scout-browser 4.101.0__py3-none-any.whl → 4.103.0__py3-none-any.whl

scout/commands/update/user.py

@@ -1,72 +1,110 @@
 import logging
+from typing import List, Optional, Tuple
 
 import click
 from flask.cli import with_appcontext
 
+from scout.adapter import MongoAdapter
 from scout.server.extensions import store
 
 LOG = logging.getLogger(__name__)
+USER_ROLES = ["admin", "mme_submitter", "beacon_submitter"]
 
 
 @click.command("user", short_help="Update a user")
-@click.option("--user-id", "-u", help="A email adress that identifies the user", required=True)
-@click.option(
-    "--update-role",
-    "-r",
-    # There will be more roles in the future
-    type=click.Choice(["admin", "mme_submitter", "beacon_submitter"]),
-    help="Add a role to the user",
-)
-@click.option("--remove-admin", is_flag=True, help="Remove admin rights from user")
-@click.option("--add-institute", "-i", multiple=True, help="Specify the institutes to add")
-@click.option("--remove-institute", multiple=True, help="Specify the institutes to remove")
+@click.option("--user-id", "-u", required=True, help="An email address that identifies the user")
+@click.option("--update-role", "-r", type=click.Choice(USER_ROLES), help="Add a role to the user")
+@click.option("--remove-admin", is_flag=True, help="(Deprecated) Remove admin role from the user")
+@click.option("--remove-role", multiple=True, help="Specify roles to remove from the user")
+@click.option("--add-institute", "-i", multiple=True, help="Specify institutes to add")
+@click.option("--remove-institute", multiple=True, help="Specify institutes to remove")
 @with_appcontext
-def user(user_id, update_role, add_institute, remove_admin, remove_institute):
-    """
-    Update a user in the database
-    """
+def user(
+    user_id: str,
+    update_role: Optional[str],
+    remove_admin: bool,
+    remove_role: Tuple[str, ...],
+    add_institute: Tuple[str, ...],
+    remove_institute: Tuple[str, ...],
+) -> None:
+    """Update roles and institutes for a user in the database."""
     adapter = store
-
     user_obj = adapter.user(user_id)
-
     if not user_obj:
         LOG.warning("User %s could not be found", user_id)
         raise click.Abort()
 
-    existing_roles = set(user_obj.get("roles", []))
-    if update_role:
-        if not update_role in user_obj["roles"]:
-            existing_roles = set(user_obj["roles"])
-            existing_roles.add(update_role)
-            LOG.info("Adding role %s to user", update_role)
+    user_obj["roles"] = process_roles(
+        current_roles=user_obj.get("roles", []),
+        add_role=update_role,
+        remove_roles=remove_role,
+        remove_admin=remove_admin,
+        user_id=user_id,
+    )
+    user_obj["institutes"] = process_institutes(
+        current_institutes=user_obj.get("institutes", []),
+        add_institutes=add_institute,
+        remove_institutes=remove_institute,
+        adapter=adapter,
+        user_id=user_id,
+    )
+    adapter.update_user(user_obj)
+
+
+def process_roles(
+    current_roles: List[str],
+    add_role: Optional[str],
+    remove_roles: Tuple[str, ...],
+    remove_admin: bool,
+    user_id: str,
+) -> List[str]:
+    """Define the list of roles for a user in the database."""
+    roles = set(current_roles)
+
+    if add_role:
+        if add_role in roles:
+            LOG.warning("User already has role '%s'", add_role)
         else:
-            LOG.warning("User already have role %s", update_role)
-
-    if remove_admin:
-        try:
-            existing_roles.remove("admin")
-            LOG.info("Removing admin rights from user %s", user_id)
-        except KeyError as err:
-            LOG.info("User %s does not have admin rights", user_id)
-
-    user_obj["roles"] = list(existing_roles)
-
-    existing_institutes = set(user_obj.get("institutes", []))
-    for institute_id in add_institute:
-        institute_obj = adapter.institute(institute_id)
-        if not institute_obj:
-            LOG.warning("Institute %s could not be found", institute_id)
+            roles.add(add_role)
+            LOG.info("Adding role '%s' to user '%s'", add_role, user_id)
+
+    all_remove = set(remove_roles)
+    if remove_admin and "admin" not in all_remove:
+        click.echo("⚠️ --remove-admin is deprecated. Use --remove-role admin instead.")
+        all_remove.add("admin")
+
+    for role in all_remove:
+        if role in roles:
+            roles.remove(role)
+            LOG.info("Removing role '%s' from user '%s'", role, user_id)
         else:
-            existing_institutes.add(institute_id)
-            LOG.info("Adding institute %s to user", institute_id)
+            LOG.info("User does not have role '%s'", role)
 
