biorazer 0.9.3__tar.gz

biorazer-0.9.3/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Fanlin Wang
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

biorazer-0.9.3/PKG-INFO

@@ -0,0 +1,149 @@
+Metadata-Version: 2.4
+Name: biorazer
+Version: 0.9.3
+Summary: A platform for analyzing various biological information
+License: MIT
+License-File: LICENSE
+Author: Fanlin Wang
+Author-email: flmaximwang@icloud.com
+Requires-Python: >=3.11,<4.0
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: POSIX :: Linux
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
+Classifier: Programming Language :: Python :: 3.15
+Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
+Provides-Extra: pyrosetta
+Requires-Dist: biopython (>=1.80,<2.0)
+Requires-Dist: biotite (>=1.6.0,<2.0.0)
+Requires-Dist: hydride (>=1.2.3,<2.0.0)
+Requires-Dist: matplotlib (>=3.7.2,<4.0.0)
+Requires-Dist: numpy (>=2,<3)
+Requires-Dist: pandas (>=2.2,<3.0)
+Requires-Dist: python-codon-tables (>=0.1.18,<0.2.0)
+Requires-Dist: rcsb-api (>=1.4.2,<2.0.0)
+Requires-Dist: rdkit (>=2024.3.5)
+Requires-Dist: scipy (>=1.16.1,<2.0.0)
+Requires-Dist: tabulate (>=0.9.0,<0.10.0)
+Requires-Dist: umap-learn (>=0.5.9.post2,<0.6.0)
+Project-URL: Homepage, https://github.com/flmaximwang/BioRazer
+Project-URL: Issues, https://github.com/flmaximwang/BioRazer/issues
+Project-URL: Repository, https://github.com/flmaximwang/BioRazer
+Description-Content-Type: text/markdown
+
+# BioRazer
+
+A Python package for analyzing various biological information, built from practical lab experience. Install with pip and you're ready for common bioinformatics analysis work.
+
+## Features
+
+- **Protein sequences** — Translation, reverse translation, codon/protein dictionaries
+- **Multiple Sequence Alignment (MSA)** — Generate MSA via ColabFold MMseqs2 API, visualize coverage, analyze amino acid frequencies
+- **Structure analysis** — Static analysis (contacts, hydrogen bonds, surface selection), dynamic trajectory analysis (MD trajectory view, XVG/XPM plots)
+- **Database access** — Query AFDB, RCSB PDB, UniProt, Ensembl
+- **Rotamer libraries** — Read external side-chain rotamer databases: PyMOL's bundled Dunbrack pickles (`sc_bb_ind` / `sc_bb_dep`) and Rosetta's Dunbrack 2002 / Shapovalov 2010 text libraries
+- **Protein design** — Sequence design, library generation, single test entries
+
+## Installation
+
+```bash
+pip install biorazer
+```
+
+### Dependencies
+
+- Python >= 3.11
+- biotite, numpy, scipy, matplotlib, hydride, umap-learn, rcsb-api
+- tabulate (for formatted output)
+
+### Development
+
+```bash
+# Install with dev and test dependencies
+poetry install --with dev,test
+
+# Or using pip with test dependencies
+pip install biorazer
+pip install pytest pytest-cov
+```
+
+## Usage
+
+### ColabFold MSA via MMseqs2 API
+
+Generate protein MSA by calling the ColabFold public API — zero additional dependencies, pure stdlib:
+
+```python
+from biorazer.sequence.protein.analysis.alignment.query import run_search
+
+# Single-chain MSA (unpaired, default)
+files, _ = run_search(
+    ["MTSENLYFQGAMG..."],
+    out_dir="msa_out/",
+)
+
+# Multi-chain paired MSA (for AF3 multimers)
+files, _ = run_search(
+    ["CHAIN1_SEQUENCE", "CHAIN2_SEQUENCE"],
+    out_dir="msa_out/",
+    pair_mode="paired",
+    pair_strategy="greedy",   # or "complete"
+)
+```
+
+Output: A3M files (`uniref.a3m`, `bfd.mgnify30.*.a3m`, `pair.a3m`) ready for downstream folding pipelines. Supports template search (`--templates`) and custom MMseqs2 server URLs.
+
+### MSA Visualization
+
+```python
+from biorazer.sequence.protein.analysis.alignment import plot_msa
+
+fig, ax = plot_msa(
+    sequences=["MTSENLYFQG", "MTSENLXFQG"],
+    labels=["Wild-type", "Mutant"],
+)
+fig.savefig("msa_plot.png")
+```
+
+## Testing
+
+```bash
+pytest tests/ -v
+```
+
+Tests cover: FASTA parsing, sequence validation, A3M merging, and module constants. All tests are pure (no network required).
+
+## Project Structure
+
+```
+biorazer/
+├── access/         # External database APIs (AFDB, RCSB, UniProt, Ensembl)
+├── database/       # Reference data & external-library readers
+│   └── molecule/   #   per-molecule data
+│       ├── atom/       #     vdW radii, charges
+│       ├── bond/       #     bond length / angle / dihedral
+│       ├── icoor/      #     internal-coordinate topology & templates
+│       └── rotamer/    #     external rotamer readers, split by source
+│           ├── rosetta/    #   Dunbrack 2002 / Shapovalov 2010 text libraries
+│           └── pymol/      #   PyMOL's bundled Dunbrack pickles
+├── design/         # Protein design tools
+├── sequence/       # Sequence analysis
+│   ├── nucleotide/
+│   ├── protein/
+│   ├── analysis/alignment/   # MSA analysis & plotting
+│   │   └── scripts/          # MSA visualizer, analyzer
+│   └── translation/
+├── structure/      # Structure analysis & I/O
+└── util/           # Utility modules (dictionaries)
+```
+
+## License
+
+This project is licensed under the [MIT License](LICENSE).
+
+This project is intended for academic and research use.
+

