protein-quest 0.10.1__py3-none-any.whl → 1.1.0__py3-none-any.whl

protein_quest/__version__.py

@@ -1,2 +1,2 @@
-__version__ = "0.10.1"
+__version__ = "1.1.0"
 """The version of the package."""

protein_quest/cli.py

@@ -8,6 +8,7 @@ import os
 import sys
 from collections.abc import Callable, Generator, Iterable, Sequence
 from contextlib import suppress
+from functools import lru_cache
 from importlib.util import find_spec
 from io import BytesIO, TextIOWrapper
 from pathlib import Path
@@ -20,6 +21,7 @@ from rich.logging import RichHandler
 from rich.markdown import Markdown
 from rich.panel import Panel
 from rich_argparse import ArgumentDefaultsRichHelpFormatter
+from rocrate_action_recorder import recorded_argparse
 from tqdm.rich import tqdm
 
 from protein_quest.__version__ import __version__
@@ -797,12 +799,18 @@ def _add_mcp_command(subparsers: argparse._SubParsersAction):
     parser.add_argument("--port", default=8000, type=int, help="Port to bind the server to")
 
 
+@lru_cache(maxsize=1)
 def make_parser() -> argparse.ArgumentParser:
     parser = argparse.ArgumentParser(
         description="Protein Quest CLI", prog="protein-quest", formatter_class=ArgumentDefaultsRichHelpFormatter
     )
     parser.add_argument("--log-level", default="WARNING", choices=["DEBUG", "INFO", "WARNING", "ERROR", "CRITICAL"])
     parser.add_argument("--version", action="version", version=f"%(prog)s {__version__}")
+    parser.add_argument(
+        "--prov",
+        action="store_true",
+        help="Whether to write provenance information about the command execution to ro-crate-metadata.json file.",
+    )
     shtab.add_argument_to(parser, ["--print-completion"])
 
     subparsers = parser.add_subparsers(dest="command", required=True)
@@ -824,7 +832,26 @@ def _name_of(file: TextIOWrapper | BytesIO) -> str:
         return "<stdout>"
 
 
-def _handle_search_uniprot(args):
+def prov(
+    input_dirs: list[str] | None = None,
+    output_dirs: list[str] | None = None,
+    input_files: list[str] | None = None,
+    output_files: list[str] | None = None,
+):
+    """Decorator to record provenance for protein-quest commands."""
+    return recorded_argparse(
+        parser=make_parser(),
+        input_dirs=input_dirs,
+        output_dirs=output_dirs,
+        input_files=input_files,
+        output_files=output_files,
+        enabled_argument="prov",
+        dataset_license="CC BY 4.0",
+    )
+
+
+@prov(output_files=["output"])
+def _handle_search_uniprot(args: argparse.Namespace):
     taxon_id = args.taxon_id
     reviewed = args.reviewed
     subcellular_location_uniprot = args.subcellular_location_uniprot
@@ -854,7 +881,8 @@ def _handle_search_uniprot(args):
     _write_lines(output_file, sorted(accs))
 
 
-def _handle_search_pdbe(args):
+@prov(input_files=["uniprot_accessions"], output_files=["output_csv"])
+def _handle_search_pdbe(args: argparse.Namespace):
     uniprot_accessions = args.uniprot_accessions
     limit = args.limit
     timeout = args.timeout
@@ -884,6 +912,7 @@ def _handle_search_pdbe(args):
     rprint(f"Written to {_name_of(output_csv)}")
 
 
+@prov(input_files=["uniprot_accessions"], output_files=["output_csv"])
 def _handle_search_alphafold(args):
     uniprot_accessions = args.uniprot_accessions
     min_sequence_length = converter.structure(args.min_sequence_length, PositiveInt | None)  # pyright: ignore[reportArgumentType]
@@ -905,6 +934,7 @@ def _handle_search_alphafold(args):
     _write_dict_of_sets2csv(output_csv, results, "af_id")
 
