Load and Inspect Active Sites
 
 ```python
 from csa3d import Mcsa
@@ -152,7 +167,7 @@ for entry in db:
         print(f"    Resolution: {site.resolution} Å")
 ```
 
-### 3. Clustering and Template Creation
+### 4. Clustering and Template Creation
 
 ```python
 # Build multiple entries

{csa3d-0.2.1 → csa3d-0.2.2}/README.md

@@ -51,28 +51,43 @@ pip install -e ".[dev,docs]"
 
 ## Quick Start
 
-### 1. Configure Data Directory
+### 1. Automatic Data Setup (Recommended)
 
-First, you need to set up the M-CSA data files. You can either:
+Download and setup M-CSA data automatically:
 
-**Option A: Download automatically (recommended)**
 ```python
-from csa3d import config
-config.setup_data("/path/to/csa3d_data")  # Downloads ~50 GB
+from csa3d import setup_data
+
+# Downloads ~50 GB of data to ~/.csa3d/data
+# Set up specific location with:
+# setup_data("/path/to/csa3d_data")
+success = setup_data()
+
+if success:
+    print("✓ Data setup complete!")
 ```
 
-**Option B: Set environment variable**
+Or via command line:
+```bash
+python -m csa3d.data_setup /path/to/csa3d_data
+```
+
+### 2. Manual Data Configuration
+
+If you prefer to download data manually:
+
+**Option A: Environment variable**
 ```bash
 export CSA3D_DATA_DIR="/path/to/csa3d_data"
 ```
 
-**Option C: Set in code**
+**Option B: Set in code**
 ```python
-from csa3d import config
-config.set_data_dir("/path/to/csa3d_data")
+from csa3d import set_data_dir
+set_data_dir("/path/to/csa3d_data")
 ```
 
-### 2. Load and Inspect Active Sites
+### 3. Load and Inspect Active Sites
 
 ```python
 from csa3d import Mcsa
@@ -97,7 +112,7 @@ for entry in db:
         print(f"    Resolution: {site.resolution} Å")
 ```
 
-### 3. Clustering and Template Creation
+### 4. Clustering and Template Creation
 
 ```python
 # Build multiple entries

csa3d-0.2.2/csa3d/__init__.py

@@ -0,0 +1,12 @@
+"""CSA-3D: Extract and analyze enzyme catalytic sites from M-CSA."""
+
+from .data_setup import setup_data
+from .config import set_data_dir, get_data_dir
+
+__version__ = "0.2.2"
+
+__all__ = [
+    "setup_data",
+    "set_data_dir",
+    "get_data_dir",
+]