biorazer-0.9.3/README.md

@@ -0,0 +1,111 @@
+# BioRazer
+
+A Python package for analyzing various biological information, built from practical lab experience. Install with pip and you're ready for common bioinformatics analysis work.
+
+## Features
+
+- **Protein sequences** — Translation, reverse translation, codon/protein dictionaries
+- **Multiple Sequence Alignment (MSA)** — Generate MSA via ColabFold MMseqs2 API, visualize coverage, analyze amino acid frequencies
+- **Structure analysis** — Static analysis (contacts, hydrogen bonds, surface selection), dynamic trajectory analysis (MD trajectory view, XVG/XPM plots)
+- **Database access** — Query AFDB, RCSB PDB, UniProt, Ensembl
+- **Rotamer libraries** — Read external side-chain rotamer databases: PyMOL's bundled Dunbrack pickles (`sc_bb_ind` / `sc_bb_dep`) and Rosetta's Dunbrack 2002 / Shapovalov 2010 text libraries
+- **Protein design** — Sequence design, library generation, single test entries
+
+## Installation
+
+```bash
+pip install biorazer
+```
+
+### Dependencies
+
+- Python >= 3.11
+- biotite, numpy, scipy, matplotlib, hydride, umap-learn, rcsb-api
+- tabulate (for formatted output)
+
+### Development
+
+```bash
+# Install with dev and test dependencies
+poetry install --with dev,test
+
+# Or using pip with test dependencies
+pip install biorazer
+pip install pytest pytest-cov
+```
+
+## Usage
+
+### ColabFold MSA via MMseqs2 API
+
+Generate protein MSA by calling the ColabFold public API — zero additional dependencies, pure stdlib:
+
+```python
+from biorazer.sequence.protein.analysis.alignment.query import run_search
+
+# Single-chain MSA (unpaired, default)
+files, _ = run_search(
+    ["MTSENLYFQGAMG..."],
+    out_dir="msa_out/",
+)
+
+# Multi-chain paired MSA (for AF3 multimers)
+files, _ = run_search(
+    ["CHAIN1_SEQUENCE", "CHAIN2_SEQUENCE"],
+    out_dir="msa_out/",
+    pair_mode="paired",
+    pair_strategy="greedy",   # or "complete"
+)
+```
+
+Output: A3M files (`uniref.a3m`, `bfd.mgnify30.*.a3m`, `pair.a3m`) ready for downstream folding pipelines. Supports template search (`--templates`) and custom MMseqs2 server URLs.
+
+### MSA Visualization
+
+```python
+from biorazer.sequence.protein.analysis.alignment import plot_msa
+
+fig, ax = plot_msa(
+    sequences=["MTSENLYFQG", "MTSENLXFQG"],
+    labels=["Wild-type", "Mutant"],
+)
+fig.savefig("msa_plot.png")
+```
+
+## Testing
+
+```bash
+pytest tests/ -v
+```
+
+Tests cover: FASTA parsing, sequence validation, A3M merging, and module constants. All tests are pure (no network required).
+
+## Project Structure
+
+```
+biorazer/
+├── access/         # External database APIs (AFDB, RCSB, UniProt, Ensembl)
+├── database/       # Reference data & external-library readers
+│   └── molecule/   #   per-molecule data
+│       ├── atom/       #     vdW radii, charges
+│       ├── bond/       #     bond length / angle / dihedral
+│       ├── icoor/      #     internal-coordinate topology & templates
+│       └── rotamer/    #     external rotamer readers, split by source
+│           ├── rosetta/    #   Dunbrack 2002 / Shapovalov 2010 text libraries
+│           └── pymol/      #   PyMOL's bundled Dunbrack pickles
+├── design/         # Protein design tools
+├── sequence/       # Sequence analysis
+│   ├── nucleotide/
+│   ├── protein/
+│   ├── analysis/alignment/   # MSA analysis & plotting
+│   │   └── scripts/          # MSA visualizer, analyzer
+│   └── translation/
+├── structure/      # Structure analysis & I/O
+└── util/           # Utility modules (dictionaries)
+```
+
+## License
+
+This project is licensed under the [MIT License](LICENSE).
+
+This project is intended for academic and research use.

