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

scout/parse/variant/genotype.py

@@ -18,6 +18,7 @@ Uses 'DV' to describe number of paired ends that supports the event and
 
 """
 
+import ast
 import logging
 from typing import Dict, List, Optional, Tuple, Union
 
@@ -101,7 +102,7 @@ def parse_genotype(variant, ind, pos):
     (_, mc_alt) = _parse_format_entry_trgt_mc(variant, pos)
     gt_call["alt_mc"] = mc_alt
 
-    (sd_ref, sd_alt) = _parse_format_entry(variant, pos, "SD", float)
+    (sd_ref, sd_alt) = _parse_format_entry(variant, pos, "SD", int)
     (ap_ref, ap_alt) = _parse_format_entry(variant, pos, "AP", float)
     (am_ref, am_alt) = _parse_format_entry(variant, pos, "AM", float)
 
@@ -122,6 +123,7 @@ def parse_genotype(variant, ind, pos):
         spanning_alt,
         flanking_alt,
         inrepeat_alt,
+        sd_alt,
         clip5_alt,
         clip3_alt,
     )
@@ -135,8 +137,10 @@ def parse_genotype(variant, ind, pos):
         spanning_ref,
         flanking_ref,
         inrepeat_ref,
+        sd_ref,
         spanning_mei_ref,
     )
+
     gt_call["ref_depth"] = ref_depth
     gt_call["read_depth"] = get_read_depth(variant, pos, alt_depth, ref_depth)
     gt_call["alt_frequency"] = get_alt_frequency(variant, pos)
@@ -202,7 +206,7 @@ def get_ffpm_info(variant: cyvcf2.Variant, pos: Dict[str, int]) -> Optional[int]
             pass
 
 
-def get_paired_ends(variant, pos):
+def get_paired_ends(variant: cyvcf2.Variant, pos: int) -> tuple:
     """Get paired ends"""
     # SV specific
     paired_end_alt = None
@@ -224,9 +228,10 @@ def get_paired_ends(variant, pos):
         values = variant.format("PR")[pos]
         try:
             alt_value = int(values[1])
-            ref_value = int(values[0])
             if alt_value >= 0:
                 paired_end_alt = alt_value
+
+            ref_value = int(values[0])
             if ref_value >= 0:
                 paired_end_ref = ref_value
         except ValueError as _ignore_error:
@@ -317,32 +322,30 @@ def get_read_depth(variant, pos, alt_depth, ref_depth):
 
 
 def get_ref_depth(
-    variant,
-    pos,
-    paired_end_ref,
-    split_read_ref,
-    spanning_ref,
-    flanking_ref,
-    inrepeat_ref,
-    spanning_mei_ref,
-):
+    variant: cyvcf2.Variant,
+    pos: int,
+    paired_end_ref: int,
+    split_read_ref: int,
+    spanning_ref: int,
+    flanking_ref: int,
+    inrepeat_ref: int,
+    sd_ref: int,
+    spanning_mei_ref: int,
+) -> int:
     """Get reference read depth"""
     ref_depth = int(variant.gt_ref_depths[pos])
     if ref_depth != -1:
         return ref_depth
 
     REF_ITEMS_LIST: List[tuple] = [
+        (sd_ref,),
         (paired_end_ref, split_read_ref),
         (spanning_ref, flanking_ref, inrepeat_ref),
     ]
 
-    for list in REF_ITEMS_LIST:
-        if all(item is None for item in list):
-            continue
-        ref_depth = 0
-        for item in list:
-            if item:
-                ref_depth += item
+    for items in REF_ITEMS_LIST:
+        if any(item is not None for item in items):
+            ref_depth = sum(item for item in items if item)
 
     if spanning_mei_ref:
         ref_depth += spanning_mei_ref
@@ -350,16 +353,17 @@ def get_ref_depth(
 
 
 def get_alt_depth(
-    variant,
-    pos,
-    paired_end_alt,
-    split_read_alt,
-    spanning_alt,
-    flanking_alt,
-    inrepeat_alt,
-    clip5_alt,
-    clip3_alt,
-):
+    variant: cyvcf2.Variant,
+    pos: int,
+    paired_end_alt: int,
+    split_read_alt: int,
+    spanning_alt: int,
+    flanking_alt: int,
+    inrepeat_alt: int,
+    sd_alt: int,
+    clip5_alt: int,
+    clip3_alt: int,
+) -> int:
     """Get alternative read depth"""
     alt_depth = int(variant.gt_alt_depths[pos])
     if alt_depth != -1:
@@ -369,19 +373,15 @@ def get_alt_depth(
         alt_depth = int(variant.format("VD")[pos][0])
 
