scout-browser 4.96.0__py3-none-any.whl → 4.97.0__py3-none-any.whl

scout/constants/file_types.py

@@ -1,121 +1,70 @@
-# Collect general information about the file types used in Scout
-# Load priority determines load order, with lowest value loaded first.
+from collections import OrderedDict
 
-FILE_TYPE_MAP = {
-    "vcf_cancer": {
-        "category": "cancer",
-        "variant_type": "clinical",
-        "load_priority": 10,
-    },
-    "vcf_cancer_research": {
-        "category": "cancer",
-        "variant_type": "research",
-        "load_priority": 110,
-    },
-    "vcf_cancer_sv": {
-        "category": "cancer_sv",
-        "variant_type": "clinical",
-        "load_priority": 20,
-    },
-    "vcf_cancer_sv_research": {
-        "category": "cancer_sv",
-        "variant_type": "research",
-        "load_priority": 120,
-    },
-    "vcf_fusion": {
-        "category": "fusion",
-        "variant_type": "clinical",
-        "load_priority": 70,
-    },
-    "vcf_fusion_research": {
-        "category": "fusion",
-        "variant_type": "research",
-        "load_priority": 170,
-    },
-    "vcf_mei": {
-        "category": "mei",
-        "variant_type": "clinical",
-        "load_priority": 60,
-    },
-    "vcf_mei_research": {
-        "category": "mei",
-        "variant_type": "research",
-        "load_priority": 160,
-    },
-    "vcf_snv": {
-        "category": "snv",
-        "variant_type": "clinical",
-        "load_priority": 35,
-    },
-    "vcf_snv_mt": {
-        "category": "snv",
-        "variant_type": "clinical",
-        "load_priority": 30,
-    },
-    "vcf_snv_research": {
-        "category": "snv",
-        "variant_type": "research",
-        "load_priority": 135,
-    },
-    "vcf_snv_research_mt": {
-        "category": "snv",
-        "variant_type": "research",
-        "load_priority": 130,
-    },
-    "vcf_sv": {
-        "category": "sv",
-        "variant_type": "clinical",
-        "load_priority": 45,
-    },
-    "vcf_sv_mt": {
-        "category": "sv",
-        "variant_type": "clinical",
-        "load_priority": 40,
-    },
-    "vcf_sv_research": {
-        "category": "sv",
-        "variant_type": "research",
-        "load_priority": 145,
-    },
-    "vcf_sv_research_mt": {
-        "category": "sv",
-        "variant_type": "research",
-        "load_priority": 140,
-    },
-    "vcf_str": {
-        "category": "str",
-        "variant_type": "clinical",
-        "load_priority": 50,
-    },
-}
+# Variants in Scout will be loadedfor a case  in the same order as these ordered dictionaries
+ORDERED_FILE_TYPE_MAP = OrderedDict(
+    [
+        ("vcf_cancer", {"category": "cancer", "variant_type": "clinical"}),
+        ("vcf_cancer_sv", {"category": "cancer_sv", "variant_type": "clinical"}),
+        ("vcf_snv_mt", {"category": "snv", "variant_type": "clinical"}),
+        ("vcf_snv", {"category": "snv", "variant_type": "clinical"}),
+        ("vcf_sv_mt", {"category": "sv", "variant_type": "clinical"}),
+        ("vcf_sv", {"category": "sv", "variant_type": "clinical"}),
+        ("vcf_str", {"category": "str", "variant_type": "clinical"}),
+        ("vcf_mei", {"category": "mei", "variant_type": "clinical"}),
+        ("vcf_fusion", {"category": "fusion", "variant_type": "clinical"}),
+        ("vcf_cancer_research", {"category": "cancer", "variant_type": "research"}),
+        ("vcf_cancer_sv_research", {"category": "cancer_sv", "variant_type": "research"}),
+        ("vcf_snv_research_mt", {"category": "snv", "variant_type": "research"}),
+        ("vcf_snv_research", {"category": "snv", "variant_type": "research"}),
+        ("vcf_sv_research_mt", {"category": "sv", "variant_type": "research"}),
+        ("vcf_sv_research", {"category": "sv", "variant_type": "research"}),
+        ("vcf_mei_research", {"category": "mei", "variant_type": "research"}),
+        ("vcf_fusion_research", {"category": "fusion", "variant_type": "research"}),
+    ]
+)
 
