Merge branch 'dev' of https://github.com/opentargets/gentropy into xg…

…1_l2g_intervals

pyproject.toml

@@ -19,64 +19,63 @@ packages = [{ include = "gentropy", from = "src" }]
 gentropy = "gentropy.cli:main"
 
 [tool.poetry.dependencies]
-python = "^3.10, <3.11"
+python = ">=3.10, <3.11"
 pyspark = "3.3.4"
-scipy = "^1.11.4"
-hydra-core = "^1.3.2"
-pyliftover = "^0.4"
-numpy = "^1.26.2"
+scipy = ">=1.11.4, <1.12.0"
+hydra-core = ">=1.3.2, <1.4.0"
+pyliftover = ">=0.4, <0.5"
+numpy = ">=1.26.2, <1.27.0"
 hail = "0.2.127"
-wandb = ">=0.16.2,<0.19.0"
-google = "^3.0.0"
-omegaconf = "^2.3.0"
-typing-extensions = "^4.9.0"
-scikit-learn = "^1.3.2"
-pandas = { extras = ["gcp", "parquet"], version = "^2.2.2" }
-skops = ">=0.9,<0.11"
-google-cloud-secret-manager = "^2.20.0"
-shap = "^0.46.0"
-matplotlib = "3.7.3"
-
-[tool.poetry.dev-dependencies]
-pre-commit = "^4.0.0"
-mypy = "^1.13"
-pep8-naming = "^0.14.1"
-interrogate = "^1.7.0"
-isort = "^5.13.2"
-darglint = "^1.8.1"
-ruff = "^0.8.1"
+wandb = ">=0.19.0, <0.20.0"
+google = ">=3.0.0, <3.1.0"
+omegaconf = ">=2.3.0, <2.4.0"
+typing-extensions = ">=4.9.0, <4.13.0"
+scikit-learn = ">=1.6.0, <1.7.0"
+pandas = { extras = ["gcp", "parquet"], version = ">=2.2.2, <2.3.0" }
+skops = ">=0.11, <0.12"
+google-cloud-secret-manager = ">=2.20.0, <2.22.0"
+shap = ">=0.46.0, <0.47.0"
+matplotlib = ">=3.7.3, <3.8.0"
+
 
 [tool.poetry.group.docs.dependencies]
-mkdocs = "^1.5.3"
-mkdocstrings-python = "^1.8.0"
+mkdocs = ">=1.5.3, <1.6.0"
+mkdocstrings-python = ">=1.12.2, <1.13.0"
 mkdocs-material = "*"
-mkdocs-section-index = "^0.3.4"
-mkdocs-git-revision-date-localized-plugin = "^1.2.2"
-mkdocs-autolinks-plugin = "^0.7.1"
-mkdocs-awesome-pages-plugin = "^2.9.2"
-mkdocs-exclude = "^1.0.2"
-mkdocs-git-committers-plugin-2 = "^2.2.3"
-lxml = "^5.1.0"
-pymdown-extensions = "^10.7"
+mkdocs-section-index = ">=0.3.4, <0.4.0"
+mkdocs-git-revision-date-localized-plugin = ">=1.2.2, <1.4.0"
+mkdocs-autolinks-plugin = ">=0.7.1, <0.8.0"
+mkdocs-awesome-pages-plugin = ">=2.9.2, <3.0.0"
+mkdocs-exclude = ">=1.0.2, <1.1.0"
+mkdocs-git-committers-plugin-2 = ">=2.2.3, <2.5.0"
+lxml = ">=5.1.0, <5.4.0"
+pymdown-extensions = ">=10.7, <10.13"
 
 
 [tool.poetry.group.tests.dependencies]
 pytest-cov = ">=4.1,<7.0"
 pytest-sugar = ">=0.9.5,<1.1.0"
 dbldatagen = ">=0.3.1,<0.5.0"
-pyparsing = "^3.1.1"
+pyparsing = ">=3.1.1, <3.3.0"
 pytest = ">=7.4.4,<9.0.0"
-pytest-xdist = "^3.5.0"
+pytest-xdist = ">=3.5.0, <3.7.0"
 
 
 [tool.poetry.group.dev.dependencies]
-ipython = "^8.19.0"
-ipykernel = "^6.28.0"
-google-cloud-dataproc = "^5.8.0"
+ipython = ">=8.19.0, <8.31.0"
+ipykernel = ">=6.28.0, <6.30.0"
+google-cloud-dataproc = ">=5.8.0, <5.16.0"
 pydoclint = ">=0.3.8,<0.6.0"
-prettier = "^0.0.7"
+prettier = ">=0.0.7, <0.1.0"
 deptry = ">=0.12,<0.21"
-yamllint = "^1.33.0"
+yamllint = ">=1.33.0, <1.36.0"
+pre-commit = ">=4.0.0, <4.1.0"
+mypy = ">=1.13, <1.14"
+pep8-naming = ">=0.14.1, <0.15.0"
+interrogate = ">=1.7.0, <1.8.0"
+isort = ">=5.13.2, <5.14.0"
+darglint = ">=1.8.1, <1.9.0"
+ruff = ">=0.8.1, <0.9.0"
 
