scout-browser 4.92__py3-none-any.whl → 4.95.0__py3-none-any.whl

scout/constants/__init__.py

@@ -23,6 +23,7 @@ from .case_tags import (
     VERBS_ICONS_MAP,
     VERBS_MAP,
 )
+from .ccv import CCV_COMPLETE_MAP, CCV_CRITERIA, CCV_MAP, CCV_OPTIONS, REV_CCV_MAP
 from .clinvar import (
     AFFECTED_STATUS,
     ALLELE_OF_ORIGIN,
@@ -126,6 +127,7 @@ COLLECTIONS = [
     "disease_term",
     "variant",
     "acmg",
+    "ccv",
 ]
 
 BUILDS = ["37", "38", "GRCh38"]

scout/constants/case_tags.py

@@ -43,6 +43,7 @@ CASE_REPORT_VARIANT_TYPES = {
     "partial_causatives_detailed": "partial_causatives",
     "suspects_detailed": "suspects",
     "classified_detailed": "acmg_classification",
+    "ccv_classified_detailed": "ccv_classification",
     "tagged_detailed": "manual_rank",
     "tier_detailed": "cancer_tier",
     "dismissed_detailed": "dismiss_variant",
@@ -105,6 +106,7 @@ CASE_TAGS = {
 
 VERBS_MAP = {
     "acmg": "updated ACMG classification for",
+    "ccv": "updated ClinGen-CGC-VIGG classification for",
     "add_case": "added case",
     "add_cohort": "updated cohort for",
     "add_phenotype": "added HPO term for",