-OMICS_FILE_TYPE_MAP = {
-    "fraser": {
-        "format": "tsv",
-        "analysis_type": "wts",
-        "category": "outlier",
-        "sub_category": "splicing",
-        "variant_type": "clinical",
-    },
-    "outrider": {
-        "format": "tsv",
-        "analysis_type": "wts",
-        "category": "outlier",
-        "sub_category": "expression",
-        "variant_type": "clinical",
-    },
-    "fraser_research": {
-        "format": "tsv",
-        "analysis_type": "wts",
-        "category": "outlier",
-        "sub_category": "splicing",
-        "variant_type": "research",
-    },
-    "outrider_research": {
-        "format": "tsv",
-        "analysis_type": "wts",
-        "category": "outlier",
-        "sub_category": "expression",
-        "variant_type": "research",
-    },
-}
+
+ORDERED_OMICS_FILE_TYPE_MAP = OrderedDict(
+    [
+        (
+            "fraser",
+            {
+                "format": "tsv",
+                "analysis_type": "wts",
+                "category": "outlier",
+                "sub_category": "splicing",
+                "variant_type": "clinical",
+            },
+        ),
+        (
+            "outrider",
+            {
+                "format": "tsv",
+                "analysis_type": "wts",
+                "category": "outlier",
+                "sub_category": "expression",
+                "variant_type": "clinical",
+            },
+        ),
+        (
+            "fraser_research",
+            {
+                "format": "tsv",
+                "analysis_type": "wts",
+                "category": "outlier",
+                "sub_category": "splicing",
+                "variant_type": "research",
+            },
+        ),
+        (
+            "outrider_research",
+            {
+                "format": "tsv",
+                "analysis_type": "wts",
+                "category": "outlier",
+                "sub_category": "expression",
+                "variant_type": "research",
+            },
+        ),
+    ]
+)

scout/constants/filters.py

@@ -6,7 +6,8 @@ CLINICAL_FILTER_BASE = {
     "region_annotations": ["exonic", "splicing"],
     "functional_annotations": SEVERE_SO_TERMS,
     "clinsig": [4, 5],
-    "clinsig_confident_always_returned": True,
+    "clinvar_trusted_revstat": True,
+    "prioritise_clinvar": True,
 }
 
 CLINICAL_FILTER_BASE_SV = {

scout/constants/gene_tags.py

@@ -79,8 +79,8 @@ UPDATE_GENES_RESOURCES = {
     "hpo_genes": ["genes_to_phenotype.txt", "genes_to_phenotype_reduced.txt"],
     "hgnc_lines": ["hgnc.txt", "hgnc_reduced_set.txt"],
     "exac_lines": [
-        "gnomad.v4.0.constraint_metrics.tsv",
-        "gnomad.v4.0.constraint_metrics_reduced.tsv",
+        "gnomad.v4.1.constraint_metrics.tsv",
+        "gnomad.v4.1.constraint_metrics_reduced.tsv",
     ],
     "ensembl_genes_37": ["ensembl_genes_37.txt", "ensembl_genes_37_reduced.txt"],
     "ensembl_genes_38": ["ensembl_genes_38.txt", "ensembl_genes_38_reduced.txt"],
@@ -94,7 +94,7 @@ UPDATE_GENES_RESOURCES = {
     ],
 }
 
-GNOMAD_CONSTRAINT_FILENAME = "gnomad.v4.0.constraint_metrics.tsv"
+GNOMAD_CONSTRAINT_FILENAME = "gnomad.v4.1.constraint_metrics.tsv"
 
 GENE_CONSTRAINT_LABELS = {
     "pli_score": "lof.pLI",

scout/constants/igv_tracks.py

@@ -3,22 +3,20 @@ HG19REF_URL = (
     "https://s3.amazonaws.com/igv.broadinstitute.org/genomes/seq/1kg_v37/human_g1k_v37_decoy.fasta"
 )
 HG19REF_INDEX_URL = "https://s3.amazonaws.com/igv.broadinstitute.org/genomes/seq/1kg_v37/human_g1k_v37_decoy.fasta.fai"
-HG19CYTOBAND_URL = "https://s3.amazonaws.com/igv.broadinstitute.org/genomes/seq/hg19/cytoBand.txt"
+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"
 
 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"
-HG38CYTOBAND_URL = (
-    "https://s3.amazonaws.com/igv.broadinstitute.org/annotations/hg38/cytoBandIdeo.txt"
-)
+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_FORMAT = "refgene"
 