 
+@prov(input_files=["uniprot_accessions"], output_files=["output_csv"])
 def _handle_search_emdb(args):
     uniprot_accessions = args.uniprot_accessions
     limit = args.limit
@@ -919,6 +949,7 @@ def _handle_search_emdb(args):
     _write_dict_of_sets2csv(output_csv, results, "emdb_id")
 
 
+@prov(output_files=["output_csv"])
 def _handle_search_go(args):
     term = structure(args.term, str)
     aspect: Aspect | None = args.aspect
@@ -934,6 +965,7 @@ def _handle_search_go(args):
     write_go_terms_to_csv(results, output_csv)
 
 
+@prov(output_files=["output_csv"])
 def _handle_search_taxonomy(args):
     query: str = args.query
     field: SearchField | None = args.field
@@ -949,6 +981,7 @@ def _handle_search_taxonomy(args):
     _write_taxonomy_csv(results, output_csv)
 
 
+@prov(input_files=["uniprot_accession"], output_files=["output_csv"])
 def _handle_search_interaction_partners(args: argparse.Namespace):
     uniprot_accession: str = args.uniprot_accession
     excludes: set[str] = set(args.exclude) if args.exclude else set()
@@ -962,6 +995,7 @@ def _handle_search_interaction_partners(args: argparse.Namespace):
     _write_lines(output_csv, results.keys())
 
 
+@prov(input_files=["uniprot_accessions"], output_files=["output_csv"])
 def _handle_search_complexes(args: argparse.Namespace):
     uniprot_accessions = args.uniprot_accessions
     limit = args.limit
@@ -975,6 +1009,7 @@ def _handle_search_complexes(args: argparse.Namespace):
     _write_complexes_csv(results, output_csv)
 
 
+@prov(input_files=["uniprot_accessions"], output_files=["output_csv"])
 def _handle_search_uniprot_details(args: argparse.Namespace):
     uniprot_accessions = args.uniprot_accessions
     timeout = args.timeout
@@ -997,6 +1032,7 @@ def _initialize_cacher(args: argparse.Namespace) -> Cacher:
     )
 
 
+@prov(input_files=["pdbe_csv"], output_dirs=["output_dir"])
 def _handle_retrieve_pdbe(args: argparse.Namespace):
     pdbe_csv = args.pdbe_csv
     output_dir = args.output_dir
@@ -1011,6 +1047,7 @@ def _handle_retrieve_pdbe(args: argparse.Namespace):
     rprint(f"Retrieved {len(result)} PDBe entries")
 
 
+@prov(input_files=["alphafold_csv"], output_dirs=["output_dir"])
 def _handle_retrieve_alphafold(args):
     download_dir = args.output_dir
     raw_formats = args.format
@@ -1042,6 +1079,7 @@ def _handle_retrieve_alphafold(args):
     rprint(f"Retrieved {total_nr_files} AlphaFold files and {len(afs)} summaries, written to {download_dir}")
 
 
+@prov(input_files=["emdb_csv"], output_dirs=["output_dir"])
 def _handle_retrieve_emdb(args):
     emdb_csv = args.emdb_csv
     output_dir = args.output_dir
@@ -1053,6 +1091,7 @@ def _handle_retrieve_emdb(args):
     rprint(f"Retrieved {len(result)} EMDB entries")
 
 
+@prov(input_dirs=["input_dir"], output_dirs=["output_dir"], output_files=["write_stats"])
 def _handle_filter_confidence(args: argparse.Namespace):
     # we are repeating types here and in add_argument call
     # TODO replace argparse with modern alternative like cyclopts
@@ -1097,6 +1136,7 @@ def _handle_filter_confidence(args: argparse.Namespace):
         rprint(f"Statistics written to {_name_of(stats_file)}")
 
 
+@prov(input_dirs=["input_dir"], output_dirs=["output_dir"], output_files=["write_stats"])
 def _handle_filter_chain(args):
     input_dir = args.input_dir
     output_dir = structure(args.output_dir, Path)
@@ -1140,6 +1180,7 @@ def _handle_filter_chain(args):
             rprint(f"[red]Discarding {result.input_file} ({result.discard_reason})[/red]")
 
