scout-browser 4.82.2__py3-none-any.whl → 4.84__py3-none-any.whl

scout/commands/update/individual.py

@@ -1,5 +1,6 @@
 """Code for updating information on individuals
 """
+
 from pathlib import Path
 
 import click
@@ -95,4 +96,8 @@ def individual(case_id, ind, key, value):
 
             ind_obj[key] = value
 
-    store.update_case(case_obj)
+    link = f"/{case_obj['owner']}/{case_obj['display_name']}"
+    institute_obj = store.institute(case_obj["owner"])
+    store.update_case_individual(
+        case_obj, user_obj=None, institute_obj=institute_obj, link=link, keep_date=False
+    )

scout/commands/update/omim.py

@@ -1,4 +1,5 @@
 """Code to handle updates of the OMIM-AUTO gene panel via scout CLI"""
+
 import logging
 
 import click

scout/commands/update/panelapp.py

@@ -1,4 +1,5 @@
 """Code to handle updates of the PANELAPP-GREEN gene panel via scout CLI"""
+
 import logging
 
 import click

scout/constants/file_types.py

@@ -1,17 +1,90 @@
 # Collect general information about the file types used in Scout
+# Load priority determines load order, with lowest value loaded first.
 
 FILE_TYPE_MAP = {
-    "vcf_cancer": {"category": "cancer", "variant_type": "clinical"},
-    "vcf_cancer_sv": {"category": "cancer_sv", "variant_type": "clinical"},
-    "vcf_cancer_research": {"category": "cancer", "variant_type": "research"},
-    "vcf_cancer_sv_research": {"category": "cancer_sv", "variant_type": "research"},
-    "vcf_fusion": {"category": "fusion", "variant_type": "clinical"},
-    "vcf_fusion_research": {"category": "fusion", "variant_type": "research"},
-    "vcf_snv": {"category": "snv", "variant_type": "clinical"},
-    "vcf_snv_research": {"category": "snv", "variant_type": "research"},
-    "vcf_sv": {"category": "sv", "variant_type": "clinical"},
-    "vcf_sv_research": {"category": "sv", "variant_type": "research"},
-    "vcf_str": {"category": "str", "variant_type": "clinical"},
-    "vcf_mei": {"category": "mei", "variant_type": "clinical"},
-    "vcf_mei_research": {"category": "mei", "variant_type": "research"},
+    "vcf_cancer": {
+        "category": "cancer",
+        "variant_type": "clinical",
+        "load_priority": 10,
+    },
+    "vcf_cancer_research": {
+        "category": "cancer",
+        "variant_type": "research",
+        "load_priority": 110,
+    },
+    "vcf_cancer_sv": {
+        "category": "cancer_sv",
+        "variant_type": "clinical",
+        "load_priority": 20,
+    },
+    "vcf_cancer_sv_research": {
+        "category": "cancer_sv",
+        "variant_type": "research",
+        "load_priority": 120,
+    },
+    "vcf_fusion": {
+        "category": "fusion",
+        "variant_type": "clinical",
+        "load_priority": 70,
+    },
+    "vcf_fusion_research": {
+        "category": "fusion",
+        "variant_type": "research",
+        "load_priority": 170,
+    },
+    "vcf_mei": {
+        "category": "mei",
+        "variant_type": "clinical",
+        "load_priority": 60,
+    },
+    "vcf_mei_research": {
+        "category": "mei",
+        "variant_type": "research",
+        "load_priority": 160,
+    },
+    "vcf_snv": {
+        "category": "snv",
+        "variant_type": "clinical",
+        "load_priority": 35,
+    },
+    "vcf_snv_mt": {
+        "category": "snv",
+        "variant_type": "clinical",
+        "load_priority": 30,
+    },
+    "vcf_snv_research": {
+        "category": "snv",
+        "variant_type": "research",
+        "load_priority": 135,
+    },
+    "vcf_snv_research_mt": {
+        "category": "snv",
+        "variant_type": "research",
+        "load_priority": 130,
+    },
+    "vcf_sv": {
+        "category": "sv",
+        "variant_type": "clinical",
+        "load_priority": 45,
+    },
+    "vcf_sv_mt": {
+        "category": "sv",
+        "variant_type": "clinical",
+        "load_priority": 40,
+    },
+    "vcf_sv_research": {
+        "category": "sv",
+        "variant_type": "research",
+        "load_priority": 145,
+    },
+    "vcf_sv_research_mt": {
+        "category": "sv",
+        "variant_type": "research",
+        "load_priority": 140,
+    },
+    "vcf_str": {
+        "category": "str",
+        "variant_type": "clinical",
+        "load_priority": 50,
+    },
 }