biorazer-0.9.3/biorazer/__init__.py

@@ -0,0 +1,17 @@
+"""BioRazer: a platform for analyzing various biological information.
+
+这是一个**常规包** (有本文件), 而不是原来的 PEP 420 命名空间包。差别是实测过的:
+命名空间包会把 ``sys.path`` 上**每一个**同名目录都并进 ``__path__``, 于是第二份
+checkout (worktree、副本、陈旧的 editable 路径) 可以**悄悄只供应一部分模块**;
+而且扫描时一个"带 ``__init__.py``"的同名目录会**整个顶掉**先出现的命名空间
+portion —— 发现器遇到没有 ``__init__.py`` 的目录只记成 portion 继续往后找, 直到
+碰上第一个常规包才停。有了本文件, 这个名字只属于一个目录, ``biorazer.__file__``
+也会指出来是哪一份。
+"""
+
+from importlib.metadata import PackageNotFoundError, version
+
+try:  # 版本只有一个来源: pyproject.toml (经安装后的 metadata 暴露)
+    __version__ = version("biorazer")
+except PackageNotFoundError:  # 直接在源码树上 import, 没装过
+    __version__ = "0.0.0.dev0"

biorazer-0.9.3/biorazer/access/cli.py

@@ -0,0 +1,139 @@
+"""biorazer access fetch 子命令: 从 RCSB / UniProt / AlphaFold DB 下载条目文件。
+
+用法: biorazer fetch <id> --source RCSB --fmt pdb -o 3e2c.pdb
+-o 缺省下载到当前目录; 传已存在目录或以 / 结尾视为目录, 否则视为目标文件名。
+"""
+
+import argparse
+import shutil
+import sys
+import tempfile
+from pathlib import Path
+
+import requests
+
+from biorazer.access.database.AFDB.files import fetch as afdb_fetch
+from biorazer.access.database.RCSB.files import fetch as rcsb_fetch
+from biorazer.access.database.uniprot.files import fetch as uniprot_fetch
+from biorazer.logger import initialize_logger
+
+# 数据来源 -> (fetch 函数, 缺省格式)
+SOURCES = {
+    "RCSB": (rcsb_fetch, "pdb"),
+    "UNIPROT": (uniprot_fetch, "fasta"),
+    "AFDB": (afdb_fetch, "cif"),
+}
+
+
+def _normalize_source(source: str) -> str:
+    """来源参数大小写不敏感。"""
+    return source.upper()
+
+
+def _resolve_target(identifier: str, fmt: str, output: str | None) -> Path:
+    """-o 语义: 省略 -> ./{id}.{fmt};
+              目录(已存在或以 / 结尾) -> 下载到目录内 {id}.{fmt};
+              否则视为完整文件路径。"""
+    if output is None:
+        return Path(f"{identifier}.{fmt}")
+    raw = str(output)
+    if raw.endswith(("/", "\\")):
+        # 以 / 结尾但目录尚不存在: 先创建, 使 _download_to 中 target.is_dir() 判定正确,
+        # 否则会被误当成目标文件名
+        path = Path(output)
+        path.mkdir(parents=True, exist_ok=True)
+        return path / f"{identifier}.{fmt}"
+    if Path(output).is_dir():
+        return Path(output) / f"{identifier}.{fmt}"
+    return Path(output)
+
+
+def _download_to(source_fetch, identifier, fmt, target: Path, overwrite: bool, logger) -> Path:
+    """经源 fetch 下载到临时目录, 再移动到目标路径。
+
+    各源 fetch 均写入 {id}.{fmt} 风格文件名, 临时目录中转使 -o 自定义文件名
+    无需改动 access 层接口。
+
+    target 为最终目标文件路径 (由 _resolve_target 解析), 源 fetch 产物改名为
+    target.name 后移动到位。
+    """
+    target.parent.mkdir(parents=True, exist_ok=True)
+    with tempfile.TemporaryDirectory(prefix="biorazer_fetch_") as tmp:
