csa3d 0.2.0__py3-none-any.whl

csa3d/config/__init__.py

@@ -0,0 +1,13 @@
+"""Configuration package for CSA-3D.
+
+Handles data paths, environment variables, and data loading.
+"""
+
+from .settings import get_config, set_data_dir, get_data_dir, validate_config
+
+__all__ = [
+    "get_config",
+    "set_data_dir",
+    "get_data_dir",
+    "validate_config",
+]

csa3d/config/loader.py

@@ -0,0 +1,290 @@
+"""Data loading utilities for CSA-3D.
+
+Loads and caches data files required by CSA-3D.
+"""
+
+import csv
+import json
+import warnings
+from collections import defaultdict
+from glob import glob
+from pathlib import Path
+from typing import Any, Dict, Set, Tuple
+
+from .settings import _data_paths
+
+
+def _load_json_mapping(file_path: Path) -> Dict[Any, Any]:
+    """Load a JSON file as a dictionary.
+
+    Args:
+        file_path: Path to JSON file
+
+    Returns:
+        Loaded JSON data
+
+    Raises:
+        FileNotFoundError: If file does not exist
+        ValueError: If JSON is invalid
+    """
+    if not file_path.exists():
+        raise FileNotFoundError(f"Data file not found: {file_path}")
+
+    try:
+        with open(file_path, "r") as f:
+            return json.load(f)
+    except json.JSONDecodeError as e:
+        raise ValueError(f"Invalid JSON in {file_path}: {e}")
+
+
+def load_uniprot_pdb_mapping() -> Dict[str, list]:
+    """Load UniProt to PDB mapping from SIFTS.
+
+    Returns:
+        Dictionary mapping UniProt IDs to list of PDB IDs
+
+    Raises:
+        FileNotFoundError: If data file not found
+    """
+    path = _data_paths.get_path("uniprot_pdb_mapping")
+
+    if not path.exists():
+        raise FileNotFoundError(
+            f"UniProt-PDB mapping file not found: {path}\n"
+            "Run csa3d.config.setup_data() to download"
+        )
+
+    mapping = {}
+    with open(path, "r") as f:
+        next(f)  # Skip header
+        for line in csv.reader(f):
+            if len(line) >= 2:
+                mapping[line[0]] = line[1].split(";")
+
+    return mapping
+
+
+def load_pdb_uniprot_mapping() -> Dict[Tuple[str, str], str]:
+    """Load PDB to UniProt mapping from SIFTS.
+
+    Returns:
+        Dictionary mapping (PDB ID, chain) tuples to UniProt IDs
+
+    Raises:
+        FileNotFoundError: If data file not found
+    """
+    path = _data_paths.get_path("pdb_uniprot_mapping")
+
+    if not path.exists():
+        raise FileNotFoundError(
+            f"PDB-UniProt mapping file not found: {path}\n"
+            "Run csa3d.config.setup_data() to download"
+        )
+
+    mapping = {}
+    with open(path, "r") as f:
+        next(f)  # Skip header
+        next(f)  # Skip second header line
+        for line in csv.reader(f):
+            if len(line) >= 3:
+                mapping[(line[0], line[1])] = line[2]
+
+    return mapping
+
+
+def load_pdb_ec_mapping() -> Dict[Tuple[str, str], str]:
+    """Load PDB to EC number mapping from SIFTS.
+
+    Returns:
+        Dictionary mapping (PDB ID, chain) tuples to EC numbers
+
+    Raises:
+        FileNotFoundError: If data file not found
+    """
+    path = _data_paths.get_path("pdb_ec_mapping")
+
+    if not path.exists():
+        raise FileNotFoundError(f"PDB-EC mapping file not found: {path}")
+
+    mapping = {}
+    with open(path, "r") as f:
+        next(f)  # Skip header
+        for line in csv.reader(f):
+            if len(line) >= 4:
+                mapping[(line[0], line[1])] = line[3]
+
+    return mapping
+
+
+def load_kegg_reactions() -> Dict[str, list]:
+    """Load KEGG reaction components mapping.
+
+    Returns:
+        Dictionary mapping EC numbers to reaction components
+
+    Raises:
+        FileNotFoundError: If data file not found
+    """
+    path = _data_paths.get_path("kegg_reactions")
+
+    if not path.exists():
+        raise FileNotFoundError(f"KEGG reactions file not found: {path}")
+
+    mapping = {}
+    with open(path, "r") as f:
+        for line in csv.reader(f):
+            if len(line) >= 2:
+                mapping[line[0]] = [line[1].split(";")]
+
+    return mapping
+
+
+def load_rhea_reactions() -> Dict[str, list]:
+    """Load RHEA reaction components mapping.
+
+    Returns:
+        Dictionary mapping EC numbers to reaction components
+
+    Raises:
+        FileNotFoundError: If data file not found
+    """
+    path = _data_paths.get_path("rhea_reactions")
+
+    if not path.exists():
+        raise FileNotFoundError(f"RHEA reactions file not found: {path}")
+
+    mapping = {}
+    with open(path, "r") as f:
+        next(f)  # Skip header
+        for line in csv.reader(f):
+            if len(line) >= 4:
+                mapping[line[2]] = line[3].split(";")
+
+    return mapping
+
+
+def load_crystallization_artifacts() -> Set[str]:
+    """Load set of crystallization artifact HET codes.
+
+    Returns:
+        Set of HET codes that are crystallization artifacts
+
+    Raises:
+        FileNotFoundError: If data file not found
+    """
+    path = _data_paths.get_path("crystallization_hets")
+
+    if not path.exists():
+        raise FileNotFoundError(f"Crystallization HETs file not found: {path}")
+
+    artifacts = set()
+    with open(path, "r") as f:
+        for line in f:
+            artifacts.add(line.strip())
+
+    return artifacts
+
+
+def load_ions() -> Tuple[Set[str], Set[str], Set[str]]:
+    """Load ion classifications.
+
+    Returns:
+        Tuple of (metals, reactive_nonmetals, noble_gases) sets
+
+    Raises:
+        FileNotFoundError: If data file not found
+    """
+    path = _data_paths.get_path("pdb_ions")
+
+    if not path.exists():
+        raise FileNotFoundError(f"PDB ions file not found: {path}")
+
+    metals = set()
+    reactive_nonmetals = set()
+    noble_gases = set()
+
+    with open(path, "r") as f:
+        next(f)  # Skip header
+        for line in csv.reader(f):
+            if len(line) >= 4:
+                ion_type = line[3]
+                if ion_type == "METAL":
+                    metals.add(line[0])
+                elif ion_type == "REACTIVE_NONMETAL":
+                    reactive_nonmetals.add(line[0])
+                elif ion_type == "NOBLE_GAS":
+                    noble_gases.add(line[0])
+
+    return metals, reactive_nonmetals, noble_gases
+
+
+def load_pdb_cofactors() -> Dict[str, Set[str]]:
+    """Load PDB ID to cofactors mapping.
+
+    Returns:
+        Dictionary mapping PDB IDs to sets of cofactors
+
+    Raises:
+        FileNotFoundError: If data file not found
+    """
+    path = _data_paths.get_path("pdb_cofactors")
+
+    if not path.exists():
+        raise FileNotFoundError(f"PDB cofactors file not found: {path}")
+
+    cofactors = defaultdict(set)
+    with open(path, "r") as f:
+        next(f)  # Skip header
+        for line in csv.reader(f, quotechar='"'):
+            if len(line) >= 5:
+                cofactors[line[0]].add(line[4])
+
+    return dict(cofactors)
+
+
+def load_mcsa_cofactors() -> Dict[str, Set[str]]:
+    """Load M-CSA EC number to cofactors mapping.
+
+    Returns:
+        Dictionary mapping EC numbers to sets of cofactors
+
+    Raises:
+        FileNotFoundError: If data file not found
+    """
+    path = _data_paths.get_path("mcsa_cofactors")
+
+    if not path.exists():
+        raise FileNotFoundError(f"M-CSA cofactors file not found: {path}")
+
+    cofactors = defaultdict(set)
+    with open(path, "r") as f:
+        next(f)  # Skip header
+        for line in csv.reader(f, quotechar='"'):
+            if len(line) >= 5:
+                for ec in line[4].split(";"):
+                    cofactors[ec].add(line[1])
+
+    return dict(cofactors)
+
+
+def load_pdb_resolution() -> Dict[str, str]:
+    """Load PDB resolution data.
+
+    Returns:
+        Dictionary mapping PDB IDs to resolution values
+
+    Raises:
+        FileNotFoundError: If data file not found
+    """
+    path = _data_paths.get_path("pdb_resolution")
+
+    if not path.exists():
+        raise FileNotFoundError(f"PDB resolution file not found: {path}")
+
+    resolution = {}
+    with open(path, "r") as f:
+        for line in csv.reader(f, delimiter=";"):
+            if len(line) >= 2:
+                resolution[line[0].strip().lower()] = line[1].strip()
+
+    return resolution

