scout-browser 4.79.1__py3-none-any.whl → 4.81__py3-none-any.whl

scout/__version__.py

@@ -1 +1 @@
-__version__ = "4.79.1"
+__version__ = "4.81"

scout/adapter/mongo/variant.py

@@ -671,7 +671,7 @@ class VariantHandler(VariantLoader):
         result = self.variant_collection.delete_many(query)
         LOG.info("{0} variants deleted".format(result.deleted_count))
 
-    def overlapping(self, variant_obj):
+    def overlapping(self, variant_obj, limit=30):
         """Return overlapping variants.
 
         Look at the genes that a variant overlaps to.
@@ -701,7 +701,7 @@ class VariantHandler(VariantLoader):
         }
         sort_key = [("rank_score", pymongo.DESCENDING)]
         # We collect the 30 most severe overlapping variants
-        variants = self.variant_collection.find(query).sort(sort_key).limit(30)
+        variants = self.variant_collection.find(query).sort(sort_key).limit(limit)
 
         return variants
 

scout/constants/__init__.py

@@ -35,6 +35,7 @@ from .clinvar import (
     COLLECTION_METHOD,
     CONDITION_PREFIX,
     GERMLINE_CLASSIF_TERMS,
+    MULTIPLE_CONDITION_EXPLANATION,
 )
 from .clnsig import CLINSIG_MAP, REV_CLINSIG_MAP, TRUSTED_REVSTAT_LEVEL
 from .disease_parsing import (
@@ -99,6 +100,7 @@ from .variants_export import (
     CANCER_EXPORT_HEADER,
     EXPORT_HEADER,
     EXPORTED_VARIANTS_LIMIT,
+    FUSION_EXPORT_HEADER,
     MITODEL_HEADER,
     MT_COV_STATS_HEADER,
     MT_EXPORT_HEADER,
@@ -202,6 +204,7 @@ CALLERS = {
         {"id": "ascat", "name": "ASCAT"},
         {"id": "dellycnv", "name": "DellyCNV"},
         {"id": "tiddit", "name": "TIDDIT"},
+        {"id": "igh_dux4", "name": "IGH-DUX4 detection"},
     ],
     "mei": [{"id": "retroseq", "name": "RetroSeq"}],
     "sv": [

scout/constants/clinvar.py

@@ -30,6 +30,7 @@ CLINVAR_HEADER = {
     "condition_id_type": "Condition ID type",
     "condition_id_value": "Condition ID value",
     "condition_comment": "Condition comment",
+    "explanation_for_multiple_conditions": "Explanation for multiple conditions",
     "clinsig": "Germline classification",
     "clinsig_comment": "Comment on classification",
     "last_evaluated": "Date last evaluated",
@@ -187,3 +188,5 @@ CONDITION_PREFIX = {
 }
 
 CLINVAR_ASSERTION_METHOD_CIT_DB_OPTIONS = {"DOI", "pmc", "PMID"}
+
+MULTIPLE_CONDITION_EXPLANATION = ["Novel disease", "Uncertain", "Co-occurring"]

scout/constants/indexes.py

@@ -34,39 +34,41 @@ INDEXES = {
             [
                 ("case_id", ASCENDING),
                 ("category", ASCENDING),
+                ("variant_type", ASCENDING),
                 ("variant_rank", ASCENDING),
+                ("hgnc_ids", ASCENDING),
             ],
-            name="caseid_variantrank",
+            name="caseid_category_varianttype_variantrank_hgncids",
             background=True,
         ),
         IndexModel(
             [
-                ("case_id", ASCENDING),
+                ("hgnc_symbols", ASCENDING),
+                ("rank_score", DESCENDING),
                 ("category", ASCENDING),
                 ("variant_type", ASCENDING),
-                ("rank_score", DESCENDING),
             ],
-            name="caseid_category_varianttype_rankscore",
+            name="hgncsymbol_rankscore_category_varianttype",
             background=True,
+            partialFilterExpression={"rank_score": {"$gt": 5}, "category": "snv"},
         ),
         IndexModel(
             [
-                ("hgnc_symbols", ASCENDING),
-                ("rank_score", DESCENDING),
+                ("variant_id", ASCENDING),
+                ("case_id", ASCENDING),
                 ("category", ASCENDING),
-                ("variant_type", ASCENDING),
             ],
-            name="hgncsymbol_rankscore_category_varianttype",
+            name="variantid_caseid_category",
             background=True,
-            partialFilterExpression={"rank_score": {"$gt": 5}, "category": "snv"},
         ),
         IndexModel(
             [
-                ("case_id", ASCENDING),
                 ("category", ASCENDING),
-                ("variant_id", ASCENDING),
+                ("case_id", ASCENDING),
+                ("variant_type", ASCENDING),
+                ("rank_score", ASCENDING),
             ],
-            name="caseid_variantid",
+            name="category_caseid_varianttype_rankscore",
             background=True,
         ),
         IndexModel(

