Merge branch 'main' into update-wagstails

.github/ISSUE_TEMPLATE/bug-report.yaml

@@ -34,6 +34,14 @@ body:
         Include full errors, stack traces, and/or relevant logs.
     validations:
       required: true
+  - type: textarea
+    attributes:
+      label: Acceptance Criteria
+      description: |
+        Provide the criteria that must be met in order for this issue to be considered fixed.
+        Be specific, and consider potential edge cases.
+    validations:
+      required: true
   - type: textarea
     attributes:
       label: Possible reason(s)

.github/ISSUE_TEMPLATE/feature-request.yaml

@@ -15,6 +15,14 @@ body:
         Why do you need this feature? For example: "I'm always frustrated when..."
     validations:
       required: true
+  - type: textarea
+    attributes:
+      label: Acceptance Criteria
+      description: |
+        Provide the criteria that must be met in order for this issue to be considered fixed.
+        Be specific, and consider potential edge cases.
+    validations:
+      required: true
   - type: textarea
     attributes:
       label: Proposed solution

.github/workflows/checks.yaml

@@ -14,7 +14,7 @@ jobs:
       THERAPY_TEST: true
     strategy:
       matrix:
-        python-version: ["3.10", "3.11", "3.12"]
+        python-version: ["3.11", "3.12", "3.13"]
     steps:
       - uses: actions/checkout@v4
 
@@ -55,3 +55,23 @@ jobs:
 
       - name: Check style
         run: python3 -m ruff check . && ruff format --check .
+
+  precommit_hooks:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        hook:
+        - "end-of-file-fixer"
+        - "trailing-whitespace"
+        - "mixed-line-ending"
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Python 3.12
+        uses: actions/setup-python@v5
+        with:
+          python-version: 3.12
+
+      - uses: pre-commit/[email protected]
+        with:
+          extra_args: ${{ matrix.hook }} --all-files

.gitignore

@@ -76,6 +76,7 @@ instance/
 
 # Sphinx documentation
 docs/_build/
+docs/build/
 
 # PyBuilder
 .pybuilder/
@@ -91,7 +92,7 @@ ipython_config.py
 # pyenv
 #   For a library or package, you might want to ignore these files since the code is
 #   intended to run in multiple environments; otherwise, check them in:
-# .python-version
+.python-version
 
 # pipenv
 #   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.

.pre-commit-config.yaml

@@ -9,6 +9,8 @@ repos:
       - id: check-merge-conflict
       - id: detect-aws-credentials
         args: [ --allow-missing-credentials ]
+      - id: mixed-line-ending
+        args: [ --fix=lf ]
   - repo: https://github.com/astral-sh/ruff-pre-commit
     rev: v0.5.0  # ruff version
     hooks:

analysis/approval_status/approval_status_notes.md

@@ -61,4 +61,3 @@ def ApprovalStatus(Enum):
     FDA_PRESCRIPTION = "fda_prescription"
     FDA_DISCONTINUED = "fda_discontinued"
     FDA_TENTATIVE = "fda_tentative"
-

pyproject.toml

@@ -16,11 +16,11 @@ classifiers = [
     "Topic :: Scientific/Engineering :: Bio-Informatics",
     "License :: OSI Approved :: MIT License",
     "Programming Language :: Python :: 3",
-    "Programming Language :: Python :: 3.10",
     "Programming Language :: Python :: 3.11",
     "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
 ]
-requires-python = ">=3.10"
+requires-python = ">=3.11"
 description = "VICC normalization routines for therapeutics"
 license = {file = "LICENSE"}
 dependencies = [
@@ -41,9 +41,10 @@ etl = [
     "wikibaseintegrator>=0.12.0",
     "wags-tails~=0.2.0",
     "tqdm",
-    "rich"
+    "rich",
+    "pyyaml"
 ]
-test = ["pytest", "pytest-cov", "pytest-mock"]
+test = ["pytest", "pytest-cov", "pytest-mock", "isodate"]
 dev = ["pre-commit>=3.7.1", "ruff==0.5.0", "lxml", "xmlformatter", "types-pyyaml"]
 