scout/export/exon.py

@@ -11,6 +11,7 @@ head develop/mip_references/grch37_scout_exons_-2017-01-.bed
 7	65413656	65413769	7-65413658-65413767	NM_173517	21492	VKORC1L1
 5	159776172	159776790	5-159776174-159776788	NM_031908	14325	C1QTNF2
 """
+
 import logging
 
 LOG = logging.getLogger(__name__)

scout/load/__init__.py

@@ -1,5 +1,4 @@
 from .all import load_scout
-from .case import load_case
 from .cytoband import load_cytobands
 from .exon import load_exons
 from .hgnc_gene import load_hgnc_genes

scout/load/all.py

@@ -3,6 +3,7 @@ import logging
 
 from scout.constants import FILE_TYPE_MAP
 from scout.exceptions.config import ConfigError
+from scout.utils.sort import get_load_priority
 
 LOG = logging.getLogger(__name__)
 
@@ -54,15 +55,18 @@ def load_region(adapter, case_id, hgnc_id=None, chrom=None, start=None, end=None
         start = gene_caption["start"]
         end = gene_caption["end"]
 
-    case_file_types = []
+    case_file_types = set()
 
     for file_type in FILE_TYPE_MAP:
         if case_obj.get("vcf_files", {}).get(file_type):
-            case_file_types.append(
+            case_file_types.add(
                 (FILE_TYPE_MAP[file_type]["variant_type"], FILE_TYPE_MAP[file_type]["category"])
             )
 
-    for variant_type, category in case_file_types:
+    for variant_type, category in sorted(
+        case_file_types,
+        key=lambda tup: get_load_priority(variant_type=tup[0], category=tup[1]),
+    ):
         if variant_type == "research" and not case_obj["is_research"]:
             continue
 
@@ -84,13 +88,12 @@ def load_region(adapter, case_id, hgnc_id=None, chrom=None, start=None, end=None
     adapter.case_variants_count(case_obj["_id"], case_obj["owner"], force_update_case=True)
 
 
-def load_scout(adapter, config, ped=None, update=False):
+def load_scout(adapter, config, update=False):
     """Load a new case from a Scout config.
 
     Args:
         adapter(MongoAdapter)
         config(dict): loading info
-        ped(Iterable(str)): Pedigree ingformation
         update(bool): If existing case should be updated
 
     DEPRECATED method, historically used by the CG monolith, which has since switched to call the Scout CLI instead.

scout/load/hgnc_gene.py

@@ -91,7 +91,7 @@ def load_hgnc_genes(
             gene_objects.append(gene_obj)
 
     LOG.info("Nr of genes without coordinates in build %s: %s", build, non_existing)
-    LOG.info(f"Loading {len(gene_objects)} genes to database")
+    LOG.info(f"Loading {len(gene_objects)} genes into the database")
     adapter.load_hgnc_bulk(gene_objects)
 
     LOG.info("Loading done. %s genes loaded", len(gene_objects))

scout/load/panel.py

@@ -7,6 +7,7 @@ functions to load panels into the database
 import logging
 import math
 from datetime import datetime
+from typing import Dict, List
 
 from click import Abort
 from flask.cli import current_app
@@ -110,7 +111,7 @@ def load_panel(panel_path, adapter, **kwargs):
         raise err
 