scout/constants/variants_export.py

@@ -15,6 +15,17 @@ EXPORT_HEADER = [
 
 CANCER_EXPORT_HEADER = EXPORT_HEADER + ["VAF TUMOR", "VAF NORMAL", "COSMIC ID"]
 
+FUSION_EXPORT_HEADER = EXPORT_HEADER + [
+    "Fusion genes",
+    "Orientation",
+    "Frame status",
+    "Observed",
+    "Exon",
+    "Junction reads",
+    "Split reads",
+    "FFPM",
+]
+
 MT_EXPORT_HEADER = [
     "Position",
     "Change",

scout/models/case/case_loading_models.py

@@ -4,6 +4,7 @@ from datetime import datetime
 from enum import Enum
 from fractions import Fraction
 from glob import glob
+from os.path import abspath, dirname, exists, isabs
 from pathlib import Path
 from typing import Any, Dict, List, Optional, Tuple, Union
 
@@ -12,7 +13,6 @@ try:
 except ImportError:
     from typing_extensions import Literal
 
-import path
 from pydantic import BaseModel, Field, field_validator, model_validator
 
 from scout.constants import ANALYSIS_TYPES
@@ -49,7 +49,11 @@ CASE_FILE_PATH_CHECKS = [
     "peddy_ped",
     "peddy_ped_check",
     "peddy_sex_check",
+    "exe_ver",
+    "smn_tsv",
+    "reference_info",
     "RNAfusion_inspector",
+    "RNAfusion_inspector_research",
     "RNAfusion_report",
     "RNAfusion_report_research",
 ]
@@ -86,18 +90,13 @@ class Sex(str, Enum):
     unknown = "unknown"
 
 
-def _get_demo_file_absolute_path(partial_path: str) -> str:
-    """returns the absolute path to a given demo file."""
-    APP_ROOT: str = path.abspath(path.join(path.dirname(__file__), ".."))
-    return path.join(APP_ROOT, partial_path)
-
-
-def _is_string_path(string_path: str) -> bool:
-    try:
-        path = Path(string_path) or Path(_get_demo_file_absolute_path(partial_path=string_path))
-        return path.is_file()
-    except AttributeError:
-        return False
+def _resource_abs_path(string_path: str) -> str:
+    """Return the absolute path to a resource file."""
+    if not exists(string_path):
+        raise FileExistsError(f"Path {string_path} could not be found on disk.")
+    if isabs(string_path):
+        return string_path
+    return abspath(string_path)
 
 
 #### VCF files class ####
@@ -125,9 +124,8 @@ class VcfFiles(BaseModel):
         """Make sure that VCF file exists on disk."""
         for item in VCF_FILE_PATH_CHECKS:
             item_path: str = values.get(item)
-            if item_path and _is_string_path(values[item]) is False:
-                raise ValueError(f"{item} path '{values[item]}' is not valid.")
-
+            if item_path:
+                values[item] = _resource_abs_path(item_path)
         return values
 
 
@@ -145,6 +143,19 @@ class ChromographImages(BaseModel):
     upd_regions: Optional[str] = None
     upd_sites: Optional[str] = None
 
