scout-browser 4.83__py3-none-any.whl → 4.84__py3-none-any.whl

scout/__version__.py

@@ -1 +1 @@
-__version__ = "4.83"
+__version__ = "4.84"

scout/adapter/mongo/case.py

@@ -14,6 +14,7 @@ from scout.constants import ACMG_MAP, FILE_TYPE_MAP, ID_PROJECTION
 from scout.exceptions import ConfigError, IntegrityError
 from scout.parse.variant.ids import parse_document_id
 from scout.utils.algorithms import ui_score
+from scout.utils.sort import get_load_priority
 
 LOG = logging.getLogger(__name__)
 
@@ -904,7 +905,10 @@ class CaseHandler(object):
                     continue
                 load_variants.add((vcf_file["variant_type"], vcf_file["category"]))
 
-            for variant_type, category in load_variants:
+            for variant_type, category in sorted(
+                load_variants,
+                key=lambda tup: get_load_priority(variant_type=tup[0], category=tup[1]),
+            ):
                 if update:
                     self.delete_variants(
                         case_id=case_obj["_id"],

scout/adapter/mongo/variant.py

@@ -2,6 +2,7 @@
 # stdlib modules
 import logging
 import re
+from typing import Any
 
 # Third party modules
 import pymongo
@@ -221,6 +222,14 @@ class VariantHandler(VariantLoader):
         query = self.build_query(case_id, query=query, variant_ids=variant_ids, category=category)
         return self.variant_collection.count_documents(query)
 
+    def variant_update_field(self, variant_id: str, field_name: str, field_value: Any) -> dict:
+        """Updates the value of the given key(field_name) in the variant document in the database."""
+        return self.variant_collection.find_one_and_update(
+            {"_id": variant_id},
+            {"$set": {field_name: field_value}},
+            return_document=pymongo.ReturnDocument.AFTER,
+        )
+
     def variant(
         self,
         document_id=None,

scout/adapter/mongo/variant_loader.py

@@ -27,6 +27,7 @@ from scout.parse.variant.headers import (
 from scout.parse.variant.ids import parse_simple_id
 from scout.parse.variant.managed_variant import parse_managed_variant_id
 from scout.parse.variant.rank_score import parse_rank_score
+from scout.utils.sort import get_load_priority
 
 LOG = logging.getLogger(__name__)
 
@@ -200,87 +201,88 @@ class VariantLoader(object):
         """
 
         case_id = case_obj["_id"]
-        # Possible categories 'snv', 'sv', 'str', 'cancer', 'cancer_sv':
-        categories = set()
-        # Possible variant types 'clinical', 'research':
-        variant_types = set()
-
-        for file_type in FILE_TYPE_MAP:
-            if case_obj.get("vcf_files", {}).get(file_type):
-                categories.add(FILE_TYPE_MAP[file_type]["category"])
-                variant_types.add(FILE_TYPE_MAP[file_type]["variant_type"])
+        # Possible categories 'snv', 'sv', 'str', 'cancer', 'cancer_sv'. Sort according to load order to ensure Cancer SNVs before
+        # Cancer SVs, in particular, and keep a consistent variant_id collision resolution order.
+        # Possible variant types are 'clinical', 'research'.
+        load_variants = {
+            (FILE_TYPE_MAP[file_type]["variant_type"], FILE_TYPE_MAP[file_type]["category"])
+            for file_type in FILE_TYPE_MAP
+            if case_obj.get("vcf_files", {}).get(file_type)
+        }
 
         coding_intervals = self.get_coding_intervals(build=build)
         # Loop over all intervals
         for chrom in CHROMOSOMES:
             intervals = coding_intervals.get(chrom, IntervalTree())
-            for var_type in variant_types:
-                for category in categories:
-                    LOG.info(
-                        "Updating compounds on chromosome:{0}, type:{1}, category:{2} for case:{3}".format(
-                            chrom, var_type, category, case_id
-                        )
+            for var_type, category in sorted(
+                list(load_variants),
+                key=lambda tup: get_load_priority(variant_type=tup[0], category=tup[1]),
+            ):
+                LOG.info(
+                    "Updating compounds on chromosome:{0}, type:{1}, category:{2} for case:{3}".format(
+                        chrom, var_type, category, case_id
                     )
+                )
+
+                # Fetch all variants from a chromosome
+                query = {"variant_type": var_type, "chrom": chrom}
+
+                # Get all variants from the database of the specific type
+                variant_objs = self.variants(
+                    case_id=case_id,
+                    query=query,
+                    category=category,
+                    nr_of_variants=-1,
+                    sort_key="position",
+                )
+
+                # Initiate a bulk
+                bulk = {}
+                current_region = None
+                special = False
 
-                    # Fetch all variants from a chromosome
-                    query = {"variant_type": var_type, "chrom": chrom}
+                # Loop over the variants and check if they are in a coding region
+                for var_obj in variant_objs:
+                    var_id = var_obj["_id"]
+                    var_chrom = var_obj["chromosome"]
+                    var_start = var_obj["position"]
+                    var_end = var_obj["end"] + 1
 