csa3d/config/settings.py

@@ -0,0 +1,218 @@
+"""Configuration settings for CSA-3D with environment variable support."""
+
+import os
+from pathlib import Path
+from typing import Dict, Optional
+
+# Default data directory locations to try
+_DEFAULT_PATHS = [
+    "/Users/riziotis/ebi/phd/data",
+    "/nfs/research/thornton/riziotis/research/phd/data",
+    str(Path.home() / ".csa3d" / "data"),
+]
+
+
+class ConfigError(Exception):
+    """Raised when configuration is invalid or incomplete."""
+
+    pass
+
+
+class DataPaths:
+    """Manages data file paths for CSA-3D.
+
+    Paths can be configured via:
+    1. Environment variable CSA3D_DATA_DIR
+    2. Direct call to set_data_dir()
+    3. Default locations
+    """
+
+    def __init__(self) -> None:
+        """Initialize data paths."""
+        self._data_dir: Optional[Path] = None
+        self._initialized = False
+
+    def set_data_dir(self, data_dir: str) -> None:
+        """Set the data directory explicitly.
+
+        Args:
+            data_dir: Path to directory containing CSA-3D data files
+
+        Raises:
+            ConfigError: If directory does not exist
+        """
+        path = Path(data_dir)
+        if not path.is_dir():
+            raise ConfigError(f"Data directory does not exist: {data_dir}")
+        self._data_dir = path
+        self._initialized = True
+
+    def get_data_dir(self) -> Path:
+        """Get the configured data directory.
+
+        Returns:
+            Path to data directory
+
+        Raises:
+            ConfigError: If no valid data directory is configured
+        """
+        if self._data_dir is not None:
+            return self._data_dir
+
+        # Try environment variable first
+        env_dir = os.environ.get("CSA3D_DATA_DIR")
+        if env_dir:
+            path = Path(env_dir)
+            if path.is_dir():
+                self._data_dir = path
+                self._initialized = True
+                return path
+            raise ConfigError(
+                f"CSA3D_DATA_DIR points to non-existent directory: {env_dir}"
+            )
+
+        # Try default locations
+        for default_path in _DEFAULT_PATHS:
+            path = Path(default_path)
+            if path.is_dir():
+                self._data_dir = path
+                self._initialized = True
+                return path
+
+        # No valid path found
+        raise ConfigError(
+            "No CSA-3D data directory found. "
+            "Please either:\n"
+            "  1. Set environment variable: export CSA3D_DATA_DIR=/path/to/data\n"
+            "  2. Call: csa3d.config.set_data_dir('/path/to/data')\n"
+            "  3. Run: csa3d.config.setup_data() to download datasets\n"
+            f"Searched in: {', '.join(_DEFAULT_PATHS)}"
+        )
+
+    def validate(self) -> bool:
+        """Validate that all required data files exist.
+
+        Returns:
+            True if configuration is valid
+
+        Raises:
+            ConfigError: If required files are missing
+        """
+        data_dir = self.get_data_dir()
+        required_files = [
+            "mcsa/catalytic_residues_homologues.json",
+            "mcsa/catalytic_residues_references.json",
+            "sifts/uniprot_pdb.csv",
+            "sifts/pdb_chain_uniprot.csv",
+            "sifts/pdb_chain_enzyme.csv",
+        ]
+
+        missing = []
+        for rel_path in required_files:
+            full_path = data_dir / rel_path