 
-def _panelapp_panel_ids():
+def _panelapp_panel_ids() -> List[str]:
     """Fetch all PanelApp panel IDs"""
     json_lines = fetch_resource(PANELAPP_BASE_URL.format("list_panels"), json=True)
     return [panel_info["Panel_Id"] for panel_info in json_lines.get("result", [])]
@@ -129,11 +130,14 @@ def _parse_panelapp_panel(adapter, panel_id, institute, confidence):
             {'version': 3.3, 'date': datetime.datetime(2023, 1, 31, 16, 43, 37, 521719), 'display_name': 'Diabetes - neonatal onset - [GREEN]', 'institute': 'cust000', 'panel_type': 'clinical', 'genes': [list of genes], 'panel_id': '55a9041e22c1fc6711b0c6c0'}
 
     """
-    hgnc_map = adapter.ensembl_to_hgnc_mapping()
+    ensembl_gene_hgnc_id_map: Dict[str, int] = adapter.ensembl_to_hgnc_id_mapping()
+    hgnc_symbol_ensembl_gene_map: Dict[str, str] = adapter.hgnc_symbol_ensembl_id_mapping()
+
     json_lines = fetch_resource(PANELAPP_BASE_URL.format("get_panel") + panel_id, json=True)
     parsed_panel = parse_panel_app_panel(
         panel_info=json_lines["result"],
-        hgnc_map=hgnc_map,
+        ensembl_gene_hgnc_id_map=ensembl_gene_hgnc_id_map,
+        hgnc_symbol_ensembl_gene_map=hgnc_symbol_ensembl_gene_map,
         institute=institute,
         confidence=confidence,
     )
@@ -160,7 +164,7 @@ def load_panelapp_panel(adapter, panel_id=None, institute="cust000", confidence=
 
     if not panel_id:
         LOG.info("Fetching all panel app panels")
-        panel_ids = _panelapp_panel_ids()
+        panel_ids: List[str] = _panelapp_panel_ids()
 
     for _ in panel_ids:
         parsed_panel = _parse_panelapp_panel(adapter, _, institute, confidence)

scout/load/setup.py

@@ -5,6 +5,7 @@ This means add a default institute, a user and the internal definitions such as
 transcripts, hpo terms etc
 
 """
+
 import logging
 
 import yaml

scout/models/case/case_loading_models.py

@@ -15,7 +15,7 @@ except ImportError:
 
 from pydantic import BaseModel, Field, field_validator, model_validator
 
-from scout.constants import ANALYSIS_TYPES
+from scout.constants import ANALYSIS_TYPES, FILE_TYPE_MAP
 from scout.exceptions import PedigreeError
 from scout.utils.date import get_date
 
@@ -58,21 +58,7 @@ CASE_FILE_PATH_CHECKS = [
     "RNAfusion_report_research",
 ]
 
-VCF_FILE_PATH_CHECKS = [
-    "vcf_cancer",
-    "vcf_cancer_research",
-    "vcf_cancer_sv",
-    "vcf_cancer_sv_research",
-    "vcf_fusion",
-    "vcf_fusion_research",
-    "vcf_snv",
-    "vcf_snv_research",
-    "vcf_mei",
-    "vcf_mei_research",
-    "vcf_str",
-    "vcf_sv",
-    "vcf_sv_research",
-]
+VCF_FILE_PATH_CHECKS = FILE_TYPE_MAP.keys()
 