scout/constants/ccv.py

@@ -0,0 +1,244 @@
+# -*- coding: utf-8 -*-
+from collections import OrderedDict
+
+# from worst to most certain benign
+CCV_MAP = OrderedDict(
+    [
+        (4, "oncogenic"),
+        (3, "likely_oncogenic"),
+        (0, "uncertain_significance"),
+        (2, "likely_benign"),
+        (1, "benign"),
+    ]
+)
+# <a href="https://cancerhotspots.org" target="_blank">cancerhotspots.org</a>
+REV_CCV_MAP = OrderedDict([(value, key) for key, value in CCV_MAP.items()])
+
+CCV_OPTIONS = [
+    {"code": "oncogenic", "short": "O", "label": "Oncogenic", "color": "danger"},
+    {
+        "code": "likely_oncogenic",
+        "short": "LO",
+        "label": "Likely Oncogenic",
+        "color": "warning",
+    },
+    {
+        "code": "uncertain_significance",
+        "short": "VUS",
+        "label": "Uncertain Significance",
+        "color": "primary",
+    },
+    {"code": "likely_benign", "short": "LB", "label": "Likely Benign", "color": "info"},
+    {"code": "benign", "short": "B", "label": "Benign", "color": "success"},
+]
+
+CCV_COMPLETE_MAP = OrderedDict([(option["code"], option) for option in CCV_OPTIONS])
+
+CCV_CRITERIA = OrderedDict()
+
+CCV_CRITERIA["oncogenicity"] = OrderedDict(
+    [
+        (
+            "Very Strong",
+            OrderedDict(
+                [
+                    (
+                        "OVS1",
+                        {
+                            "short": "Null variant in tumor supressor",
+                            "description": "Null variant (nonsense, frameshift, canonical ±1 or 2 splice sites, initiation codon, single-exon or multiexon deletion) in a bona fide tumor suppressor gene.",
+                            "documentation": 'Strength can be modified based on <a href="https://pubmed.ncbi.nlm.nih.gov/30192042/" target="blank">ClinGen’s recommendations for PVS1</a>',
+                        },
+                    )
+                ]
+            ),
+        ),
+        (
+            "Strong",
+            OrderedDict(
+                [
+                    (
+                        "OS1",
+                        {
+                            "short": "Same aa change as known oncogenic variant",
+                            "description": "Same amino acid change as a previously established oncogenic variant (using this standard) regardless of nucleotide change.",
+                        },
+                    ),
+                    (
+                        "OS2",
+                        {
+                            "short": "Well-established functional studies",
+                            "description": "Well-established in vitro or in vivo functional studies, supportive of an oncogenic effect of the variant.",
+                        },
+                    ),
+                    (
+                        "OS3",
+                        {
+                            "short": "Cancer hotspot: high frequency",
+                            "description": "Located in one of the hotspots in cancerhotspots.org with at least 50 samples with a somatic variant at the same amino acid position, and the same amino acid change count in cancerhotspots.org in at least 10 samples.",
+                        },
+                    ),
+                ]
+            ),
+        ),
+        (
+            "Moderate",
+            OrderedDict(
+                [
+                    (
+                        "OM1",
+                        {
+                            "short": "Functional domain",
+                            "description": "Located in a critical and well-established part of a functional domain (eg, active site of an enzyme).",
+                        },
+                    ),
+                    (
+                        "OM2",
+                        {
+                            "short": "Protein length change",
+                            "description": "Protein length changes as a result of in-frame deletions/insertions in a known oncogene or tumor suppressor gene or stop-loss variants in a known tumor suppressor gene.",
+                        },
+                    ),
+                    (
+                        "OM3",
+                        {
+                            "short": "Cancer hotspot: moderate frequency",
+                            "description": "Located in one of the hotspots in cancerhotspots.org with <50 samples with a somatic variant at the same amino acid position, and the same amino acid change count in cancerhotspots.org is at least 10.",
+                        },
+                    ),
+                    (
+                        "OM4",
+                        {
+                            "short": "Missense variant at aa with other oncogenic missense variant",
+                            "description": "Missense variant at an amino acid residue where a different missense variant determined to be oncogenic (using this standard) has been documented. Amino acid difference from reference amino acid should be greater or at least approximately the same as for missense change determined to be oncogenic.",
+                        },
+                    ),
+                ]
+            ),
+        ),
+        (
+            "Supporting",
+            OrderedDict(
+                [
+                    (
+                        "OP1",
+                        {
+                            "short": "Computatinal evidence",
+                            "description": "All used lines of computational evidence support an oncogenic effect of a variant (conservation/evolutionary, splicing effect, etc.).",
+                        },
+                    ),
+                    (
+                        "OP2",
+                        {
+                            "short": "Gene in a malignancy with a single genetic etiology",
+                            "description": "Somatic variant in a gene in a malignancy with a single genetic etiology. Example: retinoblastoma is caused by bi-allelic RB1 inactivation.",
+                        },
+                    ),
+                    (
+                        "OP3",
+                        {
+                            "short": "Cancer hotspots: low frequency",
+                            "description": "Located in one of the hotspots in cancerhotspots.org and the particular amino acid change count in cancerhotspots.org is below 10",
+                        },
+                    ),
+                    (
+                        "OP4",
+                        {
+                            "short": "Absent in population databases",
+                            "description": "Absent from controls (or at an extremely low frequency) in gnomAD.",
+                        },
+                    ),
+                ]
+            ),
+        ),
+    ]
+)
+
+CCV_CRITERIA["benign impact"] = OrderedDict(
+    [
+        (
+            "Very Strong",
+            OrderedDict(
+                [
+                    (
+                        "SBVS1",
+                        {
+                            "short": "MAF is >0.05",
+                            "description": "Minor allele frequency is >5%% in gnomAD in any 5 general continental populations: African, East Asian, European (non-Finnish), Latino, and South Asian.",
+                        },
+                    )
+                ]
+            ),
+        ),
+        (
+            "Strong",
+            OrderedDict(
+                [
+                    (
+                        "SBS1",
+                        {
+                            "short": "MAF is >0.01",
+                            "description": "Minor allele frequency is >1%% in gnomAD in any 5 general continental populations: African, East Asian, European (non-Finnish), Latino, and South Asian.	",
+                        },
+                    ),
+                    (
+                        "SBS2",
+                        {
+                            "short": "Well-established functional studies",
+                            "description": "Well-established in vitro or in vivo functional studies show no oncogenic effects.",
+                        },
+                    ),
+                ]
+            ),
+        ),
+        (
+            "Supporting",
+            OrderedDict(
+                [
+                    (
+                        "SBP1",
+                        {
+                            "short": "Computational evidence",
+                            "description": "All used lines of computational evidence suggest no effect of a variant (conservation/evolutionary, splicing effect, etc.).",
+                        },
+                    ),
+                    (
+                        "SBP2",
+                        {
+                            "short": "Silent mutation (no predicted impact on splicing)",
+                            "description": "A synonymous (silent) variant for which splicing prediction algorithms predict no effect on the splice consensus sequence nor the creation of a new splice site and the nucleotide is not highly conserved.",
+                        },
+                    ),
+                ]
+            ),
+        ),
+    ]
+)
+
+CCV_POTENTIAL_CONFLICTS = [
+    (
+        "OS2",
+        "OS1",
+        "If OS1 is applicable, OS2 can be used only if functional studies are based on the particular nucleotide change of the variant.",
+    ),
+    (
+        "OS3",
+        "OS1",
+        "OS3 cannot be used if OS1 is applicable, unless it is possible to observe hotspots on the basis of the particular nucleotide change.",
+    ),
+    (
+        "OM1",
+        "OVS1",
+        "OM1 cannot be used if OVS1 is applicable.",
+    ),
+    (
+        "OM3",
+        "OM1",
+        "OM3 cannot be used if OM1 is applicable.",
+    ),
+    (
+        "OM3",
+        "OM4",
+        "OM3 cannot be used if OM4 is applicable.",
+    ),
+]