+            if not full_path.exists():
+                missing.append(rel_path)
+
+        if missing:
+            raise ConfigError(
+                f"Missing required data files in {data_dir}:\n"
+                + "\n".join(f"  - {f}" for f in missing)
+                + "\nRun: csa3d.config.setup_data() to download"
+            )
+        return True
+
+    def get_path(self, key: str) -> Path:
+        """Get path to a specific data file.
+
+        Args:
+            key: File identifier (e.g., 'catalytic_residues', 'pdb_assemblies')
+
+        Returns:
+            Path to the file
+
+        Raises:
+            ConfigError: If file key is unknown
+        """
+        data_dir = self.get_data_dir()
+
+        paths = {
+            "catalytic_residues": data_dir / "mcsa" / "catalytic_residues_homologues.json",
+            "catalytic_residues_references": data_dir / "mcsa" / "catalytic_residues_references.json",
+            "mcsa_entry_info": data_dir / "mcsa" / "entry_info" / "mcsa_entry_info.*.json",
+            "pdb_assemblies": data_dir / "pdbe" / "assembly_cif" / "cif",
+            "kegg_molecules": data_dir / "kegg" / "sdf",
+            "chebi_molecules": data_dir / "chebi" / "sdf",
+            "pdbe_het_molecules": data_dir / "pdbe" / "het_sdf",
+            "uniprot_pdb_mapping": data_dir / "sifts" / "uniprot_pdb.csv",
+            "pdb_uniprot_mapping": data_dir / "sifts" / "pdb_chain_uniprot.csv",
+            "pdb_ec_mapping": data_dir / "sifts" / "pdb_chain_enzyme.csv",
+            "kegg_reactions": data_dir / "kegg" / "kegg_reaction_components.csv",
+            "rhea_reactions": data_dir / "rhea" / "rhea_reaction_components.csv",
+            "pdb_ions": data_dir / "pdbe" / "pdb_ions.csv",
+            "pdb_cofactors": data_dir / "pdbe" / "pdb_cofactors.csv",
+            "mcsa_cofactors": data_dir / "mcsa" / "mcsa_cofactors.csv",
+            "crystallization_hets": data_dir / "pdbe" / "crystallization_hets.csv",
+            "pdb_resolution": data_dir / "pdbe" / "resolu.idx",
+        }
+
+        if key not in paths:
+            raise ConfigError(
+                f"Unknown path key: {key}. "
+                f"Valid keys: {', '.join(paths.keys())}"
+            )
+
+        return paths[key]
+
+
+# Global instance
+_data_paths = DataPaths()
+
+
+def get_config() -> Dict[str, Path]:
+    """Get current configuration as dictionary.
+
+    Returns:
+        Dictionary of configuration values
+    """
+    data_dir = _data_paths.get_data_dir()
+    return {
+        "data_dir": data_dir,
+        "catalytic_residues": _data_paths.get_path("catalytic_residues"),
+        "pdb_assemblies": _data_paths.get_path("pdb_assemblies"),
+    }
+
+
+def set_data_dir(data_dir: str) -> None:
+    """Set the CSA-3D data directory.
+
+    Args:
+        data_dir: Path to directory containing CSA-3D data files
+
+    Raises:
+        ConfigError: If directory does not exist
+    """
+    _data_paths.set_data_dir(data_dir)
+
+
+def get_data_dir() -> str:
+    """Get the current CSA-3D data directory.
+
+    Returns:
+        Path to data directory as string
+
+    Raises:
+        ConfigError: If no valid configuration found
+    """
+    return str(_data_paths.get_data_dir())
+
+
+def validate_config() -> bool:
+    """Validate current configuration.
+
+    Returns:
+        True if all required data files exist
+
+    Raises:
+        ConfigError: If configuration is invalid
+    """
+    return _data_paths.validate()