csa3d-0.2.2/csa3d/data_setup.py

@@ -0,0 +1,224 @@
+"""Automatic data setup and download for CSA-3D.
+
+Downloads and organizes required data files from official sources.
+"""
+
+import logging
+import os
+from pathlib import Path
+from typing import Optional
+import urllib.request
+import urllib.error
+from urllib.parse import urljoin
+
+logger = logging.getLogger(__name__)
+
+
+class DataDownloader:
+    """Download and setup CSA-3D data files."""
+
+    # Data source URLs
+    SIFTS_URL = "https://www.ebi.ac.uk/pdbe/download/sifts/csv/"
+    KEGG_URL = "https://rest.kegg.jp/get/"
+    RHEA_URL = "https://www.rhea-db.org/download/rhea/"
+    PDBE_URL = "https://www.ebi.ac.uk/pdbe/download/"
+    MCSA_URL = "https://www.ebi.ac.uk/thornton-srv/m-csa/download/"
+
+    def __init__(self, data_dir: Path):
+        """Initialize data downloader.
+
+        Args:
+            data_dir: Root directory for CSA-3D data
+        """
+        self.data_dir = Path(data_dir)
+        self.data_dir.mkdir(parents=True, exist_ok=True)
+
+    def download_file(self, url: str, output_path: Path) -> bool:
+        """Download a file from URL.
+
+        Args:
+            url: URL to download from
+            output_path: Path to save file
+
+        Returns:
+            True if successful, False otherwise
+        """
+        output_path.parent.mkdir(parents=True, exist_ok=True)
+
+        try:
+            logger.info(f"Downloading {url} → {output_path}")
+            urllib.request.urlretrieve(url, output_path)
+            logger.info(f"✓ Downloaded {output_path.name}")
+            return True
+        except urllib.error.URLError as e:
+            logger.warning(f"✗ Failed to download {url}: {e}")
+            return False
+        except Exception as e:
+            logger.error(f"Unexpected error downloading {url}: {e}")
+            return False
+
+    def setup_sifts(self) -> bool:
+        """Setup SIFTS (PDB-UniProt mappings).
+
+        Downloads from EBI PDBe SIFTS data.
+
+        Returns:
+            True if successful
+        """
+        logger.info("Setting up SIFTS data...")
+        sifts_dir = self.data_dir / "sifts"
+        sifts_dir.mkdir(parents=True, exist_ok=True)
+
+        files = {
+            "uniprot_pdb.csv": "uniprot_pdb.csv",
+            "pdb_chain_uniprot.csv": "pdb_chain_uniprot.csv",
+            "pdb_chain_enzyme.csv": "pdb_chain_enzyme.csv",
+        }
+
+        success = True
+        for filename, remote_name in files.items():
+            url = urljoin(self.SIFTS_URL, remote_name)
+            output = sifts_dir / filename
+            if not self.download_file(url, output):
+                success = False
+
+        return success
+
+    def setup_kegg(self) -> bool:
+        """Setup KEGG reaction data.
+
+        Returns:
+            True if successful
+        """
+        logger.info("Setting up KEGG data...")
+        kegg_dir = self.data_dir / "kegg"
+        kegg_dir.mkdir(parents=True, exist_ok=True)
+
+        # KEGG reactions endpoint
+        output = kegg_dir / "kegg_reaction_components.csv"
+        logger.info("Note: KEGG data requires special API handling")
+        logger.info("Please obtain KEGG reaction data from: https://www.kegg.jp/")
+        return False
+
+    def setup_rhea(self) -> bool:
+        """Setup RHEA reaction data.
+
+        Downloads from RHEA database.
+
+        Returns:
+            True if successful
+        """
+        logger.info("Setting up RHEA data...")
+        rhea_dir = self.data_dir / "rhea"
+        rhea_dir.mkdir(parents=True, exist_ok=True)
+
+        url = urljoin(self.RHEA_URL, "rhea_reaction_components.csv")
+        output = rhea_dir / "rhea_reaction_components.csv"
+        return self.download_file(url, output)
+
+    def setup_pdbe(self) -> bool:
+        """Setup PDBe data (ions, cofactors, resolution).
+
+        Returns:
+            True if successful
+        """
+        logger.info("Setting up PDBe data...")
+        pdbe_dir = self.data_dir / "pdbe"
+        pdbe_dir.mkdir(parents=True, exist_ok=True)
+
+        files = {
+            "pdb_ions.csv": "pdb_ions.csv",
+            "pdb_cofactors.csv": "pdb_cofactors.csv",
+            "resolu.idx": "resolu.idx",
+        }
+
+        success = True
+        for filename, remote_name in files.items():
+            url = urljoin(self.PDBE_URL, remote_name)
+            output = pdbe_dir / filename
+            if not self.download_file(url, output):
+                success = False
+
+        return success
+
+    def setup_mcsa(self) -> bool:
+        """Setup M-CSA catalytic site data.
+
+        Downloads from M-CSA database.
+
+        Returns:
+            True if successful
+        """
+        logger.info("Setting up M-CSA data...")
+        mcsa_dir = self.data_dir / "mcsa"
+        mcsa_dir.mkdir(parents=True, exist_ok=True)
+
+        url = urljoin(self.MCSA_URL, "mcsa_cofactors.csv")
+        output = mcsa_dir / "mcsa_cofactors.csv"
+        return self.download_file(url, output)
+
+    def setup_all(self, skip_optional: bool = False) -> dict:
+        """Setup all data files.
+
+        Args:
+            skip_optional: Skip optional data sources (KEGG)
+
+        Returns:
+            Dictionary with setup status for each source
+        """
+        logger.info(f"Starting automatic CSA-3D data setup to {self.data_dir}")
+
+        results = {}
+        results["sifts"] = self.setup_sifts()
+        results["rhea"] = self.setup_rhea()
+        results["pdbe"] = self.setup_pdbe()
+        results["mcsa"] = self.setup_mcsa()
+
+        if not skip_optional:
+            results["kegg"] = self.setup_kegg()
+
+        # Summary
+        logger.info("\n" + "=" * 60)
+        logger.info("Data Setup Summary:")
+        for source, success in results.items():
+            status = "✓ Complete" if success else "✗ Failed/Skipped"
+            logger.info(f"  {source.upper()}: {status}")
+        logger.info("=" * 60)
+
+        return results
+
+
+def setup_data(data_dir: Optional[str] = None) -> bool:
+    """Setup CSA-3D data automatically.
+
+    Args:
+        data_dir: Directory for data files. Defaults to ~/.csa3d/data
+
+    Returns:
+        True if setup successful
+    """
+    if data_dir is None:
+        data_dir = str(Path.home() / ".csa3d" / "data")
+
+    logger.info(f"Setting up CSA-3D data in: {data_dir}")
+
+    downloader = DataDownloader(Path(data_dir))
+    results = downloader.setup_all()
+
+    success = all(results.values())
+    if success:
+        logger.info(f"\n✓ Data setup complete!")
+        logger.info(f"Set environment variable: export CSA3D_DATA_DIR={data_dir}")
+    else:
+        logger.warning("\n⚠ Some data sources failed to download")
+        logger.info("Please check logs above and retry")
+
+    return success
+
+
+if __name__ == "__main__":
+    logging.basicConfig(
+        level=logging.INFO,
+        format="%(levelname)s: %(message)s"
+    )
+    setup_data()