 [project.urls]
@@ -163,16 +164,32 @@ ignore = [
 # ANN001 - missing-type-function-argument
 # ANN2 - missing-return-type
 # ANN102 - missing-type-cls
+# D100 - undocumented-public-module
+# D102 - undocumented-public-class
 # S101 - assert
 # B011 - assert-false
 # N805 - invalid-first-argument-name-for-method
 # RUF001 - ambiguous-unicode-character-string
 # INP001 - implicit-namespace-package
 # SLF001 - private-member-access
 # PERF401 - manual-list-comprehension
-"tests/*" = ["ANN001", "ANN2", "ANN102", "S101", "B011", "INP001", "SLF001", "PERF401"]
+"tests/*" = [
+    "ANN001",
+    "ANN2",
+    "ANN102",
+    "D100",
+    "D102",
+    "S101",
+    "B011",
+    "INP001",
+    "SLF001",
+    "PERF401"
+]
 "tests/unit/test_emit_warnings.py" = ["RUF001"]
 "src/therapy/schemas.py" = ["ANN001", "ANN201", "N805"]
 
+[tool.ruff.lint.flake8-annotations]
+mypy-init-return = true
+
 [tool.ruff.format]
 docstring-code-format = true

src/therapy/database/dynamodb.py

@@ -608,7 +608,7 @@ def delete_source(self, src_name: SourceName) -> None:
                                 "concept_id": record["concept_id"],
                             }
                         )
-                    except ClientError as e:  # noqa: PERF203
+                    except ClientError as e:
                         raise DatabaseWriteError(e) from e
 
     def complete_write_transaction(self) -> None:

src/therapy/etl/guidetopharmacology.py

@@ -74,6 +74,7 @@ def _transform_ligands(self, data: dict) -> None:
                 "PubChem CID",
                 "UniProt ID",
                 "Ensembl ID",
+                "ChEMBL ID",
                 "Ligand Subunit IDs",
                 "Ligand Subunit Name",
                 "Ligand Subunit UniProt IDs",
@@ -114,14 +115,14 @@ def _transform_ligands(self, data: dict) -> None:
                     )
                 if row[10]:
                     associated_with.append(f"{NamespacePrefix.UNIPROT.value}:{row[10]}")
-                if row[16]:
-                    aliases.append(self._process_name(row[16]))  # IUPAC
                 if row[17]:
-                    # International Non-proprietary Name assigned by the WHO
-                    aliases.append(self._process_name(row[17]))
+                    aliases.append(self._process_name(row[17]))  # IUPAC
                 if row[18]:
+                    # International Non-proprietary Name assigned by the WHO
+                    aliases.append(self._process_name(row[18]))
+                if row[19]:
                     # synonyms
-                    synonyms = row[18].split("|")
+                    synonyms = row[19].split("|")
                     for s in synonyms:
                         if "&" in s and ";" in s:
                             name_code = s[s.index("&") : s.index(";") + 1]
@@ -130,9 +131,9 @@ def _transform_ligands(self, data: dict) -> None:
                                 s = s.replace(name_code, "")
                             s = html.unescape(s)
                         aliases.append(self._process_name(s))
-                if row[20]:
+                if row[21]:
                     associated_with.append(
-                        f"{NamespacePrefix.INCHIKEY.value}:{row[20]}"
+                        f"{NamespacePrefix.INCHIKEY.value}:{row[21]}"
                     )
 
                 if associated_with:

src/therapy/etl/wikidata.py

@@ -120,9 +120,7 @@ def _get_latest_version() -> str:
 
         :return: formatted string for the current date
         """
-        return datetime.datetime.now(tz=datetime.timezone.utc).strftime(
-            DATE_VERSION_PATTERN
-        )
+        return datetime.datetime.now(tz=datetime.UTC).strftime(DATE_VERSION_PATTERN)
 
     def _get_data_handler(self, data_path: Path | None = None) -> DataSource:
         """Construct data handler instance for source. Overwrites base class method

src/therapy/query.py

@@ -144,7 +144,7 @@ def _fetch_records(
                     raise KeyError(msg)
                 (response, src) = self._add_record(response, match, match_type)
                 matched_sources.add(src)
-            except ClientError as e:  # noqa: PERF203
+            except ClientError as e:
                 logger.error(e.response["Error"]["Message"])
 
         return response, matched_sources
@@ -339,7 +339,7 @@ def search(
         response = self._get_search_response(query_str, query_sources, infer)
 
         response["service_meta_"] = ServiceMeta(
-            response_datetime=datetime.datetime.now(tz=datetime.timezone.utc),
+            response_datetime=datetime.datetime.now(tz=datetime.UTC),
         ).model_dump()
         return SearchService(**response)
 
