Merge pull request #10 from haddocking/codecov

Codecov

Author: sverhoeven

.github/workflows/ci.yml

@@ -6,10 +6,16 @@ on:
     - main
   pull_request:
 
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
 jobs:
   test:
     name: test
     runs-on: ubuntu-latest
+    permissions:
+      id-token: write
     steps:
       - uses: actions/checkout@v4
       - name: Install uv
@@ -19,7 +25,26 @@ jobs:
       - name: Install pocl
         run: uv pip install pocl-binary-distribution==3.0
       - name: Run tests
-        run: uv run pytest
+        run: |
+          uv run pytest --cov --cov-branch --cov-report=xml --junitxml=junit.xml -o junit_family=legacy
+          echo $? > pytest-exitcode
+        continue-on-error: true
+      # Always upload coverage and test results, even if tests fail
+      - name: Upload coverage reports to Codecov
+        uses: codecov/codecov-action@v5
+        with:
+          use_oidc: true
+          files: coverage.xml
+      - uses: codecov/test-results-action@v1
+        with:
+          use_oidc: true
+          files: junit.xml
+      - name: Fail job if pytest failed
+        run: |
+          if [ -f pytest-exitcode ] && [ "$(cat pytest-exitcode)" -ne 0 ]; then
+            echo "Pytest failed, failing job."
+            exit 1
+          fi
   build:
     name: build
     runs-on: ubuntu-latest

.github/workflows/pages.yml

@@ -14,7 +14,7 @@ permissions:
 # Only have one deployment in progress at a time
 concurrency:
   group: "pages"
-  cancel-in-progress: false
+  cancel-in-progress: true
 
 jobs:
   build:

CONTRIBUTING.md

@@ -81,3 +81,12 @@ uv run mkdocs build
 # You can preview it with
 python3 -m http.server -d site
 ```
+
+## Contributing to tests
+
+The code coverage and tests results are stored at https://app.codecov.io/gh/haddocking/protein-quest/ .
+
+The search functions of the protein-quest package talk to web services on the Internet.
+To have fast tests we use [pytest-recording](https://github.com/kiwicom/pytest-recording) to record and replay HTTP interactions.
+See [pytest-recording documentation](https://github.com/kiwicom/pytest-recording) for more details on how to use it.
+Like overwrite previous recordings in test/cassettes/**.yaml files with `--record-mode=rewrite`.

README.md

@@ -5,6 +5,7 @@
 [![Research Software Directory Badge](https://img.shields.io/badge/rsd-00a3e3.svg)](https://www.research-software.nl/software/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.15632658.svg)](https://doi.org/10.5281/zenodo.15632658)
+[![codecov](https://codecov.io/gh/haddocking/protein-quest/graph/badge.svg?token=V2MW3WMIR1)](https://codecov.io/gh/haddocking/protein-quest)
 
 Python package to search/retrieve/filter proteins and protein structures
 

pyproject.toml

@@ -45,6 +45,9 @@ mcp = [
 dev = [
     "pyrefly>=0.23.1",
     "pytest>=8.3.5",
+    "pytest-asyncio>=1.1.0",
+    "pytest-cov>=6.2.1",
+    "pytest-recording>=0.13.4",
     "types-aiofiles>=24.1.0.20250326",
     "types-tqdm>=4.67.0.20250513",
 ]

src/protein_quest/pdbe/io.py

@@ -49,6 +49,9 @@ def write_structure(structure: gemmi.Structure, path: Path):
         path: The file path to write the structure to.
             The format depends on the file extension.
             Supported extensions are .pdb, .pdb.gz, .cif, .cif.gz.
+
+    Raises:
+        ValueError: If the file extension is not supported.
     """
     if path.name.endswith(".pdb"):
         body: str = structure.make_pdb_string()
@@ -65,6 +68,9 @@ def write_structure(structure: gemmi.Structure, path: Path):
         cif_str = doc.as_string()
         with gzip.open(path, "wt") as f:
             f.write(cif_str)
+    else:
+        msg = f"Unsupported file extension in {path.name}. Supported extensions are .pdb, .pdb.gz, .cif, .cif.gz"
+        raise ValueError(msg)
 
 
 def _split_name_and_extension(name: str) -> tuple[str, str]:

tests/alphafold/test_confidence.py

@@ -0,0 +1,63 @@
+from pathlib import Path
+
+import gemmi
+import pytest
+
+from protein_quest.alphafold.confidence import (
+    ConfidenceFilterQuery,
+    ConfidenceFilterResult,
+    filter_files_on_confidence,
+    filter_out_low_confidence_residues,
+    find_high_confidence_residues,
+)
+from protein_quest.pdbe.io import nr_residues_in_chain
+
+
+@pytest.fixture
+def sample_pdb_file() -> Path:
+    return Path(__file__).parent / "AF-A1YPR0-F1-model_v4.pdb"
+
+
+@pytest.fixture
+def sample_pdb(sample_pdb_file: Path) -> gemmi.Structure:
+    return gemmi.read_structure(str(sample_pdb_file))
+
+
+def test_find_high_confidence_residues(sample_pdb: gemmi.Structure):
+    residues = list(find_high_confidence_residues(sample_pdb, 90))
+
+    assert len(residues) == 22
+
+
+def test_filter_out_low_confidence_residues(sample_pdb: gemmi.Structure):
+    # Make sure we start with >22 residues
+    assert len(sample_pdb[0][0]) == 619
+
+    residues = set(find_high_confidence_residues(sample_pdb, 90))
+    new_structure = filter_out_low_confidence_residues(sample_pdb, residues)
+
+    assert len(new_structure[0][0]) == 22
+
+
+def test_filter_files_on_confidence(sample_pdb_file: Path, tmp_path: Path):
+    input_files = [sample_pdb_file]
+    query = ConfidenceFilterQuery(
+        confidence=90,
+        max_threshold=40,
+        min_threshold=10,
+    )
+
+    results = list(filter_files_on_confidence(input_files, query, tmp_path))
+
+    expected = [
+        ConfidenceFilterResult(
+            input_file=sample_pdb_file.name,
+            count=22,
+            filtered_file=tmp_path / sample_pdb_file.name,
+        )
+    ]
+
+    assert results == expected
+    assert results[0].filtered_file is not None
+    assert results[0].filtered_file.exists()
+    assert nr_residues_in_chain(results[0].filtered_file) == 22

tests/alphafold/test_density.py

@@ -0,0 +1,39 @@
+interactions:
+- request:
+    body: null
+    headers: {}
+    method: GET
+    uri: https://www.ebi.ac.uk/QuickGO/services/ontology/go/search?query=GO:0043293&limit=100&page=1
+  response:
+    body:
+      string: '{"numberOfHits":4,"results":[{"id":"GO:0043293","isObsolete":false,"name":"apoptosome","definition":{"text":"A
+        multisubunit protein complex involved in the signaling phase of the apoptotic
+        process. In mammals it is typically composed of seven Apaf-1 subunits bound
