protein-quest 0.5.1__py3-none-any.whl → 0.7.0__py3-none-any.whl

protein_quest/uniprot.py

@@ -1,8 +1,9 @@
 """Module for searching UniProtKB using SPARQL."""
 
 import logging
-from collections.abc import Collection, Iterable
+from collections.abc import Collection, Generator, Iterable
 from dataclasses import dataclass
+from functools import cached_property
 from itertools import batched
 from textwrap import dedent
 
@@ -24,6 +25,8 @@ class Query:
             (e.g., ["GO:0005634"]) or a collection of GO terms (e.g., ["GO:0005634", "GO:0005737"]).
         molecular_function_go: Molecular function in GO format. Can be a single GO term
             (e.g., ["GO:0003674"]) or a collection of GO terms (e.g., ["GO:0003674", "GO:0008150"]).
+        min_sequence_length: Minimum length of the canonical sequence.
+        max_sequence_length: Maximum length of the canonical sequence.
     """
 
     # TODO make taxon_id an int
@@ -32,6 +35,8 @@ class Query:
     subcellular_location_uniprot: str | None = None
     subcellular_location_go: list[str] | None = None
     molecular_function_go: list[str] | None = None
+    min_sequence_length: int | None = None
+    max_sequence_length: int | None = None
 
 
 def _first_chain_from_uniprot_chains(uniprot_chains: str) -> str:
@@ -39,16 +44,17 @@ def _first_chain_from_uniprot_chains(uniprot_chains: str) -> str:
 
     The UniProt chains string is formatted (with EBNF notation) as follows:
 
-        chain_group(=range)?(,chain_group(=range)?)*
+        chain_group=range(,chain_group=range)*
 
     where:
         chain_group := chain_id(/chain_id)*
-        chain_id    := [A-Za-z]+
+        chain_id    := [A-Za-z0-9]+
         range       := start-end
         start, end  := integer
 
     Args:
         uniprot_chains: A string representing UniProt chains, For example "B/D=1-81".
+
     Returns:
         The first chain identifier from the UniProt chain string. For example "B".
     """
@@ -66,6 +72,27 @@ def _first_chain_from_uniprot_chains(uniprot_chains: str) -> str:
     return chain
 
 
+def _chain_length_from_uniprot_chains(uniprot_chains: str) -> int:
+    """Calculates the total length of chain from a UniProt chains string.
+
+    See `_first_chain_from_uniprot_chains` for the format of the UniProt chains string.
+
+    Args:
+        uniprot_chains: A string representing UniProt chains, For example "B/D=1-81".
+
+    Returns:
+        The length of the chain in the UniProt chain string. For example 81 for "B/D=1-81".
+    """
+    total_length = 0
+    chains = uniprot_chains.split(",")
+    for chain in chains:
+        _, rangestr = chain.split("=")
+        start, stop = rangestr.split("-")
+        # Residue positions are 1-based so + 1
+        total_length += int(stop) - int(start) + 1
+    return total_length
+
+
 @dataclass(frozen=True)
 class PdbResult:
     """Result of a PDB search in UniProtKB.
@@ -82,11 +109,57 @@ class PdbResult:
     uniprot_chains: str
     resolution: str | None = None
 
-    @property
+    @cached_property
     def chain(self) -> str:
         """The first chain from the UniProt chains aka self.uniprot_chains."""
         return _first_chain_from_uniprot_chains(self.uniprot_chains)
 