-    for institute_id in remove_institute:
-        try:
-            existing_institutes.remove(institute_id)
-            LOG.info("Removing institute %s from user", institute_id)
-        except KeyError as err:
-            LOG.info("User does not have access to institute %s", institute_id)
+    return list(roles)
 
-    user_obj["institutes"] = list(existing_institutes)
 
-    adapter.update_user(user_obj)
+def process_institutes(
+    current_institutes: List[str],
+    add_institutes: Tuple[str, ...],
+    remove_institutes: Tuple[str, ...],
+    adapter: MongoAdapter,
+    user_id: str,
+) -> List[str]:
+    """Define the list of institutes for a user in the database."""
+    institutes = set(current_institutes)
+
+    for inst in add_institutes:
+        if adapter.institute(inst):
+            institutes.add(inst)
+            LOG.info("Adding institute '%s' to user '%s'", inst, user_id)
+        else:
+            LOG.warning("Institute '%s' could not be found", inst)
+
+    for inst in remove_institutes:
+        if inst in institutes:
+            institutes.remove(inst)
+            LOG.info("Removing institute '%s' from user '%s'", inst, user_id)
+        else:
+            LOG.info("User does not have access to institute '%s'", inst)
+
+    return list(institutes)

scout/constants/__init__.py

@@ -36,6 +36,7 @@ from .clinvar import (
     CONDITION_PREFIX,
     GERMLINE_CLASSIF_TERMS,
     MULTIPLE_CONDITION_EXPLANATION,
+    ONCOGENIC_CLASSIF_TERMS,
 )
 from .clnsig import CLINSIG_MAP, ONC_CLNSIG, REV_CLINSIG_MAP, TRUSTED_REVSTAT_LEVEL
 from .disease_parsing import (
@@ -78,6 +79,7 @@ from .indexes import ID_PROJECTION, INDEXES
 from .panels import PANELAPP_CONFIDENCE_EXCLUDE
 from .phenotype import (
     COHORT_TAGS,
+    HPO_LINK_URL,
     HPO_URL,
     HPOTERMS_URL,
     ORPHA_URLS,
@@ -99,8 +101,10 @@ from .variant_tags import (
     MANUAL_RANK_OPTIONS,
     MOSAICISM_OPTIONS,
     OUTLIER_TYPES,
+    REVEL_SCORE_LABEL_COLOR_MAP,
     SPIDEX_HUMAN,
     SPIDEX_LEVELS,
+    SPLICEAI_SCORE_LABEL_COLOR_MAP,
     SV_TYPES,
     VARIANT_CALL,
     VARIANT_FILTERS,

scout/constants/clinvar.py

@@ -1,8 +1,12 @@
+from scout.constants.clnsig import ONC_CLNSIG
+
 CLINVAR_API_URL_DEFAULT = "https://submit.ncbi.nlm.nih.gov/api/v1/submissions/"
 PRECLINVAR_URL = "https://preclinvar.scilifelab.se"
 
 ASSERTION_METHOD = "ACMG Guidelines, 2015"
 ASSERTION_METHOD_CIT = "PMID:25741868"
+ASSERTION_ONC_ONC_DB = "PubMed"
+ASSERTION_CRITERIA_ONC_ID = "36063163"
 NOT_PROVIDED = "not provided"
 
 # Header used to create the Variant .CSV file for the manual ClinVar submission
@@ -95,6 +99,8 @@ GERMLINE_CLASSIF_TERMS = [
     NOT_PROVIDED,
 ]
 