     ALT_ITEMS_LIST: List[tuple] = [
+        (sd_alt,),
         (paired_end_alt, split_read_alt),
         (clip5_alt, clip3_alt),
         (spanning_alt, flanking_alt, inrepeat_alt),
     ]
 
-    for list in ALT_ITEMS_LIST:
-        if all(item is None for item in list):
-            continue
-        alt_depth = 0
-        for item in list:
-            if item:
-                alt_depth += item
-
+    for items in ALT_ITEMS_LIST:
+        if any(item is not None for item in items):
+            alt_depth = sum(item for item in items if item)
     return alt_depth
 
 
@@ -430,7 +430,13 @@ def _parse_format_entry(
     alt = None
     if format_entry_name in variant.FORMAT:
         try:
-            values = split_values(variant.format(format_entry_name)[pos])
+            requested_format_entry = variant.format(format_entry_name)[pos]
+
+            values = (
+                split_values(requested_format_entry)
+                if type(requested_format_entry) is str
+                else requested_format_entry
+            )
 
             ref_value = None
             alt_value = None
@@ -440,15 +446,31 @@ def _parse_format_entry(
                 alt_value = (number_format)(values[1])
             if len(values) == 1:
                 alt_value = (number_format)(values[0])
-            if ref_value >= 0:
+            if ref_value and ref_value >= 0:
                 ref = ref_value
-            if alt_value >= 0:
+            if alt_value and alt_value >= 0:
                 alt = alt_value
         except (ValueError, TypeError) as _ignore_error:
             pass
     return (ref, alt)
 
 
+def _get_pathologic_struc(variant: cyvcf2.Variant) -> Optional[list]:
+    """Check for a PathologicStruc on the variant. If not present, return None.
+    If present, and in string format, convert to a list of ints.
+    If it is already parsed to a list by a later improvement in the parser,
+    simply return it.
+    """
+
+    pathologic_struc_entry = variant.INFO.get("PathologicStruc", None)
+    if not pathologic_struc_entry:
+        return pathologic_struc_entry
+    if type(pathologic_struc_entry) is str:
+        return ast.literal_eval(pathologic_struc_entry)
+    if type(pathologic_struc_entry) is list:
+        return pathologic_struc_entry
+
+
 def _parse_format_entry_trgt_mc(variant: cyvcf2.Variant, pos: int):
     """Parse genotype entry for TRGT FORMAT MC
 
@@ -477,14 +499,16 @@ def _parse_format_entry_trgt_mc(variant: cyvcf2.Variant, pos: int):
             if allele == 0:
                 ref_idx = idx
 
-    pathologic_struc = variant.INFO.get("PathologicStruc", None)
-    pathologic_counts = 0
+    pathologic_struc = _get_pathologic_struc(variant)
+
     for idx, allele in enumerate(mc.split(",")):
+
         mcs = allele.split("_")
 
         if len(mcs) > 1:
             pathologic_mcs = pathologic_struc or range(len(mcs))
 
+            pathologic_counts = 0
             for index, count in enumerate(mcs):
                 if index in pathologic_mcs:
                     pathologic_counts += int(count)

scout/parse/variant/variant.py

@@ -82,6 +82,8 @@ def parse_variant(
             variant_type=variant_type,
         ),
         "rank_score": parse_rank_score(variant.INFO.get("RankScore", ""), genmod_key) or 0,
+        "norm_rank_score": parse_rank_score(variant.INFO.get("RankScoreNormalized", ""), genmod_key)
+        or 0,
         "genetic_models": parse_genetic_models(variant.INFO.get("GeneticModels"), genmod_key),
         "str_swegen_mean": call_safe(float, variant.INFO.get("SweGenMean")),
         "str_swegen_std": call_safe(float, variant.INFO.get("SweGenStd")),

