protein-quest 0.5.0__py3-none-any.whl → 0.6.0__py3-none-any.whl

protein_quest/uniprot.py

@@ -525,7 +525,9 @@ def _build_complex_sparql_query(uniprot_accs: Iterable[str], limit: int) -> str:
     ?protein
     ?cp_db
     ?cp_comment
-    (GROUP_CONCAT(DISTINCT ?member; separator=",") AS ?complex_members)
+    (GROUP_CONCAT(
+        DISTINCT STRAFTER(STR(?member), "http://purl.uniprot.org/uniprot/"); separator=","
+    ) AS ?complex_members)
     (COUNT(DISTINCT ?member) AS ?member_count)
     WHERE {
     # Input UniProt accessions
@@ -550,7 +552,9 @@ def _build_complex_sparql_query(uniprot_accs: Iterable[str], limit: int) -> str:
     """
     select_clause = dedent("""\
         ?protein ?cp_db ?cp_comment
-        (GROUP_CONCAT(DISTINCT ?member; separator=",") AS ?complex_members)
+        (GROUP_CONCAT(
+            DISTINCT STRAFTER(STR(?member), "http://purl.uniprot.org/uniprot/"); separator=","
+        ) AS ?complex_members)
     """)
     where_clause = dedent("""
         # --- Complex Info ---
@@ -596,7 +600,7 @@ def _flatten_results_complex(raw_results) -> list[ComplexPortalEntry]:
         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(",")}
+        members = set(raw_result["complex_members"]["value"].split(","))
         results.append(
             ComplexPortalEntry(
                 query_protein=query_protein,

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-0.5.0.dist-info → protein_quest-0.6.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: protein_quest
-Version: 0.5.0
+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-0.6.0.dist-info/RECORD

@@ -0,0 +1,27 @@
+protein_quest/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+protein_quest/__version__.py,sha256=z_nR_Ti0YfIwFSKDD18DIrz_r3zxWQ8EGCNr2XUWkY0,56
+protein_quest/cli.py,sha256=pWwMIzWBrtqhZbvTIkvd1XhA5u9J-WAAg7A3hJZGtlk,46201
+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=rQv2srhF3_SYYK1TD3htIyxNiunU7a8FDC7CYT_oJFE,8269
+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=1FTKN0mYKTwZHlyIB4ORSAgSHFKK-UAK7T-qoFo1vyI,7162
+protein_quest/taxonomy.py,sha256=4mKv8zll4mX02Ow8CTvyqMJE2KJZvcq3QlTjjjLOJJk,5072
+protein_quest/uniprot.py,sha256=92G5YiJAJwUBKJQHPrM6DZlaLe-XG4qBg0zy0BDGFYY,24354
+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=GtE3rT7wH3vIOOeiXY2s80Fo6EzdoqlcvakW8K591Yk,1257
+protein_quest/alphafold/fetch.py,sha256=n5SlqbQfU1PE4X8saV4O1nCrKRn3Q2UcMlrNw5-163w,12801
+protein_quest/pdbe/__init__.py,sha256=eNNHtN60NAGea7gvRkIzkoTXsYPK99s-ldIcKWYO6So,61
+protein_quest/pdbe/fetch.py,sha256=e8CHWDX2QzWnVLmYXCfNrscw1UcN1lI9Uz6Z5HmEOEQ,2510
+protein_quest-0.6.0.dist-info/METADATA,sha256=8rX0ixi4Xl516LkxOlOKKRe364nKIjP7mKn67xuOcDA,9623
+protein_quest-0.6.0.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+protein_quest-0.6.0.dist-info/entry_points.txt,sha256=f1RtOxv9TFBO3w01EMEuFXBTMsqKsQcKlkxmj9zE-0g,57
+protein_quest-0.6.0.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+protein_quest-0.6.0.dist-info/RECORD,,

protein_quest-0.5.0.dist-info/RECORD

@@ -1,26 +0,0 @@
-protein_quest/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-protein_quest/__version__.py,sha256=AyGZhrskazcQPC8spzJ45d4XNxgla5DnO1bmKuzRj_Q,56
-protein_quest/cli.py,sha256=xiXt_2l3MxbTbmxm2sz0w8_OdJr8gz_B68GBVv5wHjE,44182
-protein_quest/converter.py,sha256=Y-Oxf7lDNbEicL6GS-IpNWDwaAiHgIgs5bFAcEHCKdQ,1441
-protein_quest/emdb.py,sha256=641c6RwNYnu-0GBFyCFBiI58fNc0jMkd0ZZ9MW9-Jmc,1501
-protein_quest/filters.py,sha256=-gasSXR4g5SzYSYbkfcDwR-tm2KCAhCMdpIVJrUPR1w,5224
-protein_quest/go.py,sha256=lZNEcw8nTc9wpV3cl4y2FG9Lsj8wsXQ6zemmAQs_DWE,5650
-protein_quest/mcp_server.py,sha256=PCXxcU3GElKg2sjMlxbsM63OiFxg9AtmfKwBJ1_0AQE,8130
-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=2lQ7jPHWtDySBTYnoL9VTKl5XUgQVYgp9Prb7qEnjtQ,17982
-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=wIsgPZmtnE5EoAL9G22Y6Ehx9d0md53Mw88-6LLGp0Q,12298
-protein_quest/pdbe/__init__.py,sha256=eNNHtN60NAGea7gvRkIzkoTXsYPK99s-ldIcKWYO6So,61
-protein_quest/pdbe/fetch.py,sha256=e8CHWDX2QzWnVLmYXCfNrscw1UcN1lI9Uz6Z5HmEOEQ,2510
-protein_quest/pdbe/io.py,sha256=iGLvmsD-eEYnrgZDYfkGWIDCzwDRRD5dwqB480talCs,10037
-protein_quest-0.5.0.dist-info/METADATA,sha256=atoElM2xwPd9ubxXSQsFQYz2hjALJi-AegCRkrynEYc,9236
-protein_quest-0.5.0.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-protein_quest-0.5.0.dist-info/entry_points.txt,sha256=f1RtOxv9TFBO3w01EMEuFXBTMsqKsQcKlkxmj9zE-0g,57
-protein_quest-0.5.0.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-protein_quest-0.5.0.dist-info/RECORD,,