{csa3d-0.2.1 → csa3d-0.2.2}/csa3d.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: csa3d
-Version: 0.2.1
+Version: 0.2.2
 Summary: Extract and analyze enzyme catalytic sites in 3D from the Mechanism and Catalytic Site Atlas (M-CSA)
 Author-email: Ioannis Riziotis <riziotis@ebi.ac.uk>
 License: Apache-2.0
@@ -106,28 +106,43 @@ pip install -e ".[dev,docs]"
 
 ## Quick Start
 
-### 1. Configure Data Directory
+### 1. Automatic Data Setup (Recommended)
 
-First, you need to set up the M-CSA data files. You can either:
+Download and setup M-CSA data automatically:
 
-**Option A: Download automatically (recommended)**
 ```python
-from csa3d import config
-config.setup_data("/path/to/csa3d_data")  # Downloads ~50 GB
+from csa3d import setup_data
+
+# Downloads ~50 GB of data to ~/.csa3d/data
+# Set up specific location with:
+# setup_data("/path/to/csa3d_data")
+success = setup_data()
+
+if success:
+    print("✓ Data setup complete!")
 ```
 
-**Option B: Set environment variable**
+Or via command line:
+```bash
+python -m csa3d.data_setup /path/to/csa3d_data
+```
+
+### 2. Manual Data Configuration
+
+If you prefer to download data manually:
+
+**Option A: Environment variable**
 ```bash
 export CSA3D_DATA_DIR="/path/to/csa3d_data"
 ```
 
-**Option C: Set in code**
+**Option B: Set in code**
 ```python
-from csa3d import config
-config.set_data_dir("/path/to/csa3d_data")
+from csa3d import set_data_dir
+set_data_dir("/path/to/csa3d_data")
 ```
 
-### 2. Load and Inspect Active Sites
+### 3. Load and Inspect Active Sites
 
 ```python
 from csa3d import Mcsa
@@ -152,7 +167,7 @@ for entry in db:
         print(f"    Resolution: {site.resolution} Å")
 ```
 
-### 3. Clustering and Template Creation
+### 4. Clustering and Template Creation
 
 ```python
 # Build multiple entries

{csa3d-0.2.1 → csa3d-0.2.2}/csa3d.egg-info/SOURCES.txt

@@ -1,6 +1,8 @@
 LICENSE
 README.md
 pyproject.toml
+csa3d/__init__.py
+csa3d/data_setup.py
 csa3d.egg-info/PKG-INFO
 csa3d.egg-info/SOURCES.txt
 csa3d.egg-info/dependency_links.txt

{csa3d-0.2.1 → csa3d-0.2.2}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "csa3d"
-version = "0.2.1"
+version = "0.2.2"
 description = "Extract and analyze enzyme catalytic sites in 3D from the Mechanism and Catalytic Site Atlas (M-CSA)"
 readme = "README.md"
 license = {text = "Apache-2.0"}