scout/server/app.py

@@ -4,7 +4,7 @@ import logging
 import os
 import re
 from datetime import timedelta
-from typing import Dict, Union
+from typing import Dict, List, Optional, Union
 from urllib.parse import parse_qsl, unquote, urlsplit
 
 from flask import Flask, redirect, request, url_for
@@ -14,7 +14,11 @@ from markdown import markdown as python_markdown
 from markupsafe import Markup
 
 from scout import __version__
-from scout.constants import SPIDEX_HUMAN
+from scout.constants import (
+    REVEL_SCORE_LABEL_COLOR_MAP,
+    SPIDEX_HUMAN,
+    SPLICEAI_SCORE_LABEL_COLOR_MAP,
+)
 from scout.log import init_log
 
 from . import extensions
@@ -207,6 +211,9 @@ def register_blueprints(app):
 
 
 def register_filters(app):
+    """Creates methods that can be invoked from jinja2 or views/controllers, given that they are included app.custom_filters."""
+    app.custom_filters = type("CustomFilters", (), {})()  # Create an empty object as namespace
+
     @app.template_filter()
     def human_longint(value: Union[int, str]) -> str:
         """Convert a long integers int or string representation into a human easily readable number."""
@@ -226,6 +233,27 @@ def register_filters(app):
             return "medium"
         return "high"
 
+    @app.template_filter()
+    def get_label_or_color_by_score(
+        score: float,
+        map: str,
+        map_key: str,
+    ) -> str:
+        """Return a label or color for a given score based on predefined score ranges from the provided items_map."""
+        SCORE_ITEM_MAPS = {
+            "revel": REVEL_SCORE_LABEL_COLOR_MAP,
+            "spliceai": SPLICEAI_SCORE_LABEL_COLOR_MAP,
+        }
+        for (low, high), info in SCORE_ITEM_MAPS[map].items():
+            if low <= score <= high:
+                return info[map_key]
+
+    @app.template_filter()
+    def l2fc_2_fc(l2fc: float) -> float:
+        """Converts Log2 fold change to fold change."""
+        fc = 2 ** abs(l2fc)
+        return fc if l2fc >= 0 else -1 / fc
+
     @app.template_filter()
     def human_decimal(number, ndigits=4):
         """Return a standard representation of a decimal number.
@@ -281,6 +309,33 @@ def register_filters(app):
             return "COSM" + str(cosmicId)
         return cosmicId
 
+    @app.template_filter()
+    def format_variant_canonical_transcripts(variant: dict) -> List[str]:
+        """Formats canonical transcripts for all genes in a variant."""
+
+        lines = set()
+        genes = variant.get("genes") or []
+
+        for gene in genes:
+            transcripts = gene.get("transcripts") or []
+            for tx in transcripts:
+                if not tx.get("is_canonical"):
+                    continue
+                canonical_tx = tx.get("transcript_id")
+                protein = tx.get("protein_sequence_name")
+            line_components = [f"{canonical_tx} ({gene.get('hgnc_symbol', '')})"]
+            hgvs = gene.get("hgvs_identifier")
+            if hgvs:
+                line_components.append(hgvs)
+            if protein:
+                line_components.append(protein)
+
+            lines.add(" ".join(line_components))
+
+        return list(lines)
+
+    app.custom_filters.format_variant_canonical_transcripts = format_variant_canonical_transcripts
+
     @app.template_filter()
     def upper_na(string):
         """
@@ -306,6 +361,20 @@ def register_filters(app):
         """Returns a list after removing any None values from it."""
         return [item for item in in_list if item is not None]
 
