protein-quest 0.9.0__py3-none-any.whl → 0.10.1__py3-none-any.whl

protein_quest/__version__.py

@@ -1,2 +1,2 @@
-__version__ = "0.9.0"
+__version__ = "0.10.1"
 """The version of the package."""

protein_quest/alphafold/confidence.py

@@ -209,12 +209,7 @@ def filter_files_on_confidence(
             copy_method=copy_method,
         )
 
-    scheduler_address = configure_dask_scheduler(
-        scheduler_address,
-        name="filter-confidence",
-    )
-
-    with Client(scheduler_address) as client:
+    with configure_dask_scheduler(scheduler_address, name="filter-confidence") as cluster, Client(cluster) as client:
         client.forward_logging()
         return dask_map_with_progress(
             client,

protein_quest/alphafold/fetch.py

@@ -114,7 +114,6 @@ class AlphaFoldEntry:
         """Convert paths in an AlphaFoldEntry to be relative to the session directory.
 
         Args:
-            entry: An AlphaFoldEntry instance with absolute paths.
             session_dir: The session directory to which the paths should be made relative.
 
         Returns:
@@ -483,6 +482,7 @@ def fetch_many_async(
     )
 
 
+# jscpd:ignore-start  # noqa: ERA001
 def fetch_many(
     uniprot_accessions: Iterable[str],
     save_dir: Path,
@@ -492,6 +492,7 @@ def fetch_many(
     cacher: Cacher | None = None,
     gzip_files: bool = False,
     all_isoforms: bool = False,
+    # jscpd:ignore-end  # noqa: ERA001
 ) -> list[AlphaFoldEntry]:
     """Synchronously fetches summaries and/or files like cif from AlphaFold Protein Structure Database.
 

protein_quest/filters.py

@@ -96,12 +96,13 @@ def filter_files_on_chain(
 
     # TODO make logger.debug in filter_file_on_chain show to user when --log
     # GPT-5 generated a fairly difficult setup with a WorkerPlugin, need to find a simpler approach
-    scheduler_address = configure_dask_scheduler(
-        scheduler_address,
-        name="filter-chain",
-    )
-
-    with Client(scheduler_address) as client:
+    with (
+        configure_dask_scheduler(
+            scheduler_address,
+            name="filter-chain",
+        ) as cluster,
+        Client(cluster) as client,
+    ):
         client.forward_logging()
         return dask_map_with_progress(
             client,

protein_quest/parallel.py

@@ -2,36 +2,52 @@
 
 import logging
 import os
-from collections.abc import Callable, Collection
+import sys
+import warnings
+from collections.abc import Callable, Collection, Iterator
+from contextlib import contextmanager, suppress
 from typing import Concatenate, ParamSpec, cast
 
-from dask.distributed import Client, LocalCluster, progress
+from dask.distributed import Client, LocalCluster
 from distributed.deploy.cluster import Cluster
+from distributed.diagnostics.progress import format_time
+from distributed.diagnostics.progressbar import ProgressBar
+from distributed.utils import LoopRunner
 from psutil import cpu_count
+from tornado.ioloop import IOLoop
 
 logger = logging.getLogger(__name__)
 
 
+@contextmanager
 def configure_dask_scheduler(
     scheduler_address: str | Cluster | None,
     name: str,
     nproc: int = 1,
-) -> str | Cluster:
-    """Configure the Dask scheduler by reusing existing or creating a new cluster.
+) -> Iterator[str | Cluster]:
+    """Context manager that offers a Dask cluster.
+
+    If scheduler_address is None then creates a local Dask cluster
+    else returns scheduler_address unchanged and the callee is responsible for cluster cleanup.
 
     Args:
         scheduler_address: Address of the Dask scheduler to connect to, or None for local cluster.
         name: Name for the Dask cluster.
         nproc: Number of processes to use per worker for CPU support.
 
-    Returns:
-        A Dask Cluster instance or a string address for the scheduler.
+    Yields:
+        The scheduler address as a string or a cluster.
     """
-    if scheduler_address is None:
-        scheduler_address = _configure_cpu_dask_scheduler(nproc, name)
-        logger.info(f"Using local Dask cluster: {scheduler_address}")
-
-    return scheduler_address
+    if scheduler_address is not None:
+        # Pass through existing scheduler address or cluster
+        yield scheduler_address
+        return
+    cluster = _configure_cpu_dask_scheduler(nproc, name)
+    logger.info(f"Using local Dask cluster: {cluster}")
+    try:
+        yield cluster
+    finally:
+        cluster.close()
 
 
 def nr_cpus() -> int:
@@ -74,6 +90,60 @@ def _configure_cpu_dask_scheduler(nproc: int, name: str) -> LocalCluster:
 P = ParamSpec("P")
 
