protein-quest 0.5.1__tar.gz → 0.6.0__tar.gz

{protein_quest-0.5.1 → protein_quest-0.6.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: protein_quest
-Version: 0.5.1
+Version: 0.6.0
 Summary: Search/retrieve/filter proteins and protein structures
 Project-URL: Homepage, https://github.com/haddocking/protein-quest
 Project-URL: Issues, https://github.com/haddocking/protein-quest/issues
@@ -17,6 +17,7 @@ Requires-Dist: cattrs[orjson]>=24.1.3
 Requires-Dist: dask>=2025.5.1
 Requires-Dist: distributed>=2025.5.1
 Requires-Dist: gemmi>=0.7.3
+Requires-Dist: mmcif>=0.92.0
 Requires-Dist: platformdirs>=4.3.8
 Requires-Dist: psutil>=7.0.0
 Requires-Dist: rich-argparse>=1.7.1
@@ -71,6 +72,7 @@ graph TB;
     fetchad -->|mmcif_files| confidencefilter{{Filter out low confidence}}
     confidencefilter --> |mmcif_files| ssfilter{{Filter on secondary structure}}
     residuefilter --> |mmcif_files| ssfilter
+    ssfilter -. mmcif_files .-> convert2cif([Convert to cif])
     classDef dashedBorder stroke-dasharray: 5 5;
     goterm:::dashedBorder
     taxonomy:::dashedBorder
@@ -78,6 +80,7 @@ graph TB;
     fetchemdb:::dashedBorder
     searchintactionpartners:::dashedBorder
     searchcomplexes:::dashedBorder
+    convert2cif:::dashedBorder
 ```
 
 (Dotted nodes and edges are side-quests.)
@@ -242,6 +245,14 @@ query_protein,complex_id,complex_url,complex_title,members
 Q05471,CPX-2122,https://www.ebi.ac.uk/complexportal/complex/CPX-2122,Swr1 chromatin remodelling complex,P31376;P35817;P38326;P53201;P53930;P60010;P80428;Q03388;Q03433;Q03940;Q05471;Q06707;Q12464;Q12509
 ```
 
+### Convert structure files to .cif format
+
+Some tools (for example [powerfit](https://github.com/haddocking/powerfit)) only work with `.cif` files and not `*.cif.gz` or `*.bcif` files.
+
+```shell
+protein-quest convert --output-dir ./filtered-cif ./filtered-ss
+```
+
 ##  Model Context Protocol (MCP) server
 
 Protein quest can also help LLMs like Claude Sonnet 4 by providing a [set of tools](https://modelcontextprotocol.io/docs/learn/server-concepts#tools-ai-actions) for protein structures.

{protein_quest-0.5.1 → protein_quest-0.6.0}/README.md

@@ -40,6 +40,7 @@ graph TB;
     fetchad -->|mmcif_files| confidencefilter{{Filter out low confidence}}
     confidencefilter --> |mmcif_files| ssfilter{{Filter on secondary structure}}
     residuefilter --> |mmcif_files| ssfilter
+    ssfilter -. mmcif_files .-> convert2cif([Convert to cif])
     classDef dashedBorder stroke-dasharray: 5 5;
     goterm:::dashedBorder
     taxonomy:::dashedBorder
@@ -47,6 +48,7 @@ graph TB;
     fetchemdb:::dashedBorder
     searchintactionpartners:::dashedBorder
     searchcomplexes:::dashedBorder
+    convert2cif:::dashedBorder
 ```
 
 (Dotted nodes and edges are side-quests.)
@@ -211,6 +213,14 @@ query_protein,complex_id,complex_url,complex_title,members
 Q05471,CPX-2122,https://www.ebi.ac.uk/complexportal/complex/CPX-2122,Swr1 chromatin remodelling complex,P31376;P35817;P38326;P53201;P53930;P60010;P80428;Q03388;Q03433;Q03940;Q05471;Q06707;Q12464;Q12509
 ```
 
+### Convert structure files to .cif format
+
+Some tools (for example [powerfit](https://github.com/haddocking/powerfit)) only work with `.cif` files and not `*.cif.gz` or `*.bcif` files.
+
+```shell
+protein-quest convert --output-dir ./filtered-cif ./filtered-ss
+```
+
 ##  Model Context Protocol (MCP) server
 
 Protein quest can also help LLMs like Claude Sonnet 4 by providing a [set of tools](https://modelcontextprotocol.io/docs/learn/server-concepts#tools-ai-actions) for protein structures.