+        to cytochrome c and caspase-9. A similar complex to promote apoptosis is formed
+        from homologous gene products in other eukaryotic organisms."},"aspect":"cellular_component"},{"id":"GO:0000811","isObsolete":false,"name":"GINS
+        complex","definition":{"text":"A heterotetrameric protein complex that associates
+        with replication origins, where it is required for the initiation of DNA replication,
+        and with replication forks."},"aspect":"cellular_component"},{"id":"GO:0070966","isObsolete":false,"name":"nuclear-transcribed
+        mRNA catabolic process, no-go decay","definition":{"text":"The chemical reactions
+        and pathways resulting in the breakdown of the transcript body of a nuclear-transcribed
+        mRNA with stalls in translation elongation."},"aspect":"biological_process"},{"id":"GO:0001591","isObsolete":false,"name":"dopamine
+        neurotransmitter receptor activity, coupled via Gi/Go","definition":{"text":"Combining
+        with the neurotransmitter dopamine and activating adenylate cyclase via coupling
+        to Gi/Go to initiate a change in cell activity."},"aspect":"molecular_function"}],"pageInfo":{"resultsPerPage":100,"current":1,"total":1}}'
+    headers:
+      Access-Control-Allow-Headers:
+      - Content-Type
+      Access-Control-Allow-Origin:
+      - '*'
+      Content-Type:
+      - application/json
+      Date:
+      - Mon, 18 Aug 2025 13:57:47 GMT
+      Strict-Transport-Security:
+      - max-age=0
+      Transfer-Encoding:
+      - chunked
+    status:
+      code: 200
+      message: ''
+version: 1

tests/cassettes/test_go/test_search_go_term.yaml

@@ -0,0 +1,66 @@
+interactions:
+- request:
+    body: null
+    headers:
+      Accept:
+      - application/sparql-results+json,application/json,text/javascript,application/javascript
+      Connection:
+      - close
+      Host:
+      - sparql.uniprot.org
+      User-Agent:
+      - sparqlwrapper 2.0.0 (rdflib.github.io/sparqlwrapper)
+    method: GET
+    uri: https://sparql.uniprot.org/sparql?query=%0A++++++++PREFIX+up%3A+%3Chttp%3A//purl.uniprot.org/core/%3E%0A++++++++PREFIX+taxon%3A+%3Chttp%3A//purl.uniprot.org/taxonomy/%3E%0A++++++++PREFIX+rdf%3A+%3Chttp%3A//www.w3.org/1999/02/22-rdf-syntax-ns%23%3E%0A++++++++PREFIX+rdfs%3A+%3Chttp%3A//www.w3.org/2000/01/rdf-schema%23%3E%0A++++++++PREFIX+skos%3A+%3Chttp%3A//www.w3.org/2004/02/skos/core%23%3E%0A++++++++PREFIX+GO%3A%3Chttp%3A//purl.obolibrary.org/obo/GO_%3E%0A%0A++++++++SELECT+%3Fprotein+%3Faf_db%0A++++++++WHERE+%7B%0A%0A++++++++%23+---+Protein+Selection+---%0A++++++++VALUES+%28%3Fac%29+%7B+%28%22P05067%22%29%7D%0A++++++++BIND+%28IRI%28CONCAT%28%22http%3A//purl.uniprot.org/uniprot/%22%2C%3Fac%29%29+AS+%3Fprotein%29%0A++++++++%3Fprotein+a+up%3AProtein+.%0A%0A%0A%23+---+Protein+Selection+---%0A%3Fprotein+a+up%3AProtein+.%0A%0A%23+---+AlphaFoldDB+Info+---%0A%3Fprotein+rdfs%3AseeAlso+%3Faf_db+.%0A%3Faf_db+up%3Adatabase+%3Chttp%3A//purl.uniprot.org/database/AlphaFoldDB%3E+.%0A%0A%0A++++++++%7D%0A%0A++++++++LIMIT+1%0A&format=json&output=json&results=json
+  response:
+    body:
+      string: "{\n  \"head\" : {\n    \"vars\" : [\n      \"protein\",\n      \"af_db\"\n
+        \   ]\n  },\n  \"results\" : {\n    \"bindings\" : [\n      {\n        \"protein\"
+        : {\n          \"type\" : \"uri\",\n          \"value\" : \"http://purl.uniprot.org/uniprot/P05067\"\n
+        \       },\n        \"af_db\" : {\n          \"type\" : \"uri\",\n          \"value\"
+        : \"http://purl.uniprot.org/alphafolddb/P05067\"\n        }\n      }\n    ]\n
+        \ }\n}"
+    headers:
+      Access-Control-Allow-Headers:
+      - origin, x-requested-with, content-type, X-Release, queryid
+      Access-Control-Allow-Origin:
+      - '*'
+      Access-Control-Expose-Headers:
+      - X-Total-Results, X-Release, queryid, content-type, user-agent, cache-control,
+        etag, range
+      Cache-Control:
+      - public
+      Connection:
+      - close
+      Content-Disposition:
+      - attachment; filename="sparql-A8EBFEAA11A5F303CCDAC4F54F9AE459.srj"
+      Content-Length:
+      - '375'
+      Content-Type:
+      - application/sparql-results+json
+      Date:
+      - Mon, 18 Aug 2025 13:40:18 GMT
+      ETag:
+      - W/"2025_03"
+      Expires:
+      - Tue, 19 Aug 2025 13:40:18 GMT
+      Server:
+      - Apache
+      Strict-Transport-Security:
+      - max-age=31536001; includeSubDomains
+      Vary:
+      - Negotiate,Accept,Accept-Encoding,Content-Type
+      X-Content-Type-Options:
+      - nosniff
+      X-Frame-Options:
+      - SAMEORIGIN
+      X-Powered-By:
+      - sib.swiss
+      X-Release:
+      - '2025_03'
+      queryid:
+      - '10827012252'
+    status:
+      code: 200
+      message: ''
+version: 1