+    @cached_property
+    def chain_length(self) -> int:
+        """The length of the chain from the UniProt chains aka self.uniprot_chains."""
+        return _chain_length_from_uniprot_chains(self.uniprot_chains)
+
+
+type PdbResults = dict[str, set[PdbResult]]
+"""Dictionary with uniprot accessions as keys and sets of PDB results as values."""
+
+
+def filter_pdb_results_on_chain_length(
+    pdb_results: PdbResults,
+    min_residues: int | None,
+    max_residues: int | None,
+) -> PdbResults:
+    """Filter PDB results based on chain length.
+
+    Args:
+        pdb_results: Dictionary with protein IDs as keys and sets of PDB results as values.
+        min_residues: Minimum number of residues required in the chain mapped to the UniProt accession.
+            If None, no minimum is applied.
+        max_residues: Maximum number of residues allowed in chain mapped to the UniProt accession.
+            If None, no maximum is applied.
+
+    Returns:
+        Filtered dictionary with protein IDs as keys and sets of PDB results as values.
+    """
+    if min_residues is None and max_residues is None:
+        # No filtering needed
+        return pdb_results
+    if min_residues is not None and max_residues is not None and max_residues <= min_residues:
+        msg = f"Maximum number of residues ({max_residues}) must be > minimum number of residues ({min_residues})"
+        raise ValueError(msg)
+    results: PdbResults = {}
+    for uniprot_accession, pdb_entries in pdb_results.items():
+        filtered_pdb_entries = {
+            pdb_entry
+            for pdb_entry in pdb_entries
+            if (min_residues is None or pdb_entry.chain_length >= min_residues)
+            and (max_residues is None or pdb_entry.chain_length <= max_residues)
+        }
+        if filtered_pdb_entries:
+            # Only include uniprot_accession if there are any pdb entries left after filtering
+            results[uniprot_accession] = filtered_pdb_entries
+    return results
+
 
 def _query2dynamic_sparql_triples(query: Query):
     parts: list[str] = []
@@ -110,6 +183,13 @@ def _query2dynamic_sparql_triples(query: Query):
         molecular_function_filter = _create_go_filter(go_terms, "Molecular function")
         parts.append(molecular_function_filter)
 
+    if query.min_sequence_length is not None or query.max_sequence_length is not None:
+        length_filter = _build_sparql_query_sequence_length_filter(
+            min_length=query.min_sequence_length,
+            max_length=query.max_sequence_length,
+        )
+        parts.append(length_filter)
+
     return "\n".join(parts)
 
 
@@ -237,6 +317,57 @@ def _build_sparql_query_uniprot(query: Query, limit=10_000) -> str:
     return _build_sparql_generic_query(select_clause, dedent(where_clause), limit)
 
 
+def _build_sparql_query_sequence_length_filter(min_length: int | None = None, max_length: int | None = None) -> str:
+    """Builds a SPARQL filter for sequence length.
+
+    See 107_uniprot_sequences_and_mark_which_is_cannonical_for_human
+    on https://sparql.uniprot.org/.well-known/sparql-examples/ for similar query.
+
+    Args:
+        min_length: Minimum sequence length. If None, no minimum is applied.
+        max_length: Maximum sequence length. If None, no maximum is applied.
+    """
+    if min_length is None and max_length is None:
+        return ""
+    # An uniprot entry can have multiple isoforms,
+    # we want to check the length of the canonical isoform
+    # We do this by selecting the isoform that is not based on another isoform
+    # and excluding isoforms from other uniprot entries.
+    # For example for http://purl.uniprot.org/uniprot/P42284:
+    # - http://purl.uniprot.org/isoforms/P42284-2 is ok
+    # - http://purl.uniprot.org/isoforms/P42284-1 is not ok, because it is based on P42284-2
+    # - http://purl.uniprot.org/isoforms/Q7KQZ4-1 is not ok, because it is from another uniprot entry
+    # TODO use same approach as in retrieve_uniprot_details function
+    header = dedent("""\
+        ?protein up:sequence ?isoform .
+        FILTER NOT EXISTS { ?isoform up:basedOn ?parent_isoform }
+        FILTER(
+            STRAFTER(STR(?protein), "http://purl.uniprot.org/uniprot/") =
+            STRBEFORE(STRAFTER(STR(?isoform), "http://purl.uniprot.org/isoforms/"), "-"))
+        ?isoform rdf:value ?sequence .
+        BIND (STRLEN(?sequence) AS ?seq_length)
+    """)
+    if min_length is not None and max_length is not None:
+        if max_length <= min_length:
+            msg = f"Maximum sequence length ({max_length}) must be greater than minimum sequence length ({min_length})"
+            raise ValueError(msg)
+        return dedent(f"""\
+            {header}
+            FILTER (?seq_length >= {min_length} && ?seq_length <= {max_length})
+        """)
+    if min_length is not None:
+        return dedent(f"""\
+            {header}
+            FILTER (?seq_length >= {min_length})
+        """)
+    if max_length is not None:
+        return dedent(f"""\
+            {header}
+            FILTER (?seq_length <= {max_length})
+        """)
+    return ""
+
+
 def _build_sparql_query_pdb(uniprot_accs: Iterable[str], limit=10_000) -> str:
     # For http://purl.uniprot.org/uniprot/O00268 + http://rdf.wwpdb.org/pdb/1H3O
     # the chainSequenceMapping are
@@ -248,7 +379,7 @@ def _build_sparql_query_pdb(uniprot_accs: Iterable[str], limit=10_000) -> str:
     # http://purl.uniprot.org/isoforms/O00255-2#PDB_3U84_tt2tt459
     # To get the the chain belonging to the uniprot/pdb pair we need to
     # do some string filtering.
-    # Also there can be multiple cnhins for the same uniprot/pdb pair, so we need to
+    # Also there can be multiple chains for the same uniprot/pdb pair, so we need to
     # do a group by and concat
 