-HG38GENES_FORMAT = "gtf"
-HG38GENES_URL = "https://s3.amazonaws.com/igv.broadinstitute.org/annotations/hg38/genes/Homo_sapiens.GRCh38.80.sorted.gtf.gz"
-HG38GENES_INDEX_URL = "https://s3.amazonaws.com/igv.broadinstitute.org/annotations/hg38/genes/Homo_sapiens.GRCh38.80.sorted.gtf.gz.tbi"
-HG19GENES_FORMAT = "refgene"
 HG19GENES_URL = "https://s3.amazonaws.com/igv.org.genomes/hg19/ncbiRefSeq.sorted.txt.gz"
 HG19GENES_INDEX_URL = "https://s3.amazonaws.com/igv.org.genomes/hg19/ncbiRefSeq.sorted.txt.gz.tbi"
+HG19GENES_FORMAT = "refgene"
 
 HG38CLINVAR_URL = "https://hgdownload.soe.ucsc.edu/gbdb/hg38/bbi/clinvar/clinvarMain.bb"
 HG19CLINVAR_URL = "https://hgdownload.soe.ucsc.edu/gbdb/hg19/bbi/clinvar/clinvarMain.bb"
@@ -104,7 +102,6 @@ CLINVAR_SV_38 = {
 # Human genes track, build 37
 HUMAN_GENES_37 = {
     "name": "Genes",
-    "track_name": "genes_track",
     "type": "annotation",
     "sourceType": "file",
     "displayMode": "EXPANDED",
@@ -117,14 +114,13 @@ HUMAN_GENES_37 = {
 # Human genes track, build 38
 HUMAN_GENES_38 = {
     "name": "Genes",
-    "track_name": "genes_track",
     "type": "annotation",
     "sourceType": "file",
     "displayMode": "EXPANDED",
     "visibilityWindow": 300000000,
     "format": HG38GENES_FORMAT,
     "url": HG38GENES_URL,
-    "indexURL": HG38GENES_INDEX_URL,
+    "order": 1000000,
 }
 
 CASE_SPECIFIC_TRACKS = {

scout/constants/query_terms.py

@@ -18,13 +18,14 @@ FUNDAMENTAL_CRITERIA = [
     "variant_ids",
     "hide_dismissed",
     "show_unaffected",
+    "show_soft_filtered",
 ]
 
 # If there is only one primary criterion given without any secondary, it will also be
 # added as a top level '$and'.
 # Otherwise, primary criteria are added as a high level '$or' and all secondary criteria
 # are joined together with them as a single lower level '$and'.
-PRIMARY_CRITERIA = ["clinsig"]
+PRIMARY_CRITERIA = ["clinsig", "clinvar_tag"]
 
 # Secondary, excluding filter criteria will hide variants in general,
 # but can be overridden by an including, major filter criteria
@@ -53,7 +54,6 @@ SECONDARY_CRITERIA = [
     "somatic_score",
     "control_frequency",
     "mvl_tag",
-    "clinvar_tag",
     "cosmic_tag",
     "tumor_frequency",
     "fusion_score",

scout/demo/643594.config.yaml

@@ -131,6 +131,8 @@ vcf_mei_research: scout/demo/643594.research.mei.vcf.gz
 omics_files:
     fraser: scout/demo/drop/fraser_top_hits_clinical.tsv
     outrider: scout/demo/drop/outrider_top_hits_clinical.tsv
+    fraser_research: scout/demo/drop/fraser_top_hits_clinical.tsv
+    outrider_research: scout/demo/drop/outrider_top_hits_clinical.tsv
 
 smn_tsv: scout/demo/643594.solo.smn.tsv
 
@@ -140,6 +142,10 @@ peddy_ped: scout/demo/643594.peddy.ped
 peddy_check: scout/demo/643594.ped_check.csv
 peddy_sex: scout/demo/643594.sex_check.csv
 