+    @model_validator(mode="before")
+    def validate_file_path(cls, config_values: Dict) -> "SampleLoader":
+        """Make sure that chromograph paths associated to samples exist on disk and are absolute paths. Chromograph paths are incomplete paths, containing the path to the directory containing a number of files plus the prefix of the files."""
+
+        for key in cls.model_fields:
+            item_path: str = config_values.get(key)
+            if item_path:
+                item_path_dirname: str = dirname(item_path)
+                config_values[key] = item_path.replace(
+                    item_path_dirname, _resource_abs_path(item_path_dirname)
+                )
+        return config_values
+
 
 class Mitodel(BaseModel):
     discordant: Optional[int] = None
@@ -160,6 +171,15 @@ class REViewer(BaseModel):
     reference: Optional[str] = None
     reference_index: Optional[str] = None
 
+    @model_validator(mode="before")
+    def validate_file_path(cls, config_values: Dict) -> "SampleLoader":
+        """Make sure that REViewer paths associated to samples exist on disk and are absolute paths."""
+        for key in cls.model_fields:
+            item_path: str = config_values.get(key)
+            if item_path:
+                config_values[key] = _resource_abs_path(item_path)
+        return config_values
+
 
 class SampleLoader(BaseModel):
     alignment_path: Optional[str] = None
@@ -246,9 +266,8 @@ class SampleLoader(BaseModel):
         """Make sure that files associated to samples (mostly alignment files) exist on disk."""
         for item in SAMPLES_FILE_PATH_CHECKS:
             item_path: str = values.get(item)
-            if item_path and _is_string_path(values[item]) is False:
-                raise ValueError(f"{item} path '{values[item]}' is not valid.")
-
+            if item_path:
+                values[item] = _resource_abs_path(item_path)
         return values
 
     @field_validator("capture_kits", mode="before")
@@ -283,8 +302,9 @@ class Image(BaseModel):
             raise TypeError(
                 f"Custom images should be of type: {', '.join(SUPPORTED_IMAGE_FORMATS)}"
             )
-        if REPID not in path and _is_string_path(path) is False:
+        if REPID not in path and exists(path) is False:
             raise ValueError(f"Image path '{path}' is not valid.")
+
         return path
 
 
@@ -317,13 +337,14 @@ def set_custom_images(images: Optional[List[Image]]) -> Optional[List[Image]]:
                     "description": image.description.replace(REPID, match["repid"]),
                     "height": image.height,
                     "format": None,
-                    "path": str(match["path"]),
+                    "path": _resource_abs_path(str(match["path"])),
                     "str_repid": match["repid"],
                     "title": image.title.replace(REPID, match["repid"]),
                     "width": image.width,
                 }
                 real_folder_images.append(Image(**new_image))
         else:
+            image.path = _resource_abs_path(image.path)
             real_folder_images.append(image)  # append other non-repid images
 
     return real_folder_images
@@ -387,6 +408,7 @@ class CaseLoader(BaseModel):
     peddy_sex_check: Optional[str] = Field(None, alias="peddy_sex")  # Soon to be deprecated
     phenotype_groups: Optional[List[str]] = None
     phenotype_terms: Optional[List[str]] = None
+    exe_ver: Optional[str] = None
     rank_model_version: Optional[str] = None
     rank_score_threshold: Optional[int] = 0
     reference_info: Optional[str] = None
@@ -502,8 +524,8 @@ class CaseLoader(BaseModel):
         """Make sure the files associated to the case (mostly reports) exist on disk."""
         for item in CASE_FILE_PATH_CHECKS:
             item_path: str = values.get(item)
-            if item_path and _is_string_path(values[item]) is False:
-                raise ValueError(f"{item} path '{values[item]}' is not valid.")
+            if item_path:
+                values[item] = _resource_abs_path(item_path)
 
         return values
 

scout/models/clinvar.py

@@ -31,6 +31,7 @@ clinvar_variant = {
     "condition_id_type": str,  # enum: "HPO", "OMIM"
     "condition_id_value": str,  # example: HP:0001298;HP:0001250
     "condition_comment": str,
+    "explanation_for_multiple_conditions": str,
     "start": int,
     "stop": int,
     "ref": str,

scout/parse/variant/variant.py

@@ -271,7 +271,6 @@ def get_genmod_key(case):
     """
     case_id = case["_id"]
     if "-" in case_id:
-        LOG.debug("iCase ID contains '-'. Using display_name as case _id.")
         return case["display_name"]
     return case["_id"]
 