 GENOME_BUILDS = ["37", "38"]
 TRACKS = ["rare", "cancer"]
@@ -110,12 +96,16 @@ class VcfFiles(BaseModel):
     vcf_cancer_sv: Optional[str] = None
     vcf_cancer_sv_research: Optional[str] = None
     vcf_snv: Optional[str] = None
+    vcf_snv_mt: Optional[str] = None
     vcf_snv_research: Optional[str] = None
+    vcf_snv_research_mt: Optional[str] = None
     vcf_mei: Optional[str] = None
     vcf_mei_research: Optional[str] = None
     vcf_str: Optional[str] = None
     vcf_sv: Optional[str] = None
+    vcf_sv_mt: Optional[str] = None
     vcf_sv_research: Optional[str] = None
+    vcf_sv_research_mt: Optional[str] = None
     vcf_fusion: Optional[str] = None
     vcf_fusion_research: Optional[str] = None
 

scout/models/hgnc_map.py

@@ -2,6 +2,8 @@ from __future__ import unicode_literals
 
 from typing import List, Optional
 
+from pydantic import BaseModel, Field, field_validator, model_validator
+
 
 class Exon(dict):
     """Exon dictionary
@@ -66,90 +68,51 @@ class HgncTranscript(dict):
                 self["mane_plus_clinical"] = mane_plus_clinical
 
 
-class HgncGene(dict):
-    """HgncGene dictionary
-
-    'hgnc_id': int, # This is the hgnc id, required:
-    'hgnc_symbol': str, # The primary symbol, required
-    'ensembl_id': str, # required
-    'build': str, # '37' or '38', defaults to '37', required
-
-    'chromosome': str, # required
-    'start': int, # required
-    'end': int, # required
-
-    'description': str, # Gene description
-    'aliases': list(), # Gene symbol aliases, includes hgnc_symbol, str
-    'entrez_id': int,
-    'omim_id': int,
-    'pli_score': float,
-    'primary_transcripts': list(), # List of refseq transcripts (str)
-    'ucsc_id': str,
-    'uniprot_ids': list(), # List of str
-    'vega_id': str,
-
-    # Inheritance information
-    'inheritance_models': list(), # List of model names
-    'incomplete_penetrance': bool, # Acquired from HPO
-
-    # Phenotype information
-    'phenotypes': list(), # List of dictionaries with phenotype information
-    """
-
-    def __init__(
-        self,
-        hgnc_id,
-        hgnc_symbol,
-        ensembl_id,
-        chrom,
-        start,
-        end,
-        description=None,
-        aliases=None,
-        entrez_id=None,
-        omim_id=None,
-        pli_score=None,
-        primary_transcripts=None,
-        ucsc_id=None,
-        uniprot_ids=None,
-        vega_id=None,
-        inheritance_models=None,
-        incomplete_penetrance=False,
-        phenotypes=None,
-        build="37",
-    ):
-        super(HgncGene, self).__init__()
-        self["hgnc_id"] = int(hgnc_id)
-        self["hgnc_symbol"] = hgnc_symbol
-        self["ensembl_id"] = ensembl_id
-
-        self["chromosome"] = chrom
-        self["start"] = int(start)
-        self["end"] = int(end)
-        self["length"] = self["end"] - self["start"]
-
-        self["description"] = description
-        self["aliases"] = aliases
-        self["primary_transcripts"] = primary_transcripts
-        self["inheritance_models"] = inheritance_models
-        self["phenotypes"] = phenotypes
-
-        self["entrez_id"] = entrez_id
-        if entrez_id:
-            self["entrez_id"] = int(entrez_id)
-
-        self["omim_id"] = omim_id
-        if omim_id:
-            self["omim_id"] = int(omim_id)
-
-        self["ucsc_id"] = ucsc_id
-        self["uniprot_ids"] = uniprot_ids
-        self["vega_id"] = vega_id
-
-        self["pli_score"] = pli_score
-        if pli_score:
-            self["pli_score"] = float(pli_score)
-
-        self["incomplete_penetrance"] = incomplete_penetrance
-
-        self["build"] = build
+class HgncGene(BaseModel):
+    hgnc_id: int
+    hgnc_symbol: str
+    build: str
+    chromosome: str
+    start: int
+    end: int
+    length: int
+    description: Optional[str] = None
+    ensembl_id: Optional[str] = Field(None, alias="ensembl_gene_id")
+    aliases: Optional[List[str]] = Field(None, alias="previous_symbols")
+    entrez_id: Optional[int] = None
+    omim_id: Optional[int] = None
+    primary_transcripts: Optional[List[str]] = Field(None, alias="ref_seq")
+    ucsc_id: Optional[str] = None
+    uniprot_ids: Optional[List[str]] = None
+    vega_id: Optional[str] = None
+    inheritance_models: Optional[List[str]] = None
+    incomplete_penetrance: Optional[bool] = False
+    phenotypes: Optional[List[dict]] = None
+    pli_score: Optional[float] = None
+    constraint_lof_oe: Optional[float] = None
+    constraint_lof_oe_ci_lower: Optional[float] = None
+    constraint_lof_oe_ci_upper: Optional[float] = None
+    constraint_lof_z: Optional[float] = None
+    constraint_mis_oe: Optional[float] = None
+    constraint_mis_oe_ci_lower: Optional[float] = None
+    constraint_mis_oe_ci_upper: Optional[float] = None
+    constraint_mis_z: Optional[float] = None
+
+    @model_validator(mode="before")
+    def set_gene_length(cls, values) -> "HgncGene":
+        """Set gene length."""
+        if None in [values.get("end"), values.get("start")]:
+            values.update({"length": None})
+        else:
+            values.update({"length": values.get("end") - values.get("start")})
+        return values
+
+    @field_validator("phenotypes", mode="before")
+    @classmethod
+    def set_phenotypes_inheritance(cls, phenotypes) -> Optional[List[dict]]:
+        """Convert field 'inheritance' of each phenotype in phenotypes from set to list."""
+        for phenotype in phenotypes:
+            phenotype["inheritance_models"] = list(phenotype.get("inheritance", {}))
+            phenotype.pop("inheritance", None)
+
+        return phenotypes

