Merge ef62950 into 9d8fa3c

HISTORY.rst

@@ -23,6 +23,7 @@ Full Change List
 - Strip trailing slashes in beconsite entrypoints (#388)
 - Documenting PAP setup (#393)
 - Adding more indices (#395)
+- Fixing discrepancy with REST API query shortcuts (#402)
 
 ------
 v1.1.0

docs_manual/developer_development.rst

@@ -63,7 +63,7 @@ To do so, go to the `VarFish repository <https://github.com/bihealth/varfish-ser
 Update Main
 ===========
 
-`Pull with rebase on gitready <https://gitready.com/advanced/2009/02/11/pull-with-rebase.html>`_
+`Pull with rebase on gitready <https://gitready.com/advanced/2009/02/11/pull-with-rebase.html>`__
 
 .. code-block:: bash
 
@@ -103,7 +103,7 @@ We suggest to first squash your commits and then do a rebase to the main branch.
 Squash Multiple Commits (Or Use Amend)
 --------------------------------------
 
-`Pull with rebase on gitready <https://gitready.com/advanced/2009/02/10/squashing-commits-with-rebase.html>`_
+`Pull with rebase on gitready <https://gitready.com/advanced/2009/02/10/squashing-commits-with-rebase.html>`__
 
 We prefer to have only one commit per feature (most of the time there is only one feature per branch).
 When your branch is rebased on the main branch, do:

variants/queries.py

@@ -1012,14 +1012,28 @@ def _build_gene_sub_query(self, hgnc_field, gene_list):
         )
 
 
+def normalize_chrom(chrom, release):
+    """Normalize chromosome for the given ``release``."""
+    while chrom.startswith("chr"):
+        chrom = chrom[len("chr") :]
+    if chrom in ("M", "MT"):
+        if release == "GRCh37":
+            return "MT"
+        else:
+            return "chrM"
+    else:
+        return f"chr{chrom}" if release != "GRCh37" else chrom
+
+
 class ExtendQueryPartsGenomicRegionFilter(ExtendQueryPartsBase):
     def extend_conditions(self, _query_parts):
+        case = self._case_for_release()
         if self.kwargs["genomic_region"]:
             return [
                 or_(
                     *[
                         and_(
-                            SmallVariant.sa.chromosome == chrom,
+                            SmallVariant.sa.chromosome == normalize_chrom(chrom, case.release),
                             (SmallVariant.sa.start >= start) if start else True,
                             (SmallVariant.sa.start <= end) if end else True,
                         )
@@ -1029,6 +1043,12 @@ def extend_conditions(self, _query_parts):
             ]
         return []
 
+    def _case_for_release(self):
+        if hasattr(self, "cases"):
+            return self.cases[0]
+        else:
+            return self.case
+
 
 class ExtendQueryPartsLoadPrefetchedBase(ExtendQueryPartsBase):
     def __init__(self, *args, **kwargs):

variants/query_presets.py

@@ -576,15 +576,17 @@ class _ImpactPresets:
         "transcripts_coding": True,
         "transcripts_noncoding": False,
         "effects": (
+            "3_prime_UTR_exon_variant",
+            "3_prime_UTR_intron_variant",
+            "5_prime_UTR_exon_variant",
+            "5_prime_UTR_intron_variant",
             "coding_transcript_intron_variant",
             "complex_substitution",
             "direct_tandem_duplication",
             "disruptive_inframe_deletion",
             "disruptive_inframe_insertion",
             "exon_loss_variant",
             "feature_truncation",
-            "five_prime_UTR_exon_variant",
-            "five_prime_UTR_intron_variant",
             "frameshift_elongation",
             "frameshift_truncation",
             "frameshift_variant",
@@ -602,8 +604,6 @@ class _ImpactPresets:
             "stop_retained_variant",
             "structural_variant",
             "synonymous_variant",
-            "three_prime_UTR_exon_variant",
-            "three_prime_UTR_intron_variant",
             "transcript_ablation",
         ),
     }
@@ -615,6 +615,10 @@ class _ImpactPresets:
         "transcripts_coding": True,
         "transcripts_noncoding": True,
         "effects": (
+            "3_prime_UTR_exon_variant",
+            "3_prime_UTR_intron_variant",
+            "5_prime_UTR_exon_variant",
+            "5_prime_UTR_intron_variant",
             "coding_transcript_intron_variant",
             "complex_substitution",
             "direct_tandem_duplication",
@@ -623,8 +627,6 @@ class _ImpactPresets:
             "downstream_gene_variant",
             "exon_loss_variant",
             "feature_truncation",
-            "five_prime_UTR_exon_variant",
-            "five_prime_UTR_intron_variant",
             "frameshift_elongation",
             "frameshift_truncation",
             "frameshift_variant",
@@ -645,8 +647,6 @@ class _ImpactPresets:
             "stop_retained_variant",
             "structural_variant",
             "synonymous_variant",
-            "three_prime_UTR_exon_variant",
-            "three_prime_UTR_intron_variant",
             "transcript_ablation",
             "upstream_gene_variant",
         ),
@@ -773,25 +773,25 @@ class _ChromosomePresets:
     }
     #: Presets for the "autosomes" chromosome/region/gene settings
     autosomes: typing.Dict[str, typing.Any] = {
-        "genomic_region": tuple(f"chr{num}" for num in range(1, 23)),
+        "genomic_region": tuple(f"{num}" for num in range(1, 23)),
         "gene_allowlist": (),
         "gene_blocklist": (),
     }
     #: Presets for the "X-chromosome" chromosome/region/gene settings
     x_chromosome: typing.Dict[str, typing.Any] = {
-        "genomic_region": ("chrX",),
+        "genomic_region": ("X",),
         "gene_allowlist": (),
         "gene_blocklist": (),
     }
     #: Presets for the "Y-chromosomes" chromosome/region/gene settings
     y_chromosome: typing.Dict[str, typing.Any] = {
-        "genomic_region": ("chrY",),
+        "genomic_region": ("Y",),
         "gene_allowlist": (),
         "gene_blocklist": (),
     }
     #: Presets for the "mitochondrial" chromosome/region/gene settings
     mt_chromosome: typing.Dict[str, typing.Any] = {
-        "genomic_region": ("chrMT",),
+        "genomic_region": ("MT",),
         "gene_allowlist": (),
         "gene_blocklist": (),
     }

