protein-quest 0.3.1__py3-none-any.whl → 0.4.0__py3-none-any.whl

protein_quest/taxonomy.py

@@ -9,9 +9,9 @@ from typing import Literal, get_args
 from aiohttp.client import ClientResponse
 from aiohttp_retry import RetryClient
 from cattrs.gen import make_dict_structure_fn, override
-from cattrs.preconf.orjson import make_converter
 from yarl import URL
 
+from protein_quest.converter import converter
 from protein_quest.go import TextIOWrapper
 from protein_quest.utils import friendly_session
 
@@ -42,8 +42,6 @@ class SearchTaxonResponse:
     results: list[Taxon]
 
 
-converter = make_converter()
-
 converter.register_structure_hook(
     Taxon,
     make_dict_structure_fn(

protein_quest/uniprot.py

@@ -201,7 +201,7 @@ def _build_sparql_generic_query(select_clause: str, where_clause: str, limit: in
     """)
 
 
-def _build_sparql_generic_by_uniprot_accesions_query(
+def _build_sparql_generic_by_uniprot_accessions_query(
     uniprot_accs: Iterable[str], select_clause: str, where_clause: str, limit: int = 10_000, groupby_clause=""
 ) -> str:
     values = " ".join(f'("{ac}")' for ac in uniprot_accs)
@@ -269,7 +269,7 @@ def _build_sparql_query_pdb(uniprot_accs: Iterable[str], limit=10_000) -> str:
     """)
 
     groupby_clause = "?protein ?pdb_db ?pdb_method ?pdb_resolution"
-    return _build_sparql_generic_by_uniprot_accesions_query(
+    return _build_sparql_generic_by_uniprot_accessions_query(
         uniprot_accs, select_clause, where_clause, limit, groupby_clause
     )
 
@@ -284,7 +284,7 @@ def _build_sparql_query_af(uniprot_accs: Iterable[str], limit=10_000) -> str:
         ?protein rdfs:seeAlso ?af_db .
         ?af_db up:database <http://purl.uniprot.org/database/AlphaFoldDB> .
     """)
-    return _build_sparql_generic_by_uniprot_accesions_query(uniprot_accs, select_clause, dedent(where_clause), limit)
+    return _build_sparql_generic_by_uniprot_accessions_query(uniprot_accs, select_clause, dedent(where_clause), limit)
 
 
 def _build_sparql_query_emdb(uniprot_accs: Iterable[str], limit=10_000) -> str:
@@ -297,7 +297,7 @@ def _build_sparql_query_emdb(uniprot_accs: Iterable[str], limit=10_000) -> str:
         ?protein rdfs:seeAlso ?emdb_db .
         ?emdb_db up:database <http://purl.uniprot.org/database/EMDB> .
     """)
-    return _build_sparql_generic_by_uniprot_accesions_query(uniprot_accs, select_clause, dedent(where_clause), limit)
+    return _build_sparql_generic_by_uniprot_accessions_query(uniprot_accs, select_clause, dedent(where_clause), limit)
 