     select_clause = dedent("""\
@@ -274,7 +405,12 @@ def _build_sparql_query_pdb(uniprot_accs: Iterable[str], limit=10_000) -> str:
     )
 
 
-def _build_sparql_query_af(uniprot_accs: Iterable[str], limit=10_000) -> str:
+def _build_sparql_query_af(
+    uniprot_accs: Iterable[str],
+    min_sequence_length: int | None = None,
+    max_sequence_length: int | None = None,
+    limit=10_000,
+) -> str:
     select_clause = "?protein ?af_db"
     where_clause = dedent("""
         # --- Protein Selection ---
@@ -284,6 +420,12 @@ 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> .
     """)
+    if min_sequence_length is not None or max_sequence_length is not None:
+        length_filter = _build_sparql_query_sequence_length_filter(
+            min_length=min_sequence_length,
+            max_length=max_sequence_length,
+        )
+        where_clause += "\n" + length_filter
     return _build_sparql_generic_by_uniprot_accessions_query(uniprot_accs, select_clause, dedent(where_clause), limit)
 
 
@@ -337,8 +479,8 @@ def _execute_sparql_search(
     return bindings
 
 
-def _flatten_results_pdb(rawresults: Iterable) -> dict[str, set[PdbResult]]:
-    pdb_entries: dict[str, set[PdbResult]] = {}
+def _flatten_results_pdb(rawresults: Iterable) -> PdbResults:
+    pdb_entries: PdbResults = {}
     for result in rawresults:
         protein = result["protein"]["value"].split("/")[-1]
         if "pdb_db" not in result:  # Should not happen with build_sparql_query_pdb
@@ -424,7 +566,7 @@ def search4uniprot(query: Query, limit: int = 10_000, timeout: int = 1_800) -> s
 
 def search4pdb(
     uniprot_accs: Collection[str], limit: int = 10_000, timeout: int = 1_800, batch_size: int = 10_000
-) -> dict[str, set[PdbResult]]:
+) -> PdbResults:
     """
     Search for PDB entries in UniProtKB accessions.
 
@@ -456,13 +598,20 @@ def search4pdb(
 
 
 def search4af(
-    uniprot_accs: Collection[str], limit: int = 10_000, timeout: int = 1_800, batch_size: int = 10_000
+    uniprot_accs: Collection[str],
+    min_sequence_length: int | None = None,
+    max_sequence_length: int | None = None,
+    limit: int = 10_000,
+    timeout: int = 1_800,
+    batch_size: int = 10_000,
 ) -> dict[str, set[str]]:
     """
     Search for AlphaFold entries in UniProtKB accessions.
 