{protein_quest-0.5.1 → protein_quest-0.6.0}/docs/notebooks/pdbe.ipynb

@@ -111,12 +111,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": null,
    "id": "52a42ec2",
    "metadata": {},
    "outputs": [],
    "source": [
-    "from protein_quest.pdbe.io import write_single_chain_pdb_file"
+    "from protein_quest.structure import write_single_chain_structure_file"
    ]
   },
   {
@@ -139,7 +139,9 @@
    "source": [
     "# A8MT69\t4NDY\tB/D/H/L/M/N/U/V/W/X=8-81\n",
     "# above is the identifier, chain and position info for the structure from https://www.uniprot.org/uniprotkb/A8MT69/entry#structure\n",
-    "output_4dny_file = write_single_chain_pdb_file(input_file=save_dir / \"4ndy.cif.gz\", chain2keep=\"B\", output_dir=save_dir)\n",
+    "output_4dny_file = write_single_chain_structure_file(\n",
+    "    input_file=save_dir / \"4ndy.cif.gz\", chain2keep=\"B\", output_dir=save_dir\n",
+    ")\n",
     "output_4dny_file"
    ]
   },
@@ -162,13 +164,15 @@
    ],
    "source": [
     "# A8MT69\t4DRA\tE/F/G/H=1-81\n",
-    "output_4dra_file = write_single_chain_pdb_file(input_file=save_dir / \"4dra.cif.gz\", chain2keep=\"E\", output_dir=save_dir)\n",
+    "output_4dra_file = write_single_chain_structure_file(\n",
+    "    input_file=save_dir / \"4dra.cif.gz\", chain2keep=\"E\", output_dir=save_dir\n",
+    ")\n",
     "output_4dra_file"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": null,
    "id": "673d1274",
    "metadata": {},
    "outputs": [
@@ -184,7 +188,7 @@
     }
    ],
    "source": [
-    "output_1xwh_file = write_single_chain_pdb_file(\n",
+    "output_1xwh_file = write_single_chain_structure_file(\n",
     "    input_file=save_dir / \"1xwh.cif.gz\",\n",
     "    chain2keep=\"A\",\n",
     "    output_dir=save_dir,\n",
@@ -194,7 +198,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": null,
    "id": "5f03eb2c",
    "metadata": {},
    "outputs": [
@@ -211,7 +215,7 @@
    ],
    "source": [
     "# O00268      │ 8WAS    │ D/d=1-1085\n",
-    "output_8was_file = write_single_chain_pdb_file(\n",
+    "output_8was_file = write_single_chain_structure_file(\n",
     "    input_file=save_dir / \"8was.cif.gz\",\n",
     "    chain2keep=\"D\",\n",
     "    output_dir=save_dir,\n",

{protein_quest-0.5.1 → protein_quest-0.6.0}/pyproject.toml

@@ -21,6 +21,7 @@ dependencies = [
     "tqdm>=4.67.1",
     "yarl>=1.20.1",
     "platformdirs>=4.3.8",
+    "mmcif>=0.92.0",
 ]
 
 [project.urls]

{protein_quest-0.5.1 → protein_quest-0.6.0}/src/protein_quest/__version__.py

@@ -1,2 +1,2 @@
-__version__ = "0.5.1"
+__version__ = "0.6.0"
 """The version of the package."""