 
 def _execute_sparql_search(
@@ -509,3 +509,156 @@ def search4emdb(uniprot_accs: Iterable[str], limit: int = 10_000, timeout: int =
     )
     limit_check("Search for EMDB entries on uniprot", limit, len(raw_results))
     return _flatten_results_emdb(raw_results)
+
+
+def _build_complex_sparql_query(uniprot_accs: Iterable[str], limit: int) -> str:
+    """Builds a SPARQL query to retrieve ComplexPortal information for given UniProt accessions.
+
+    Example:
+
+    ```sparql
+    PREFIX up:   <http://purl.uniprot.org/core/>
+    PREFIX rdf:  <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
+    PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
+
+    SELECT
+    ?protein
+    ?cp_db
+    ?cp_comment
+    (GROUP_CONCAT(DISTINCT ?member; separator=",") AS ?complex_members)
+    (COUNT(DISTINCT ?member) AS ?member_count)
+    WHERE {
+    # Input UniProt accessions
+    VALUES (?ac) { ("P05067") ("P60709") ("Q05471")}
+    BIND (IRI(CONCAT("http://purl.uniprot.org/uniprot/", ?ac)) AS ?protein)
+
+    # ComplexPortal cross-reference for each input protein
+    ?protein a up:Protein ;
+            rdfs:seeAlso ?cp_db .
+    ?cp_db up:database <http://purl.uniprot.org/database/ComplexPortal> .
+    OPTIONAL { ?cp_db rdfs:comment ?cp_comment . }
+
+    # All member proteins of the same ComplexPortal complex
+    ?member a up:Protein ;
+            rdfs:seeAlso ?cp_db .
+    }
+    GROUP BY ?protein ?cp_db ?cp_comment
+    ORDER BY ?protein ?cp_db
+    LIMIT 500
+    ```
+
+    """
+    select_clause = dedent("""\
+        ?protein ?cp_db ?cp_comment
+        (GROUP_CONCAT(DISTINCT ?member; separator=",") AS ?complex_members)
+    """)
+    where_clause = dedent("""
+        # --- Complex Info ---
+        ?protein a up:Protein ;
+                rdfs:seeAlso ?cp_db .
+        ?cp_db up:database <http://purl.uniprot.org/database/ComplexPortal> .
+        OPTIONAL { ?cp_db rdfs:comment ?cp_comment . }
+        # All member proteins of the same ComplexPortal complex
+        ?member a up:Protein ;
+        rdfs:seeAlso ?cp_db .
+    """)
+    group_by = dedent("""
+       ?protein ?cp_db ?cp_comment
+    """)
+    return _build_sparql_generic_by_uniprot_accessions_query(
+        uniprot_accs, select_clause, where_clause, limit, groupby_clause=group_by
+    )
+
+
+@dataclass(frozen=True)
+class ComplexPortalEntry:
+    """A ComplexPortal entry.
+
+    Parameters:
+        query_protein: The UniProt accession used to find entry.
+        complex_id: The ComplexPortal identifier (for example "CPX-1234").
+        complex_url: The URL to the ComplexPortal entry.
+        complex_title: The title of the complex.
+        members: UniProt accessions which are members of the complex.
+    """
+
+    query_protein: str
+    complex_id: str
+    complex_url: str
+    complex_title: str
+    members: set[str]
+
+
+def _flatten_results_complex(raw_results) -> list[ComplexPortalEntry]:
+    results = []
+    for raw_result in raw_results:
+        query_protein = raw_result["protein"]["value"].split("/")[-1]
+        complex_id = raw_result["cp_db"]["value"].split("/")[-1]
+        complex_url = f"https://www.ebi.ac.uk/complexportal/complex/{complex_id}"
+        complex_title = raw_result.get("cp_comment", {}).get("value", "")
+        members = {m.split("/")[-1] for m in raw_result["complex_members"]["value"].split(",")}
+        results.append(
+            ComplexPortalEntry(
+                query_protein=query_protein,
+                complex_id=complex_id,
+                complex_url=complex_url,
+                complex_title=complex_title,
+                members=members,
+            )
+        )
+    return results
+
+
+def search4macromolecular_complexes(
+    uniprot_accs: Iterable[str], limit: int = 10_000, timeout: int = 1_800
+) -> list[ComplexPortalEntry]:
+    """Search for macromolecular complexes by UniProtKB accessions.
+
+    Queries for references to/from https://www.ebi.ac.uk/complexportal/ database in the Uniprot SPARQL endpoint.
+
+    Args:
+        uniprot_accs: UniProt accessions.
+        limit: Maximum number of results to return.
+        timeout: Timeout for the SPARQL query in seconds.
+
+    Returns:
+        List of ComplexPortalEntry objects.
+    """
+    sparql_query = _build_complex_sparql_query(uniprot_accs, limit)
+    logger.info("Executing SPARQL query for macromolecular complexes: %s", sparql_query)
+    raw_results = _execute_sparql_search(
+        sparql_query=sparql_query,
+        timeout=timeout,
+    )
+    limit_check("Search for complexes", limit, len(raw_results))
+    return _flatten_results_complex(raw_results)
+
+
+def search4interaction_partners(
+    uniprot_acc: str, excludes: set[str] | None = None, limit: int = 10_000, timeout: int = 1_800
+) -> dict[str, set[str]]:
+    """Search for interaction partners of a given UniProt accession using ComplexPortal database references.
+
+    Args:
+        uniprot_acc: UniProt accession to search interaction partners for.
+        excludes: Set of UniProt accessions to exclude from the results.
+            For example already known interaction partners.
+            If None then no complex members are excluded.
+        limit: Maximum number of results to return.
+        timeout: Timeout for the SPARQL query in seconds.
+
+    Returns:
+        Dictionary with UniProt accessions of interaction partners as keys and sets of ComplexPortal entry IDs
+        in which the interaction occurs as values.
+    """
+    ucomplexes = search4macromolecular_complexes([uniprot_acc], limit=limit, timeout=timeout)
+    hits: dict[str, set[str]] = {}
+    if excludes is None:
+        excludes = set()
+    for ucomplex in ucomplexes:
+        for member in ucomplex.members:
+            if member != uniprot_acc and member not in excludes:
+                if member not in hits:
+                    hits[member] = set()
+                hits[member].add(ucomplex.complex_id)
+    return hits

