build: require >=3.10 (#32)

pyproject.toml

@@ -23,7 +23,7 @@ classifiers = [
     "Intended Audience :: Science/Research",
     "Topic :: Scientific/Engineering :: Bio-Informatics",
 ]
-requires-python = ">=3.8"
+requires-python = ">=3.10"
 dependencies = [
     "requests",
     "biopython",

src/dcd_mapping/align.py

@@ -4,7 +4,6 @@
 import subprocess
 import tempfile
 from pathlib import Path
-from typing import List, Optional
 from urllib.parse import urlparse
 
 import requests
@@ -39,7 +38,7 @@ class AlignmentError(Exception):
     """Raise when errors encountered during alignment."""
 
 
-def _write_query_file(file: Path, lines: List[str]) -> None:
+def _write_query_file(file: Path, lines: list[str]) -> None:
     """Write lines to query file. This method is broken out to enable easy mocking while
     testing.
 
@@ -65,7 +64,7 @@ def _build_query_file(scoreset_metadata: ScoresetMetadata, query_file: Path) ->
 
 
 def get_ref_genome_file(
-    silent: bool = True, dcd_mapping_dir: Optional[Path] = None
+    silent: bool = True, dcd_mapping_dir: Path | None = None
 ) -> Path:
     """Acquire reference genome file in 2bit format from UCSC.
 
@@ -174,7 +173,7 @@ def _get_blat_output(metadata: ScoresetMetadata, silent: bool) -> QueryResult:
     return output
 
 
-def _get_best_hit(output: QueryResult, urn: str, chromosome: Optional[str]) -> Hit:
+def _get_best_hit(output: QueryResult, urn: str, chromosome: str | None) -> Hit:
     """Get best hit from BLAT output.
 
     First, try to return hit corresponding to expected chromosome taken from scoreset
@@ -223,7 +222,7 @@ def _get_best_hit(output: QueryResult, urn: str, chromosome: Optional[str]) -> H
     return best_score_hit
 
 
-def _get_best_hsp(hit: Hit, urn: str, gene_location: Optional[GeneLocation]) -> HSP:
+def _get_best_hsp(hit: Hit, urn: str, gene_location: GeneLocation | None) -> HSP:
     """Retrieve preferred HSP from BLAT Hit object.
 
     If gene location data is available, prefer the HSP with the least distance

src/dcd_mapping/annotate.py

@@ -2,7 +2,6 @@
 import json
 import logging
 from pathlib import Path
-from typing import Dict, List, Optional
 
 import hgvs.edit
 import hgvs.location
@@ -179,7 +178,7 @@ def get_vod_postmapped(allele: dict) -> dict:
     }
 
 
-def get_vod_haplotype(allele_list: List[dict]) -> dict:
+def get_vod_haplotype(allele_list: list[dict]) -> dict:
     """Define VOD model for haplotype
 
     :param allele_list: A list of VRS allele dictionaries
@@ -191,7 +190,7 @@ def get_vod_haplotype(allele_list: List[dict]) -> dict:
 def get_computed_reference_sequence(
     ss: str,
     layer: AnnotationLayer,
-    tx_output: Optional[TxSelectResult] = None,
+    tx_output: TxSelectResult | None = None,
 ) -> ComputedReferenceSequence:
     """Report the computed reference sequence for a score set
 
@@ -218,8 +217,8 @@ def get_computed_reference_sequence(
 
 def get_mapped_reference_sequence(
     layer: AnnotationLayer,
-    tx_output: Optional[TxSelectResult] = None,
-    align_result: Optional[AlignmentResult] = None,
+    tx_output: TxSelectResult | None = None,
+    align_result: AlignmentResult | None = None,
 ) -> MappedReferenceSequence:
     """Report the mapped reference sequence for a score set
 
@@ -248,7 +247,7 @@ def get_mapped_reference_sequence(
     )
 
 
-def _set_layer(ss: str, mappings: List[VrsObject1_x]) -> AnnotationLayer:
+def _set_layer(ss: str, mappings: list[VrsObject1_x]) -> AnnotationLayer:
     if ss.startswith("urn:mavedb:00000097"):
         return AnnotationLayer.PROTEIN
     for var in mappings:
@@ -257,7 +256,7 @@ def _set_layer(ss: str, mappings: List[VrsObject1_x]) -> AnnotationLayer:
     return AnnotationLayer.PROTEIN
 