 
+@prov(input_dirs=["input_dir"], output_dirs=["output_dir"], output_files=["write_stats"])
 def _handle_filter_residue(args):
     input_dir = structure(args.input_dir, Path)
     output_dir = structure(args.output_dir, Path)
@@ -1169,6 +1210,7 @@ def _handle_filter_residue(args):
         rprint(f"Statistics written to {_name_of(stats_file)}")
 
 
+@prov(input_dirs=["input_dir"], output_dirs=["output_dir"], output_files=["write_stats"])
 def _handle_filter_ss(args):
     input_dir = structure(args.input_dir, Path)
     output_dir = structure(args.output_dir, Path)
@@ -1236,7 +1278,7 @@ def _handle_mcp(args):
         msg = "Unable to start MCP server, please install `protein-quest[mcp]`."
         raise ImportError(msg)
 
-    from protein_quest.mcp_server import mcp  # noqa: PLC0415
+    from protein_quest.mcp_server import mcp  # noqa: PLC0415 fastmcp is an extra dependency
 
     if args.transport == "stdio":
         mcp.run(transport=args.transport)
@@ -1244,6 +1286,7 @@ def _handle_mcp(args):
         mcp.run(transport=args.transport, host=args.host, port=args.port)
 
 
+@prov(input_dirs=["input_dir"], output_files=["output"])
 def _handle_convert_uniprot(args):
     input_dir = structure(args.input_dir, Path)
     output_file: TextIOWrapper = args.output
@@ -1264,6 +1307,7 @@ def _handle_convert_uniprot(args):
         _write_lines(output_file, sorted(uniprot_accessions))
 
 
+@prov(input_dirs=["input_dir"], output_dirs=["output_dir"])
 def _handle_convert_structures(args):
     input_dir = structure(args.input_dir, Path)
     output_dir = input_dir if args.output_dir is None else structure(args.output_dir, Path)

protein_quest/converter.py

@@ -13,7 +13,7 @@ type PositiveInt = int
 converter = make_converter()
 """cattrs converter to read JSON document or dict to Python objects."""
 converter.register_structure_hook(URL, lambda v, _: URL(v))
-converter.register_unstructure_hook(URL, lambda u: str(u))
+converter.register_unstructure_hook(URL, str)
 
 
 @converter.register_structure_hook

protein_quest/mcp_server.py

@@ -7,8 +7,8 @@ Can be run with:
 fastmcp dev src/protein_quest/mcp_server.py
 # or from inspector
 npx @modelcontextprotocol/inspector
-# tranport type: stdio
-# comand: protein-quest
+# transport type: stdio
+# command: protein-quest
 # arguments: mcp
 
 # or with server and inspector

protein_quest/parallel.py

@@ -86,12 +86,15 @@ def _configure_cpu_dask_scheduler(nproc: int, name: str) -> LocalCluster:
     return LocalCluster(name=name, threads_per_worker=1, n_workers=n_workers)
 
 
-# Generic type parameters used across helpers
-P = ParamSpec("P")
+class MyProgressBar(ProgressBar):
+    """Show progress of Dask computations.
 
+    Copy of distributed.diagnostics.progressbar.TextProgressBar that:
 
-class _StderrTextProgressBar(ProgressBar):
-    """Copy of distributed.diagnostics.progressbar.TextProgressBar that prints to stderr instead of stdout."""
+    - prints to stderr instead of stdout
+    - Can have its interval (in seconds) set with `TQDM_MININTERVAL` environment variable
+
+    """
 
     __loop: IOLoop | None = None
 
@@ -107,6 +110,11 @@ class _StderrTextProgressBar(ProgressBar):
         **kwargs,  # noqa: ARG002
     ):
         self._loop_runner = loop_runner = LoopRunner(loop=loop)
+        if interval == "100ms":
+            interval_env = os.getenv("TQDM_MININTERVAL")
+            if interval_env is not None:
+                interval = interval_env + "s"
+
         super().__init__(keys, scheduler, interval, complete)
         self.width = width
 