     Args:
         uniprot_accs: UniProt accessions.
+        min_sequence_length: Minimum length of the canonical sequence.
+        max_sequence_length: Maximum length of the canonical sequence.
         limit: Maximum number of results to return.
         timeout: Timeout for the SPARQL query in seconds.
         batch_size: Size of batches to process the UniProt accessions.
@@ -474,7 +623,7 @@ def search4af(
     total = len(uniprot_accs)
     with tqdm(total=total, desc="Searching for AlphaFolds of uniprots", disable=total < batch_size, unit="acc") as pbar:
         for batch in batched(uniprot_accs, batch_size, strict=False):
-            sparql_query = _build_sparql_query_af(batch, limit)
+            sparql_query = _build_sparql_query_af(batch, min_sequence_length, max_sequence_length, limit)
             logger.info("Executing SPARQL query for AlphaFold: %s", sparql_query)
 
             raw_results = _execute_sparql_search(
@@ -639,12 +788,12 @@ def search4macromolecular_complexes(
 
 
 def search4interaction_partners(
-    uniprot_acc: str, excludes: set[str] | None = None, limit: int = 10_000, timeout: int = 1_800
+    uniprot_accession: 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.
+        uniprot_accession: 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.
@@ -655,14 +804,137 @@ def search4interaction_partners(
         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)
+    ucomplexes = search4macromolecular_complexes([uniprot_accession], 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 != uniprot_accession and member not in excludes:
                 if member not in hits:
                     hits[member] = set()
                 hits[member].add(ucomplex.complex_id)
     return hits
+
+
+@dataclass(frozen=True)
+class UniprotDetails:
+    """Details of an UniProt entry.
+
+    Parameters:
+        uniprot_accession: UniProt accession.
+        uniprot_id: UniProt ID (mnemonic).
+        sequence_length: Length of the canonical sequence.
+        reviewed: Whether the entry is reviewed (Swiss-Prot) or unreviewed (TrEMBL).
+        protein_name: Recommended protein name.
+        taxon_id: NCBI Taxonomy ID of the organism.
+        taxon_name: Scientific name of the organism.
+    """
+
+    uniprot_accession: str
+    uniprot_id: str
+    sequence_length: int
+    reviewed: bool
+    protein_name: str
+    taxon_id: int
+    taxon_name: str
+
+
+def map_uniprot_accessions2uniprot_details(
+    uniprot_accessions: Collection[str], timeout: int = 1_800, batch_size: int = 1000
+) -> Generator[UniprotDetails]:
+    """Map UniProt accessions to UniProt details by querying the UniProt SPARQL endpoint.
+
+    Example:
+
+    SPARQL query to get details for 7 UniProt entries, run on [https://sparql.uniprot.org/sparql](https://sparql.uniprot.org/sparql).
+
+    ```sparql
+    PREFIX skos: <http://www.w3.org/2004/02/skos/core#>
+    PREFIX up:   <http://purl.uniprot.org/core/>
+    PREFIX rdf:  <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
+
+    SELECT
+    (?ac AS ?uniprot_accession)
+    ?uniprot_id
+    (STRAFTER(STR(?organism), "taxonomy/") AS ?taxon_id)
+    ?taxon_name
+    ?reviewed
+    ?protein_name
+    (STRLEN(?sequence) AS ?seq_length)
+    WHERE {
+    # Input UniProt accessions
+    VALUES (?ac) { ("P05067") ("A6NGD5") ("O14627") ("P00697") ("P42284") ("A0A0B5AC95") ("A0A0S2Z4R0")}
+    BIND (IRI(CONCAT("http://purl.uniprot.org/uniprot/", ?ac)) AS ?protein)
+    ?protein a up:Protein .
+    ?protein up:mnemonic ?uniprot_id .
+    ?protein up:organism ?organism .
+    ?organism up:scientificName ?taxon_name .
+    ?protein up:reviewed ?reviewed .
+    ?protein up:recommendedName/up:fullName ?protein_name .
+    ?protein up:sequence ?isoform .
+    ?isoform a up:Simple_Sequence .
+    ?isoform rdf:value ?sequence .
+    BIND (STRBEFORE(STRAFTER(STR(?isoform), "http://purl.uniprot.org/isoforms/"), "-") AS ?ac_of_isoform)
+    FILTER(?ac_of_isoform = ?ac)
+    }
+    ```
+
+    Args:
+        uniprot_accessions: Iterable of UniProt accessions.
+        timeout: Timeout for the SPARQL query in seconds.
+        batch_size: Size of batches to process the UniProt accessions.
+
+    Yields:
+        UniprotDetails objects in random order.
+    """
+    select_clause = dedent("""\
+        (?ac AS ?uniprot_accession)
+        ?uniprot_id
+        (STRAFTER(STR(?organism), "taxonomy/") AS ?taxon_id)
+        ?taxon_name
+        ?reviewed
+        ?protein_name
+        (STRLEN(?sequence) AS ?seq_length)
+    """)
+    where_clause = dedent("""
+        ?protein a up:Protein .
+        ?protein up:mnemonic ?uniprot_id .
+        ?protein up:organism ?organism .
+        ?organism up:scientificName ?taxon_name .
+        ?protein up:reviewed ?reviewed .
+        ?protein up:recommendedName/up:fullName ?protein_name .
+        ?protein up:sequence ?isoform .
+        ?isoform a up:Simple_Sequence .
+        ?isoform rdf:value ?sequence .
+        BIND (STRBEFORE(STRAFTER(STR(?isoform), "http://purl.uniprot.org/isoforms/"), "-") AS ?ac_of_isoform)
+        FILTER(?ac_of_isoform = ?ac)
+    """)
+    total = len(uniprot_accessions)
+    with tqdm(
+        total=total,
+        desc="Retrieving UniProt details",
+        disable=total < batch_size,
+        unit="acc",
+    ) as pbar:
+        for batch in batched(uniprot_accessions, batch_size, strict=False):
+            sparql_query = _build_sparql_generic_by_uniprot_accessions_query(
+                batch, select_clause, where_clause, limit=batch_size
+            )
+            logger.info("Executing SPARQL query for UniProt details: %s", sparql_query)
+            raw_results = _execute_sparql_search(
+                sparql_query=sparql_query,
+                timeout=timeout,
+            )
+            for raw_result in raw_results:
+                result = UniprotDetails(
+                    uniprot_accession=raw_result["uniprot_accession"]["value"],
+                    uniprot_id=raw_result["uniprot_id"]["value"],
+                    sequence_length=int(raw_result["seq_length"]["value"]),
+                    reviewed=raw_result["reviewed"]["value"] == "true",
+                    protein_name=raw_result["protein_name"]["value"],
+                    taxon_id=int(raw_result["taxon_id"]["value"]),
+                    taxon_name=raw_result["taxon_name"]["value"],
+                )
+                yield result
+            pbar.update(len(batch))

