scout-browser 4.98.0__py3-none-any.whl → 4.100.0__py3-none-any.whl

scout/constants/file_types.py

@@ -23,6 +23,18 @@ ORDERED_FILE_TYPE_MAP = OrderedDict(
     ]
 )
 
+DNA_SAMPLE_VARIANT_CATEGORIES = [
+    "snv",
+    "sv",
+    "mei",
+    "str",
+    "vcf_snv_mt",
+    "vcf_snv_research_mt",
+    "vcf_snv_research",
+    "vcf_sv_research_mt",
+    "vcf_sv_research",
+    "vcf_mei_research",
+]
 
 ORDERED_OMICS_FILE_TYPE_MAP = OrderedDict(
     [

scout/constants/igv_tracks.py

@@ -11,7 +11,7 @@ HG38REF_INDEX_URL = "https://s3.amazonaws.com/igv.broadinstitute.org/genomes/seq
 HG38ALIAS_URL = "https://igv.org/genomes/data/hg38/hg38_alias.tab"
 HG38CYTOBAND_URL = "https://igv-genepattern-org.s3.amazonaws.com/genomes/hg38/cytoBandIdeo.txt.gz"
 
-HG38GENES_URL = "https://s3.amazonaws.com/igv.org.genomes/hg38/refGene.txt.gz"
+HG38GENES_URL = "https://hgdownload.soe.ucsc.edu/goldenPath/hg38/database/ncbiRefSeq.txt.gz"
 HG38GENES_FORMAT = "refgene"
 
 HG19GENES_URL = "https://s3.amazonaws.com/igv.org.genomes/hg19/ncbiRefSeq.sorted.txt.gz"
@@ -124,11 +124,14 @@ HUMAN_GENES_38 = {
 }
 
 CASE_SPECIFIC_TRACKS = {
-    "rhocall_bed": "Rhocall Zygosity",
-    "rhocall_wig": "Rhocall Regions",
-    "tiddit_coverage_wig": "TIDDIT Coverage",
-    "upd_regions_bed": "UPD regions",
-    "upd_sites_bed": "UPD sites",
+    "paraphase_alignments": "Paraphase Alignment",
+    "assembly_alignments": "de novo Assembly Alignment",
+    "minor_allele_frequency_wigs": "SV Caller Minor Allele Frequency",
+    "rhocall_beds": "Rhocall Zygosity",
+    "rhocall_wigs": "Rhocall Regions",
+    "tiddit_coverage_wigs": "SV Caller Coverage",
+    "upd_regions_beds": "UPD Regions",
+    "upd_sites_beds": "UPD Sites",
 }
 
 HUMAN_REFERENCE = {"37": HUMAN_REFERENCE_37, "38": HUMAN_REFERENCE_38}

scout/constants/indexes.py

@@ -99,20 +99,21 @@ INDEXES = {
                 ("category", ASCENDING),
                 ("case_id", ASCENDING),
                 ("variant_type", ASCENDING),
-                ("rank_score", ASCENDING),
+                ("rank_score", DESCENDING),
+                ("hgnc_ids", ASCENDING),
             ],
-            name="category_caseid_varianttype_rankscore",
+            name="category_caseid_varianttype_rankscore_hgncids",
         ),
         IndexModel(
             [
+                ("chromosome", ASCENDING),
                 ("case_id", ASCENDING),
                 ("category", ASCENDING),
                 ("variant_type", ASCENDING),
-                ("chromosome", ASCENDING),
                 ("start", ASCENDING),
                 ("end", ASCENDING),
             ],
-            name="caseid_category_chromosome_start_end",
+            name="chromosome_caseid_category_start_end",
         ),
         IndexModel(
             [("variant_id", ASCENDING), ("institute", ASCENDING)],

scout/constants/panels.py

@@ -25,3 +25,6 @@ PRESELECTED_PANELAPP_PANEL_TYPE_SLUGS = [
     "gms-signed-off",
     "rare-disease-100k",
 ]
+
+PANELAPPGREEN_NAME = "PANELAPP-GREEN"
+PANELAPPGREEN_DISPLAY_NAME = "PanelApp Green Genes"