 
+class _StderrTextProgressBar(ProgressBar):
+    """Copy of distributed.diagnostics.progressbar.TextProgressBar that prints to stderr instead of stdout."""
+
+    __loop: IOLoop | None = None
+
+    def __init__(
+        self,
+        keys,
+        scheduler=None,
+        interval="100ms",
+        width=40,
+        loop=None,
+        complete=True,
+        start=True,
+        **kwargs,  # noqa: ARG002
+    ):
+        self._loop_runner = loop_runner = LoopRunner(loop=loop)
+        super().__init__(keys, scheduler, interval, complete)
+        self.width = width
+
+        if start:
+            loop_runner.run_sync(self.listen)
+
+    @property
+    def loop(self) -> IOLoop | None:
+        loop = self.__loop
+        if loop is None:
+            # If the loop is not running when this is called, the LoopRunner.loop
+            # property will raise a DeprecationWarning
+            # However subsequent calls might occur - eg atexit, where a stopped
+            # loop is still acceptable - so we cache access to the loop.
+            self.__loop = loop = self._loop_runner.loop
+        return loop
+
+    @loop.setter
+    def loop(self, value: IOLoop) -> None:
+        warnings.warn("setting the loop property is deprecated", DeprecationWarning, stacklevel=2)
+        self.__loop = value
+
+    def _draw_bar(self, remaining, all, **kwargs):  # noqa: A002, ARG002
+        frac = (1 - remaining / all) if all else 1.0
+        bar = "#" * int(self.width * frac)
+        percent = int(100 * frac)
+        elapsed = format_time(self.elapsed)
+        msg = "\r[{0:<{1}}] | {2}% Completed | {3}".format(bar, self.width, percent, elapsed)
+        with suppress(ValueError):
+            sys.stderr.write(msg)
+            sys.stderr.flush()
+
+    def _draw_stop(self, **kwargs):  # noqa: ARG002
+        sys.stderr.write("\33[2K\r")
+        sys.stderr.flush()
+
+
 def dask_map_with_progress[T, R, **P](
     client: Client,
     func: Callable[Concatenate[T, P], R],
@@ -99,6 +169,6 @@ 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)
-    progress(futures)
+    _StderrTextProgressBar(futures)
     results = client.gather(futures)
     return cast("list[R]", results)

protein_quest/structure.py

@@ -1,7 +1,6 @@
 """Module for querying and modifying [gemmi structures][gemmi.Structure]."""
 
 import logging
-from collections.abc import Iterable
 from datetime import UTC, datetime
 from pathlib import Path
 
@@ -123,11 +122,28 @@ def chains_in_structure(structure: gemmi.Structure) -> set[gemmi.Chain]:
 class ChainNotFoundError(IndexError):
     """Exception raised when a chain is not found in a structure."""
 
-    def __init__(self, chain: str, file: Path | str, available_chains: Iterable[str]):
-        super().__init__(f"Chain {chain} not found in {file}. Available chains are: {available_chains}")
-        self.chain_id = chain
+    def __init__(self, chain_id: str, file: Path | str, available_chains: set[str]):
+        super().__init__(f"Chain {chain_id} not found in {file}. Available chains are: {available_chains}")
+        self.available_chains = available_chains
+        self.chain_id = chain_id
         self.file = file
 
+    def __reduce__(self):
+        """Helper for pickling the exception."""
+        return (self.__class__, (self.chain_id, self.file, self.available_chains))
+
+    def __eq__(self, other):
+        if not isinstance(other, ChainNotFoundError):
+            return NotImplemented
+        return (
+            self.chain_id == other.chain_id
+            and self.file == other.file
+            and self.available_chains == other.available_chains
+        )
+
+    def __hash__(self):
+        return hash((self.chain_id, str(self.file), frozenset(self.available_chains)))
+
 
 def write_single_chain_structure_file(
     input_file: Path,
@@ -194,7 +210,7 @@ def write_single_chain_structure_file(
         copyfile(input_file, output_file, copy_method)
         return output_file
 
-    gemmi.Selection(chain_name).remove_not_selected(structure)
+    gemmi.Selection(f"/1/{chain_name}").remove_not_selected(structure)
     for m in structure:
         m.remove_ligands_and_waters()
     structure.setup_entities()
@@ -203,6 +219,14 @@ def write_single_chain_structure_file(
     _dedup_sheets(structure, out_chain)
     _add_provenance_info(structure, chain_name, out_chain)
 