scout/constants/gene_tags.py

@@ -33,20 +33,30 @@ INHERITANCE_PALETTE = {
     "other": {"bgcolor": "bg-light", "text_color": "text-dark"},
 }
 
-INCOMPLETE_PENETRANCE_MAP = {"unknown": None, "Complete": None, "Incomplete": True}
+INCOMPLETE_PENETRANCE_MAP = {"unknown": None, "None": None, "Complete": False, "Incomplete": True}
 
 MODELS_MAP = {
-    "monoallelic_not_imprinted": ["AD"],
-    "monoallelic_maternally_imprinted": ["AD"],
-    "monoallelic_paternally_imprinted": ["AD"],
-    "monoallelic": ["AD"],
-    "biallelic": ["AR"],
-    "monoallelic_and_biallelic": ["AD", "AR"],
-    "monoallelic_and_more_severe_biallelic": ["AD", "AR"],
-    "xlinked_biallelic": ["XR"],
-    "xlinked_monoallelic": ["XD"],
-    "mitochondrial": ["MT"],
-    "unknown": [],
+    "MONOALLELIC, autosomal or pseudoautosomal, NOT imprinted": ["AD"],
+    "MONOALLELIC, autosomal or pseudoautosomal, imprinted status unknown": ["AD"],
+    "MONOALLELIC, autosomal or pseudoautosomal, maternally imprinted (paternal allele expressed)": [
+        "AD"
+    ],
+    "MONOALLELIC, autosomal or pseudoautosomal, paternally imprinted (maternal allele expressed)": [
+        "AD"
+    ],
+    "BIALLELIC, autosomal or pseudoautosomal": ["AR"],
+    "BOTH monoallelic and biallelic, autosomal or pseudoautosomal": ["AD", "AR"],
+    "BOTH monoallelic and biallelic (but BIALLELIC mutations cause a more SEVERE disease form), autosomal or pseudoautosomal": [
+        "AD",
+        "AR",
+    ],
+    "X-LINKED: hemizygous mutation in males, biallelic mutations in females": ["XR"],
+    "X-LINKED: hemizygous mutation in males, monoallelic mutations in females may cause disease (may be less severe, later onset than males)": [
+        "XD"
+    ],
+    "MITOCHONDRIAL": ["MT"],
+    "Other": [],
+    "Other - please specifiy in evaluation comments": [],
 }
 