protein_quest/utils.py

@@ -265,6 +265,7 @@ async def retrieve_files(
     desc: str = "Downloading files",
     cacher: Cacher | None = None,
     chunk_size: int = 524288,  # 512 KiB
+    gzip_files: bool = False,
 ) -> list[Path]:
     """Retrieve files from a list of URLs and save them to a directory.
 
@@ -277,6 +278,7 @@ async def retrieve_files(
         desc: Description for the progress bar.
         cacher: An optional cacher to use for caching files.
         chunk_size: The size of each chunk to read from the response.
+        gzip_files: Whether to gzip the downloaded files.
 
     Returns:
         A list of paths to the downloaded files.
@@ -292,6 +294,7 @@ async def retrieve_files(
                 semaphore=semaphore,
                 cacher=cacher,
                 chunk_size=chunk_size,
+                gzip_files=gzip_files,
             )
             for url, filename in urls
         ]
@@ -299,6 +302,10 @@ async def retrieve_files(
         return files
 
 
+class InvalidContentEncodingError(aiohttp.ClientResponseError):
+    """Content encoding is invalid."""
+
+
 async def _retrieve_file(
     session: RetryClient,
     url: URL | str,
@@ -306,6 +313,7 @@ async def _retrieve_file(
     semaphore: asyncio.Semaphore,
     cacher: Cacher | None = None,
     chunk_size: int = 524288,  # 512 KiB
+    gzip_files: bool = False,
 ) -> Path:
     """Retrieve a single file from a URL and save it to a specified path.
 