@@ -358,7 +358,7 @@ def _add_merged_meta(self, response: NormalizationService) -> NormalizationServi
         for src in sources:
             try:
                 src_name = SourceName(PREFIX_LOOKUP[src])
-            except KeyError:  # noqa: PERF203
+            except KeyError:
                 # not an imported source
                 continue
             else:
@@ -522,7 +522,7 @@ def _prepare_normalized_response(self, query: str) -> dict[str, Any]:
             "match_type": MatchType.NO_MATCH,
             "warnings": self._emit_char_warnings(query),
             "service_meta_": ServiceMeta(
-                response_datetime=datetime.datetime.now(tz=datetime.timezone.utc)
+                response_datetime=datetime.datetime.now(tz=datetime.UTC)
             ),
         }
 

tests/data/drugbank/drugbank_5.1.10.csv

@@ -1,8 +1,8 @@
-DrugBank ID,Accession Numbers,Common name,CAS,UNII,Synonyms,Standard InChI Key
-DB00515,APRD00359,Cisplatin,15663-27-1,Q20Q21Q62J,CDDP | Cis-DDP | cis-diamminedichloroplatinum(II) | Cisplatin | cisplatino,LXZZYRPGZAFOLE-UHFFFAOYSA-L
-DB00522,APRD00818,Bentiromide,37106-97-1,239IF5W61J,Bentiromide | Bentiromido | Bentiromidum | BTPABA | PFT,SPPTWHFVYKCNNK-FQEVSTJZSA-N
-DB01143,APRD00021,Amifostine,20537-88-6,ILA426L95O,Amifostina | Amifostine | Amifostine anhydrous | Amifostinum | Aminopropylaminoethyl thiophosphate | Ethiofos,JKOQGQFVAUAYPM-UHFFFAOYSA-N
-DB01174,APRD00184,Phenobarbital,50-06-6,YQE403BP4D,"5-ethyl-5-phenyl-2,4,6(1H,3H,5H)-pyrimidinetrione | 5-Ethyl-5-phenyl-pyrimidine-2,4,6-trione | 5-Ethyl-5-phenylbarbituric acid | 5-ethyl-5-phenylpyrimidine-2,4,6(1H,3H,5H)-trione | 5-Phenyl-5-ethylbarbituric acid | Fenobarbital | Phenobarbital | Phenobarbitol | Phenobarbitone | Phenobarbituric Acid | Phenyläthylbarbitursäure | Phenylethylbarbiturate | Phenylethylbarbituric Acid | Phenylethylbarbitursäure | Phenylethylmalonylurea",DDBREPKUVSBGFI-UHFFFAOYSA-N
-DB06145,,Spiramycin,24916-50-5,033ECH6IFG,Demycarosylturimycin H | Foromacidin A | Foromacidine A | Spiramycin 1 | Spiramycin A | Spiramycin I,ACTOXUHEUCPTEW-CEUOBAOPSA-N
-DB12117,,Mitometh,107465-03-2,H8MTN7XVC2,DDP,MOTIYCLHZZLHHQ-UHFFFAOYSA-N
-DB14257,,Aloe ferox leaf,,0D145J8EME,Aloe (Aloe Ferox) | Aloe Candelabrum Leaf | Aloe Capensis | Aloe Ferox Dry Leaf Juice | Aloe Ferox Juice | Aloe Ferox Leaf Extract | Aloe Ferox Leaf Exudate | Aloe Ferox Leaf Gel | Aloe Ferox Leaf Juice | Aloe Ferox Leaf Juice Extract | Aloe Ferox Leaf Juice Powder | Aloe Ferox Leaf Powder | Aloe Ferox Leaf Preparation | Aloe Folii Extractus (Aloe Ferox) | Aloe Folium (Aloe Ferox) | Aloe Galpinii Leaf | Aloe Herba (Aloe Ferox) | Aloe Horrida Leaf | Aloe Muricata Leaf | Aloe Pallancae Leaf | Aloe Pseudoferox Leaf | Aloe Subferox Leaf | Aloe Supralaevis Leaf | Aloes (Aloe Ferox) | Busipho Ferox Leaf | Cape Aloe Leaf | Cape Aloes | Lu Hui (Aloe Ferox) | Luhui (Aloe Ferox) | New Aloe | Pachidendron Ferox Leaf | Pachidendron Pseudoferox Leaf | Pachidendron Supralaeve Leaf,