+        # source_fetch writes into the temp dir; its generated name is discarded,
+        # we rename to the resolved target name (which may differ, e.g. -o out.pdb)
+        produced_path = source_fetch(identifier, fmt=fmt, download_dir=tmp, overwrite=True, logger=logger)
+        produced = list(Path(tmp).iterdir())
+        if len(produced) != 1:
+            raise RuntimeError(
+                f"fetch 在临时目录产生了 {len(produced)} 个文件, 预期 1 个: {produced}"
+            )
+        produced_path = produced[0]
+        shutil.move(str(produced_path), target)
+        if str(target.parent) == ".":
+            logger.info(f"{produced_path.name} moved to current directory")
+        else:
+            logger.info(f"{produced_path.name} moved to {target.parent}")
+    return target
+
+
+def _run_fetch(args) -> None:
+    """执行 fetch 子命令。"""
+    fetch, default_fmt = SOURCES[args.source]
+    fmt = args.fmt or default_fmt
+    target = _resolve_target(args.id, fmt, args.output)
+    logger = initialize_logger(__name__)
+    try:
+        if target.exists() and not args.overwrite:
+            logger.warning(f"{target} already exists, skipping")
+        else:
+            _download_to(fetch, args.id, fmt, target, args.overwrite, logger)
+    except ValueError as e:
+        print(f"错误: {e}", file=sys.stderr)
+        sys.exit(1)
+    except requests.exceptions.RequestException as e:
+        print(f"网络错误: {e}", file=sys.stderr)
+        sys.exit(1)
+    print(target)
+
+
+def _add_fetch_parser(sub) -> argparse.ArgumentParser:
+    """在 argparse subparsers 上注册 fetch 子命令。"""
+    p = sub.add_parser(
+        "fetch",
+        help="从 RCSB / UniProt / AlphaFold DB 下载条目文件",
+        description="从 access 支持的各数据库下载条目文件到本地",
+        formatter_class=argparse.RawDescriptionHelpFormatter,
+    )
+    p.add_argument(
+        "id",
+        help="数据库条目 ID (如 PDB 代码 3e2c、UniProt 登录号 P0DP23)",
+    )
+    p.add_argument(
+        "-s", "--source",
+        required=True,
+        type=_normalize_source,
+        choices=["RCSB", "UNIPROT", "AFDB"],
+        help="数据来源 (缺省格式: RCSB=pdb, UNIPROT=fasta, AFDB=cif)",
+    )
+    p.add_argument(
+        "--fmt",
+        default=None,
+        help="下载格式, 缺省按来源取默认 (RCSB=pdb / UNIPROT=fasta / AFDB=cif)",
+    )
+    p.add_argument(
+        "-o", "--output",
+        default=None,
+        help="输出路径: 省略 -> 当前目录 ./{id}.{fmt}; 目录(已存在或以 / 结尾) -> 下载到目录内; 否则视为目标文件名",
+    )
+    p.add_argument(
+        "--overwrite",
+        action="store_true",
+        help="已存在同名文件时强制重新下载",
+    )
+    p.set_defaults(func=_run_fetch)
+    return p
+
+
+def register_subcommand(sub) -> None:
+    """在 argparse subparsers 上注册 access fetch 子命令。"""
+    _add_fetch_parser(sub)