+    @app.template_filter()
+    def spliceai_max(values) -> Optional[float]:
+        """Returns a list of SpliceAI values, extracting floats only from values like 'score:0.23'."""
+        float_values = []
+        for value in values:
+            if isinstance(value, str):
+                if ":" in value:  # Variant hits multiple genes
+                    value = value.split(":")[1].strip()
+            if value in [None, "-", "None"]:
+                continue
+            float_values.append(float(value))
+        if float_values:
+            return max(float_values)
+
 
 def register_tests(app):
     @app.template_test("existing")

scout/server/blueprints/alignviewers/controllers.py

@@ -8,7 +8,11 @@ from flask_login import current_user
 
 from scout.constants import CASE_SPECIFIC_TRACKS, HUMAN_REFERENCE, IGV_TRACKS
 from scout.server.extensions import config_igv_tracks, store
-from scout.server.utils import case_append_alignments, find_index
+from scout.server.utils import (
+    case_append_alignments,
+    find_index,
+    get_case_genome_build,
+)
 from scout.utils.ensembl_rest_clients import EnsemblRestApiClient
 
 LOG = logging.getLogger(__name__)
@@ -88,7 +92,8 @@ def make_igv_tracks(
         display_obj["locus"] = "chr{0}:{1}-{2}".format(chromosome, start, stop)
 
     # Set genome build for displaying alignments:
-    if "38" in str(case_obj.get("genome_build", "37")) or chromosome == "M":
+
+    if get_case_genome_build(case_obj) == "38" or chromosome == "M":
         build = "38"
     else:
         build = "37"
@@ -137,10 +142,7 @@ def make_sashimi_tracks(
     """
 
     locus = "All"
-
-    build = "38"
-    if "37" in str(case_obj.get("rna_genome_build", "38")):
-        build = "37"
+    build = "37" if "37" in str(case_obj.get("rna_genome_build", "38")) else "38"
 
     if variant_id:
         variant_obj = store.variant(document_id=variant_id)

scout/server/blueprints/alignviewers/templates/alignviewers/igv_viewer.html

@@ -35,6 +35,8 @@
   $(document).ready(function () {
       var div = $("#igvDiv")[0],
               options = {
+                    loadDefaultGenomes: false,
+                    genomeList: "https://raw.githubusercontent.com/igvteam/igv-data/main/genomes/web/genomes.json",
                     showNavigation: true,
                     showRuler: true,
                     {% if display_center_guide %}
@@ -117,6 +119,8 @@
                         indexURL: "{{ url_for('alignviewers.remote_static', file=track.indexURL) }}",
                         sourceType: "file",
                         groupBy: "tag:HP",
+                        showInsertionText: true,
+                        showDeletionText: true,
                         showSoftClips: {{track.show_soft_clips | lower }},
                         format: "{{ track.format }}",
                         height: "{{track.height}}"

scout/server/blueprints/alignviewers/templates/alignviewers/utils.html

@@ -1,5 +1,5 @@
 {% macro igv_script() %}
   <link rel="shortcut icon" href="//igv.org/web/img/favicon.ico">
   <!-- IGV JS-->
-  <script src="https://cdn.jsdelivr.net/npm/igv@3.2.0/dist/igv.min.js" integrity="sha512-MHnbGQeONlQXyEs6PgiW2bhwywJW5IwUnRKfQKrPaVSrzopctBTU1VtOiEXMf/ZPBk47eFimlVRxdff+sdsyAg==" crossorigin="anonymous"></script>
+  <script src="https://cdn.jsdelivr.net/npm/igv@3.3.0/dist/igv.min.js" integrity="sha512-U3drIflKJksG0+kiVuqYrQaI9SsloPhKfISeZr8bzVpO/oRFz7hE1vdJirvDyYIfv51CSucKJgcLAdupqitBcQ==" crossorigin="anonymous"></script>
 {% endmacro %}

scout/server/blueprints/cases/controllers.py

@@ -22,6 +22,7 @@ from scout.constants import (
     CUSTOM_CASE_REPORTS,
     DATE_DAY_FORMATTER,
     GENOME_REGION,
+    HPO_LINK_URL,
     INHERITANCE_PALETTE,
     MITODEL_HEADER,
     MT_COV_STATS_HEADER,
@@ -66,6 +67,7 @@ from scout.server.utils import (
     case_has_mt_alignments,
     case_has_mtdna_report,
     case_has_rna_tracks,
+    get_case_genome_build,
     get_case_mito_chromosome,
     institute_and_case,
 )
@@ -157,7 +159,12 @@ def coverage_report_contents(base_url, institute_obj, case_obj):
     return html_body_content
 