scout/constants/query_terms.py

@@ -62,4 +62,5 @@ SECONDARY_CRITERIA = [
     "split_reads",
     "fusion_caller",
     "rank_score",
+    "clinsig_onc",
 ]

scout/constants/variant_tags.py

@@ -244,7 +244,7 @@ CANCER_TIER_OPTIONS = {
     "4": {
         "label": "Tier IV",
         "description": "Observed at high frequency in the population. No published evidence.",
-        "label_class": "default",
+        "label_class": "success",
     },
 }
 
@@ -334,7 +334,7 @@ MANUAL_RANK_OPTIONS = OrderedDict(
                 "label": "VUS",
                 "name": "Unknown Significance",
                 "description": "Variant of unknown significance",
-                "label_class": "default",
+                "label_class": "primary",
             },
         ),
         (
@@ -361,7 +361,7 @@ MANUAL_RANK_OPTIONS = OrderedDict(
                 "label": "RF",
                 "name": "Risk Factor",
                 "description": "Established risk allele - strong evidence for a small risk increase",
-                "label_class": "default",
+                "label_class": "dark",
             },
         ),
         (
@@ -370,7 +370,7 @@ MANUAL_RANK_OPTIONS = OrderedDict(
                 "label": "LRF",
                 "name": "Likely Risk Factor",
                 "description": "Likely risk allele - some evidence for a small risk increase",
-                "label_class": "default",
+                "label_class": "dark",
             },
         ),
         (
@@ -379,7 +379,7 @@ MANUAL_RANK_OPTIONS = OrderedDict(
                 "label": "URF",
                 "name": "Uncertain Risk Factor",
                 "description": "Uncertain risk allele - uncertain evidence for a small risk increase",
-                "label_class": "default",
+                "label_class": "dark",
             },
         ),
         (
@@ -388,7 +388,7 @@ MANUAL_RANK_OPTIONS = OrderedDict(
                 "label": "O",
                 "name": "Other",
                 "description": "Other, phenotype not related to disease",
-                "label_class": "default",
+                "label_class": "dark",
             },
         ),
     ]

scout/demo/643594.config.yaml

@@ -88,6 +88,7 @@ samples:
     splice_junctions_bed: scout/demo/ACC5963A1_lanes_1234_star_sorted_sj_filtered_sorted.bed.gz
     d4_file: scout/demo/ADM1059A3.d4
 
+
 custom_images:
   str_variants_images:
     - title: A png image

scout/load/panelapp.py

@@ -11,7 +11,6 @@ from scout.parse.panelapp import parse_panelapp_panel
 from scout.server.extensions import panelapp
 
 LOG = logging.getLogger(__name__)
-PANEL_NAME = "PANELAPP-GREEN"
 
 
 def load_panelapp_panel(
@@ -72,7 +71,14 @@ def get_panelapp_genes(
     return genes
 
 
-def load_panelapp_green_panel(adapter: MongoAdapter, institute: str, force: bool, signed_off: bool):
+def load_panelapp_green_panel(
+    adapter: MongoAdapter,
+    institute: str,
+    force: bool,
+    signed_off: bool,
+    panel_id: str,
+    panel_display_name: str,
+):
     """Load/Update the panel containing all Panelapp Green genes."""
 
     def parse_types_filter(types_filter: str, available_types: List[str]) -> List[str]:
@@ -85,10 +91,10 @@ def load_panelapp_green_panel(adapter: MongoAdapter, institute: str, force: bool
         return [available_types[i] for i in index_list]
 