+ONCOGENIC_CLASSIF_TERMS = ONC_CLNSIG
+
 REVSTAT_TERMS = {
     "conflicting_interpretations",
     "multiple_submitters",
@@ -187,6 +193,10 @@ CONDITION_PREFIX = {
     "Orphanet": "ORPHA",
 }
 
+CONDITION_DBS_API = ["HP", "MedGen", "MeSH", "MONDO", "OMIM", "Orphanet"]
+
 CLINVAR_ASSERTION_METHOD_CIT_DB_OPTIONS = {"DOI", "pmc", "PMID"}
+CITATION_DBS_API = ["PubMed", "BookShelf", "DOI", "pmc"]
 
 MULTIPLE_CONDITION_EXPLANATION = ["Novel disease", "Uncertain", "Co-occurring"]
+PRESENCE_IN_NORMAL_TISSUE = ["present", "absent", "not tested"]

scout/constants/igv_tracks.py

@@ -4,11 +4,15 @@ HG19REF_URL = (
 )
 HG19REF_INDEX_URL = "https://s3.amazonaws.com/igv.broadinstitute.org/genomes/seq/1kg_v37/human_g1k_v37_decoy.fasta.fai"
 HG19CYTOBAND_URL = "https://raw.githubusercontent.com/Clinical-Genomics/reference-files/refs/heads/master/rare-disease/region/grch37_cytoband.bed"
-HG19ALIAS_URL = "https://igv.org/genomes/data/hg19/hg19_alias.tab"
+HG19ALIAS_URL = (
+    "https://raw.githubusercontent.com/igvteam/igv-data/refs/heads/main/data/hg19/hg19_alias.tab"
+)
 
 HG38REF_URL = "https://s3.amazonaws.com/igv.broadinstitute.org/genomes/seq/hg38/hg38.fa"
 HG38REF_INDEX_URL = "https://s3.amazonaws.com/igv.broadinstitute.org/genomes/seq/hg38/hg38.fa.fai"
-HG38ALIAS_URL = "https://igv.org/genomes/data/hg38/hg38_alias.tab"
+HG38ALIAS_URL = (
+    "https://raw.githubusercontent.com/igvteam/igv-data/refs/heads/main/data/hg38/hg38_alias.tab"
+)
 HG38CYTOBAND_URL = "https://igv-genepattern-org.s3.amazonaws.com/genomes/hg38/cytoBandIdeo.txt.gz"
 
 HG38GENES_URL = "https://hgdownload.soe.ucsc.edu/goldenPath/hg38/database/ncbiRefSeq.txt.gz"

scout/constants/phenotype.py

@@ -2,6 +2,7 @@ HPO_URL = "http://purl.obolibrary.org/obo/hp/hpoa/{}"
 HPOTERMS_URL = (
     "https://raw.githubusercontent.com/obophenotype/human-phenotype-ontology/master/hp.obo"
 )
+HPO_LINK_URL = "https://hpo.jax.org/browse/term/"
 
 ORPHA_URLS = {
     "orpha_to_hpo": "https://www.orphadata.com/data/xml/en_product4.xml",

scout/constants/variant_tags.py

@@ -19,6 +19,22 @@ CONSERVATION = {
     "phylop": {"conserved_min": 2.5, "conserved_max": 100},
 }
 