 
-def _populate_case_groups(store, case_obj, case_groups, case_group_label):
+def _populate_case_groups(
+    store: MongoAdapter,
+    case_obj: dict,
+    case_groups: Dict[str, List[str]],
+    case_group_label: Dict[str, str],
+):
     """Case groups allow display of information about user linked cases together on one case.
     Notably variantS lists show shared annotations and alignment views show all alignments
     available for the group.
@@ -178,20 +185,21 @@ def _populate_case_groups(store, case_obj, case_groups, case_group_label):
             case_group_label[group] = store.case_group_label(group)
 
 
-def _get_partial_causatives(store: MongoAdapter, case_obj: Dict) -> List[Dict]:
-    """Return any partial causatives a case has, populated as causative objs.
-    Args:
-        store(adapter.MongoAdapter)
-        case_obj(models.Case)
-    Returns:
-        partial(list(dict))
+def _get_partial_causatives(store: MongoAdapter, institute_obj: dict, case_obj: dict) -> List[Dict]:
+    """Check for partial causatives and associated phenotypes.
+    Return any partial causatives a case has, populated as causative objs.
     """
 
     partial_causatives = []
     if case_obj.get("partial_causatives"):
         for var_id, values in case_obj["partial_causatives"].items():
+            variant_obj = store.variant(var_id)
+            if variant_obj:
+                decorated_variant_obj = _get_decorated_var(
+                    store, var_obj=variant_obj, institute_obj=institute_obj, case_obj=case_obj
+                )
             causative_obj = {
-                "variant": store.variant(var_id) or var_id,
+                "variant": decorated_variant_obj or var_id,
                 "disease_terms": values.get("diagnosis_phenotypes"),
                 "hpo_terms": values.get("phenotype_terms"),
             }
@@ -287,7 +295,7 @@ def bionano_case(store, institute_obj, case_obj) -> Dict:
     return data
 
 
-def sma_case(store, institute_obj, case_obj):
+def sma_case(store: MongoAdapter, institute_obj: dict, case_obj: dict) -> dict:
     """Preprocess a case for tabular view, SMA."""
 
     _populate_case_individuals(case_obj)
@@ -299,11 +307,31 @@ def sma_case(store, institute_obj, case_obj):
         "case": case_obj,
         "comments": store.events(institute_obj, case=case_obj, comments=True),
         "events": _get_events(store, institute_obj, case_obj),
-        "region": GENOME_REGION[case_obj.get("genome_build", "38")],
+        "region": GENOME_REGION[get_case_genome_build(case_obj)],
     }
     return data
 
 
+def _get_suspects_or_causatives(
+    store: MongoAdapter, institute_obj: dict, case_obj: dict, kind: str = "suspects"
+) -> list:
+    """Fetch the variant objects for suspects and causatives and decorate them.
+    If no longer available, append variant_id instead."""
+
+    marked_vars = []
+    for variant_id in case_obj.get(kind, []):
+        variant_obj = store.variant(variant_id)
+        if variant_obj:
+            marked_vars.append(
+                _get_decorated_var(
+                    store, var_obj=variant_obj, institute_obj=institute_obj, case_obj=case_obj
+                )
+            )
+        else:
+            marked_vars.append(variant_id)
+    return marked_vars
+
+
 def case(
     store: MongoAdapter, institute_obj: dict, case_obj: dict, hide_matching: bool = True
 ) -> dict:
@@ -331,25 +359,19 @@ def case(
     case_group_label = {}
     _populate_case_groups(store, case_obj, case_groups, case_group_label)
 
-    # Fetch the variant objects for suspects and causatives
-    suspects = [
-        store.variant(variant_id) or variant_id for variant_id in case_obj.get("suspects", [])
-    ]
+    suspects = _get_suspects_or_causatives(store, institute_obj, case_obj, "suspects")
     _populate_assessments(suspects)
-    causatives = [
-        store.variant(variant_id) or variant_id for variant_id in case_obj.get("causatives", [])
-    ]
+
+    causatives = _get_suspects_or_causatives(store, institute_obj, case_obj, "causatives")
     _populate_assessments(causatives)
 