@@ -316,6 +324,7 @@ async def _retrieve_file(
         semaphore: A semaphore to limit the number of concurrent downloads.
         cacher: An optional cacher to use for caching files.
         chunk_size: The size of each chunk to read from the response.
+        gzip_files: Whether to gzip the downloaded file.
 
     Returns:
         The path to the saved file.
@@ -330,12 +339,27 @@ async def _retrieve_file(
         logger.debug(f"File {save_path} was copied from cache {cached_file}. Skipping download from {url}.")
         return save_path
 
+    # Alphafold server and many other web servers can return gzipped responses,
+    # when we want to save as *.gz, we use raw stream
+    # otherwise aiohttp will decompress it automatically for us.
+    auto_decompress = not gzip_files
+    headers = {"Accept-Encoding": "gzip"}
     async with (
         semaphore,
-        session.get(url) as resp,
+        session.get(url, headers=headers, auto_decompress=auto_decompress) as resp,
     ):
         resp.raise_for_status()
-        await cacher.write_iter(save_path, resp.content.iter_chunked(chunk_size))
+        if gzip_files and resp.headers.get("Content-Encoding") != "gzip":
+            msg = f"Server did not send gzip encoded content for {url}, can not save as gzipped file."
+            raise InvalidContentEncodingError(
+                request_info=resp.request_info,
+                history=resp.history,
+                status=415,
+                message=msg,
+                headers=resp.headers,
+            )
+        iterator = resp.content.iter_chunked(chunk_size)
+        await cacher.write_iter(save_path, iterator)
     return save_path
 
 

{protein_quest-0.5.1.dist-info → protein_quest-0.7.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: protein_quest
-Version: 0.5.1
+Version: 0.7.0
 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
@@ -11,12 +11,12 @@ Requires-Python: >=3.13
 Requires-Dist: aiofiles>=24.1.0
 Requires-Dist: aiohttp-retry>=2.9.1
 Requires-Dist: aiohttp[speedups]>=3.11.18
-Requires-Dist: aiopath>=0.7.7
 Requires-Dist: attrs>=25.3.0
 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
@@ -26,7 +26,7 @@ Requires-Dist: tqdm>=4.67.1
 Requires-Dist: yarl>=1.20.1
 Provides-Extra: mcp
 Requires-Dist: fastmcp>=2.11.3; extra == 'mcp'
-Requires-Dist: pydantic>=2.11.7; extra == 'mcp'
+Requires-Dist: pydantic>=2.12.0; extra == 'mcp'
 Description-Content-Type: text/markdown
 
 # protein-quest
@@ -61,6 +61,7 @@ graph TB;
     searchuniprot --> |uniprot_accessions|searchpdbe[/Search PDBe/]
     searchuniprot --> |uniprot_accessions|searchaf[/Search Alphafold/]
     searchuniprot -. uniprot_accessions .-> searchemdb[/Search EMDB/]
+    searchuniprot -. uniprot_accessions .-> searchuniprotdetails[/Search UniProt details/]
     searchintactionpartners[/Search interaction partners/] -.-x |uniprot_accessions|searchuniprot
     searchcomplexes[/Search complexes/]
     searchpdbe -->|pdb_ids|fetchpdbe[Retrieve PDBe]
@@ -71,6 +72,8 @@ 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])
+    ssfilter -. mmcif_files .-> convert2uniprot_accessions([Convert to UniProt accessions])
     classDef dashedBorder stroke-dasharray: 5 5;
     goterm:::dashedBorder
     taxonomy:::dashedBorder
@@ -78,6 +81,9 @@ graph TB;
     fetchemdb:::dashedBorder
     searchintactionpartners:::dashedBorder
     searchcomplexes:::dashedBorder
+    searchuniprotdetails:::dashedBorder
+    convert2cif:::dashedBorder
+    convert2uniprot_accessions:::dashedBorder
 ```
 
 (Dotted nodes and edges are side-quests.)
@@ -108,7 +114,7 @@ This behavior can be customized with the `--no-cache`, `--cache-dir`, and `--cop
 protein-quest search uniprot \
     --taxon-id 9606 \
     --reviewed \
-    --subcellular-location-uniprot nucleus \
+    --subcellular-location-uniprot "nucleus" \
     --subcellular-location-go GO:0005634 \
     --molecular-function-go GO:0003677 \
     --limit 100 \
@@ -191,7 +197,7 @@ protein-quest filter residue  \
 
 ### To filter on secondary structure
 
-To filter on structure being mostly alpha helices and have no beta sheets.
+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 \
@@ -242,6 +248,37 @@ 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
 ```
 