@@ -144,6 +152,10 @@ class _StderrTextProgressBar(ProgressBar):
         sys.stderr.flush()
 
 
+# Generic type parameters used across helpers
+P = ParamSpec("P")
+
+
 def dask_map_with_progress[T, R, **P](
     client: Client,
     func: Callable[Concatenate[T, P], R],
@@ -154,6 +166,10 @@ def dask_map_with_progress[T, R, **P](
     """
     Wrapper for map, progress, and gather of Dask that returns a correctly typed list.
 
+    Environment variables:
+        - Set interval (in seconds) of progress updates with `TQDM_MININTERVAL`
+        - Disabled by setting `TQDM_DISABLE` to any value
+
     Args:
         client: Dask client.
         func: Function to map; first parameter comes from ``iterable`` and any
@@ -169,6 +185,7 @@ def dask_map_with_progress[T, R, **P](
     if client.dashboard_link:
         logger.info(f"Follow progress on dask dashboard at: {client.dashboard_link}")
     futures = client.map(func, iterable, *args, **kwargs)
-    _StderrTextProgressBar(futures)
+    if not os.getenv("TQDM_DISABLE"):
+        MyProgressBar(futures)
     results = client.gather(futures)
     return cast("list[R]", results)

protein_quest/uniprot.py

@@ -332,7 +332,7 @@ def _build_sparql_generic_by_uniprot_accessions_query(
 
 def _build_sparql_query_uniprot(query: Query, limit=10_000) -> str:
     dynamic_triples = _query2dynamic_sparql_triples(query)
-    # TODO add usefull columns that have 1:1 mapping to protein
+    # TODO add useful columns that have 1:1 mapping to protein
     # like uniprot_id with `?protein up:mnemonic ?mnemonic .`
     # and sequence, take care to take first isoform
     # ?protein up:sequence ?isoform .

{protein_quest-0.10.1.dist-info → protein_quest-1.1.0.dist-info}/METADATA

@@ -1,12 +1,27 @@
 Metadata-Version: 2.4
 Name: protein_quest
-Version: 0.10.1
+Version: 1.1.0
 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
 Project-URL: Documentation, https://www.bonvinlab.org/protein-quest/
 Project-URL: Source, https://github.com/haddocking/protein-quest
 License-File: LICENSE
+Keywords: alphafold,mmcif,pdb,protein,protein structure,uniprot
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Environment :: Console
+Classifier: Framework :: AsyncIO
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Natural Language :: English
+Classifier: Operating System :: MacOS
+Classifier: Operating System :: POSIX
+Classifier: Operating System :: POSIX :: Linux
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
+Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
+Classifier: Topic :: Scientific/Engineering :: Chemistry
+Classifier: Typing :: Typed
 Requires-Python: >=3.13
 Requires-Dist: aiofiles>=24.1.0
 Requires-Dist: aiohttp-retry>=2.9.1
@@ -21,6 +36,7 @@ Requires-Dist: platformdirs>=4.3.8
 Requires-Dist: psutil>=7.0.0
 Requires-Dist: rich-argparse>=1.7.1
 Requires-Dist: rich>=14.0.0
+Requires-Dist: rocrate-action-recorder>=0.2.0
 Requires-Dist: shtab>=1.7.2
 Requires-Dist: sparqlwrapper>=2.0.0
 Requires-Dist: tqdm>=4.67.1
@@ -38,19 +54,22 @@ Description-Content-Type: text/markdown
 [![bio.tools](https://img.shields.io/badge/bio.tools-protein--quest-009fdf.svg)](https://bio.tools/protein-quest)
 [![PyPI](https://img.shields.io/pypi/v/protein-quest)](https://pypi.org/project/protein-quest/)
 [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.16941288.svg)](https://doi.org/10.5281/zenodo.16941288)
+[![Poster DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.17910832.svg)](https://doi.org/10.5281/zenodo.17910832)
 [![Codacy Badge](https://app.codacy.com/project/badge/Coverage/7a3f3f1fe64640d583a5e50fe7ba828e)](https://app.codacy.com/gh/haddocking/protein-quest/coverage?utm_source=gh&utm_medium=referral&utm_content=&utm_campaign=Badge_coverage)
 [![FAIR checklist badge](https://fairsoftwarechecklist.net/badge.svg)](https://fairsoftwarechecklist.net/v0.2?f=31&a=32113&i=32121&r=133)
 [![fair-software.eu](https://img.shields.io/badge/fair--software.eu-%E2%97%8F%20%20%E2%97%8F%20%20%E2%97%8F%20%20%E2%97%8F%20%20%E2%97%8F-green)](https://fair-software.eu)
 [![Copy/paste detector](https://raw.githubusercontent.com/kucherenko/jscpd/refs/tags/v3.5.10/assets/jscpd-badge.svg?sanitize=true)](https://github.com/kucherenko/jscpd/)
 