{protein_quest-0.5.1 → protein_quest-0.6.0}/src/protein_quest/alphafold/confidence.py

@@ -8,7 +8,7 @@ from pathlib import Path
 import gemmi
 
 from protein_quest.converter import Percentage, PositiveInt, converter
-from protein_quest.pdbe.io import write_structure
+from protein_quest.io import read_structure, write_structure
 from protein_quest.ss import nr_of_residues_in_total
 from protein_quest.utils import CopyMethod, copyfile
 
@@ -127,7 +127,7 @@ def filter_file_on_residues(
         result with filtered_file property set to Path where filtered PDB file is saved.
             or None if structure was filtered out.
     """
-    structure = gemmi.read_structure(str(file))
+    structure = read_structure(file)
     residues = set(find_high_confidence_residues(structure, query.confidence))
     count = len(residues)
     if count < query.min_residues or count > query.max_residues:

{protein_quest-0.5.1 → protein_quest-0.6.0}/src/protein_quest/alphafold/fetch.py

@@ -125,15 +125,15 @@ async def fetch_summary(
     fn: AsyncPath | None = None
     if save_dir is not None:
         fn = AsyncPath(save_dir / f"{qualifier}.json")
+        if await fn.exists():
+            logger.debug(f"File {fn} already exists. Skipping download from {url}.")
+            raw_data = await fn.read_bytes()
+            return converter.loads(raw_data, list[EntrySummary])
         cached_file = await cacher.copy_from_cache(Path(fn))
         if cached_file is not None:
             logger.debug(f"Using cached file {cached_file} for summary of {qualifier}.")
             raw_data = await AsyncPath(cached_file).read_bytes()
             return converter.loads(raw_data, list[EntrySummary])
-        if await fn.exists():
-            logger.debug(f"File {fn} already exists. Skipping download from {url}.")
-            raw_data = await fn.read_bytes()
-            return converter.loads(raw_data, list[EntrySummary])
     async with semaphore, session.get(url) as response:
         response.raise_for_status()
         raw_data = await response.content.read()
@@ -170,6 +170,7 @@ async def fetch_many_async(
     what: set[DownloadableFormat],
     max_parallel_downloads: int = 5,
     cacher: Cacher | None = None,
+    gzip_files: bool = False,
 ) -> AsyncGenerator[AlphaFoldEntry]:
     """Asynchronously fetches summaries and files from
     [AlphaFold Protein Structure Database](https://alphafold.ebi.ac.uk/).
@@ -180,6 +181,7 @@ async def fetch_many_async(
         what: A set of formats to download.
         max_parallel_downloads: The maximum number of parallel downloads.
         cacher: A cacher to use for caching the fetched files. Only used if summary is in what set.
+        gzip_files: Whether to gzip the downloaded files.
 
     Yields:
         A dataclass containing the summary, pdb file, and pae file.
@@ -193,7 +195,7 @@ async def fetch_many_async(
         )
     ]
 
-    files = files_to_download(what, summaries)
+    files = files_to_download(what, summaries, gzip_files)
 
     await retrieve_files(
         files,
@@ -201,36 +203,40 @@ async def fetch_many_async(
         desc="Downloading AlphaFold files",
         max_parallel_downloads=max_parallel_downloads,
         cacher=cacher,
+        gzip_files=gzip_files,
     )
+    gzext = ".gz" if gzip_files else ""
     for summary in summaries:
         yield AlphaFoldEntry(
             uniprot_acc=summary.uniprotAccession,
             summary=summary,
             summary_file=save_dir / f"{summary.uniprotAccession}.json" if save_dir_for_summaries is not None else None,
-            bcif_file=save_dir / summary.bcifUrl.name if "bcif" in what else None,
-            cif_file=save_dir / summary.cifUrl.name if "cif" in what else None,
-            pdb_file=save_dir / summary.pdbUrl.name if "pdb" in what else None,
-            pae_image_file=save_dir / summary.paeImageUrl.name if "paeImage" in what else None,
-            pae_doc_file=save_dir / summary.paeDocUrl.name if "paeDoc" in what else None,
+            bcif_file=save_dir / (summary.bcifUrl.name + gzext) if "bcif" in what else None,
+            cif_file=save_dir / (summary.cifUrl.name + gzext) if "cif" in what else None,
+            pdb_file=save_dir / (summary.pdbUrl.name + gzext) if "pdb" in what else None,
+            pae_image_file=save_dir / (summary.paeImageUrl.name + gzext) if "paeImage" in what else None,
+            pae_doc_file=save_dir / (summary.paeDocUrl.name + gzext) if "paeDoc" in what else None,
             am_annotations_file=(
-                save_dir / summary.amAnnotationsUrl.name
+                save_dir / (summary.amAnnotationsUrl.name + gzext)
                 if "amAnnotations" in what and summary.amAnnotationsUrl
                 else None
             ),
             am_annotations_hg19_file=(
-                save_dir / summary.amAnnotationsHg19Url.name
+                save_dir / (summary.amAnnotationsHg19Url.name + gzext)
                 if "amAnnotationsHg19" in what and summary.amAnnotationsHg19Url
                 else None
             ),
             am_annotations_hg38_file=(
-                save_dir / summary.amAnnotationsHg38Url.name
+                save_dir / (summary.amAnnotationsHg38Url.name + gzext)
                 if "amAnnotationsHg38" in what and summary.amAnnotationsHg38Url
                 else None
             ),
         )
 