     # check and set panel version
-    old_panel = adapter.gene_panel(panel_id=PANEL_NAME)
+    old_panel = adapter.gene_panel(panel_id=panel_id)
     green_panel = {
-        "panel_name": PANEL_NAME,
-        "display_name": "PanelApp Green Genes",
+        "panel_name": panel_id,
+        "display_name": panel_display_name,
         "institute": institute,
         "version": float(math.floor(old_panel["version"]) + 1) if old_panel else 1.0,
         "date": datetime.now(),

scout/models/case/case.py

@@ -14,6 +14,7 @@ individual = dict(
     mother=str,  # Individual id of mother
     capture_kits=list,  # List of names of capture kits
     bam_file=str,  # Path to bam file
+    minor_allele_frequency_wig=str,  # Path to wig file
     rhocall_bed=str,  # Path to bed file
     rhocall_wig=str,  # Path to wig file
     tiddit_coverage_wig=str,  # Path to wig file

scout/models/case/case_loading_models.py

@@ -25,9 +25,12 @@ LOG = logging.getLogger(__name__)
 REPID = "{REPID}"
 
 SAMPLES_FILE_PATH_CHECKS = [
+    "assembly_alignment_path",
     "bam_file",
     "d4_file",
+    "minor_allele_frequency_wig",
     "mitodel_file",
+    "paraphase_alignment_path",
     "rhocall_bed",
     "rhocall_wig",
     "rna_alignment_path",
@@ -201,6 +204,7 @@ class REViewer(BaseModel):
 
 class SampleLoader(BaseModel):
     alignment_path: Optional[str] = None
+    assembly_alignment_path: Optional[str] = None
     analysis_type: Literal[ANALYSIS_TYPES] = None
     bam_file: Optional[str] = ""
     bam_path: Optional[str] = None
@@ -216,11 +220,13 @@ class SampleLoader(BaseModel):
     individual_id: str = Field(alias="sample_id")
     is_sma: Optional[str] = None
     is_sma_carrier: Optional[str] = None
+    minor_allele_frequency_wig: Optional[str] = None
     mitodel_file: Optional[str] = None
     mitodel: Optional[Mitodel] = Mitodel()
     mother: Optional[str] = None
     msi: Optional[str] = None
     mt_bam: Optional[str] = None
+    paraphase_alignment_path: Optional[str] = None
     phenotype: Literal["affected", "unaffected", "unknown"]
     predicted_ancestry: Optional[str] = None
     reviewer: Optional[REViewer] = REViewer()
@@ -237,7 +243,7 @@ class SampleLoader(BaseModel):
     smn_27134_cn: Optional[int] = None
     splice_junctions_bed: Optional[str] = None
     subject_id: Optional[str] = None
-    tiddit_coverage_wig: Optional[str] = None
+    tiddit_coverage_wig: Optional[str] = Field(None, alias="coverage_wig")
     tissue_type: Optional[str] = None
     tmb: Optional[str] = None
     tumor_purity: Optional[float] = 0.0

scout/parse/ensembl.py

@@ -3,6 +3,8 @@
 import logging
 from typing import Any, Dict, List
 
+from scout.utils.ensembl_biomart_clients import CHROM_SEPARATOR
+
 LOG = logging.getLogger(__name__)
 
 
@@ -120,8 +122,8 @@ def parse_ensembl_genes(lines):
         if index == 0:
             header = line.rstrip().split("\t")
             continue
-        # After that each line represents a gene
-
+        elif line == CHROM_SEPARATOR:
+            continue
         yield parse_ensembl_line(line, header)
 
 
@@ -143,7 +145,8 @@ def parse_ensembl_transcripts(lines):
         # File allways start with a header line
         if index == 0:
             header = line.rstrip().split("\t")
-        # After that each line represents a transcript
+        elif line == CHROM_SEPARATOR:
+            continue
         else:
             yield parse_ensembl_line(line, header)
 
@@ -165,6 +168,8 @@ def parse_ensembl_exons(lines):
         if index == 0:
             header = line.rstrip().split("\t")
             continue
+        elif line == CHROM_SEPARATOR:
+            continue
 
         exon_info = parse_ensembl_line(line, header)
 

scout/parse/variant/clnsig.py

@@ -3,9 +3,47 @@ from typing import Dict, List, Optional, Union
 
 import cyvcf2
 
+from scout.constants.clnsig import ONC_CLNSIG
+
 LOG = logging.getLogger(__name__)
 