 PANEL_GENE_INFO_TRANSCRIPTS = [

scout/demo/643594.config.yaml

@@ -113,8 +113,8 @@ custom_images:
         path: scout/demo/images/custom_images/640x480_one.png
       - title: A jpg image
         description: A very good description
-        width: 500
-        path: scout/demo/images/custom_images/640x480_two.jpg
+        width: 1300
+        path: scout/demo/images/custom_images/1300x1000.jpg
     section_two:
       - title: An SVG image
         description: Another very good description

scout/load/panelapp.py

@@ -1,9 +1,9 @@
 import logging
 import math
 from datetime import datetime
-from typing import Dict, List, Set
+from typing import List, Set
 
-from click import Abort, progressbar
+from click import progressbar
 
 from scout.adapter import MongoAdapter
 from scout.constants.panels import PRESELECTED_PANELAPP_PANEL_TYPE_SLUGS
@@ -28,15 +28,11 @@ def load_panelapp_panel(
         LOG.info("Fetching all panel app panels")
         panel_ids: List[str] = panelapp.get_panel_ids(signed_off=False)
 
-    ensembl_id_to_hgnc_id_map: Dict[str, int] = adapter.ensembl_to_hgnc_id_mapping()
-    hgnc_symbol_to_ensembl_id_map: Dict[int, str] = adapter.hgnc_symbol_ensembl_id_mapping()
-
-    for _ in panel_ids:
+    for panel_id in panel_ids:
         panel_info: dict = panelapp.get_panel(panel_id)
         parsed_panel = parse_panelapp_panel(
+            hgnc_gene_ids=adapter.hgnc_ids(),
             panel_info=panel_info,
-            ensembl_id_to_hgnc_id_map=ensembl_id_to_hgnc_id_map,
-            hgnc_symbol_to_ensembl_id_map=hgnc_symbol_to_ensembl_id_map,
             institute=institute,
             confidence=confidence,
         )
@@ -54,8 +50,6 @@ def get_panelapp_genes(
     """Parse and collect genes from one or more panelApp panels."""
 
     genes = set()
-    ensembl_id_to_hgnc_id_map: Dict[str, int] = adapter.ensembl_to_hgnc_id_mapping()
-    hgnc_symbol_to_ensembl_id_map: Dict[int, str] = adapter.hgnc_symbol_ensembl_id_mapping()
 
     with progressbar(panel_ids, label="Parsing panels", length=len(panel_ids)) as panel_ids:
         for panel_id in panel_ids:
@@ -66,9 +60,8 @@ def get_panelapp_genes(
                 continue
 
             parsed_panel = parse_panelapp_panel(
+                hgnc_gene_ids=adapter.hgnc_ids(),
                 panel_info=panel_dict,
-                ensembl_id_to_hgnc_id_map=ensembl_id_to_hgnc_id_map,
-                hgnc_symbol_to_ensembl_id_map=hgnc_symbol_to_ensembl_id_map,
                 institute=institute,
                 confidence="green",
             )
@@ -86,6 +79,8 @@ def load_panelapp_green_panel(adapter: MongoAdapter, institute: str, force: bool
         """Translate panel type input from users to panel type slugs."""
         if not types_filter:
             return PRESELECTED_PANELAPP_PANEL_TYPE_SLUGS
+        if "all" in types_filter:
+            return available_types
         index_list = [int(typeint) - 1 for typeint in types_filter.replace(" ", "").split(",")]
         return [available_types[i] for i in index_list]
 
@@ -107,6 +102,7 @@ def load_panelapp_green_panel(adapter: MongoAdapter, institute: str, force: bool
     available_types: List[str] = panelapp.get_panel_types()
     for number, type in enumerate(available_types, 1):
         LOG.info(f"{number}: {type}")
+    LOG.info("all: all types above")
     preselected_options_idx: List[str] = [
         str(available_types.index(presel) + 1)
         for presel in PRESELECTED_PANELAPP_PANEL_TYPE_SLUGS