 
-def files_to_download(what: set[DownloadableFormat], summaries: Iterable[EntrySummary]) -> set[tuple[URL, str]]:
+def files_to_download(
+    what: set[DownloadableFormat], summaries: Iterable[EntrySummary], gzip_files: bool
+) -> set[tuple[URL, str]]:
     if not (set(what) <= downloadable_formats):
         msg = (
             f"Invalid format(s) specified: {set(what) - downloadable_formats}. "
@@ -238,7 +244,7 @@ def files_to_download(what: set[DownloadableFormat], summaries: Iterable[EntrySu
         )
         raise ValueError(msg)
 
-    files: set[tuple[URL, str]] = set()
+    url_filename_pairs: set[tuple[URL, str]] = set()
     for summary in summaries:
         for fmt in what:
             if fmt == "summary":
@@ -248,9 +254,10 @@ def files_to_download(what: set[DownloadableFormat], summaries: Iterable[EntrySu
             if url is None:
                 logger.warning(f"Summary {summary.uniprotAccession} does not have a URL for format '{fmt}'. Skipping.")
                 continue
-            file = (url, url.name)
-            files.add(file)
-    return files
+            fn = url.name + (".gz" if gzip_files else "")
+            url_filename_pair = (url, fn)
+            url_filename_pairs.add(url_filename_pair)
+    return url_filename_pairs
 
 
 def fetch_many(
@@ -259,6 +266,7 @@ def fetch_many(
     what: set[DownloadableFormat],
     max_parallel_downloads: int = 5,
     cacher: Cacher | None = None,
+    gzip_files: bool = False,
 ) -> list[AlphaFoldEntry]:
     """Synchronously fetches summaries and pdb and pae files from AlphaFold Protein Structure Database.
 
@@ -268,6 +276,7 @@ def fetch_many(
         what: A set of formats to download.
         max_parallel_downloads: The maximum number of parallel downloads.
         cacher: A cacher to use for caching the fetched files. Only used if summary is in what set.
+        gzip_files: Whether to gzip the downloaded files.
 
     Returns:
         A list of AlphaFoldEntry dataclasses containing the summary, pdb file, and pae file.
@@ -277,7 +286,7 @@ def fetch_many(
         return [
             entry
             async for entry in fetch_many_async(
-                ids, save_dir, what, max_parallel_downloads=max_parallel_downloads, cacher=cacher
+                ids, save_dir, what, max_parallel_downloads=max_parallel_downloads, cacher=cacher, gzip_files=gzip_files
             )
         ]
 