scout/models/phenotype_term.py

@@ -14,9 +14,9 @@ class HpoTerm(BaseModel):
     """
 
     hpo_id: str  # id field in the hpo.obo file
-    hpo_number: Optional[
-        int
-    ] = None  # id field in the hpo.obo file, stripped of the 'HP:' part and the zeroes
+    hpo_number: Optional[int] = (
+        None  # id field in the hpo.obo file, stripped of the 'HP:' part and the zeroes
+    )
     description: str  # name field in the hpo.obo file
     ancestors: List = []
     all_ancestors: List = []

scout/parse/case.py

@@ -86,7 +86,6 @@ def parse_case_data(**kwargs):
         config_dict["case_id"] = config_dict["family"]
 
     if config_dict.get("smn_tsv"):
-        LOG.info("Adding SMN info from {}.".format(config_dict["smn_tsv"]))
         add_smn_info_case(config_dict)
 
     return remove_none_recursive(config_dict)

scout/parse/disease_terms.py

@@ -1,4 +1,5 @@
 """Code for parsing disease terms from OMIM and ORPHA data"""
+
 import logging
 from typing import Dict, List
 

scout/parse/omim.py

@@ -1,4 +1,5 @@
 """Code for parsing OMIM formatted files"""
+
 import logging
 from typing import Any, Dict, Iterable
 

scout/parse/orpha.py

@@ -1,4 +1,5 @@
 """Code for parsing ORPHA formatted files"""
+
 import logging
 from typing import Any, Dict, List
 from xml.etree.ElementTree import Element

scout/parse/panel.py

@@ -1,6 +1,8 @@
 """Code to parse panel information"""
+
 import logging
 from datetime import datetime
+from typing import Dict, List, Optional
 
 from scout.constants import (
     INCOMPLETE_PENETRANCE_MAP,
@@ -233,7 +235,12 @@ def parse_genes(gene_lines):
 
 
 def parse_gene_panel(
-    path, institute="cust000", panel_id="test", panel_type="clinical", genes=None, **kwargs
+    path,
+    institute="cust000",
+    panel_id="test",
+    panel_type="clinical",
+    genes=None,
+    **kwargs,
 ):
     """Parse the panel info and return a gene panel
 
@@ -268,17 +275,14 @@ def parse_gene_panel(
     return gene_panel
 
 
-def parse_panel_app_gene(app_gene, hgnc_map, confidence):
-    """Parse a panel app formatted gene.
+def parse_panel_app_gene(
+    app_gene: dict,
+    ensembl_gene_hgnc_id_map: Dict[str, int],
+    hgnc_symbol_ensembl_gene_map: Dict[str, str],
+    confidence: str,
+) -> dict:
+    """Parse a panel app-formatted gene."""
 
