protein-quest 0.6.0__py3-none-any.whl → 0.8.0__py3-none-any.whl

{protein_quest-0.6.0.dist-info → protein_quest-0.8.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: protein_quest
-Version: 0.6.0
+Version: 0.8.0
 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
@@ -11,7 +11,6 @@ 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
@@ -22,12 +21,13 @@ 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: shtab>=1.7.2
 Requires-Dist: sparqlwrapper>=2.0.0
 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
@@ -62,6 +62,7 @@ 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]
@@ -73,6 +74,7 @@ graph TB;
     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
@@ -80,7 +82,9 @@ graph TB;
     fetchemdb:::dashedBorder
     searchintactionpartners:::dashedBorder
     searchcomplexes:::dashedBorder
+    searchuniprotdetails:::dashedBorder
     convert2cif:::dashedBorder
+    convert2uniprot_accessions:::dashedBorder
 ```
 
 (Dotted nodes and edges are side-quests.)
@@ -111,7 +115,7 @@ 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 \
@@ -151,7 +155,7 @@ protein-quest retrieve pdbe pdbe.csv downloads-pdbe/
 protein-quest retrieve alphafold alphafold.csv downloads-af/
 ```
 
-For each entry downloads the summary.json and cif file.
+For each entry downloads the cif file.
 
 ### To retrieve EMDB volume files
 
@@ -194,7 +198,7 @@ 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 \
@@ -245,12 +249,35 @@ 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 --output-dir ./filtered-cif ./filtered-ss
+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
@@ -273,6 +300,26 @@ protein-quest mcp
 
 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://shtab.readthedocs.io/).
+
+Initialize for bash shell with:
+
+```shell
+mkdir -p ~/.local/share/bash-completion/completions
+protein-quest --print-completion bash > ~/.local/share/bash-completion/completions/protein-quest
+```
+
+Initialize for zsh shell with:
+
+```shell
+mkdir -p ~/.local/share/zsh/site-functions
+protein-quest --print-completion zsh > ~/.local/share/zsh/site-functions/_protein-quest
+fpath=("$HOME/.local/share/zsh/site-functions" $fpath)
+autoload -Uz compinit && compinit
+```
+
 ## Contributing
 
 For development information and contribution guidelines, please see [CONTRIBUTING.md](CONTRIBUTING.md).

{protein_quest-0.6.0.dist-info → protein_quest-0.8.0.dist-info}/RECORD

@@ -1,27 +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/__version__.py,sha256=z22DsH46rJUgc917FJyc2z9XDmdScvBS92-z4i4GZ98,56
+protein_quest/cli.py,sha256=bE0Xq93LjdMnDoHeRIDUXUU79LyWICnhX8B3m2Lk8ZE,57264
 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/mcp_server.py,sha256=oHbNjN-Lctc2mY-sjEuo82yRsp1bBsHo2Ag5MwsWx8k,8547
 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/structure.py,sha256=QozElPz0kbPB_HW-J1WxArTT5e-1vRyBJoBSfHnwoRM,8117
 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/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=mVAYTIzdbR8xBjRiUzA0at8wJq9vpfEQWPz5cJefLKs,6766
-protein_quest/alphafold/entry_summary.py,sha256=GtE3rT7wH3vIOOeiXY2s80Fo6EzdoqlcvakW8K591Yk,1257
-protein_quest/alphafold/fetch.py,sha256=n5SlqbQfU1PE4X8saV4O1nCrKRn3Q2UcMlrNw5-163w,12801
+protein_quest/alphafold/entry_summary.py,sha256=Qhnw75RXFaoOU332g7axg_jYbbdZbUpsGPUOwPNDSeU,2114
+protein_quest/alphafold/fetch.py,sha256=eKCQHkAMko-d36VvRHLCllLxuAXBdbBUhUONOSCPsds,21970
 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-0.8.0.dist-info/METADATA,sha256=jotRxaLadElgixAW72Axk8qL8wAvzl-cq26mYJBy9zc,11335
+protein_quest-0.8.0.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+protein_quest-0.8.0.dist-info/entry_points.txt,sha256=f1RtOxv9TFBO3w01EMEuFXBTMsqKsQcKlkxmj9zE-0g,57
+protein_quest-0.8.0.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+protein_quest-0.8.0.dist-info/RECORD,,