-
 Python package to search/retrieve/filter proteins and protein structures.
 
 It uses
 
-- [Uniprot Sparql endpoint](https://sparql.uniprot.org/) to search for proteins and their measured or predicted 3D structures.
-- [Uniprot taxonomy](https://www.uniprot.org/taxonomy?query=*) to search for taxonomy.
-- [QuickGO](https://www.ebi.ac.uk/QuickGO/api/index.html) to search for Gene Ontology terms.
+- [Uniprot Sparql endpoint](https://sparql.uniprot.org/) to search for proteins
+  and their measured or predicted 3D structures.
+- [Uniprot taxonomy](https://www.uniprot.org/taxonomy?query=*) to search for
+  taxonomy.
+- [QuickGO](https://www.ebi.ac.uk/QuickGO/api/index.html) to search for Gene
+  Ontology terms.
 - [gemmi](https://project-gemmi.github.io/) to work with macromolecular models.
 - [dask-distributed](https://docs.dask.org/en/latest/) to compute in parallel.
 
@@ -101,18 +120,24 @@ pip install protein-quest
 ```
 
 Or to use the latest development version:
-```
+
+```shell
 pip install git+https://github.com/haddocking/protein-quest.git
 ```
 
 ## Usage
 
-The main entry point is the `protein-quest` command line tool which has multiple subcommands to perform actions.
+The main entry point is the `protein-quest` command line tool which has multiple
+subcommands to perform actions.
 
-To use programmaticly, see the [Jupyter notebooks](https://www.bonvinlab.org/protein-quest/notebooks) and [API documentation](https://www.bonvinlab.org/protein-quest/autoapi/protein_quest/).
+To use programmaticly, see the
+[Jupyter notebooks](https://www.bonvinlab.org/protein-quest/notebooks) and
+[API documentation](https://www.bonvinlab.org/protein-quest/autoapi/protein_quest/).
 
-While downloading or copying files it uses a global cache (located at `~/.cache/protein-quest`) and hardlinks to save disk space and improve speed.
-This behavior can be customized with the `--no-cache`, `--cache-dir`, and `--copy-method` command line arguments.
+While downloading or copying files it uses a global cache (located at
+`~/.cache/protein-quest`) and hardlinks to save disk space and improve speed.
+This behavior can be customized with the `--no-cache`, `--cache-dir`, and
+`--copy-method` command line arguments.
 