{protein_quest-0.5.1 → protein_quest-0.6.0}/src/protein_quest/cli.py

@@ -28,8 +28,13 @@ from protein_quest.converter import converter
 from protein_quest.emdb import fetch as emdb_fetch
 from protein_quest.filters import filter_files_on_chain, filter_files_on_residues
 from protein_quest.go import Aspect, allowed_aspects, search_gene_ontology_term, write_go_terms_to_csv
+from protein_quest.io import (
+    convert_to_cif_files,
+    glob_structure_files,
+    locate_structure_file,
+    valid_structure_file_extensions,
+)
 from protein_quest.pdbe import fetch as pdbe_fetch
-from protein_quest.pdbe.io import glob_structure_files, locate_structure_file
 from protein_quest.ss import SecondaryStructureFilterQuery, filter_files_on_secondary_structure
 from protein_quest.taxonomy import SearchField, _write_taxonomy_csv, search_fields, search_taxon
 from protein_quest.uniprot import (
@@ -297,6 +302,38 @@ def _add_search_complexes_parser(subparsers: argparse._SubParsersAction):
     parser.add_argument("--timeout", type=int, default=1_800, help="Maximum seconds to wait for query to complete")
 
 
+def _add_copy_method_arguments(parser):
+    parser.add_argument(
+        "--copy-method",
+        type=str,
+        choices=copy_methods,
+        default="hardlink",
+        help=dedent("""\
+            How to make target file be same file as source file.
+            By default uses hardlinks to save disk space.
+            Note that hardlinks only work within the same filesystem and are harder to track.
+            If you want to track cached files easily then use 'symlink'.
+            On Windows you need developer mode or admin privileges to create symlinks.
+        """),
+    )
+
+
+def _add_cacher_arguments(parser: argparse.ArgumentParser):
+    """Add cacher arguments to parser."""
+    parser.add_argument(
+        "--no-cache",
+        action="store_true",
+        help="Disable caching of files to central location.",
+    )
+    parser.add_argument(
+        "--cache-dir",
+        type=Path,
+        default=user_cache_root_dir(),
+        help="Directory to use as cache for files.",
+    )
+    _add_copy_method_arguments(parser)
+
+
 def _add_retrieve_pdbe_parser(subparsers: argparse._SubParsersAction):
     """Add retrieve pdbe subcommand parser."""
     parser = subparsers.add_parser(
@@ -345,6 +382,11 @@ def _add_retrieve_alphafold_parser(subparsers: argparse._SubParsersAction):
         help=dedent("""AlphaFold formats to retrieve. Can be specified multiple times.
             Default is 'summary' and 'cif'."""),
     )
+    parser.add_argument(
+        "--gzip-files",
+        action="store_true",
+        help="Whether to gzip the downloaded files. Excludes summary files, they are always uncompressed.",
+    )
     parser.add_argument(
         "--max-parallel-downloads",
         type=int,
@@ -561,6 +603,33 @@ def _add_filter_subcommands(subparsers: argparse._SubParsersAction):
     _add_filter_ss_parser(subsubparsers)
 
 
+def _add_convert_subcommands(subparsers: argparse._SubParsersAction):
+    """Add convert command."""
+    parser = subparsers.add_parser(
+        "convert", help="Convert structure files between formats", formatter_class=ArgumentDefaultsRichHelpFormatter
+    )
+    parser.add_argument(
+        "input_dir",
+        type=Path,
+        help=f"Directory with structure files. Supported extensions are {valid_structure_file_extensions}",
+    )
+    parser.add_argument(
+        "--output-dir",
+        type=Path,
+        help=dedent("""\
+            Directory to write converted structure files. If not given, files are written to `input_dir`.
+        """),
+    )
+    parser.add_argument(
+        "--format",
+        type=str,
+        choices=("cif",),
+        default="cif",
+        help="Output format to convert to.",
+    )
+    _add_copy_method_arguments(parser)
+
+
 def _add_mcp_command(subparsers: argparse._SubParsersAction):
     """Add MCP command."""
 