csa3d-0.2.0.dist-info/METADATA

@@ -0,0 +1,422 @@
+Metadata-Version: 2.4
+Name: csa3d
+Version: 0.2.0
+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
+Project-URL: Homepage, https://github.com/your-username/csa3d
+Project-URL: Documentation, https://csa3d.readthedocs.io
+Project-URL: Repository, https://github.com/your-username/csa3d
+Project-URL: Issue Tracker, https://github.com/your-username/csa3d/issues
+Keywords: enzymes,catalysis,structural-biology,M-CSA,active-sites
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
+Classifier: Topic :: Scientific/Engineering :: Chemistry
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: biopython>=1.81
+Requires-Dist: numpy>=1.21.0
+Requires-Dist: pandas>=1.3.0
+Requires-Dist: scipy>=1.7.0
+Requires-Dist: scikit-learn>=0.24.0
+Requires-Dist: rdkit>=2021.09.0
+Requires-Dist: natsort>=8.0.0
+Requires-Dist: dendrogram-cut>=0.1.0
+Requires-Dist: parity-core>=0.5.0
+Requires-Dist: rmsd>=1.4.0
+Provides-Extra: dev
+Requires-Dist: pytest>=7.0; extra == "dev"
+Requires-Dist: pytest-cov>=4.0; extra == "dev"
+Requires-Dist: black>=23.0; extra == "dev"
+Requires-Dist: isort>=5.12; extra == "dev"
+Requires-Dist: flake8>=6.0; extra == "dev"
+Requires-Dist: mypy>=1.0; extra == "dev"
+Requires-Dist: types-setuptools; extra == "dev"
+Requires-Dist: types-requests; extra == "dev"
+Provides-Extra: docs
+Requires-Dist: sphinx>=6.0; extra == "docs"
+Requires-Dist: sphinx-rtd-theme>=1.2; extra == "docs"
+Requires-Dist: myst-parser>=0.19; extra == "docs"
+Provides-Extra: examples
+Requires-Dist: jupyter>=1.0; extra == "examples"
+Requires-Dist: notebook>=6.0; extra == "examples"
+Requires-Dist: matplotlib>=3.5; extra == "examples"
+Dynamic: license-file
+
+# CSA-3D: 3D Analysis of Enzyme Catalytic Sites
+
+A Python package for extracting, analyzing, and manipulating enzyme catalytic sites in three dimensions from the **Mechanism and Catalytic Site Atlas (M-CSA)** hosted at [EMBL-EBI](https://www.ebi.ac.uk/thornton-srv/m-csa/).
+
+## What is CSA-3D?
+
+CSA-3D enables computational biochemists and structural biologists to:
+
+- **Extract** catalytic site geometries from PDB structures and UniProt sequences
+- **Compare** active sites across homologous proteins using RMSD clustering
+- **Create** structure templates for enzyme active sites with geometric constraints
+- **Analyze** ligand proximity and chemical similarity in active sites
+- **Visualize** and export catalytic site information in multiple formats
+
+This package was developed to support research on enzyme mechanisms and is particularly useful for:
+- Comparative structural analysis of enzyme families
+- Active site template generation for molecular docking
+- Catalytic site conservation studies
+- Structure-guided annotation of enzyme function
+
+**See also**: [CSA-3D paper](https://www.sciencedirect.com/science/article/pii/S0022283622000912)
+
+## Installation
+
+### Requirements
+
+- Python 3.8 or higher
+- ~50 GB of disk space for complete M-CSA dataset (can work with subsets)
+
+### Installation from PyPI
+
+```bash
+pip install csa3d
+```
+
+### Installation from Source
+
+```bash
+git clone https://github.com/your-username/csa3d.git
+cd csa3d
+pip install -e ".[dev]"
+```
+
+### Development Installation
+
+For development with testing and documentation tools:
+
+```bash
+pip install -e ".[dev,docs]"
+```
+
+## Quick Start
+
+### 1. Configure Data Directory
+
+First, you need to set up the M-CSA data files. You can either:
+
+**Option A: Download automatically (recommended)**
+```python
+from csa3d import config
+config.setup_data("/path/to/csa3d_data")  # Downloads ~50 GB
+```
+
+**Option B: Set environment variable**
+```bash
+export CSA3D_DATA_DIR="/path/to/csa3d_data"
+```
+
+**Option C: Set in code**
+```python
+from csa3d import config
+config.set_data_dir("/path/to/csa3d_data")
+```
+
+### 2. Load and Inspect Active Sites
+
+```python
+from csa3d import Mcsa
+
+# Initialize the database
+db = Mcsa()
+