 ### Search Uniprot accessions
 
@@ -126,7 +151,9 @@ protein-quest search uniprot \
     --limit 100 \
     uniprot_accs.txt
 ```
-([GO:0005634](https://www.ebi.ac.uk/QuickGO/term/GO:0005634) is "Nucleus" and [GO:0003677](https://www.ebi.ac.uk/QuickGO/term/GO:0003677) is  "DNA binding")
+
+([GO:0005634](https://www.ebi.ac.uk/QuickGO/term/GO:0005634) is "Nucleus" and
+[GO:0003677](https://www.ebi.ac.uk/QuickGO/term/GO:0003677) is "DNA binding")
 
 ### Search for PDBe structures of uniprot accessions
 
@@ -134,7 +161,8 @@ protein-quest search uniprot \
 protein-quest search pdbe uniprot_accs.txt pdbe.csv
 ```
 
-`pdbe.csv` file is written containing the the PDB id and chain of each uniprot accession.
+`pdbe.csv` file is written containing the the PDB id and chain of each uniprot
+accession.
 
 ### Search for Alphafold structures of uniprot accessions
 
@@ -170,8 +198,8 @@ protein-quest retrieve emdb emdbs.csv downloads-emdb/
 
 ### To filter AlphaFold structures on confidence
 
-Filter AlphaFoldDB structures based on confidence (pLDDT).
-Keeps entries with requested number of residues which have a confidence score above the threshold.
+Filter AlphaFoldDB structures based on confidence (pLDDT). Keeps entries with
+requested number of residues which have a confidence score above the threshold.
 Also writes pdb files with only those residues.
 
 ```shell
@@ -184,7 +212,8 @@ protein-quest filter confidence \
 
 ### To filter PDBe files on chain of uniprot accession
 
-Make PDBe files smaller by only keeping first chain of found uniprot entry and renaming to chain A.
+Make PDBe files smaller by only keeping first chain of found uniprot entry and
+renaming to chain A.
 
 ```shell
 protein-quest filter chain \
@@ -203,7 +232,10 @@ protein-quest filter residue  \
 
 ### To filter on secondary structure
 
-To filter on structure being mostly alpha helices and have no beta sheets. See the following [notebook](https://www.bonvinlab.org/protein-detective/SSE_elements.html) to determine the ratio of secondary structure elements.
+To filter on structure being mostly alpha helices and have no beta sheets. See
+the following
+[notebook](https://www.bonvinlab.org/protein-detective/SSE_elements.html) to
+determine the ratio of secondary structure elements.
 
 ```shell
 protein-quest filter secondary-structure \
@@ -221,8 +253,10 @@ protein-quest search taxonomy "Homo sapiens" -
 
 ### Search Gene Ontology (GO)
 
-You might not know what the identifier of a [Gene Ontology](https://geneontology.org/) term is at `protein-quest search uniprot`.
-You can use following command to search for a Gene Ontology (GO) term.
+You might not know what the identifier of a
+[Gene Ontology](https://geneontology.org/) term is at
+`protein-quest search uniprot`. You can use following command to search for a
+Gene Ontology (GO) term.
 
 ```shell
 protein-quest search go --limit 5 --aspect cellular_component apoptosome -
@@ -230,18 +264,21 @@ protein-quest search go --limit 5 --aspect cellular_component apoptosome -
 
 ### Search for interaction partners
 
-Use https://www.ebi.ac.uk/complexportal to find interaction partners of given UniProt accession.
+Use <https://www.ebi.ac.uk/complexportal> to find interaction partners of given
+UniProt accession.
 
 ```shell
 protein-quest search interaction-partners Q05471 interaction-partners-of-Q05471.txt
 ```
 
-The `interaction-partners-of-Q05471.txt` file contains uniprot accessions (one per line).
+The `interaction-partners-of-Q05471.txt` file contains uniprot accessions (one
+per line).
 
 ### Search for complexes
 
-Given Uniprot accessions search for macromolecular complexes at https://www.ebi.ac.uk/complexportal
-and return the complex entries and their members.
+Given Uniprot accessions search for macromolecular complexes at
+<https://www.ebi.ac.uk/complexportal> and return the complex entries and their
+members.
 
 ```shell
 echo Q05471 | protein-quest search complexes - complexes.csv
@@ -256,7 +293,8 @@ Q05471,CPX-2122,https://www.ebi.ac.uk/complexportal/complex/CPX-2122,Swr1 chroma
 
 ### Search for UniProt details
 
-To get details (like protein name, sequence length, organism) for a list of UniProt accessions.
+To get details (like protein name, sequence length, organism) for a list of
+UniProt accessions.
 