biorazer-0.9.3/biorazer/access/database/AFDB/files.py

@@ -0,0 +1,105 @@
+"""AlphaFold DB 预测结构文件下载。"""
+import requests
+from pathlib import Path
+
+from ....logger import initialize_logger
+from .info import AFDBEntry
+from .query import uniprot_to_entries
+
+# AlphaFold DB 提供的文件类型 (与 AFDBEntry.file_types 一致)
+SUPPORTED_FMT = ["bcif", "cif", "pdb", "pdbImage", "plddtDoc", "paeDoc"]
+
+
+def fetch(
+    uniprot_id: str,
+    fmt: str = "cif",
+    download_dir: str | Path = ".",
+    overwrite=False,
+    logger=None,
+):
+    """下载 AlphaFold DB 中该 UniProt 登录号对应的预测结构文件。
+
+    Parameters
+    ----------
+    uniprot_id : str
+        UniProt 登录号, 例如 "P0DP23"。也支持完整 AlphaFold ID 如 "AF-P0DP23-F1-model-v4"。
+    fmt : str
+        文件类型, 见 SUPPORTED_FMT。
+    download_dir : str | Path
+        下载目录。
+    overwrite : bool
+        已存在同名文件时是否覆盖。
+    logger : logging.Logger
+        日志器, 缺省自动初始化。
+
+    Returns
+    -------
+    Path
+        下载得到的文件路径。
+    """
+    if not logger:
+        logger = initialize_logger(__name__)
+    if fmt not in SUPPORTED_FMT:
+        raise ValueError(
+            f"Unsupported format: {fmt} (supported: {', '.join(SUPPORTED_FMT)})"
+        )
+    
+    # Parse requested version from full AFDB ID
+    requested_version = None
+    if uniprot_id.startswith("AF-") and "-model-v" in uniprot_id:
+        # Extract version: AF-P0AFB5-F1-model-v4 -> v4 -> 4
+        version_part = uniprot_id.split("-model-v")[-1]
+        if version_part.isdigit():
+            requested_version = int(version_part)
+    
+    entries = uniprot_to_entries(uniprot_id)
+    if not isinstance(entries, list) or not entries or not hasattr(entries[0], 'data'):
+        raise ValueError(f"No AFDB entry found for {uniprot_id}")
+    
+    # Select entry based on requested version
+    entry = entries[0]  # Default to first entry (latest version if multiple fragments)
+    if requested_version is not None:
+        # Check if requested version is available
+        all_versions = entry.data.get("allVersions", [])
+        if requested_version not in all_versions:
+            raise ValueError(
+                f"Requested version v{requested_version} not available for {uniprot_id}. "
+                f"Available versions: {all_versions}"
+            )
+        # Check if the file exists - AlphaFold DB only keeps latest version available for download
+        url = f"https://alphafold.ebi.ac.uk/files/{entry.id}-model_v{requested_version}.{fmt}"
+        r = requests.head(url)
+        if r.status_code != 200:
+            raise ValueError(
+                f"Version v{requested_version} is listed in API but no download available. "
+                f"AlphaFold DB only keeps the latest version (v{entry.data['latestVersion']}) "
+                f"publicly available."
+            )
+    else:
+        entry.requested_version = None
+    
+    # The entry already has correct URLs from API (for latest version or requested version)
+    # The filename from URL already includes version, so we don't need to construct it
+    url_key = f"{fmt}Url"
+    if requested_version is None:
+        # Get filename from the API URL which already has version
+        url = entry.data.get(url_key, "")
+        if url:
+            file_name = url.split("/")[-1]
+        else:
+            file_name = f"{entry.id}.{fmt}"
+    else:
+        # We'll construct URL in download(), filename will be correct there
+        # entryId is AF-P0AFB5-F1, filename will be AF-P0AFB5-F1-model_vX.fmt
+        file_name = f"{entry.id}-model_v{requested_version}.{fmt}"
+    
+    file_path = Path(download_dir) / file_name
+    if file_path.exists() and not overwrite:
+        logger.warning(f"{file_path} already exists, skipping")
+        return file_path
+    Path(download_dir).mkdir(parents=True, exist_ok=True)
+    # 只传 download 必需参数; requested_version 已在 files.py 中用于 URL/文件名解析,
+    # 真实 AFDBEntry.download 内部会自行构造 URL (其第 3 参有默认值)
+    entry.download(fmt, folder_dir=str(download_dir))
+    logger.info(f"{file_name} downloaded to {download_dir}")
+    return file_path