@@ -474,39 +473,44 @@ def add_gene_and_transcript_info_for_fusions(
         Return:
             parsed_transcripts(list)
     """
+
     parsed_transcripts = []
     genes = []
+    hgnc_ids = []
+    hgnc_symbols = []
+
     for suffix in ["a", "b"]:
-        genes.append(
-            {
-                "hgnc_symbol": parsed_variant[f"gene_{suffix}"],
+        # If fusions have transcript information about a fusion partner
+        parsed_transcript = {}
+        if parsed_variant.get(f"transcript_id_{suffix}"):
+            # Add transcript info to genes if available
+            parsed_transcript = {
+                "transcript_id": parsed_variant[f"transcript_id_{suffix}"],
                 "hgnc_id": parsed_variant[f"hgnc_id_{suffix}"],
-                "transcripts": [],
+                "hgnc_symbol": parsed_variant[f"gene_{suffix}"],
+                "exon": parsed_variant[f"exon_number_{suffix}"],
             }
-        )
-        # If fusions have transcript information about both fusion partners
-        if parsed_variant["transcript_id_a"] and parsed_variant["transcript_id_b"]:
-            parsed_transcripts.append(
+            parsed_transcripts.append(parsed_transcript)
+
+        if parsed_variant.get(f"hgnc_id_{suffix}"):
+            if parsed_variant.get(f"gene_{suffix}"):
+                # Add hgnc_symbol to variant if available
+                hgnc_symbols.append(parsed_variant.get(f"gene_{suffix}"))
+
+            # Add hgnc_id to variant if available
+            hgnc_ids.append(parsed_variant.get(f"hgnc_id_{suffix}"))
+
+            genes.append(
                 {
-                    "transcript_id": parsed_variant[f"transcript_id_{suffix}"],
-                    "hgnc_id": parsed_variant[f"hgnc_id_{suffix}"],
                     "hgnc_symbol": parsed_variant[f"gene_{suffix}"],
-                    "exon": parsed_variant[f"exon_number_{suffix}"],
+                    "hgnc_id": parsed_variant[f"hgnc_id_{suffix}"],
+                    "transcripts": [parsed_transcript] if parsed_transcript else [],
                 }
             )
 
-    # Add transcript info to genes if available
-    if parsed_transcripts:
-        genes[0]["transcripts"] = [parsed_transcripts[0]]
-        genes[1]["transcripts"] = [parsed_transcripts[1]]
-
-    # Add hgnc_id to variant if available
-    hgnc_ids = []
-    if parsed_variant["hgnc_id_a"] and parsed_variant["hgnc_id_b"]:
-        hgnc_ids = [gene["hgnc_id"] for gene in genes]
-        parsed_variant["genes"] = genes
-
+    parsed_variant["genes"] = genes
     parsed_variant["hgnc_ids"] = hgnc_ids
+    parsed_variant["hgnc_symbols"] = hgnc_symbols
 
     return parsed_transcripts
 

scout/server/blueprints/api/views.py

@@ -67,6 +67,12 @@ def pin_variant(
 
     (institute_obj, case_obj, variant_obj) = _lookup_variant(variant_id, institute_id, case_name)
 
+    if not institute_id:
+        institute_id = variant_obj["institute"]
+
+    if not case_name:
+        case_name = case_obj.get("display_name")
+
     user_obj = store.user(current_user.email)
     link = url_for(
         "variant.variant",
@@ -88,6 +94,12 @@ def unpin_variant(
 
     (institute_obj, case_obj, variant_obj) = _lookup_variant(variant_id, institute_id, case_name)
 