 ```shell
 protein-quest search uniprot-details uniprot_accs.txt uniprot_details.csv
@@ -271,7 +309,8 @@ A0A087WUV0,ZN892_HUMAN,522,True,Zinc finger protein 892,9606,Homo sapiens
 
 ### 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.
+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 structures --format cif --output-dir ./filtered-cif ./filtered-ss
@@ -279,15 +318,25 @@ protein-quest convert structures --format cif --output-dir ./filtered-cif ./filt
 
 ### Convert structure files to UniProt accessions
 
-After running some filters you might want to know which UniProt accessions are still present in the filtered structures.
+After running some filters you might want to know which UniProt accessions are
+still present in the filtered structures.
 
 ```shell
 protein-quest convert uniprot ./filtered-ss uniprot_accs.filtered.txt
 ```
 
-##  Model Context Protocol (MCP) server
+## Provenance
+
+You can use `protein-quest --prov ...` to store provenance information of your
+CLI invocations in a
+[Research Object crate](https://www.researchobject.org/ro-crate/) file called
+ro-crate-metadata.json.
+
+## 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 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 MCP workflow](https://github.com/haddocking/protein-quest/raw/main/docs/protein-quest-mcp.png)
 
@@ -303,11 +352,13 @@ The server can be started with:
 protein-quest mcp
 ```
 
-The mcp server contains an prompt template to search/retrieve/filter candidate structures.
+The mcp server contains an prompt template to search/retrieve/filter candidate
+structures.
 
 ## Shell autocompletion
 
-The `protein-quest` command line tool supports shell autocompletion using [shtab](https://docs.iterative.ai/shtab).
+The `protein-quest` command line tool supports shell autocompletion using
+[shtab](https://docs.iterative.ai/shtab).
 
 Initialize for bash shell with:
 
@@ -327,4 +378,5 @@ autoload -Uz compinit && compinit
 
 ## Contributing
 
-For development information and contribution guidelines, please see [CONTRIBUTING.md](CONTRIBUTING.md).
+For development information and contribution guidelines, please see
+[CONTRIBUTING.md](CONTRIBUTING.md).

{protein_quest-0.10.1.dist-info → protein_quest-1.1.0.dist-info}/RECORD

@@ -1,18 +1,18 @@
 protein_quest/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-protein_quest/__version__.py,sha256=qCmLtq4uktEgR1D3vZFBaO_0UsYFvPWt7gmxqgWwku0,57
-protein_quest/cli.py,sha256=aWqdAeseUm7s8UGmrPFNfJPW6W83RmpJAsEy4sZscQY,57506
-protein_quest/converter.py,sha256=Y-Oxf7lDNbEicL6GS-IpNWDwaAiHgIgs5bFAcEHCKdQ,1441
+protein_quest/__version__.py,sha256=1-Y-bSMxz0yut5o_jEVM46EG2KW008II37JW_koD3Oc,56
+protein_quest/cli.py,sha256=2_bEP7gGYxvxaqlcwEaiJc9i6hf_HtMj_xucNeaOqv4,59587