+somalier_ancestry: scout/demo/643594.somalier.ancestry.tsv
+somalier_pairs: scout/demo/643594.somalier.pairs.tsv
+somalier_samples: scout/demo/643594.somalier.samples.tsv
+
 delivery_report: scout/demo/delivery_report.html
 gene_fusion_report: scout/demo/draw-fusions-example.pdf
 rna_delivery_report: scout/demo/delivery_report.html

scout/demo/643594.peddy.ped

@@ -1,4 +1,4 @@
 #family_id	sample_id	paternal_id	maternal_id	sex	phenotype	het_call_rate	het_ratio	het_mean_depth	het_idr_baf	ancestry-prediction	PC1	PC2	PC3	sex_het_ratio
-643594-300M	ADM1059A2	ADM1059A1	ADM1059A3	1	1	1	0.4899	23.7	0.2871	EUR	-0.2145	-1.629	-0.4117	0.03289
+643594-300M	ADM1059A2	ADM1059A1	ADM1059A3	1	2	1	0.4899	23.7	0.2871	EUR	-0.2145	-1.629	-0.4117	0.03289
 643594-300M	ADM1059A1	0	0	1	1	1	0.4815	24	0.2802	EUR	-0.1179	-1.482	-0.62	0.0328
 643594-300M	ADM1059A3	0	0	2	1	1	0.475	21.95	0.2941	EUR	-0.3578	-1.546	-0.4366	1.7

scout/demo/643594.somalier.ancestry.tsv

@@ -0,0 +1,4 @@
+#sample_id	predicted_ancestry	given_ancestry
+ADM1059A2	EUR	EUR
+ADM1059A1	EUR	EUR
+ADM1059A3	EUR	EUR

scout/demo/643594.somalier.pairs.tsv

@@ -0,0 +1,4 @@
+#sample_a	sample_b	relatedness	ibs0	ibs2	hom_concordance	hets_a	hets_b	hets_ab	shared_hets	hom_alts_a	hom_alts_b	shared_hom_alts	n	x_ibs0	x_ibs2	expected_relatedness
+ADM1059A2	ADM1059A1	0.5051	7	8452	1	8019	7882	1	3995	1	1	1	16370	7	8452	0.5
+ADM1059A2	ADM1059A3	0.5012	5	8384	1	8019	7776	1	3907	1	1	1	16370	5	8384	0.5
+ADM1059A1	ADM1059A3	-0.01492	1539	5097	1	7882	7776	1	2962	1	1	1	16370	1539	5097	0

scout/demo/643594.somalier.samples.tsv

@@ -0,0 +1,4 @@
+#family_id	sample_id	paternal_id	maternal_id	sex	phenotype	original_pedigree_sex	gt_depth_mean	gt_depth_sd	depth_mean	depth_sd	ab_mean	ab_std	n_hom_ref	n_het	n_hom_alt	n_unknown	p_middling_ab	X_depth_mean	X_n	X_hom_ref	X_het	X_hom_alt	Y_depth_mean	Y_n
+643594-300M	ADM1059A2	ADM1059A1	ADM1059A3	1	2	male	31.6	8.0	31.6	8.0	0.53	0.39	4569	6770	5632	413	0.009	16.45	347	164	0	183	18.38	16
+643594-300M	ADM1059A1	0	0	1	1	male	31.6	8.0	31.6	8.0	0.53	0.39	4569	6770	5632	413	0.009	16.45	347	164	0	183	18.38	16
+643594-300M	ADM1059A3	0	0	2	1	female	31.6	8.0	31.6	8.0	0.53	0.39	4569	6770	5632	413	0.009	16.45	347	164	0	183	18.38	16

scout/demo/cancer.load_config.yaml

@@ -17,6 +17,7 @@ samples:
     vcf2cytosure: scout/demo/999-99.test.cgh
     tmb: 7
     msi: 15
+    hrd: 93
     tumor_purity: 0.1
 
   - analysis_type: panel

scout/demo/resources/__init__.py

@@ -10,7 +10,7 @@ BASE_PATH = "scout.demo.resources"
 reduced_resources_path = str(files(BASE_PATH))
 hgnc_reduced_path = str(files(BASE_PATH).joinpath("hgnc_reduced_set.txt"))
 constraint_reduced_path = str(
-    files(BASE_PATH).joinpath("gnomad.v4.0.constraint_metrics_reduced.tsv")
+    files(BASE_PATH).joinpath("gnomad.v4.1.constraint_metrics_reduced.tsv")
 )
 transcripts37_reduced_path = str(files(BASE_PATH).joinpath("ensembl_transcripts_37_reduced.txt"))
 transcripts38_reduced_path = str(files(BASE_PATH).joinpath("ensembl_transcripts_38_reduced.txt"))