@@ -580,38 +649,6 @@ def _add_mcp_command(subparsers: argparse._SubParsersAction):
     parser.add_argument("--port", default=8000, type=int, help="Port to bind the server to")
 
 
-def _add_copy_method_arguments(parser):
-    parser.add_argument(
-        "--copy-method",
-        type=str,
-        choices=copy_methods,
-        default="hardlink",
-        help=dedent("""\
-            How to make target file be same file as source file.
-            By default uses hardlinks to save disk space.
-            Note that hardlinks only work within the same filesystem and are harder to track.
-            If you want to track cached files easily then use 'symlink'.
-            On Windows you need developer mode or admin privileges to create symlinks.
-        """),
-    )
-
-
-def _add_cacher_arguments(parser: argparse.ArgumentParser):
-    """Add cacher arguments to parser."""
-    parser.add_argument(
-        "--no-cache",
-        action="store_true",
-        help="Disable caching of files to central location.",
-    )
-    parser.add_argument(
-        "--cache-dir",
-        type=Path,
-        default=user_cache_root_dir(),
-        help="Directory to use as cache for files.",
-    )
-    _add_copy_method_arguments(parser)
-
-
 def make_parser() -> argparse.ArgumentParser:
     parser = argparse.ArgumentParser(
         description="Protein Quest CLI", prog="protein-quest", formatter_class=ArgumentDefaultsRichHelpFormatter
@@ -624,27 +661,12 @@ def make_parser() -> argparse.ArgumentParser:
     _add_search_subcommands(subparsers)
     _add_retrieve_subcommands(subparsers)
     _add_filter_subcommands(subparsers)
+    _add_convert_subcommands(subparsers)
     _add_mcp_command(subparsers)
 
     return parser
 
 
-def main():
-    """Main entry point for the CLI."""
-    parser = make_parser()
-    args = parser.parse_args()
-    logging.basicConfig(level=args.log_level, handlers=[RichHandler(show_level=False)])
-
-    # Dispatch table to reduce complexity
-    cmd = args.command
-    sub = getattr(args, f"{cmd}_cmd", None)
-    handler = HANDLERS.get((cmd, sub))
-    if handler is None:
-        msg = f"Unknown command: {cmd} {sub}"
-        raise SystemExit(msg)
-    handler(args)
-
-
 def _handle_search_uniprot(args):
     taxon_id = args.taxon_id
     reviewed = args.reviewed
@@ -798,6 +820,7 @@ def _handle_retrieve_alphafold(args):
     alphafold_csv = args.alphafold_csv
     max_parallel_downloads = args.max_parallel_downloads
     cacher = _initialize_cacher(args)
+    gzip_files = args.gzip_files
 
     if what_formats is None:
         what_formats = {"summary", "cif"}
@@ -808,7 +831,12 @@ def _handle_retrieve_alphafold(args):
     validated_what: set[DownloadableFormat] = structure(what_formats, set[DownloadableFormat])
     rprint(f"Retrieving {len(af_ids)} AlphaFold entries with formats {validated_what}")
     afs = af_fetch(
-        af_ids, download_dir, what=validated_what, max_parallel_downloads=max_parallel_downloads, cacher=cacher
+        af_ids,
+        download_dir,
+        what=validated_what,
+        max_parallel_downloads=max_parallel_downloads,
+        cacher=cacher,
+        gzip_files=gzip_files,
     )
     total_nr_files = sum(af.nr_of_files() for af in afs)
     rprint(f"Retrieved {total_nr_files} AlphaFold files and {len(afs)} summaries, written to {download_dir}")
@@ -1017,24 +1045,24 @@ def _handle_mcp(args):
         mcp.run(transport=args.transport, host=args.host, port=args.port)
 