scout/models/ccv_evaluation.py

@@ -0,0 +1,26 @@
+# -*- coding: utf-8 -*-
+"""
+scout.models.ccv_evaluation
+~~~~~~~~~~~~~~~~~~
+
+Define a document to describe a ClinGen-CGC-VIGG evaluation
+
+Evaluations are stored in its own collection
+
+"""
+
+from datetime import datetime
+
+ccv_evaluation = dict(
+    variant_specific=str,  # md5 document id
+    variant_id=str,  # md5 variant id
+    institute_id=str,  # Institute _id, required
+    case_id=str,  # case_id, required
+    classification=str,  # What did the evaluation end up in?
+    # All evaluations will have an author
+    user_id=str,  # user email, required
+    user_name=str,  # user name
+    criteria=list,  # List of dictionaries with criterias
+    # timestamps
+    created_at=datetime,
+)

scout/models/variant/variant.py

@@ -94,6 +94,7 @@ variant = dict(
     manual_rank=int,  # choices=[0, 1, 2, 3, 4, 5]
     dismiss_variant=list,
     acmg_classification=str,  # choices=ACMG_TERMS
+    ccv_classification=str,  # choices=CCV_TERMS
 )
 
 compound = dict(

scout/parse/omim.py

@@ -311,7 +311,6 @@ def get_mim_genes(genemap_lines, mim2gene_lines):
         mim_number = entry["mim_number"]
         inheritance = entry["inheritance"]
         phenotype_info = entry["phenotypes"]
-        hgnc_symbol = entry["hgnc_symbol"]
         hgnc_symbols = entry["hgnc_symbols"]
         if mim_number in genes:
             genes[mim_number]["inheritance"] = inheritance
@@ -354,11 +353,11 @@ def get_mim_disease(genemap_lines: Iterable[str]) -> Dict[str, Any]:
     """
     diseases_found = {}
 
-    # Genemap is a file with one entry per gene.
-    # Each line hold a lot of information and in specific it
-    # has information about the phenotypes that a gene is associated with
-    # From this source we collect inheritane patterns and what hgnc symbols
-    # a disease is associated with
+    # Genemap2 is a file with one entry per gene.
+    # Each line hold a lot of information and in particular it
+    # has information about the phenotypes that a gene is associated with.
+    # From this source we collect inheritance patterns and what hgnc symbols
+    # a disease is associated with.
     for entry in parse_genemap2(genemap_lines):
         hgnc_symbol = entry["hgnc_symbol"]
         for disease in entry["phenotypes"]:

scout/parse/panelapp.py

@@ -1,7 +1,7 @@
 """Code to parse panel information"""
 
 import logging
-from typing import Dict, Optional
+from typing import Optional, Set
 
 from scout.constants import INCOMPLETE_PENETRANCE_MAP, MODELS_MAP, PANELAPP_CONFIDENCE_EXCLUDE
 from scout.utils.date import get_date
@@ -11,9 +11,8 @@ PANELAPP_PANELS_URL = "https://panelapp.genomicsengland.co.uk/panels/"
 
 
 def parse_panel_app_gene(
+    hgnc_gene_ids: Set[int],
     panelapp_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."""
@@ -23,55 +22,30 @@ def parse_panel_app_gene(
     if confidence_level in PANELAPP_CONFIDENCE_EXCLUDE[confidence]:
         return gene_info
 
-    hgnc_symbol = panelapp_gene["gene_data"]["gene_symbol"]
-    ensembl_ids = [
-        version["ensembl_id"]
-        for genome in panelapp_gene["gene_data"]["ensembl_genes"].values()
-        for version in genome.values()
-    ]
-
-    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(
-        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)
+    gene_symbol = panelapp_gene["gene_data"]["gene_symbol"]
+    hgnc_id = int(panelapp_gene["gene_data"]["hgnc_id"].split(":")[1])
+    if hgnc_id not in hgnc_gene_ids:
+        LOG.warning("Gene %s does not exist in database. Skipping gene...", gene_symbol)
         return gene_info
 
-    if len(hgnc_ids) > 1:
-        LOG.warning("Gene %s has unclear identifier. Choose random id", hgnc_symbol)
+    gene_info["hgnc_id"] = hgnc_id
+    gene_info["hgnc_symbol"] = gene_symbol
 