+REVEL_SCORE_LABEL_COLOR_MAP = {
+    (0.932, 1.000): {"label": "Strong pathogenic", "color": "danger"},
+    (0.773, 0.932): {"label": "Moderate pathogenic", "color": "red"},
+    (0.644, 0.773): {"label": "Supporting pathogenic", "color": "orange"},
+    (0.290, 0.644): {"label": "Uncertain significance", "color": "secondary"},
+    (0.183, 0.290): {"label": "Supporting benign", "color": "info"},
+    (0.016, 0.183): {"label": "Moderate benign", "color": "info"},
+    (0.0, 0.016): {"label": "Strong to very strong benign", "color": "success"},
+}
+
+SPLICEAI_SCORE_LABEL_COLOR_MAP = {
+    (0.20, 1.00): {"label": "Predicted impact on splicing", "color": "warning"},
+    (0.10, 0.20): {"label": "Not informative", "color": "secondary"},
+    (0.00, 0.10): {"label": "No impact on splicing", "color": "success"},
+}
+
 FEATURE_TYPES = (
     "exonic",
     "splicing",
@@ -535,6 +551,7 @@ CALLERS = {
         {"id": "deepvariant", "name": "DeepVariant"},
         _FREEBAYES,
         _GATK,
+        {"id": "mutect2", "name": "MuTect2"},
         {"id": "samtools", "name": "SAMtools"},
     ],
     "cancer": [
@@ -562,6 +579,7 @@ CALLERS = {
         {"id": "cnvpytor", "name": "CNVpytor"},
         {"id": "delly", "name": "Delly"},
         _GATK,
+        {"id": "gcnvcaller", "name": "GATK GermlineCNV"},
         {"id": "hificnv", "name": "HiFiCNV"},
         _MANTA,
         {"id": "severus", "name": "Severus"},

scout/demo/__init__.py

@@ -25,6 +25,7 @@ gene_fusion_report_path = str(files(BASE_PATH).joinpath("draw-fusions-example.pd
 clinical_snv_path = str(files(BASE_PATH).joinpath("643594.clinical.vcf.gz"))
 clinical_sv_path = str(files(BASE_PATH).joinpath("643594.clinical.SV.vcf.gz"))
 clinical_str_path = str(files(BASE_PATH).joinpath("643594.clinical.str.stranger.vcf.gz"))
+str_trgt_path = str(files(BASE_PATH).joinpath("NIST.trgt.stranger.vcf.gz"))
 clinical_fusion_path = str(files(BASE_PATH).joinpath("fusion_data.vcf"))
 customannotation_snv_path = str(files(BASE_PATH).joinpath("customannotations_one.vcf.gz"))
 vep_97_annotated_path = str(

scout/load/hpo.py

@@ -1,6 +1,6 @@
 import logging
 from datetime import datetime
-from typing import Dict, Iterable, Optional
+from typing import Iterable, Optional
 
 from click import progressbar
 
@@ -45,7 +45,13 @@ def load_hpo_terms(
         if not gene_info:
             continue
 
-        hgnc_id = gene_info["true"]
+        if gene_info["true"] is not None:
+            hgnc_id = gene_info["true"]
+        elif len(gene_info["ids"]) == 1:
+            # unique aliases can be used
+            hgnc_id = list(gene_info["ids"])[0]
+        else:
+            continue
 
         if hpo_id not in hpo_terms:
             continue

scout/models/clinvar.py

@@ -1,6 +1,12 @@
 from datetime import date, datetime
+from enum import Enum
+from typing import List, Literal, Optional
 
 from bson.objectid import ObjectId
+from pydantic import BaseModel
+
+from scout.constants import CHROMOSOMES
+from scout.constants.clinvar import CITATION_DBS_API, ONCOGENIC_CLASSIF_TERMS
 