+### Search for UniProt details
+
+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
+```
+
+The `uniprot_details.csv` looks like:
+
+```csv
+uniprot_accession,uniprot_id,sequence_length,reviewed,protein_name,taxon_id,taxon_name
+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.
+
+```shell
+protein-quest convert structures --format cif --output-dir ./filtered-cif ./filtered-ss
+```
+
+### 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.
+
+```shell
+protein-quest convert uniprot ./filtered-ss uniprot_accs.filtered.txt
+```
+
 ##  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-0.7.0.dist-info/RECORD

@@ -0,0 +1,27 @@
+protein_quest/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+protein_quest/__version__.py,sha256=F9kNagC7uEvuPDju8Gzo4Jt81LSvbf0VyONV3GMXT2M,56
+protein_quest/cli.py,sha256=082CmSSmxVZoWbnX35AmhqedA4T1dD9v-eMe0vsIDp4,55572
+protein_quest/converter.py,sha256=Y-Oxf7lDNbEicL6GS-IpNWDwaAiHgIgs5bFAcEHCKdQ,1441
+protein_quest/emdb.py,sha256=641c6RwNYnu-0GBFyCFBiI58fNc0jMkd0ZZ9MW9-Jmc,1501
+protein_quest/filters.py,sha256=Xr-cJTtbNjHKuzmXLBf7yZfqKf_U3RTivcVbr620LVU,5225
+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=tZkSG1yx4ocN1rlKgVlU8nUbs6LKpyLrNqP3y6fbJm0,8564
+protein_quest/parallel.py,sha256=ZJrLO1t2HXs4EeNctytvBTyROPBq-4-gLf35PiolHf0,3468
+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/taxonomy.py,sha256=4mKv8zll4mX02Ow8CTvyqMJE2KJZvcq3QlTjjjLOJJk,5072
+protein_quest/uniprot.py,sha256=mODAcneCnDvinvJ3jffyR11klsgq5b96T_4aVWd-Luw,35158
+protein_quest/utils.py,sha256=6OF8X4ia_z1HOYiXy6e-zEWlp_bF1DoZCVrCSg1qivY,19076
+protein_quest/alphafold/__init__.py,sha256=Ktasi5BRp71wO7-PpOGDpIRRtBEefs8knIdlKQeLQpk,51
+protein_quest/alphafold/confidence.py,sha256=mVAYTIzdbR8xBjRiUzA0at8wJq9vpfEQWPz5cJefLKs,6766
+protein_quest/alphafold/entry_summary.py,sha256=Qhnw75RXFaoOU332g7axg_jYbbdZbUpsGPUOwPNDSeU,2114
+protein_quest/alphafold/fetch.py,sha256=l8pcXeuDfoXYiwpW5N_uB_9oZpomBgUeF9kROLrM11M,14038
+protein_quest/pdbe/__init__.py,sha256=eNNHtN60NAGea7gvRkIzkoTXsYPK99s-ldIcKWYO6So,61
+protein_quest/pdbe/fetch.py,sha256=e8CHWDX2QzWnVLmYXCfNrscw1UcN1lI9Uz6Z5HmEOEQ,2510
+protein_quest-0.7.0.dist-info/METADATA,sha256=JvsZl9XGN57iJn5oSBRIVNIqL6aYEHXQlGpE87nsSvQ,10722
+protein_quest-0.7.0.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+protein_quest-0.7.0.dist-info/entry_points.txt,sha256=f1RtOxv9TFBO3w01EMEuFXBTMsqKsQcKlkxmj9zE-0g,57
+protein_quest-0.7.0.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+protein_quest-0.7.0.dist-info/RECORD,,