-    gene_info["hgnc_symbol"] = hgnc_symbol
-    for hgnc_id in hgnc_ids:
-        gene_info["hgnc_id"] = hgnc_id
+    if panelapp_gene["penetrance"] in ["Complete", "Incomplete"]:
+        gene_info["reduced_penetrance"] = INCOMPLETE_PENETRANCE_MAP.get(panelapp_gene["penetrance"])
 
-    gene_info["reduced_penetrance"] = INCOMPLETE_PENETRANCE_MAP.get(panelapp_gene["penetrance"])
+    mode_of_inheritance = panelapp_gene.get("mode_of_inheritance")
+    if mode_of_inheritance not in MODELS_MAP:
+        LOG.warning(f"Mode of inheritance '{mode_of_inheritance}' not found in MODELS_MAP.")
 
-    inheritance_models = []
-    for model in MODELS_MAP.get(panelapp_gene["mode_of_inheritance"], []):
-        inheritance_models.append(model)
-
-    gene_info["inheritance_models"] = inheritance_models
+    gene_info["inheritance_models"] = MODELS_MAP.get(mode_of_inheritance, [])
 
     return gene_info
 
 
 def parse_panelapp_panel(
+    hgnc_gene_ids: Set[int],
     panel_info: dict,
-    ensembl_id_to_hgnc_id_map: Dict[str, int],
-    hgnc_symbol_to_ensembl_id_map: Dict[str, str],
     institute: Optional[str] = "cust000",
     confidence: Optional[str] = "green",
 ) -> dict:
@@ -101,7 +75,7 @@ def parse_panelapp_panel(
     nr_genes = 0
     for nr_genes, gene in enumerate(panel_info["genes"], 1):
         gene_info = parse_panel_app_gene(
-            gene, ensembl_id_to_hgnc_id_map, hgnc_symbol_to_ensembl_id_map, confidence
+            hgnc_gene_ids=hgnc_gene_ids, panelapp_gene=gene, confidence=confidence
         )
         if not gene_info:
             nr_excluded += 1

scout/parse/variant/compound.py

@@ -1,43 +1,42 @@
 import logging
+from typing import List
 
 from scout.utils.md5 import generate_md5_key
 
 LOG = logging.getLogger(__name__)
 
 
-def parse_compounds(compound_info, case_id, variant_type):
-    """Get a list with compounds objects for this variant.
+def parse_compounds(compound_info: str, case_id: str, variant_type: str) -> List[dict]:
+    """Get a list with compounds objects(dicts) for this variant.
 
-    Arguments:
-        compound_info(str): A Variant dictionary
-        case_id (str): unique family id
-        variant_type(str): 'research' or 'clinical'
+    Scout IDs do not have "chr" prefixed chromosome names, hence we lstrip that from
+    any compound names.
+
+    We need the case id to construct the correct id, as well as the variant type (clinical or research).
 
-    Returns:
-        compounds(list(dict)): A list of compounds
     """
-    # We need the case to construct the correct id
+
     compounds = []
     if compound_info:
         for family_info in compound_info.split(","):
-            splitted_entry = family_info.split(":")
+            split_entry = family_info.split(":")
             # This is the family id
-            if splitted_entry[0] == case_id:
-                for compound in splitted_entry[1].split("|"):
-                    splitted_compound = compound.split(">")
-                    compound_obj = {}
-                    compound_name = splitted_compound[0]
-                    compound_obj["variant"] = generate_md5_key(
-                        compound_name.split("_") + [variant_type, case_id]
-                    )
+            if split_entry[0] == case_id:
+                for compound in split_entry[1].split("|"):
+                    split_compound = compound.split(">")
+                    compound_name = split_compound[0].lstrip("chr")
+                    compound_obj = {
+                        "display_name": compound_name,
+                        "variant": generate_md5_key(
+                            compound_name.split("_") + [variant_type, case_id]
+                        ),
+                    }
 
                     try:
-                        compound_score = float(splitted_compound[1])
+                        compound_score = float(split_compound[1])
                     except (TypeError, IndexError):
                         compound_score = 0.0
-
                     compound_obj["score"] = compound_score
-                    compound_obj["display_name"] = compound_name
 
                     compounds.append(compound_obj)