 
-def _format_score_mapping(var: VrsObject1_x, layer: AnnotationLayer) -> Optional[Dict]:
+def _format_score_mapping(var: VrsObject1_x, layer: AnnotationLayer) -> dict | None:
     if var and var.layer == layer:
         if "members" in var.pre_mapped_variants:
             pre_mapped_members = []
@@ -283,10 +282,10 @@ def _format_score_mapping(var: VrsObject1_x, layer: AnnotationLayer) -> Optional
 
 def save_mapped_output_json(
     ss: str,
-    mappings: List[VrsObject1_x],
+    mappings: list[VrsObject1_x],
     align_result: AlignmentResult,
-    tx_output: Optional[TxSelectResult] = None,
-    output_path: Optional[Path] = None,
+    tx_output: TxSelectResult | None = None,
+    output_path: Path | None = None,
 ) -> None:
     """Save mapping output for a score set in a JSON file
 
@@ -316,15 +315,15 @@ def save_mapped_output_json(
         mapped_scores.append(formatted_score_mapping)
     mapped_ss_output["mapped_scores"] = mapped_scores
 
-    ss = ss.strip("urn:mavedb:")  # noqa: B005
+    ss = ss.removeprefix("urn:mavedb:")
     if not output_path:
         output_path = LOCAL_STORE_PATH / f"{ss}_mapping.json"
 
     with output_path.open("w") as file:
         json.dump(mapped_ss_output, file, indent=4)
 
 
-def _format_start_end(ss: str, start: int, end: int) -> List[int]:
+def _format_start_end(ss: str, start: int, end: int) -> list[int]:
     """Format start and end coordinates for vrs_ref_allele_seq for known edge cases
 
     :param ss: score set
@@ -346,10 +345,10 @@ def _format_start_end(ss: str, start: int, end: int) -> List[int]:
 
 
 def annotate(
-    tx_select_results: Optional[TxSelectResult],
-    vrs_results: List[VrsObject1_x],
+    tx_select_results: TxSelectResult | None,
+    vrs_results: list[VrsObject1_x],
     metadata: ScoresetMetadata,
-) -> List[VrsObject1_x]:
+) -> list[VrsObject1_x]:
     """TODO"""
     sr = get_seqrepo()
     for var in vrs_results:

src/dcd_mapping/cli.py

@@ -2,7 +2,6 @@
 import asyncio
 import logging
 from pathlib import Path
-from typing import Optional
 
 import click
 
@@ -32,7 +31,7 @@
     default=None,
     help="Desired location at which output file should be saved",
 )
-def cli(urn: str, debug: bool, output: Optional[Path]) -> None:
+def cli(urn: str, debug: bool, output: Path | None) -> None:
     """Get VRS mapping on preferred transcript for URN.
 
     For example:

src/dcd_mapping/lookup.py

@@ -10,7 +10,6 @@
 import logging
 import os
 from pathlib import Path
-from typing import List, Optional
 
 import polars as pl
 import requests
@@ -78,7 +77,7 @@ def __new__(cls) -> CoolSeqTool:
         """
 
         class _AugmentedSeqRepoAccess(SeqRepoAccess):
-            def derive_refget_accession(self, ac: str) -> Optional[str]:
+            def derive_refget_accession(self, ac: str) -> str | None:
                 if ac is None:
                     return None
 
@@ -104,7 +103,7 @@ def __init__(
                 lrg_refseqgene_path: Path = LRG_REFSEQGENE_PATH,
                 mane_data_path: Path = MANE_SUMMARY_PATH,
                 db_url: str = UTA_DB_URL,
-                sr: Optional[SeqRepo] = None,
+                sr: SeqRepo | None = None,
             ) -> None:
                 if not sr:
                     sr = SeqRepo(root_dir=SEQREPO_ROOT_DIR)
@@ -184,7 +183,7 @@ def __new__(cls, data_proxy: SeqRepoDataProxy) -> AlleleTranslator:
 # ----------------------------------- UTA ----------------------------------- #
 
 
-async def get_protein_accession(transcript: str) -> Optional[str]:
+async def get_protein_accession(transcript: str) -> str | None:
     """Retrieve protein accession for a transcript.
 
     :param transcript: transcript accession, e.g. ``"NM_002529.3"``
@@ -203,7 +202,7 @@ async def get_protein_accession(transcript: str) -> Optional[str]:
 
 async def get_transcripts(
     gene_symbol: str, chromosome_ac: str, start: int, end: int
-) -> List[str]:
+) -> list[str]:
     """Get transcript accessions matching given parameters (excluding non-coding RNA).
 
     TODO: may be able to successfully query with only one of gene symbol/chromosome ac.
@@ -233,7 +232,7 @@ async def get_transcripts(
 # ------------------------------ Gene Normalizer ------------------------------ #
 
 
-def _get_hgnc_symbol(term: str) -> Optional[str]:
+def _get_hgnc_symbol(term: str) -> str | None:
     """Fetch HGNC symbol from gene term.
 
     :param term: gene referent
@@ -248,7 +247,7 @@ def _get_hgnc_symbol(term: str) -> Optional[str]:
     return None
 
 
-def get_gene_symbol(metadata: ScoresetMetadata) -> Optional[str]:
+def get_gene_symbol(metadata: ScoresetMetadata) -> str | None:
     """Acquire HGNC gene symbol given provided metadata from scoreset.
 