+# Build a specific entry (e.g., M-CSA ID 1)
+db.build(entry_ids=1, annotate=True)
+
+# Iterate over entries
+for entry in db:
+    print(f"Entry {entry.mcsa_id}: {len(entry.pdbsites)} PDB sites")
+    
+    # Get information
+    print(f"  EC Number: {entry.info['ec']}")
+    print(f"  Enzyme: {entry.info['enzyme_name']}")
+    
+    # Inspect active sites
+    for site in entry.get_pdbsites(sane_only=True):
+        print(f"    PDB: {site.pdb_id}, {len(site.residues)} residues")
+        print(f"    Resolution: {site.resolution} Å")
+```
+
+### 3. Clustering and Template Creation
+
+```python
+# Build multiple entries
+db.build(entry_ids=[1, 2, 3], annotate=True)
+entry = db.entries[1]
+
+# Calculate RMSD between all active sites
+sites = list(entry.get_pdbsites(sane_only=True))
+rmsd_matrix = entry.rmsd_matrix(sites)
+
+# Cluster sites by similarity
+clusters = entry.clustering(rmsd_matrix, height=1.5)
+
+print(f"Found {len(clusters)} clusters")
+for cluster_id, site_ids in clusters.items():
+    print(f"  Cluster {cluster_id}: {len(site_ids)} sites")
+
+# Create a template from conserved sites
+template = entry.create_template(outdir="./templates")
+print(f"Template created: {template.id}")
+```
+
+## Data Requirements
+
+CSA-3D requires data from several external sources:
+
+### Core M-CSA Data
+- `mcsa/catalytic_residues_homologues.json` - Homologous catalytic residues
+- `mcsa/catalytic_residues_references.json` - Reference catalytic residues
+- `mcsa/entry_info/mcsa_entry_info.*.json` - Entry metadata
+
+### PDB Data
+- `pdbe/assembly_cif/cif/` - PDB assembly structures (mmCIF format)
+- `pdbe/pdb_ions.csv` - Ion classification
+- `pdbe/pdb_cofactors.csv` - Cofactor information
+- `pdbe/crystallization_hets.csv` - Crystallization artifacts
+
+### Sequence/Mapping Data (SIFTS)
+- `sifts/uniprot_pdb.csv` - UniProt to PDB mapping
+- `sifts/pdb_chain_uniprot.csv` - PDB to UniProt mapping
+- `sifts/pdb_chain_enzyme.csv` - PDB to EC number mapping
+
+### Reaction Data
+- `kegg/kegg_reaction_components.csv` - KEGG enzyme reactions
+- `rhea/rhea_reaction_components.csv` - RHEA reactions
+- `pdbe/resolu.idx` - PDB resolution index
+
+### Molecule Data
+- `kegg/sdf/` - KEGG small molecules
+- `chebi/sdf/` - ChEBI compounds
+- `pdbe/het_sdf/` - PDB heteroatom structures
+
+To download all data:
+```python
+from csa3d.config import setup_data
+setup_data("/path/to/csa3d_data")
+```
+
+Alternatively, download manually from:
+- M-CSA: https://www.ebi.ac.uk/thornton-srv/m-csa/download/
+- PDBe: https://www.ebi.ac.uk/pdbe/download/
+- SIFTS: https://www.ebi.ac.uk/pdbe/docs/sifts/
+- KEGG: https://www.kegg.jp/
+- RHEA: https://www.rhea-db.org/
+
+## Usage Examples
+
+### Comparing Two Active Sites
+
+```python
+from csa3d import Mcsa
+
+db = Mcsa()
+db.build(entry_ids=1)
+entry = db.entries[1]
+
+sites = list(entry.get_pdbsites(sane_only=True))
+if len(sites) >= 2:
+    site1, site2 = sites[0], sites[1]
+    
+    # Structural alignment
+    rotation, translation, rmsd_ca, rmsd_all = site1.fit(site2, weighted=True)
+    print(f"RMSD (backbone): {rmsd_ca:.2f} Å")
+    print(f"RMSD (all atoms): {rmsd_all:.2f} Å")
+```
+
+### Writing Templates for Docking
+
+```python
+# Create template with specific parameters
+template = entry.create_template(
+    ca=False,                    # Use all heavy atoms
+    outdir="./templates",
+    outfile="myenzyme.template.pdb",
+    all_fuzzy=False,            # Use conservative fuzzy matching
+    no_alt=False                # Include alternative residue options
+)
+
+# Template can be used with docking software like TESS/Jess
+```
+
+### Batch Processing
+
+```python
+from csa3d import Mcsa
+
+db = Mcsa()
+
+# Build all entries (takes time)
+entry_ids = list(db.catalytic_residue_info.keys())
+db.build(entry_ids=entry_ids[:10], verbose=True)  # First 10
+
+# Analyze
+for entry in db:
+    n_sites = len(entry.pdbsites)
+    n_clusters = len(entry.clustering(entry.rmsd_matrix(list(entry.get_pdbsites()))))