 [tool.semantic_release]
 logging_use_named_masks = true

src/gentropy/config.py

@@ -17,7 +17,8 @@ class SessionConfig:
     write_mode: str = "errorifexists"
     spark_uri: str = "local[*]"
     hail_home: str = os.path.dirname(hail_location)
-    extended_spark_conf: dict[str, str] | None = field(default_factory=dict[str, str])
+    extended_spark_conf: dict[str, str] | None = field(
+        default_factory=dict[str, str])
     output_partitions: int = 200
     _target_: str = "gentropy.common.session.Session"
 
@@ -39,7 +40,8 @@ class ColocalisationConfig(StepConfig):
     credible_set_path: str = MISSING
     coloc_path: str = MISSING
     colocalisation_method: str = MISSING
-    colocalisation_method_params: dict[str, Any] = field(default_factory=dict[str, Any])
+    colocalisation_method_params: dict[str, Any] = field(
+        default_factory=dict[str, Any])
     _target_: str = "gentropy.colocalisation.ColocalisationStep"
 
 
@@ -124,7 +126,8 @@ class EqtlCatalogueConfig(StepConfig):
     eqtl_catalogue_paths_imported: str = MISSING
     eqtl_catalogue_study_index_out: str = MISSING
     eqtl_catalogue_credible_sets_out: str = MISSING
-    mqtl_quantification_methods_blacklist: list[str] = field(default_factory=lambda: [])
+    mqtl_quantification_methods_blacklist: list[str] = field(
+        default_factory=lambda: [])
     eqtl_lead_pvalue_threshold: float = 1e-3
     _target_: str = "gentropy.eqtl_catalogue.EqtlCatalogueStep"
 
@@ -146,7 +149,8 @@ class FinngenStudiesConfig(StepConfig):
     )
     finngen_summary_stats_url_suffix: str = ".gz"
     efo_curation_mapping_url: str = "https://raw.githubusercontent.com/opentargets/curation/24.09.1/mappings/disease/manual_string.tsv"
-    sample_size: int = 453733  # https://www.finngen.fi/en/access_results#:~:text=Total%20sample%20size%3A%C2%A0453%2C733%C2%A0(254%2C618%C2%A0females%20and%C2%A0199%2C115%20males)
+    # https://www.finngen.fi/en/access_results#:~:text=Total%20sample%20size%3A%C2%A0453%2C733%C2%A0(254%2C618%C2%A0females%20and%C2%A0199%2C115%20males)
+    sample_size: int = 453733
     _target_: str = "gentropy.finngen_studies.FinnGenStudiesStep"
 
 
@@ -199,7 +203,6 @@ class LDIndexConfig(StepConfig):
             "nfe",  # Non-Finnish European
         ]
     )
-    use_version_from_input: bool = False
     _target_: str = "gentropy.gnomad_ingestion.LDIndexStep"
 
 
@@ -416,7 +419,6 @@ class GnomadVariantConfig(StepConfig):
             "remaining",  # Other
         ]
     )
-    use_version_from_input: bool = False
     _target_: str = "gentropy.gnomad_ingestion.GnomadVariantIndexStep"
 
 
@@ -439,7 +441,6 @@ class PanUKBBConfig(StepConfig):
             "EUR",  # European
         ]
     )
-    use_version_from_input: bool = False
     _target_: str = "gentropy.pan_ukb_ingestion.PanUKBBVariantIndexStep"
 
 
@@ -687,7 +688,8 @@ class Config:
     """Application configuration."""
 
     # this is unfortunately verbose due to @dataclass limitations
-    defaults: List[Any] = field(default_factory=lambda: ["_self_", {"step": MISSING}])
+    defaults: List[Any] = field(default_factory=lambda: [
+                                "_self_", {"step": MISSING}])
     step: StepConfig = MISSING
     datasets: dict[str, str] = field(default_factory=dict)
 
@@ -721,7 +723,8 @@ def register_config() -> None:
         name="gwas_catalog_top_hit_ingestion",
         node=GWASCatalogTopHitIngestionConfig,
     )
-    cs.store(group="step", name="ld_based_clumping", node=LDBasedClumpingConfig)
+    cs.store(group="step", name="ld_based_clumping",
+             node=LDBasedClumpingConfig)
     cs.store(group="step", name="ld_index", node=LDIndexConfig)
     cs.store(group="step", name="locus_to_gene", node=LocusToGeneConfig)
     cs.store(
@@ -739,7 +742,8 @@ def register_config() -> None:
 
     cs.store(group="step", name="pics", node=PICSConfig)
     cs.store(group="step", name="gnomad_variants", node=GnomadVariantConfig)
-    cs.store(group="step", name="ukb_ppp_eur_sumstat_preprocess", node=UkbPppEurConfig)
+    cs.store(group="step", name="ukb_ppp_eur_sumstat_preprocess",
+             node=UkbPppEurConfig)
     cs.store(group="step", name="variant_index", node=VariantIndexConfig)
     cs.store(group="step", name="variant_to_vcf", node=ConvertToVcfStepConfig)
     cs.store(
@@ -772,5 +776,7 @@ def register_config() -> None:
         name="locus_to_gene_associations",
         node=LocusToGeneAssociationsStepConfig,
     )
-    cs.store(group="step", name="finngen_ukb_meta_ingestion", node=FinngenUkbMetaConfig)
-    cs.store(group="step", name="credible_set_qc", node=CredibleSetQCStepConfig)
+    cs.store(group="step", name="finngen_ukb_meta_ingestion",
+             node=FinngenUkbMetaConfig)
+    cs.store(group="step", name="credible_set_qc",
+             node=CredibleSetQCStepConfig)