     Right now, we use two sources for normalizing:
@@ -271,7 +270,7 @@ def get_gene_symbol(metadata: ScoresetMetadata) -> Optional[str]:
     return None
 
 
-def _normalize_gene(term: str) -> Optional[Gene]:
+def _normalize_gene(term: str) -> Gene | None:
     """Fetch normalizer response for gene term.
 
     :param term: gene name or referent to normalize
@@ -286,7 +285,7 @@ def _normalize_gene(term: str) -> Optional[Gene]:
 
 def _get_normalized_gene_response(
     metadata: ScoresetMetadata,
-) -> Optional[Gene]:
+) -> Gene | None:
     """Fetch best normalized concept given available scoreset metadata.
 
     :param metadata: salient scoreset metadata items
@@ -308,8 +307,8 @@ def _get_normalized_gene_response(
 
 
 def _get_genomic_interval(
-    extensions: List[Extension], src_name: str
-) -> Optional[GeneLocation]:
+    extensions: list[Extension], src_name: str
+) -> GeneLocation | None:
     """Extract start/end coords from extension list. Extensions in normalized genes
     can be of several different types, but we only want SequenceLocation data.
 
@@ -332,7 +331,7 @@ def _get_genomic_interval(
     return None
 
 
-def get_gene_location(metadata: ScoresetMetadata) -> Optional[GeneLocation]:
+def get_gene_location(metadata: ScoresetMetadata) -> GeneLocation | None:
     """Acquire gene location data from gene normalizer using metadata provided by
     scoreset.
 
@@ -404,7 +403,7 @@ def get_ucsc_chromosome_name(chromosome: str) -> str:
         raise KeyError from e
 
 
-def get_chromosome_identifier_from_vrs_id(sequence_id: str) -> Optional[str]:
+def get_chromosome_identifier_from_vrs_id(sequence_id: str) -> str | None:
     """Get NC_ identifier given a VRS sequence ID.
 
     :param sequence_id: identifier a la ``ga4gh:SQ.XXXXXX``
@@ -420,7 +419,7 @@ def get_chromosome_identifier_from_vrs_id(sequence_id: str) -> Optional[str]:
     return sorted_results[-1]
 
 
-def get_vrs_id_from_identifier(sequence_id: str) -> Optional[str]:
+def get_vrs_id_from_identifier(sequence_id: str) -> str | None:
     """Get GA4GH SQ identifier given an NP_ sequence id:
     :param: GA4GH SQ digest
     :raise KeyError: if unable to retrieve identifier
@@ -436,8 +435,8 @@ def get_vrs_id_from_identifier(sequence_id: str) -> Optional[str]:
 
 def get_sequence(
     sequence_id: str,
-    start: Optional[int] = None,
-    end: Optional[int] = None,
+    start: int | None = None,
+    end: int | None = None,
 ) -> str:
     """Get reference sequence given a sequence identifier.
 
@@ -490,7 +489,7 @@ def translate_hgvs_to_vrs(hgvs: str) -> Allele:
 # ----------------------------------- MANE ----------------------------------- #
 
 
-def get_mane_transcripts(transcripts: List[str]) -> List[ManeDescription]:
+def get_mane_transcripts(transcripts: list[str]) -> list[ManeDescription]:
     """Get corresponding MANE data for transcripts. Results given in order of
     transcript preference.
 
@@ -542,7 +541,7 @@ def _sort_mane_result(description: ManeDescription) -> int:
 # ---------------------------------- Misc. ---------------------------------- #
 
 
-def get_uniprot_sequence(uniprot_id: str) -> Optional[str]:
+def get_uniprot_sequence(uniprot_id: str) -> str | None:
     """Get sequence directly from UniProt.
 
     :param uniprot_id: ID provided with target info

src/dcd_mapping/main.py

@@ -1,7 +1,6 @@
 """Provide core MaveDB mapping methods."""
 import logging
 from pathlib import Path
-from typing import List, Optional
 
 import click
 
@@ -21,9 +20,9 @@
 
 async def map_scoreset(
     metadata: ScoresetMetadata,
-    records: List[ScoreRow],
+    records: list[ScoreRow],
     silent: bool = True,
-    output_path: Optional[Path] = None,
+    output_path: Path | None = None,
 ) -> None:
     """Given information about a MAVE experiment, map to VRS and save output as JSON.
 
@@ -62,7 +61,7 @@ async def map_scoreset(
 
 
 async def map_scoreset_urn(
-    urn: str, silent: bool = True, output_path: Optional[Path] = None
+    urn: str, silent: bool = True, output_path: Path | None = None
 ) -> None:
     """Perform end-to-end mapping for a scoreset.