-    # get evaluated variants
     evaluated_variants = store.evaluated_variants(case_obj["_id"], case_obj["owner"])
     _populate_assessments(evaluated_variants)
 
-    # check for partial causatives and associated phenotypes
-    partial_causatives = _get_partial_causatives(store, case_obj)
+    partial_causatives = _get_partial_causatives(store, institute_obj, case_obj)
     _populate_assessments(partial_causatives)
 
-    case_obj["clinvar_variants"] = store.case_to_clinVars(case_obj["_id"])
+    case_obj["clinvar_variants"] = store.case_to_clinvars(case_obj["_id"])
 
     # check for variants submitted to clinVar but not present in suspects for the case
     clinvar_variants_not_in_suspects = [
@@ -367,9 +389,7 @@ def case(
     for hpo_term in itertools.chain(
         case_obj.get("phenotype_groups") or [], case_obj.get("phenotype_terms") or []
     ):
-        hpo_term["hpo_link"] = "http://hpo.jax.org/app/browse/term/{}".format(
-            hpo_term["phenotype_id"]
-        )
+        hpo_term["hpo_link"] = f"{HPO_LINK_URL}{hpo_term['phenotype_id']}"
 
     _set_rank_model_links(case_obj)
 
@@ -471,7 +491,7 @@ def case(
         "tissue_types": SAMPLE_SOURCE,
         "report_types": CUSTOM_CASE_REPORTS,
         "mme_nodes": matchmaker.connected_nodes,
-        "gens_info": gens.connection_settings(case_obj.get("genome_build")),
+        "gens_info": gens.connection_settings(get_case_genome_build(case_obj)),
         "display_rerunner": rerunner.connection_settings.get("display", False),
         "hide_matching": hide_matching,
         "audits": store.case_events_by_verb(
@@ -676,7 +696,9 @@ def case_report_variants(store: MongoAdapter, case_obj: dict, institute_obj: dic
             add_bayesian_acmg_classification(var_obj)
             add_bayesian_ccv_classification(var_obj)
             evaluated_variants_by_type[eval_category].append(
-                _get_decorated_var(var_obj=var_obj, institute_obj=institute_obj, case_obj=case_obj)
+                _get_decorated_var(
+                    store, var_obj=var_obj, institute_obj=institute_obj, case_obj=case_obj
+                )
             )
 
     for var_obj in store.evaluated_variants(
@@ -689,7 +711,9 @@ def case_report_variants(store: MongoAdapter, case_obj: dict, institute_obj: dic
     data["variants"] = evaluated_variants_by_type
 
 
-def _get_decorated_var(var_obj: dict, institute_obj: dict, case_obj: dict) -> dict:
+def _get_decorated_var(
+    store: MongoAdapter, var_obj: dict, institute_obj: dict, case_obj: dict
+) -> dict:
     """Decorate a variant object for display using the variant controller"""
     return variant_decorator(
         store=store,
@@ -719,7 +743,9 @@ def _append_evaluated_variant_by_type(
             add_bayesian_ccv_classification(var_obj)
 
             evaluated_variants_by_type[eval_category].append(
-                _get_decorated_var(var_obj=var_obj, institute_obj=institute_obj, case_obj=case_obj)
+                _get_decorated_var(
+                    store, var_obj=var_obj, institute_obj=institute_obj, case_obj=case_obj
+                )
             )
 
 
@@ -765,6 +791,7 @@ def case_report_content(store: MongoAdapter, institute_obj: dict, case_obj: dict
     data["genetic_models"] = dict(GENETIC_MODELS)
     data["report_created_at"] = datetime.datetime.now().strftime("%Y-%m-%d %H:%M")
     data["current_scout_version"] = __version__
+    data["hpo_link_url"] = HPO_LINK_URL
 
     case_report_variants(store, case_obj, institute_obj, data)
 
@@ -1395,6 +1422,7 @@ def matchmaker_matches(request, institute_id, case_name):
             pat_matches = parse_matches(patient_id, server_resp["content"]["matches"])
         matches[patient_id] = pat_matches
 
+    data["hpo_link_url"] = HPO_LINK_URL
     data["matches"] = matches
     return data