+DrugBank ID,Accession Numbers,Common name,CAS,UNII,Synonyms,Standard InChI Key
+DB00515,APRD00359,Cisplatin,15663-27-1,Q20Q21Q62J,CDDP | Cis-DDP | cis-diamminedichloroplatinum(II) | Cisplatin | cisplatino,LXZZYRPGZAFOLE-UHFFFAOYSA-L
+DB00522,APRD00818,Bentiromide,37106-97-1,239IF5W61J,Bentiromide | Bentiromido | Bentiromidum | BTPABA | PFT,SPPTWHFVYKCNNK-FQEVSTJZSA-N
+DB01143,APRD00021,Amifostine,20537-88-6,ILA426L95O,Amifostina | Amifostine | Amifostine anhydrous | Amifostinum | Aminopropylaminoethyl thiophosphate | Ethiofos,JKOQGQFVAUAYPM-UHFFFAOYSA-N
+DB01174,APRD00184,Phenobarbital,50-06-6,YQE403BP4D,"5-ethyl-5-phenyl-2,4,6(1H,3H,5H)-pyrimidinetrione | 5-Ethyl-5-phenyl-pyrimidine-2,4,6-trione | 5-Ethyl-5-phenylbarbituric acid | 5-ethyl-5-phenylpyrimidine-2,4,6(1H,3H,5H)-trione | 5-Phenyl-5-ethylbarbituric acid | Fenobarbital | Phenobarbital | Phenobarbitol | Phenobarbitone | Phenobarbituric Acid | Phenyläthylbarbitursäure | Phenylethylbarbiturate | Phenylethylbarbituric Acid | Phenylethylbarbitursäure | Phenylethylmalonylurea",DDBREPKUVSBGFI-UHFFFAOYSA-N
+DB06145,,Spiramycin,24916-50-5,033ECH6IFG,Demycarosylturimycin H | Foromacidin A | Foromacidine A | Spiramycin 1 | Spiramycin A | Spiramycin I,ACTOXUHEUCPTEW-CEUOBAOPSA-N
+DB12117,,Mitometh,107465-03-2,H8MTN7XVC2,DDP,MOTIYCLHZZLHHQ-UHFFFAOYSA-N
+DB14257,,Aloe ferox leaf,,0D145J8EME,Aloe (Aloe Ferox) | Aloe Candelabrum Leaf | Aloe Capensis | Aloe Ferox Dry Leaf Juice | Aloe Ferox Juice | Aloe Ferox Leaf Extract | Aloe Ferox Leaf Exudate | Aloe Ferox Leaf Gel | Aloe Ferox Leaf Juice | Aloe Ferox Leaf Juice Extract | Aloe Ferox Leaf Juice Powder | Aloe Ferox Leaf Powder | Aloe Ferox Leaf Preparation | Aloe Folii Extractus (Aloe Ferox) | Aloe Folium (Aloe Ferox) | Aloe Galpinii Leaf | Aloe Herba (Aloe Ferox) | Aloe Horrida Leaf | Aloe Muricata Leaf | Aloe Pallancae Leaf | Aloe Pseudoferox Leaf | Aloe Subferox Leaf | Aloe Supralaevis Leaf | Aloes (Aloe Ferox) | Busipho Ferox Leaf | Cape Aloe Leaf | Cape Aloes | Lu Hui (Aloe Ferox) | Luhui (Aloe Ferox) | New Aloe | Pachidendron Ferox Leaf | Pachidendron Pseudoferox Leaf | Pachidendron Supralaeve Leaf,

tests/data/guidetopharmacology/gtop_ligand_id_mapping_2023.2.tsv → tests/data/guidetopharmacology/gtop_ligand_id_mapping_2024.3.tsv