+    print(f"{entry.mcsa_id}: {n_sites} sites, {n_clusters} clusters")
+```
+
+## Key Classes
+
+### Mcsa
+Main database class. Load and manage M-CSA entries.
+```python
+db = Mcsa()
+db.build(entry_ids=1)  # Build specific entry
+entry = db.entries[1]  # Access Entry object
+```
+
+### Entry
+Represents one M-CSA entry containing PDB and UniProt active sites.
+```python
+entry.pdbsites           # List of PdbSite objects
+entry.unisites           # List of UniSite objects
+entry.create_template()  # Generate template
+entry.clustering()       # RMSD-based clustering
+```
+
+### PdbSite
+A catalytic site from a PDB structure.
+```python
+site.pdb_id              # PDB identifier
+site.residues            # Catalytic residues
+site.ligands             # Proximal ligands
+site.fit(other_site)     # Structural alignment
+```
+
+### UniSite
+A catalytic site from UniProt sequence.
+```python
+site.uniprot_id          # UniProt accession
+site.residues            # Catalytic residues
+```
+
+## Configuration
+
+### Environment Variables
+
+- `CSA3D_DATA_DIR` - Path to M-CSA data directory (default: auto-detect)
+
+### Configuration File
+
+Create `~/.csa3d/config.yml`:
+```yaml
+data_dir: /path/to/csa3d_data
+```
+
+### In Code
+
+```python
+from csa3d import config
+
+config.set_data_dir("/path/to/data")
+config.validate_config()  # Check if valid
+print(config.get_data_dir())
+```
+
+## Documentation
+
+- [Architecture Guide](docs/architecture.md) - System design and data flow
+- [API Reference](https://csa3d.readthedocs.io) - Full API documentation
+- [Examples](examples/) - Jupyter notebooks and scripts
+
+## Testing
+
+Run tests with pytest:
+```bash
+pytest tests/
+```
+
+Run with coverage:
+```bash
+pytest --cov=csa3d tests/
+```
+
+## Performance Considerations
+
+- **First run** is slow (~minutes) as PDB structures are parsed and cached
+- **RMSD clustering** on large site sets can be memory-intensive
+- **Template creation** involves fitting multiple structures (depends on cluster size)
+
+Tips:
+- Use `sane_only=True` to filter low-quality sites
+- Process entries in batches
+- Use `resolution_cutoff` to filter low-resolution structures
+- Cache parsed entries with pickle for reuse
+
+## Citation
+
+If you use CSA-3D in your research, please cite:
+
+```bibtex
+@article{Riziotis2022,
+    title={CSA-3D: {A} framework to manipulate enzyme catalytic sites in three dimensions},
+    author={Riziotis, Ioannis and others},
+    journal={Journal of Molecular Biology},
+    volume={434},
+    number={5},
+    pages={167488},
+    year={2022},
+    issn={0022-2836},
+    doi={10.1016/j.jmb.2022.167488},
+    url={https://www.sciencedirect.com/science/article/pii/S0022283622000912}
+}
+```
+
+## Contributing
+
+Contributions are welcome! Please:
+
+1. Fork the repository
+2. Create a feature branch: `git checkout -b feature/my-feature`
+3. Make changes and add tests
+4. Run quality checks: `make lint`
+5. Submit a pull request
+
+## Issues & Support
+
+- **Bug reports**: [GitHub Issues](https://github.com/your-username/csa3d/issues)
+- **Questions**: Create a discussion or post an issue
+- **Feature requests**: Open an issue with `[FEATURE]` prefix
+
+## License
+
+Apache License 2.0 - see LICENSE file for details
+
+## Contact
+
+- **Author**: Ioannis Riziotis
+- **Email**: riziotis@ebi.ac.uk
+- **Affiliation**: EMBL-EBI, Wellcome Trust Genome Campus, Cambridge, UK
+
+## Acknowledgments
+
+CSA-3D is built on top of several excellent packages:
+- [Biopython](https://biopython.org/) - Biological computation
+- [NumPy](https://numpy.org/) - Numerical computing
+- [SciPy](https://scipy.org/) - Scientific computing
+- [scikit-learn](https://scikit-learn.org/) - Machine learning
+- [RDKit](https://www.rdkit.org/) - Cheminformatics
+
+## Changelog
+
+See [CHANGELOG.md](CHANGELOG.md) for version history and breaking changes.
+
+---
+
+**Questions?** See [docs/faq.md](docs/faq.md) or open an issue.