protein_quest/utils.py

@@ -2,11 +2,12 @@
 
 import asyncio
 import logging
+import shutil
 from collections.abc import Coroutine, Iterable
 from contextlib import asynccontextmanager
 from pathlib import Path
 from textwrap import dedent
-from typing import Any
+from typing import Any, Literal, get_args
 
 import aiofiles
 import aiohttp
@@ -138,3 +139,29 @@ def run_async[R](coroutine: Coroutine[Any, Any, R]) -> R:
         return asyncio.run(coroutine)
     except RuntimeError as e:
         raise NestedAsyncIOLoopError from e
+
+
+CopyMethod = Literal["copy", "symlink"]
+copy_methods = set(get_args(CopyMethod))
+
+
+def copyfile(source: Path, target: Path, copy_method: CopyMethod = "copy"):
+    """Make target path be same file as source by either copying or symlinking.
+
+    Args:
+        source: The source file to copy or symlink.
+        target: The target file to create.
+        copy_method: The method to use for copying.
+
+    Raises:
+        FileNotFoundError: If the source file or parent of target does not exist.
+        ValueError: If the method is not "copy" or "symlink".
+    """
+    if copy_method == "copy":
+        shutil.copyfile(source, target)
+    elif copy_method == "symlink":
+        rel_source = source.relative_to(target.parent, walk_up=True)
+        target.symlink_to(rel_source)
+    else:
+        msg = f"Unknown method: {copy_method}"
+        raise ValueError(msg)

{protein_quest-0.3.1.dist-info → protein_quest-0.4.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: protein_quest
-Version: 0.3.1
+Version: 0.4.0
 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
@@ -56,17 +56,23 @@ graph TB;
     searchuniprot --> |uniprot_accessions|searchpdbe[/Search PDBe/]
     searchuniprot --> |uniprot_accessions|searchaf[/Search Alphafold/]
     searchuniprot -. uniprot_accessions .-> searchemdb[/Search EMDB/]
+    searchintactionpartners[/Search interaction partners/] -.-x |uniprot_accessions|searchuniprot
+    searchcomplexes[/Search complexes/]
     searchpdbe -->|pdb_ids|fetchpdbe[Retrieve PDBe]
     searchaf --> |uniprot_accessions|fetchad(Retrieve AlphaFold)
     searchemdb -. emdb_ids .->fetchemdb[Retrieve EMDB]
-    fetchpdbe -->|mmcif_files_with_uniprot_acc| chainfilter{Filter on chain of uniprot}
-    chainfilter --> |mmcif_files| residuefilter{Filter on chain length}
-    fetchad -->|pdb_files| confidencefilter{Filter out low confidence}
+    fetchpdbe -->|mmcif_files| chainfilter{{Filter on chain of uniprot}}
+    chainfilter --> |mmcif_files| residuefilter{{Filter on chain length}}
+    fetchad -->|mmcif_files| confidencefilter{{Filter out low confidence}}
+    confidencefilter --> |mmcif_files| ssfilter{{Filter on secondary structure}}
+    residuefilter --> |mmcif_files| ssfilter
     classDef dashedBorder stroke-dasharray: 5 5;
     goterm:::dashedBorder
     taxonomy:::dashedBorder
     searchemdb:::dashedBorder
     fetchemdb:::dashedBorder
+    searchintactionpartners:::dashedBorder
+    searchcomplexes:::dashedBorder
 ```
 
 (Dotted nodes and edges are side-quests.)
@@ -175,6 +181,18 @@ protein-quest filter residue  \
     ./filtered-chains ./filtered
 ```
 