-    Args:
-        app_gene(dict): dict with panel app info, where Ensembl ids are present as a loist with key "EnsembleGeneIds"
-        hgnc_map(dict): a dictionary with Ensembl IDs as keys and HGNC ids as values
-        confidence(str): enum green|amber|red
-
-    Returns:
-        gene_info(dict): Scout infromation
-    """
     gene_info = {}
     confidence_level = app_gene["LevelOfConfidence"]
     # Return empty gene if not confident gene
@@ -288,8 +292,22 @@ def parse_panel_app_gene(app_gene, hgnc_map, confidence):
     hgnc_symbol = app_gene["GeneSymbol"]
 
     ensembl_ids = app_gene["EnsembleGeneIds"]
+
+    if not ensembl_ids:  # This gene is probably tagged as ensembl_ids_known_missing on PanelApp
+        if hgnc_symbol in hgnc_symbol_ensembl_gene_map:
+            LOG.warning(
+                f"PanelApp gene {hgnc_symbol} does not contain Ensembl IDs. Using Ensembl IDs from internal gene collection instead."
+            )
+            ensembl_ids = [hgnc_symbol_ensembl_gene_map[hgnc_symbol]]
+        else:
+            LOG.warning(
+                f"PanelApp gene {hgnc_symbol} does not contain Ensembl IDs and gene symbol does not correspond to a gene in scout."
+            )
+
     hgnc_ids = set(
-        hgnc_map.get(ensembl_id) for ensembl_id in ensembl_ids if hgnc_map.get(ensembl_id)
+        ensembl_gene_hgnc_id_map.get(ensembl_id)
+        for ensembl_id in ensembl_ids
+        if ensembl_gene_hgnc_id_map.get(ensembl_id)
     )
     if not hgnc_ids:
         LOG.warning("Gene %s does not exist in database. Skipping gene...", hgnc_symbol)
@@ -314,8 +332,13 @@ def parse_panel_app_gene(app_gene, hgnc_map, confidence):
 
 
 def parse_panel_app_panel(
-    panel_info, hgnc_map, institute="cust000", panel_type="clinical", confidence="green"
-):
+    panel_info: dict,
+    ensembl_gene_hgnc_id_map: Dict[str, int],
+    hgnc_symbol_ensembl_gene_map: Dict[str, str],
+    institute: Optional[str] = "cust000",
+    panel_type: Optional[str] = "clinical",
+    confidence: Optional[str] = "green",
+) -> dict:
     """Parse a PanelApp panel
 
     Args:
@@ -346,7 +369,9 @@ def parse_panel_app_panel(
     nr_excluded = 0
     nr_genes = 0
     for nr_genes, gene in enumerate(panel_info["Genes"], 1):
-        gene_info = parse_panel_app_gene(gene, hgnc_map, confidence)
+        gene_info = parse_panel_app_gene(
+            gene, ensembl_gene_hgnc_id_map, hgnc_symbol_ensembl_gene_map, confidence
+        )
         if not gene_info:
             nr_excluded += 1
             continue

scout/parse/variant/conservation.py

@@ -1,4 +1,5 @@
 """Code for parsing conservation"""
+
 import logging
 import numbers
 

scout/resources/__init__.py

@@ -12,3 +12,6 @@ cytoband_files = {
     "37": cytobands_37_path,
     "38": cytobands_38_path,
 }
+
+# Custom IGV tracks
+mane_igv_track_path = str(files(BASE_PATH).joinpath("custom_igv_tracks", "mane.bb"))