+protein_quest/converter.py,sha256=Qk-hIyp-YGUK4vvOZlES3BktZsK14-ShgBvVyo9Wjh8,1428
 protein_quest/emdb.py,sha256=641c6RwNYnu-0GBFyCFBiI58fNc0jMkd0ZZ9MW9-Jmc,1501
 protein_quest/filters.py,sha256=em1FYD7Y9z98ZSaJGYCv1VCGRADLbat8FfSOlNJNAJM,5663
 protein_quest/go.py,sha256=lZNEcw8nTc9wpV3cl4y2FG9Lsj8wsXQ6zemmAQs_DWE,5650
 protein_quest/io.py,sha256=ngV_HU2HIQFO-bP2xQj_fhgv0MYjW4puqz_9CxGpBv8,13017
-protein_quest/mcp_server.py,sha256=ZmEs18crS_Ce1-b_PM4m5kmS5C8lLlcrgpocTt7GVrg,8551
-protein_quest/parallel.py,sha256=uf26nD5l1Gp4Z5AFgb0K3vNBUlzvfFh8NSDbGzePSr0,5856
+protein_quest/mcp_server.py,sha256=N22DT8g6i1EXI2bunpPppLbwsGkBBOdKpmtTuooXuOk,8553
+protein_quest/parallel.py,sha256=hmwjv-KeiC7qSs5xApAvh3ZKkJ9HDW5zmr1zuwOzFpg,6367
 protein_quest/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 protein_quest/ss.py,sha256=4ZGIHfjTlodYTXqGUKhMnGbgaStYOGaWg2oYrWIjdgo,10118
 protein_quest/structure.py,sha256=3TdzrXbGpmnskp3gjwVevwD1tfhKfAUPOHWi9ViaheM,9101
 protein_quest/taxonomy.py,sha256=4mKv8zll4mX02Ow8CTvyqMJE2KJZvcq3QlTjjjLOJJk,5072
-protein_quest/uniprot.py,sha256=kV1lOZ_ugcF-LUff9hvmJPaGwA_uaHPJCL_3DLBIvSE,36798
+protein_quest/uniprot.py,sha256=1tqAQqnQIH7OV0dhjWv8TJIIrY6sXgrfFvlf-OieP1s,36797
 protein_quest/utils.py,sha256=5Ncdid-dslggy-Ti1yhOHwdAM7Bxpyia7Re-xDkc2P0,19909
 protein_quest/alphafold/__init__.py,sha256=Ktasi5BRp71wO7-PpOGDpIRRtBEefs8knIdlKQeLQpk,51
 protein_quest/alphafold/confidence.py,sha256=UtS2MJEReaZ1kTXbQf8Vrc9gzGjAOiGLYs4glqN-1do,8098
@@ -20,8 +20,8 @@ protein_quest/alphafold/entry_summary.py,sha256=Qhnw75RXFaoOU332g7axg_jYbbdZbUps
 protein_quest/alphafold/fetch.py,sha256=D-RWKWo5kWpCko_LNT_sslzrpeR3HX9nu5F4MUOFRtI,21979
 protein_quest/pdbe/__init__.py,sha256=eNNHtN60NAGea7gvRkIzkoTXsYPK99s-ldIcKWYO6So,61
 protein_quest/pdbe/fetch.py,sha256=e8CHWDX2QzWnVLmYXCfNrscw1UcN1lI9Uz6Z5HmEOEQ,2510
-protein_quest-0.10.1.dist-info/METADATA,sha256=Mz2JLKRAqBvcbMsr1I1rdeYlJK8lTUXCX3AwBpSywxI,11939
-protein_quest-0.10.1.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-protein_quest-0.10.1.dist-info/entry_points.txt,sha256=f1RtOxv9TFBO3w01EMEuFXBTMsqKsQcKlkxmj9zE-0g,57
-protein_quest-0.10.1.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-protein_quest-0.10.1.dist-info/RECORD,,
+protein_quest-1.1.0.dist-info/METADATA,sha256=BnrYu853g1P2RJom3E13vTWsumEurdo1XwdEJ2b7wJE,13045
+protein_quest-1.1.0.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
+protein_quest-1.1.0.dist-info/entry_points.txt,sha256=f1RtOxv9TFBO3w01EMEuFXBTMsqKsQcKlkxmj9zE-0g,57
+protein_quest-1.1.0.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+protein_quest-1.1.0.dist-info/RECORD,,

{protein_quest-0.10.1.dist-info → protein_quest-1.1.0.dist-info}/WHEEL

@@ -1,4 +1,4 @@
 Wheel-Version: 1.0
-Generator: hatchling 1.27.0
+Generator: hatchling 1.28.0
 Root-Is-Purelib: true
 Tag: py3-none-any