-                    # Get all variants from the database of the specific type
-                    variant_objs = self.variants(
-                        case_id=case_id,
-                        query=query,
-                        category=category,
-                        nr_of_variants=-1,
-                        sort_key="position",
+                    update_bulk = True
+                    new_region = None
+
+                    # Check if the variant is in a coding region
+                    genomic_regions = coding_intervals.get(var_chrom, IntervalTree()).overlap(
+                        var_start, var_end
                     )
 
-                    # Initiate a bulk
-                    bulk = {}
-                    current_region = None
-                    special = False
-
-                    # Loop over the variants and check if they are in a coding region
-                    for var_obj in variant_objs:
-                        var_id = var_obj["_id"]
-                        var_chrom = var_obj["chromosome"]
-                        var_start = var_obj["position"]
-                        var_end = var_obj["end"] + 1
-
-                        update_bulk = True
-                        new_region = None
-
-                        # Check if the variant is in a coding region
-                        genomic_regions = coding_intervals.get(var_chrom, IntervalTree()).overlap(
-                            var_start, var_end
-                        )
-
-                        # If the variant is in a coding region
-                        if genomic_regions:
-                            # We know there is data here so get the interval id
-                            new_region = genomic_regions.pop().data
-
-                        if new_region and (new_region == current_region):
-                            # If the variant is in the same region as previous
-                            # we add it to the same bulk
-                            update_bulk = False
-
-                        current_region = new_region
-
-                        # If the variant is not in a current region we update the compounds
-                        # from the previous region, if any. Otherwise continue
-                        if update_bulk and bulk:
-                            self.update_compounds(bulk)
-                            self.update_mongo_compound_variants(bulk)
-                            bulk = {}
-
-                        if new_region:
-                            bulk[var_id] = var_obj
-
-                    if not bulk:
-                        continue
-
-                    self.update_compounds(bulk)
-                    self.update_mongo_compound_variants(bulk)
+                    # If the variant is in a coding region
+                    if genomic_regions:
+                        # We know there is data here so get the interval id
+                        new_region = genomic_regions.pop().data
+
+                    if new_region and (new_region == current_region):
+                        # If the variant is in the same region as previous
+                        # we add it to the same bulk
+                        update_bulk = False
+
+                    current_region = new_region
+
+                    # If the variant is not in a current region we update the compounds
+                    # from the previous region, if any. Otherwise continue
+                    if update_bulk and bulk:
+                        self.update_compounds(bulk)
+                        self.update_mongo_compound_variants(bulk)
+                        bulk = {}
+
+                    if new_region:
+                        bulk[var_id] = var_obj
+
+                if not bulk:
+                    continue
+
+                self.update_compounds(bulk)
+                self.update_mongo_compound_variants(bulk)
 
         LOG.info("All compounds updated")
 

scout/build/genes/hgnc_gene.py

@@ -1,6 +1,5 @@
 import logging
 
-from scout.constants import GENE_CONSTRAINT_LABELS
 from scout.models.hgnc_map import HgncGene
 
 LOG = logging.getLogger(__name__)
@@ -16,137 +15,9 @@ def build_phenotype(phenotype_info):
     return phenotype_obj
 
 
-def build_hgnc_gene(gene_info, build="37"):
-    """Build a hgnc_gene object
+def build_hgnc_gene(gene_info: dict, build: bool = "37") -> dict:
+    """Build a HGNC gene object"""
 