+    if not institute_id:
+        institute_id = variant_obj["institute"]
+
+    if not case_name:
+        case_name = case_obj.get("display_name")
+
     user_obj = store.user(current_user.email)
     link = url_for(
         "variant.variant",

scout/server/blueprints/cases/controllers.py

@@ -4,7 +4,7 @@ import itertools
 import json
 import logging
 import os
-from typing import Dict, List, Set
+from typing import Dict, List, Optional, Set
 
 import query_phenomizer
 import requests
@@ -45,6 +45,8 @@ from scout.server.extensions import RerunnerError, bionano_access, gens, matchma
 from scout.server.links import disease_link
 from scout.server.utils import (
     case_has_alignments,
+    case_has_chanjo2_coverage,
+    case_has_chanjo_coverage,
     case_has_mt_alignments,
     case_has_rna_tracks,
     institute_and_case,
@@ -83,6 +85,61 @@ def phenomizer_diseases(hpo_ids, case_obj, p_value_treshold=1):
         flash("Could not establish a conection to Phenomizer", "danger")
 
 
+def chanjo2_coverage_report_contents(
+    institute_obj: dict, case_obj: dict, panel_name: str, panel_id: Optional[str], report_type: str
+) -> Optional[str]:
+    """Retrieve the HTML contents of the Chanjo2 coverage report/overview for a case."""
+
+    if panel_id:
+        hgnc_gene_ids: List[int] = store.panel_to_genes(panel_id=panel_id, gene_format="hgnc_id")
+    elif panel_name == "HPO Panel":
+        hgnc_gene_ids: List[int] = [
+            gene["hgnc_id"] for gene in case_obj.get("dynamic_gene_list", [])
+        ]
+    else:
+        hgnc_gene_ids: List[int] = _get_default_panel_genes(store, case_obj)
+
+    if not hgnc_gene_ids:
+        flash("Case should have at least one default gene panel containing genes", "warning")
+        return
+
+    query_samples: List[dict] = []
+    analysis_types: List[str] = []
+
+    for ind in case_obj.get("individuals", []):
+        if not ind.get("d4_file"):
+            continue
+        query_samples.append(
+            {
+                "name": ind.get("display_name"),
+                "coverage_file_path": ind.get("d4_file"),
+                "case_name": case_obj["display_name"],
+                "analysis_date": case_obj["analysis_date"].isoformat(),
+            }
+        )
+        analysis_types.append(ind.get("analysis_type"))
+
+    interval_type = "genes"
+    if "wes" in analysis_types:
+        interval_type = "transcripts"
+    elif "wts" in analysis_types:
+        interval_type = "exons"
+
+    report_query: dict = {
+        "build": "GRCh38" if "38" in case_obj.get("genome_build", "37") else "GRCh37",
+        "default_level": institute_obj.get("coverage_cutoff"),
+        "interval_type": interval_type,
+        "panel_name": panel_name,
+        "case_display_name": case_obj["display_name"],
+        "hgnc_gene_ids": hgnc_gene_ids,
+        "samples": query_samples,
+    }
+
+    report_url: str = "/".join([current_app.config.get("CHANJO2_URL"), report_type])
+    response = requests.post(report_url, json=report_query)
+    return response.text
+
+
 def coverage_report_contents(base_url, institute_obj, case_obj):
     """Capture the contents of a case coverage report (chanjo-report), to be displayed in the general case report
 
@@ -298,9 +355,11 @@ def case(store, institute_obj, case_obj):
         store.user(user_id=user_id) for user_id in case_obj.get("assignees", [])
     ]
 
-    # Provide basic info on alignment files availability for this case
+    # Provide basic info on alignment files & coverage data availability for this case
     case_has_alignments(case_obj)
     case_has_mt_alignments(case_obj)
+    case_has_chanjo_coverage(case_obj)
+    case_has_chanjo2_coverage(case_obj)
 
     case_groups = {}
     case_group_label = {}
@@ -324,10 +383,18 @@ def case(store, institute_obj, case_obj):
     partial_causatives = _get_partial_causatives(store, case_obj)
     _populate_assessments(partial_causatives)
 