+    if not (len(structure) == 1 and len(structure[0]) == 1 and len(structure[0][out_chain]) > 0):
+        msg = (
+            f"After processing, structure does not have exactly one model ({len(structure)}) "
+            f"with one chain (found {len(structure[0])}) called {out_chain} "
+            f"with some residues ({len(structure[0][out_chain])})."
+        )
+        raise ValueError(msg)
+
     write_structure(structure, output_file)
 
     return output_file

{protein_quest-0.9.0.dist-info → protein_quest-0.10.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: protein_quest
-Version: 0.9.0
+Version: 0.10.1
 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
@@ -35,9 +35,14 @@ Description-Content-Type: text/markdown
 [![Documentation](https://img.shields.io/badge/Documentation-bonvinlab.org-blue?style=flat-square&logo=gitbook)](https://www.bonvinlab.org/protein-quest/)
 [![CI](https://github.com/haddocking/protein-quest/actions/workflows/ci.yml/badge.svg)](https://github.com/haddocking/protein-quest/actions/workflows/ci.yml)
 [![Research Software Directory Badge](https://img.shields.io/badge/rsd-00a3e3.svg)](https://www.research-software.nl/software/protein-quest)
+[![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)
 [![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.
 
@@ -104,7 +109,7 @@ pip install git+https://github.com/haddocking/protein-quest.git
 
 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/summary/).
+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.
@@ -302,7 +307,7 @@ The mcp server contains an prompt template to search/retrieve/filter candidate s
 
 ## Shell autocompletion
 
-The `protein-quest` command line tool supports shell autocompletion using [shtab](https://shtab.readthedocs.io/).
+The `protein-quest` command line tool supports shell autocompletion using [shtab](https://docs.iterative.ai/shtab).
 
 Initialize for bash shell with:
 

{protein_quest-0.9.0.dist-info → protein_quest-0.10.1.dist-info}/RECORD

@@ -1,27 +1,27 @@
 protein_quest/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-protein_quest/__version__.py,sha256=A6xdUp_IQF1iQCvcfinhBk_OF7aPTf2HnTokoy3XfPA,56
+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/emdb.py,sha256=641c6RwNYnu-0GBFyCFBiI58fNc0jMkd0ZZ9MW9-Jmc,1501
-protein_quest/filters.py,sha256=Iosivg8ws5msx_154jIt3Xt_0tqsW3rS_T9tOUeyYFo,5649
+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=ZJrLO1t2HXs4EeNctytvBTyROPBq-4-gLf35PiolHf0,3468
+protein_quest/parallel.py,sha256=uf26nD5l1Gp4Z5AFgb0K3vNBUlzvfFh8NSDbGzePSr0,5856
 protein_quest/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 protein_quest/ss.py,sha256=4ZGIHfjTlodYTXqGUKhMnGbgaStYOGaWg2oYrWIjdgo,10118
-protein_quest/structure.py,sha256=QozElPz0kbPB_HW-J1WxArTT5e-1vRyBJoBSfHnwoRM,8117
+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/utils.py,sha256=5Ncdid-dslggy-Ti1yhOHwdAM7Bxpyia7Re-xDkc2P0,19909
 protein_quest/alphafold/__init__.py,sha256=Ktasi5BRp71wO7-PpOGDpIRRtBEefs8knIdlKQeLQpk,51
-protein_quest/alphafold/confidence.py,sha256=6I21bueHjV-gLbYUq2kwBIF_3kxq1IG66RMxZ3O5ULo,8144
+protein_quest/alphafold/confidence.py,sha256=UtS2MJEReaZ1kTXbQf8Vrc9gzGjAOiGLYs4glqN-1do,8098
 protein_quest/alphafold/entry_summary.py,sha256=Qhnw75RXFaoOU332g7axg_jYbbdZbUpsGPUOwPNDSeU,2114
-protein_quest/alphafold/fetch.py,sha256=eKCQHkAMko-d36VvRHLCllLxuAXBdbBUhUONOSCPsds,21970
+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-0.9.0.dist-info/METADATA,sha256=jqtceWZY7GUks47JBzwm4lPF8Txf7nKLL4Dah9NkOCM,11335
-protein_quest-0.9.0.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-protein_quest-0.9.0.dist-info/entry_points.txt,sha256=f1RtOxv9TFBO3w01EMEuFXBTMsqKsQcKlkxmj9zE-0g,57
-protein_quest-0.9.0.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-protein_quest-0.9.0.dist-info/RECORD,,
+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,,