-    Args:
-        gene_info(dict): Gene information
-
-    Returns:
-        gene_obj(dict)
-
-        {
-            '_id': ObjectId(),
-            # This is the hgnc id, required:
-            'hgnc_id': int,
-            # The primary symbol, required
-            'hgnc_symbol': str,
-            '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,
-            'transcripts': list(), # List of hgnc_transcript
-
-            # 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
-        }
-    """
-    try:
-        hgnc_id = int(gene_info["hgnc_id"])
-    except KeyError as err:
-        raise KeyError("Gene has to have a hgnc_id")
-    except ValueError as err:
-        raise ValueError("hgnc_id has to be integer")
-
-    try:
-        hgnc_symbol = gene_info["hgnc_symbol"]
-    except KeyError as err:
-        raise KeyError("Gene has to have a hgnc_symbol")
-
-    try:
-        ensembl_id = gene_info["ensembl_gene_id"]
-    except KeyError as err:
-        raise KeyError("Gene has to have a ensembl_id")
-
-    try:
-        chromosome = gene_info["chromosome"]
-    except KeyError as err:
-        raise KeyError("Gene has to have a chromosome")
-
-    try:
-        start = int(gene_info["start"])
-    except KeyError as err:
-        raise KeyError("Gene has to have a start position")
-    except TypeError as err:
-        raise TypeError("Gene start has to be a integer")
-
-    try:
-        end = int(gene_info["end"])
-    except KeyError as err:
-        raise KeyError("Gene has to have a end position")
-    except TypeError as err:
-        raise TypeError("Gene end has to be a integer")
-
-    gene_obj = HgncGene(
-        hgnc_id=hgnc_id,
-        hgnc_symbol=hgnc_symbol,
-        ensembl_id=ensembl_id,
-        chrom=chromosome,
-        start=start,
-        end=end,
-        build=build,
-    )
-
-    if gene_info.get("description"):
-        gene_obj["description"] = gene_info["description"]
-        # LOG.debug("Adding info %s", gene_info['description'])
-
-    if gene_info.get("previous_symbols"):
-        gene_obj["aliases"] = gene_info["previous_symbols"]
-
-    if gene_info.get("entrez_id"):
-        gene_obj["entrez_id"] = int(gene_info["entrez_id"])
-
-    if gene_info.get("omim_id"):
-        gene_obj["omim_id"] = int(gene_info["omim_id"])
-
-    for constraint in GENE_CONSTRAINT_LABELS.keys():
-        if gene_info.get(constraint):
-            gene_obj[constraint] = float(gene_info[constraint])
-
-    if gene_info.get("ref_seq"):
-        gene_obj["primary_transcripts"] = gene_info["ref_seq"]
-
-    if gene_info.get("ucsc_id"):
-        gene_obj["ucsc_id"] = gene_info["ucsc_id"]
-
-    if gene_info.get("uniprot_ids"):
-        gene_obj["uniprot_ids"] = gene_info["uniprot_ids"]
-
-    if gene_info.get("vega_id"):
-        gene_obj["vega_id"] = gene_info["vega_id"]
-
-    if gene_info.get("incomplete_penetrance"):
-        gene_obj["incomplete_penetrance"] = True
-
-    if gene_info.get("inheritance_models"):
-        gene_obj["inheritance_models"] = gene_info["inheritance_models"]
-
-    phenotype_objs = []
-    for phenotype_info in gene_info.get("phenotypes", []):
-        phenotype_objs.append(build_phenotype(phenotype_info))
-
-    if phenotype_objs:
-        gene_obj["phenotypes"] = phenotype_objs
-
-    for key in list(gene_obj):
-        if gene_obj[key] is None:
-            gene_obj.pop(key)
-
-    return gene_obj
+    gene_info["build"] = build
+    hgnc_gene = HgncGene(**gene_info)
+    return hgnc_gene.model_dump(exclude_none=True)

scout/commands/download/ensembl.py

@@ -1,4 +1,5 @@
 """Code for handling downloading of ensembl files used by scout from CLI"""
+
 import logging
 import pathlib
 from typing import List, Optional

scout/commands/download/everything.py

@@ -1,6 +1,7 @@
 """Code for handling downloading Download all necessary resources for scout used by scout from
 CLI
 """
+
 import logging
 import pathlib
 

scout/commands/download/exac.py

@@ -1,4 +1,5 @@
 """Code for handling downloading of the ExAC genes file used by scout from CLI"""
+
 import logging
 import pathlib
 

scout/commands/download/hgnc.py

@@ -1,4 +1,5 @@
 """Code for handling downloading of HPO files used by scout from CLI"""
+
 import logging
 import pathlib
 

scout/commands/download/hpo.py

@@ -1,4 +1,5 @@
 """Code for handling downloading of HPO files used by scout from CLI"""
+
 import logging
 import pathlib
 

scout/commands/download/omim.py

@@ -1,4 +1,5 @@
 """Code for handling downloading of HPO files used by scout from CLI"""
+
 import logging
 from pathlib import Path
 from typing import Dict

scout/commands/export/database.py

@@ -3,6 +3,7 @@
 Since the variants collection is very large this dump will be optional.
 
 """
+
 import logging
 import subprocess
 from subprocess import CalledProcessError

scout/commands/load/panel.py

@@ -1,4 +1,5 @@
 """Code for scout load panel CLI functionality"""
+
 import logging
 
 import click

scout/commands/load/report.py

@@ -1,4 +1,5 @@
 """Code for updating reports"""
+
 import logging
 
 import click

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

@@ -1,21 +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_mt": {"category": "snv", "variant_type": "clinical"},
-    "vcf_snv_research": {"category": "snv", "variant_type": "research"},
-    "vcf_snv_research_mt": {"category": "snv", "variant_type": "research"},
-    "vcf_sv": {"category": "sv", "variant_type": "clinical"},
-    "vcf_sv_mt": {"category": "sv", "variant_type": "clinical"},
-    "vcf_sv_research": {"category": "sv", "variant_type": "research"},
-    "vcf_sv_research_mt": {"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/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__)
 
@@ -62,7 +63,10 @@ def load_region(adapter, case_id, hgnc_id=None, chrom=None, start=None, end=None
                 (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
 

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))