@@ -1,8 +1,8 @@
-"# GtoPdb Version: 2023.2 - published: 2023-08-07"
-"Ligand id"	"Name"	"Species"	"Type"	"PubChem SID"	"PubChem CID"	"ChEMBl ID"	"Chebi ID"	"UniProt id"	"Ensembl ID"	"IUPAC name"	"INN"	"CAS"	"DrugBank ID"	"Drug Central ID"
-"2169"	"arginine vasotocin"	""	"Peptide"	"135652004"	"68649"	""	""	""	""	"L-cysteinyl-L-tyrosyl-(3S)-DL-isoleucyl-L-glutaminyl-L-asparagyl-L-cysteinyl-DL-prolyl-L-arginyl-glycinamide (1->6)-disulfide"	"argiprestocin"	"113-80-4"	""	""
-"240"	"cisapride"	""	"Synthetic organic"	"135650104"	"2769"	"CHEMBL1729"	"CHEBI:151790"	""	""	"4-amino-5-chloro-N-[1-[3-(4-fluorophenoxy)propyl]-3-methoxypiperidin-4-yl]-2-methoxybenzamide"	"cisapride"	"81098-60-4"	"DB00604"	"660"
-"5343"	"cisplatin"	""	"Inorganic"	"178102005"	"441203"	"CHEMBL11359"	"CHEBI:27899"	""	""	""	"cisplatin"	"15663-27-1"	"DB00515"	""
-"3303"	"L745870"	""	"Synthetic organic"	"178100340"	"5311200"	"CHEMBL267014"	""	""	""	"3-[[4-(4-chlorophenyl)piperazin-1-yl]methyl]-1H-pyrrolo[2,3-b]pyridine"	""	"158985-00-3"	""	""
-"2804"	"phenobarbital"	""	"Synthetic organic"	"135650817"	"4763"	"CHEMBL40"	"CHEBI:8069"	""	""	"5-ethyl-5-phenyl-1,3-diazinane-2,4,6-trione"	"phenobarbital"	"50-06-6"	"DB01174"	"2134"
-"5260"	"rolipram"	""	"Synthetic organic"	"178101944"	"5092"	"CHEMBL63"	"CHEBI:104872"	""	""	"4-[3-(cyclopentyloxy)-4-methoxyphenyl]pyrrolidin-2-one"	"rolipram"	"61413-54-5"	"DB04149|DB03606"	""
+"# GtoPdb Version: 2024.3 - published: 2024-10-03"
+"Ligand id"	"Name"	"Species"	"Type"	"PubChem SID"	"PubChem CID"	"ChEMBl ID"	"Chebi ID"	"UniProt id"	"Ensembl ID"	"IUPAC name"	"INN"	"CAS"	"DrugBank ID"	"Drug Central ID"
+"2169"	"arginine vasotocin"	""	"Peptide"	"135652004"	"68649"	""	""	""	""	"L-cysteinyl-L-tyrosyl-(3S)-DL-isoleucyl-L-glutaminyl-L-asparagyl-L-cysteinyl-DL-prolyl-L-arginyl-glycinamide (1->6)-disulfide"	"argiprestocin"	"113-80-4"	""	""
+"240"	"cisapride"	""	"Synthetic organic"	"135650104"	"2769"	"CHEMBL1729"	"CHEBI:151790"	""	""	"4-amino-5-chloro-N-[1-[3-(4-fluorophenoxy)propyl]-3-methoxypiperidin-4-yl]-2-methoxybenzamide"	"cisapride"	"81098-60-4"	"DB00604"	"660"
+"5343"	"cisplatin"	""	"Inorganic"	"178102005"	"441203"	"CHEMBL11359"	"CHEBI:27899"	""	""	""	"cisplatin"	"15663-27-1"	"DB00515"	""
+"3303"	"L745870"	""	"Synthetic organic"	"178100340"	"5311200"	"CHEMBL267014"	""	""	""	"3-[[4-(4-chlorophenyl)piperazin-1-yl]methyl]-1H-pyrrolo[2,3-b]pyridine"	""	"158985-00-3"	""	""
+"2804"	"phenobarbital"	""	"Synthetic organic"	"135650817"	"4763"	"CHEMBL40"	"CHEBI:8069"	""	""	"5-ethyl-5-phenyl-1,3-diazinane-2,4,6-trione"	"phenobarbital"	"50-06-6"	"DB01174"	"2134"
+"5260"	"rolipram"	""	"Synthetic organic"	"178101944"	"5092"	"CHEMBL63"	"CHEBI:104872"	""	""	"4-[3-(cyclopentyloxy)-4-methoxyphenyl]pyrrolidin-2-one"	"rolipram"	"61413-54-5"	"DB04149|DB03606"	""