biorazer-0.9.3/biorazer/access/database/AFDB/info.py

@@ -0,0 +1,47 @@
+import requests
+from pathlib import Path
+from dataclasses import dataclass
+
+
+@dataclass
+class AFDBEntry:
+
+    data: dict = None
+
+    @property
+    def id(self):
+        return self.data["entryId"]
+
+    @property
+    def file_types(self):
+        return ["bcif", "cif", "pdb", "pdbImage", "plddtDoc", "paeDoc"]
+
+    @property
+    def file_Urls(self):
+        result = {}
+        for file_type in self.file_types:
+            key = f"{file_type}Url"
+            result[key] = self.data.get(key, None)
+        return result
+
+    def download(self, file_type: str, folder_dir=".", requested_version=None):
+        # If requested specific version, construct URL manually
+        if requested_version is not None:
+            # AlphaFold filename convention: AF-{uniprot}-F1-model_v{version}.{ext}
+            # entryId is already AF-{uniprot}-F1
+            # Note: it's model_v{version} with underscore, not hyphen
+            url = f"https://alphafold.ebi.ac.uk/files/{self.id}-model_v{requested_version}.{file_type}"
+        else:
+            url = self.file_Urls[f"{file_type}Url"]
+            if url is None:
+                raise ValueError(f"File type {file_type} not found for entry {self.id}")
+        
+        r = requests.get(url)
+        if r.status_code != 200:
+            raise ValueError(f"Failed to download {file_type} from {url} (status code: {r.status_code})")
+        
+        # Get filename from URL always (includes version)
+        filename = url.split("/")[-1]
+        
+        with open(Path(folder_dir) / filename, "wb") as f:
+            f.write(r.content)

biorazer-0.9.3/biorazer/access/database/AFDB/query.py

@@ -0,0 +1,21 @@
+import requests
+from .info import AFDBEntry
+
+
+def uniprot_to_entries(uniprot_id: str):
+    # If input is full AFDB ID like AF-P0AFB5-F1-model-v4, extract UniProt ID
+    if uniprot_id.startswith("AF-"):
+        # Format: AF-{uniprot}-F1-model-v{...}
+        parts = uniprot_id.split("-")
+        if len(parts) >= 2:
+            uniprot_id = parts[1]
+    r = requests.get(f"https://alphafold.ebi.ac.uk/api/prediction/{uniprot_id}")
+    entries = r.json()
+    # Handle API errors - API returns dict with "error" instead of list
+    if isinstance(entries, dict) and "error" in entries:
+        raise ValueError(f"AlphaFold DB API error: {entries['error']}")
+    if not isinstance(entries, list):
+        raise ValueError(f"AlphaFold DB API returned unexpected format: {type(entries)}")
+    for i in range(len(entries)):
+        entries[i] = AFDBEntry(data=entries[i])
+    return entries

biorazer-0.9.3/biorazer/access/database/RCSB/files.py

@@ -0,0 +1,43 @@
+import logging, requests, re
+from dataclasses import dataclass
+from pathlib import Path
+from xml.etree import ElementTree as ET
+from html import unescape
+from ....logger import initialize_logger
+
+
+@dataclass
+class PDBStructure:
+    pdb_code: str = None
+
+    def download(
+        self,
+        fmt="pdb",
+        folder_dir=".",
+        overwrite=False,
+        logger: logging.Logger = None,
+    ):
+        if not logger:
+            logger = initialize_logger(__name__)
+        logger.info(f"Downloading {self.pdb_code}.{fmt} to {folder_dir}")
+        if Path(f"{folder_dir}/{self.pdb_code}.{fmt}").exists() and not overwrite:
+            logger.warning(
+                f"{self.pdb_code}.{fmt} already exists in {folder_dir}, skipping"
+            )
+        else:
+            r = requests.get(f"https://files.rcsb.org/download/{self.pdb_code}.{fmt}")
+            if r.status_code != 200:
+                logger.warning(f"\n{r.text}")
+            if not Path(folder_dir).exists():
+                Path(folder_dir).mkdir(parents=True)
+            with open(Path(f"{folder_dir}") / f"{self.pdb_code}.{fmt}", "wb") as f:
+                f.write(r.content)
+            if logger:
+                logger.info(f"{self.pdb_code}.{fmt} downloaded to {folder_dir}")
+
+
+def fetch(pdb_code: str, fmt="pdb", download_dir=".", overwrite=False, logger=None):
+    structure = PDBStructure(pdb_code)
+    structure.download(
+        fmt=fmt, folder_dir=download_dir, overwrite=overwrite, logger=logger
+    )