 
-HANDLERS: dict[tuple[str, str | None], Callable] = {
-    ("search", "uniprot"): _handle_search_uniprot,
-    ("search", "pdbe"): _handle_search_pdbe,
-    ("search", "alphafold"): _handle_search_alphafold,
-    ("search", "emdb"): _handle_search_emdb,
-    ("search", "go"): _handle_search_go,
-    ("search", "taxonomy"): _handle_search_taxonomy,
-    ("search", "interaction-partners"): _handle_search_interaction_partners,
-    ("search", "complexes"): _handle_search_complexes,
-    ("retrieve", "pdbe"): _handle_retrieve_pdbe,
-    ("retrieve", "alphafold"): _handle_retrieve_alphafold,
-    ("retrieve", "emdb"): _handle_retrieve_emdb,
-    ("filter", "confidence"): _handle_filter_confidence,
-    ("filter", "chain"): _handle_filter_chain,
-    ("filter", "residue"): _handle_filter_residue,
-    ("filter", "secondary-structure"): _handle_filter_ss,
-    ("mcp", None): _handle_mcp,
-}
+def _handle_convert(args):
+    input_dir = structure(args.input_dir, Path)
+    output_dir = input_dir if args.output_dir is None else structure(args.output_dir, Path)
+    copy_method: CopyMethod = structure(args.copy_method, CopyMethod)  # pyright: ignore[reportArgumentType]
+
+    input_files = sorted(glob_structure_files(input_dir))
+    rprint(f"Converting {len(input_files)} files in {input_dir} directory to cif format.")
+    for _ in tqdm(
+        convert_to_cif_files(
+            input_files,
+            output_dir,
+            copy_method=copy_method,
+        ),
+        total=len(input_files),
+        unit="file",
+    ):
+        pass
+    rprint(f"Converted {len(input_files)} files into {output_dir}.")
 
 
 def _read_lines(file: TextIOWrapper) -> list[str]:
@@ -1118,3 +1146,40 @@ def _write_complexes_csv(complexes: list[ComplexPortalEntry], output_csv: TextIO
                 members_str,
             ]
         )
+
+
+HANDLERS: dict[tuple[str, str | None], Callable] = {
+    ("search", "uniprot"): _handle_search_uniprot,
+    ("search", "pdbe"): _handle_search_pdbe,
+    ("search", "alphafold"): _handle_search_alphafold,
+    ("search", "emdb"): _handle_search_emdb,
+    ("search", "go"): _handle_search_go,
+    ("search", "taxonomy"): _handle_search_taxonomy,
+    ("search", "interaction-partners"): _handle_search_interaction_partners,
+    ("search", "complexes"): _handle_search_complexes,
+    ("retrieve", "pdbe"): _handle_retrieve_pdbe,
+    ("retrieve", "alphafold"): _handle_retrieve_alphafold,
+    ("retrieve", "emdb"): _handle_retrieve_emdb,
+    ("filter", "confidence"): _handle_filter_confidence,
+    ("filter", "chain"): _handle_filter_chain,
+    ("filter", "residue"): _handle_filter_residue,
+    ("filter", "secondary-structure"): _handle_filter_ss,
+    ("mcp", None): _handle_mcp,
+    ("convert", None): _handle_convert,
+}
+
+
+def main():
+    """Main entry point for the CLI."""
+    parser = make_parser()
+    args = parser.parse_args()
+    logging.basicConfig(level=args.log_level, handlers=[RichHandler(show_level=False)])
+
+    # Dispatch table to reduce complexity
+    cmd = args.command
+    sub = getattr(args, f"{cmd}_cmd", None)
+    handler = HANDLERS.get((cmd, sub))
+    if handler is None:
+        msg = f"Unknown command: {cmd} {sub}"
+        raise SystemExit(msg)
+    handler(args)

{protein_quest-0.5.1 → protein_quest-0.6.0}/src/protein_quest/filters.py

@@ -11,10 +11,7 @@ from distributed.deploy.cluster import Cluster
 from tqdm.auto import tqdm
 
 from protein_quest.parallel import configure_dask_scheduler, dask_map_with_progress
-from protein_quest.pdbe.io import (
-    nr_residues_in_chain,
-    write_single_chain_pdb_file,
-)
+from protein_quest.structure import nr_residues_in_chain, write_single_chain_structure_file
 from protein_quest.utils import CopyMethod, copyfile
 
 logger = logging.getLogger(__name__)
@@ -38,7 +35,7 @@ def filter_file_on_chain(
     input_file, chain_id = file_and_chain
     logger.debug("Filtering %s on chain %s", input_file, chain_id)
     try:
-        output_file = write_single_chain_pdb_file(
+        output_file = write_single_chain_structure_file(
             input_file, chain_id, output_dir, out_chain=out_chain, copy_method=copy_method
         )
         return ChainFilterStatistics(