csa3d-0.2.0.dist-info/RECORD

@@ -0,0 +1,8 @@
+csa3d/config/__init__.py,sha256=BxCHYnrzkdMPMof8a0mg0dxD8kehXqtq4m-d9ofApLA,278
+csa3d/config/loader.py,sha256=R9ZOIJHUTYbPKZWpvxAr647e5dTY-2g-zwCQa7BQR-Q,7591
+csa3d/config/settings.py,sha256=py2nZxOymZv1nSBVTxmpIlT-RlTHzE4i-WXuELeDULQ,6704
+csa3d-0.2.0.dist-info/licenses/LICENSE,sha256=NXn2B_GTwWQMeoG4INqSiXR-PW6m6HpLPSgmr3vXMUE,10289
+csa3d-0.2.0.dist-info/METADATA,sha256=vAbOv9Oxb4UeV2tbQfEe2zN7j85Q_A53GNTKjEZMUy4,12133
+csa3d-0.2.0.dist-info/WHEEL,sha256=mOdXR9C3wMVov7cSY8PY-XCzo3SmmWCHvGQr5csJoao,91
+csa3d-0.2.0.dist-info/top_level.txt,sha256=ESGt81ShErdbujT7-D3RcXmBzbF5g5zm4J7HQYRFlPs,6
+csa3d-0.2.0.dist-info/RECORD,,

csa3d-0.2.0.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (84.2.1)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

csa3d-0.2.0.dist-info/licenses/LICENSE

@@ -0,0 +1,180 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined in Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity exercising
+      permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or Object
+      form, made available under the License, as indicated by a copyright
+      notice that is included in or attached to the work (an example is
+      provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship, thus including
+      but not limited to any software source code, documentation source,
+      and configuration files, and any object code generated from such
+      Source form (and excluding any modifications made for the purpose of
+      understanding or correcting errors or deficiencies in the Work or
+      for other reasons that would not be considered original works of
+      authorship, such as mere reformatting).
+
+      "Contribution" shall mean any work of authorship, including
+      the original Work and any Derivative Works thereof, that is
+      intentionally submitted to, or received by, Licensor for inclusion
+      in the Work by the copyright owner or by an individual or Legal
+      Entity authorized to submit on behalf of the copyright owner. For
+      the purposes of this definition, "submitted" means any form of
+      electronic, verbal, or written communication sent by or on behalf
+      of a party, including but not limited to communication on electronic
+      mailing lists, source code control systems, and issue tracking
+      systems that are managed by, or on behalf of, the Licensor for the
+      purpose of discussing and improving the Work, but excluding
+      communication that is conspicuously marked or otherwise designated
+      in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any Legal Entity on behalf of
+      whom a Contribution has been received by Licensor and subsequently
+      incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file, then any
+          Derivative Works that You distribute must include a readable
+          copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE from the Work, provided that
+          such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions of this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to Licensor shall be under the terms and conditions of
+      this License, without limitation of any additional terms or
+      conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contribution.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS

csa3d-0.2.0.dist-info/top_level.txt

@@ -0,0 +1 @@
+csa3d