+### To filter on secondary structure
+
+To filter on structure being mostly alpha helices and have no beta sheets.
+
+```shell
+protein-quest filter secondary-structure \
+    --ratio-min-helix-residues 0.5 \
+    --ratio-max-sheet-residues 0.0 \
+    --write-stats filtered-ss/stats.csv \
+    ./filtered-chains ./filtered-ss
+```
+
 ### Search Taxonomy
 
 ```shell
@@ -190,6 +208,32 @@ You can use following command to search for a Gene Ontology (GO) term.
 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.
+
+```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).
+
+### 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.
+
+```shell
+echo Q05471 | protein-quest search complexes - complexes.csv
+```
+
+The `complexes.csv` looks like
+
+```csv
+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
+```
+
 ##  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-0.4.0.dist-info/RECORD

@@ -0,0 +1,26 @@
+protein_quest/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+protein_quest/__version__.py,sha256=je7v2gXyxr6yRVCFAS0wS-iABSLJOuCb-IPR-x90UAU,56
+protein_quest/cli.py,sha256=9Cgvn5BXbrAloIU2KCiFxLxJSyAoa2RLdmuB0HGsUJM,43078
+protein_quest/converter.py,sha256=Y-Oxf7lDNbEicL6GS-IpNWDwaAiHgIgs5bFAcEHCKdQ,1441
+protein_quest/emdb.py,sha256=QEeU0VJQ4lLM-o5yAU3QZlrtzDZNgnC5fCjlqPtTyAY,1370
+protein_quest/filters.py,sha256=-gasSXR4g5SzYSYbkfcDwR-tm2KCAhCMdpIVJrUPR1w,5224
+protein_quest/go.py,sha256=lZNEcw8nTc9wpV3cl4y2FG9Lsj8wsXQ6zemmAQs_DWE,5650
+protein_quest/mcp_server.py,sha256=CXw5rTStunXdAVQ3BWPXy19zmgQGwV5uPcWlN1HF9do,7389
+protein_quest/parallel.py,sha256=ZJrLO1t2HXs4EeNctytvBTyROPBq-4-gLf35PiolHf0,3468
+protein_quest/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+protein_quest/ss.py,sha256=qOr0aMycNAtZmXXvhCN-KZH3Qp4EejnBcE6fsFgCrmY,10343
+protein_quest/taxonomy.py,sha256=4mKv8zll4mX02Ow8CTvyqMJE2KJZvcq3QlTjjjLOJJk,5072
+protein_quest/uniprot.py,sha256=DIwQYzWZREZ7SGhkJT4Ozgl36pdz47FNfZ1QoEgEaXE,24239
+protein_quest/utils.py,sha256=z4PPPcog6nvPhA93DWVf7stv5uJ4h_2BP5owdhoO5mo,5626
+protein_quest/alphafold/__init__.py,sha256=Ktasi5BRp71wO7-PpOGDpIRRtBEefs8knIdlKQeLQpk,51
+protein_quest/alphafold/confidence.py,sha256=pYIuwYdkuPuHLagcX1dSvSyZ_84xboRLfHUxkEoc4MY,6766
+protein_quest/alphafold/entry_summary.py,sha256=GtE3rT7wH3vIOOeiXY2s80Fo6EzdoqlcvakW8K591Yk,1257
+protein_quest/alphafold/fetch.py,sha256=iFHORaO-2NvPwmpm33tfOFUcSJx8mBGwMXxwc4bRuk8,11336
+protein_quest/pdbe/__init__.py,sha256=eNNHtN60NAGea7gvRkIzkoTXsYPK99s-ldIcKWYO6So,61