 """Model of the document that gets saved/updated in the clinvar_submission collection
  for each institute that has cases with ClinVar submission objects"""
@@ -76,3 +82,83 @@ clinvar_casedata = {
     "method_purpose": str,  # default: "discovery"
     "reported_at": date,
 }
+
+### Models used for oncogenocity submissions via API
+
+
+CitationDB = Enum("CitationDB", {db.upper(): db for db in CITATION_DBS_API})
+OncogenicityClassificationDescription = Enum(
+    "OncogenicityClassificationDescription",
+    {term.upper().replace(" ", "_"): term for term in ONCOGENIC_CLASSIF_TERMS},
+)
+
+
+class Citation(BaseModel):
+    db: CitationDB
+    id: str
+
+
+class OncogenicityClassification(BaseModel):
+    oncogenicityClassificationDescription: OncogenicityClassificationDescription
+    dateLastEvaluated: str
+    comment: Optional[str] = None
+    citation: Optional[List[Citation]] = None
+
+
+class ObservedIn(BaseModel):
+    alleleOrigin: str
+    affectedStatus: str
+    collectionMethod: str
+    numberOfIndividuals: int
+    presenceOfSomaticVariantInNormalTissue: str
+    somaticVariantAlleleFraction: Optional[float] = None
+
+
+class Gene(BaseModel):
+    symbol: str
+
+
+Chromosome = Enum(
+    "Chromosome", {c: c for c in CHROMOSOMES}
+)  # ClinVar API accepts only 'MT' chromosome
+
+
+class Variant(BaseModel):
+    """It's defined by either coordinates or hgvs."""
+
+    alternateAllele: Optional[str] = None
+    assembly: Optional[Literal["GRCh37", "GRCh38"]] = None
+    chromosome: Optional[Chromosome] = None
+    gene: Optional[List[Gene]] = None
+    hgvs: Optional[str] = None
+    start: Optional[int] = None
+    stop: Optional[int] = None
+
+
+class VariantSet(BaseModel):
+    variant: List[Variant]
+
+
+class Condition(BaseModel):
+    db: Optional[str] = None
+    id: Optional[str] = None
+    name: Optional[str] = None
+
+
+class ConditionSet(BaseModel):
+    condition: List[Condition]
+
+
+class OncogenicitySubmissionItem(BaseModel):
+    # Field necessary for the API submissions:
+    recordStatus: str
+    oncogenicityClassification: OncogenicityClassification
+    observedIn: List[ObservedIn]
+    variantSet: VariantSet
+    conditionSet: ConditionSet
+
+    # Fields necessary to map the variant to a variant in Scout:
+    institute_id: str
+    case_id: str
+    case_name: str
+    variant_id: str

scout/parse/variant/coordinates.py

@@ -1,6 +1,6 @@
 """Code to parse variant coordinates"""
 
-from scout.constants import BND_ALT_PATTERN, CHR_PATTERN, CYTOBANDS_37, CYTOBANDS_38
+from scout.constants import BND_ALT_PATTERN, CHR_PATTERN, CYTOBANDS_37, CYTOBANDS_38, SV_TYPES
 
 
 def get_cytoband_coordinates(chrom, pos, build):
@@ -144,6 +144,10 @@ def parse_coordinates(variant, category, build="37"):
         svtype = variant.INFO.get("SVTYPE")
         if svtype:
             svtype = svtype.lower()
+        else:
+            alt_type = alt.lstrip("<").rstrip(">").lower()
+            if alt_type in SV_TYPES:
+                svtype = alt_type
         sub_category = svtype
         if sub_category == "bnd":
             end_chrom = get_end_chrom(alt, chrom)

scout/parse/variant/gene.py

@@ -48,10 +48,6 @@ def parse_genes(transcripts):
     # List with all genes and their transcripts
     genes = []
 
-    hgvs_identifier = None
-    canonical_transcript = None
-    exon = None
-
     # Loop over all genes
     for gene_id in genes_to_transcripts:
         # Get the transcripts for a gene
@@ -78,8 +74,7 @@ def parse_genes(transcripts):
             hgnc_symbol = transcript["hgnc_symbol"]
             if not hgvs_identifier:
                 hgvs_identifier = transcript.get("coding_sequence_name")
-            if not canonical_transcript:
-                canonical_transcript = transcript["transcript_id"]
+
             if not exon:
                 exon = transcript["exon"]
 
@@ -102,10 +97,11 @@ def parse_genes(transcripts):
                 most_severe_spliceai_position = transcript["spliceai_delta_position"]
                 spliceai_prediction = transcript["spliceai_prediction"]
 
-            if transcript["is_canonical"] and transcript.get("coding_sequence_name"):
-                hgvs_identifier = transcript.get("coding_sequence_name")
+            if transcript["is_canonical"]:
                 canonical_transcript = transcript["transcript_id"]
-                exon = transcript["exon"]
+                if transcript.get("coding_sequence_name"):
+                    hgvs_identifier = transcript.get("coding_sequence_name")
+                    exon = transcript["exon"]
 
         gene = {
             "transcripts": gene_transcripts,