-    case_obj["default_genes"] = _get_default_panel_genes(store, case_obj)
+    case_obj["clinvar_variants"] = store.case_to_clinVars(case_obj["_id"])
 
-    # Sort panels alphabetically on display name
-    case_obj["panels"] = sorted(case_obj.get("panels", []), key=lambda d: d["display_name"])
+    # check for variants submitted to clinVar but not present in suspects for the case
+    clinvar_variants_not_in_suspects = [
+        store.variant(variant_id) or variant_id
+        for variant_id in case_obj["clinvar_variants"]
+        if variant_id not in [entry.get("_id") for entry in suspects]
+    ]
+
+    case_obj["clinvar_variants_not_in_suspects"] = clinvar_variants_not_in_suspects
+
+    case_obj["default_genes"] = _get_default_panel_genes(store, case_obj)
 
     for hpo_term in itertools.chain(
         case_obj.get("phenotype_groups") or [], case_obj.get("phenotype_terms") or []
@@ -355,7 +422,6 @@ def case(store, institute_obj, case_obj):
             if institute_obj.get("collaborators")
             and collab["_id"] in institute_obj.get("collaborators")
         ]
-    case_obj["clinvar_variants"] = store.case_to_clinVars(case_obj["_id"])
 
     # if updated_at is a list, set it to the last update datetime
     if case_obj.get("updated_at") and isinstance(case_obj["updated_at"], list):

scout/server/blueprints/cases/templates/cases/case.html

@@ -5,7 +5,6 @@
 {% from "cases/individuals_table.html" import cancer_individuals_table, individuals_table %}
 {% from "cases/phenotype.html" import hpo_item, cohort_panel, diagnosis_phenotypes, phenotype_groups_panel, add_phenotype_terms_panel, hpo_panel %}
 {% from "cases/gene_panel.html" import genepanels_table, hpo_genelist_panel %}
-{% from "cases/clinvar.html" import clinvar_vars %}
 
 {% block title %}
   {{ super() }} - {{ institute.display_name }} - {{ case.display_name }}
@@ -148,9 +147,6 @@
       <div class="row">
         <div class="col">{{ causatives_list(causatives, partial_causatives, evaluated_variants, institute, case, manual_rank_options, cancer_tier_options) }}</div>
         <div class="col">{{ suspects_list(suspects, institute, case, manual_rank_options, cancer_tier_options) }}</div>
-        {% if case.clinvar_variants or case.suspects %}
-          <div class="col">{{ clinvar_vars(institute, case, suspects) }}</div>
-        {% endif %}
         <!-- end of data sharing panels -->
       </div>
 
@@ -516,24 +512,6 @@
   </form>
 {% endmacro %}
 
-{% macro remove_form(url, hidden_input=None, button_name=None, button_value=None) %}
-  <form action="{{ url }}" method="POST">
-    {% if hidden_input %}
-      <input type="hidden"
-             name="{{ hidden_input[0] }}"
-             value="{{ hidden_input[1] }}">
-    {% endif %}
-    <div class="float-end">
-      <button class="btn btn-link btn-sm"
-              name="{{ button_name if button_name }}"
-              value="{{ button_value if button_value }}"
-              type="submit">
-        <em class="fa fa-remove"></em>
-      </button>
-    </div>
-  </form>
-{% endmacro %}
-
 {% macro solve_modal(institute, case, case_tag_options) %}
 <div class="modal fade" id="solve_modal" tabindex="-1" role="dialog" aria-labelledby="solveCaseLabel" aria-hidden="true">
   <div class="modal-dialog" role="document">
@@ -623,6 +601,7 @@
       paging: false,
       searching: false,
       ordering: true,
+      order:[[1, 'desc'],[0, 'asc']],
       info: false
     });
   {% endif %}

scout/server/blueprints/cases/templates/cases/case_bionano.html

@@ -42,7 +42,9 @@
         </div>
         <div class="col-md-8">
           {{ synopsis_panel() }}
+          <div class="panel-default">
           {{ comments_panel(institute, case, current_user, comments) }}
+          </div>
         </div>
       </div> <!-- end of div row -->