+protein_quest/pdbe/fetch.py,sha256=tlCrWoaOrwxnQFrf-PnimUUa6lmtHwwysS51efYsBcA,2379
+protein_quest/pdbe/io.py,sha256=iGLvmsD-eEYnrgZDYfkGWIDCzwDRRD5dwqB480talCs,10037
+protein_quest-0.4.0.dist-info/METADATA,sha256=y5DAnM4mhSincjslsvQZ4zk1QcMysGmnsBltK_Vz4MQ,8842
+protein_quest-0.4.0.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+protein_quest-0.4.0.dist-info/entry_points.txt,sha256=f1RtOxv9TFBO3w01EMEuFXBTMsqKsQcKlkxmj9zE-0g,57
+protein_quest-0.4.0.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+protein_quest-0.4.0.dist-info/RECORD,,

protein_quest-0.3.1.dist-info/RECORD

@@ -1,24 +0,0 @@
-protein_quest/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-protein_quest/__version__.py,sha256=Bu2gp24I4eIxc1qgY2e0PnF8N-szjUpFQwVAe10IRAo,56
-protein_quest/cli.py,sha256=xjiWtRDqv-Ruv1fpvXq4dmDSuuyewxw81akDs1ktVbI,31772
-protein_quest/emdb.py,sha256=QEeU0VJQ4lLM-o5yAU3QZlrtzDZNgnC5fCjlqPtTyAY,1370
-protein_quest/filters.py,sha256=3vqfFH87Lz7r9uYiSvwMxzShMfRNv1Zv_freJtDljrU,4051
-protein_quest/go.py,sha256=ycV3-grxuIKFt28bFgH6iRKmt5AEGi7txoTbaAnBxQE,5684
-protein_quest/mcp_server.py,sha256=1_CGC0peqoNUFBvgFWupKwIWjmHsKxN5Vxy1K7dt5Dw,7130
-protein_quest/parallel.py,sha256=ZJrLO1t2HXs4EeNctytvBTyROPBq-4-gLf35PiolHf0,3468
-protein_quest/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-protein_quest/taxonomy.py,sha256=wPzLjum5n_SEkL2rHUKvyRnjL1pG7bhEnE2vMmXixEc,5105
-protein_quest/uniprot.py,sha256=8qWV4GWqHTRfed0bE_TdgsLYcnDT_vzKu-6JxIgapJQ,18680
-protein_quest/utils.py,sha256=YhlTJreIr1bExbh1M514l6sz4GmLVa3RN57mI1kjjuw,4730
-protein_quest/alphafold/__init__.py,sha256=Ktasi5BRp71wO7-PpOGDpIRRtBEefs8knIdlKQeLQpk,51
-protein_quest/alphafold/confidence.py,sha256=GGd_vYsqVvs9InvFKtqHdGKB_61GHllPmDyIztvzG7E,5625
-protein_quest/alphafold/entry_summary.py,sha256=GtE3rT7wH3vIOOeiXY2s80Fo6EzdoqlcvakW8K591Yk,1257
-protein_quest/alphafold/fetch.py,sha256=1mDbQNm01cxlwFNDsKHBWD7MEwzB3PaheskdaLN7XJs,11491
-protein_quest/pdbe/__init__.py,sha256=eNNHtN60NAGea7gvRkIzkoTXsYPK99s-ldIcKWYO6So,61
-protein_quest/pdbe/fetch.py,sha256=tlCrWoaOrwxnQFrf-PnimUUa6lmtHwwysS51efYsBcA,2379
-protein_quest/pdbe/io.py,sha256=J6fHlRLHLALnpxDgSUUnFCNFV9Hr3u6eJDO6j81ftT4,6936
-protein_quest-0.3.1.dist-info/METADATA,sha256=fWvmMbm5aEMb3WbWgPAqwEOWeYJSY47iuZLaRIgBuuk,7305
-protein_quest-0.3.1.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-protein_quest-0.3.1.dist-info/entry_points.txt,sha256=f1RtOxv9TFBO3w01EMEuFXBTMsqKsQcKlkxmj9zE-0g,57
-protein_quest-0.3.1.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-protein_quest-0.3.1.dist-info/RECORD,,