variants/query_schemas.py

@@ -4,9 +4,11 @@
 import copy
 import os.path
 import json
+import re
 import typing
 
 import attr
+import attrs
 import cattr
 from jsonschema import Draft7Validator, validators
 
@@ -136,6 +138,18 @@ class GenomicRegionV1:
     chromosome: str
     range: typing.Optional[RangeV1] = None
 
+    def with_chr_stripped(self):
+        chromosome = self.chromosome
+        if chromosome.startswith("chr"):
+            chromosome = chromosome[len("chr") :]
+        return GenomicRegionV1(chromosome, self.range)
+
+    def to_str(self):
+        if not self.range:
+            return self.chromosome
+        else:
+            return "%s:%d-%d" % (self.chromosome, self.range.start, self.range.end)
+
 
 def convert_genomic_region_v1(region: GenomicRegionV1):
     if region.range:
@@ -265,7 +279,7 @@ class CaseQueryV1:
     helixmtdb_hom_count: typing.Optional[int] = None
 
     mitomap_count: typing.Optional[int] = None
-    mitmomap_frequency: typing.Optional[float] = None
+    mitomap_frequency: typing.Optional[float] = None
 
 
 class QueryJsonToFormConverter:
@@ -296,6 +310,7 @@ def convert(self, case: Case, query: CaseQueryV1) -> typing.Dict[str, typing.Any
             "inhouse_enabled": query.inhouse_enabled,
             "inhouse_carriers": query.inhouse_carriers,
             "inhouse_heterozygous": query.inhouse_heterozygous,
+            "inhouse_homozygous": query.inhouse_homozygous,
             "mtdb_enabled": query.mtdb_enabled,
             "mtdb_count": query.mtdb_count,
             "mtdb_frequency": query.mtdb_frequency,
@@ -420,4 +435,26 @@ def convert_query_json_to_small_variant_filter_form_v1(
     tmp = copy.deepcopy(query_json)
     DefaultValidatingDraft7Validator(SCHEMA_QUERY_V1).validate(tmp)
     query = cattr.structure(tmp, CaseQueryV1)
+    if query.genomic_region:
+        query = attrs.evolve(
+            query,
+            genomic_region=list(map(GenomicRegionV1.with_chr_stripped, query.genomic_region)),
+        )
     return QueryJsonToFormConverter().convert(case, query)
+
+
+def _structure_genomic_region(s, _):
+    if not re.match("^[a-zA-Z0-9]+(:(\\d+(,\\d+)*)-(\\d+(,\\d+)*))?$", s):
+        raise RuntimeError("Invalid genomic region string: %s" % repr(s))
+    if ":" in s:
+        chrom, range = s.split(":")
+        start, end = range.split("-")
+        return GenomicRegionV1(chromosome=chrom, range=RangeV1(int(start), int(end)))
+    else:
+        return GenomicRegionV1(chromosome=s)
+
+
+cattr.register_structure_hook(GenomicRegionV1, _structure_genomic_region)
+
+
+cattr.register_unstructure_hook(GenomicRegionV1, GenomicRegionV1.to_str)

variants/tests/factories.py

@@ -653,6 +653,7 @@ class Meta:
 
 
 CHROMOSOME_MAPPING = {str(chrom): i + 1 for i, chrom in enumerate(list(range(1, 23)) + ["X", "Y"])}
+CHROMOSOME_MAPPING.update({f"chr{chrom}": i for chrom, i in CHROMOSOME_MAPPING.items()})
 
 
 class SmallVariantFactory(factory.django.DjangoModelFactory):