 
+def split_groups(value: str) -> List[str]:
+    """Removes leading underscore from a string and splits it into a list of items."""
+    return [
+        item.lstrip("_").replace(" ", "_")
+        for group in value.replace("&", ",").split(",")
+        for item in group.split("/")
+    ]
+
+
+def parse_clnsig_onc(variant: cyvcf2.Variant) -> List[dict]:
+    """Collect somatic oncogenicity ClinVar classifications for a variant, if available."""
+    if not variant.INFO.get("ONC"):
+        return []
+    acc = int(variant.INFO.get("CLNVID", 0))
+    onc_sig_groups = split_groups(value=variant.INFO.get("ONC", "").lower())
+    onc_revstat = ",".join(split_groups(value=variant.INFO.get("ONCREVSTAT", "").lower()))
+    onc_dn_groups = split_groups(variant.INFO.get("ONCDN", ""))
+
+    onc_clnsig_accessions = []
+
+    for i, onc_sig in enumerate(onc_sig_groups):
+        if (
+            onc_sig.capitalize() not in ONC_CLNSIG
+        ):  # This is excluding entries with ONC=no_classification_for_the_single_variant
+            continue
+        onc_clnsig_accessions.append(
+            {
+                "accession": acc,
+                "value": onc_sig,
+                "revstat": onc_revstat,
+                "dn": onc_dn_groups[i].replace("|", ","),
+            }
+        )
+    return onc_clnsig_accessions
+
+
 def parse_clnsig_low_penetrance(sig_groups: List[str]) -> List[str]:
     """If 'low_penetrance' is among the clnsig terms of an array, the term gets appended to the term immediately before in the array."""
     result = []

scout/parse/variant/genotype.py

@@ -27,16 +27,10 @@ GENOTYPE_MAP = {0: "0", 1: "1", -1: "."}
 LOG = logging.getLogger(__name__)
 
 
-def parse_genotypes(variant, individuals, individual_positions):
-    """Parse the genotype calls for a variant
-
-    Args:
-        variant(cyvcf2.Variant)
-        individuals: List[dict]
-        individual_positions(dict)
-    Returns:
-        genotypes(list(dict)): A list of genotypes
-    """
+def parse_genotypes(
+    variant: cyvcf2.Variant, individuals: List[Dict], individual_positions: Dict
+) -> List[Dict]:
+    """Parse the genotype calls for a variant"""
     genotypes = []
     for ind in individuals:
         pos = individual_positions[ind["individual_id"]]

scout/parse/variant/models.py

@@ -1,19 +1,13 @@
-def parse_genetic_models(models_info, case_id):
+def parse_genetic_models(models_info: str, case_id: str) -> list:
     """Parse the genetic models entry of a vcf
 
-    Args:
-        models_info(str): The raw vcf information
-        case_id(str)
-
-    Returns:
-        genetic_models(list)
-
+    Return inheritance patterns.
     """
     genetic_models = []
     if models_info:
         for family_info in models_info.split(","):
-            splitted_info = family_info.split(":")
-            if splitted_info[0] == case_id:
-                genetic_models = splitted_info[1].split("|")
+            split_info = family_info.split(":")
+            if split_info[0] == case_id:
+                genetic_models = split_info[1].split("|")
 
     return genetic_models

scout/parse/variant/rank_score.py

@@ -1,17 +1,9 @@
-def parse_rank_score(rank_score_entry, case_id):
-    """Parse the rank score
-
-    Args:
-        rank_score_entry(str): The raw rank score entry
-        case_id(str)
-
-    Returns:
-        rank_score(float)
-    """
+def parse_rank_score(rank_score_entry: str, case_id: str) -> float:
+    """Parse the rank score from the raw rank score entry"""
     rank_score = None
     if rank_score_entry:
         for family_info in rank_score_entry.split(","):
-            splitted_info = family_info.split(":")
-            if case_id == splitted_info[0]:
-                rank_score = float(splitted_info[1])
+            split_info = family_info.split(":")
+            if case_id == split_info[0]:
+                rank_score = float(split_info[1])
     return rank_score