def defFavorFlt(metadata_record):
assert metadata_record.get("data_schema") == "FAVOR", (
"FAVOR data schema expected: " + metadata_record.get("data_schema"))
filters = FilterPrepareSetH(metadata_record,
anfisaVariables,
check_identifiers=False)
with filters.viewGroup("Coordinates"):
filters.statusUnit("Chromosome",
"/_filters/chromosome",
variants=[
"chr1", "chr2", "chr3", "chr4", "chr5", "chr6",
"chr7", "chr8", "chr9", "chr10", "chr11",
"chr12", "chr13", "chr14", "chr15", "chr16",
"chr17", "chr18", "chr19", "chr20", "chr21",
"chr22", "chr23", "chrX", "chrY", "undefined"
],
default_value="undefined")
filters.intValueUnit("Position",
"/_filters/position",
default_value=sys.maxsize)
with filters.viewGroup("Genes"):
genes_unit = filters.multiStatusUnit(
"Symbol",
# "/_filters/genes[]",
"/_view/general/genes[]",
compact_mode=True)
filters.panelsUnit("Panels",
genes_unit,
"Symbol",
view_path="/_view/general/gene_panels")
filters.intValueUnit("Num_Genes",
"/_view/general/genes",
conversion="len",
default_value=0)
with filters.viewGroup("gnomAD"):
filters.floatValueUnit("gnomAD_Total_AF",
"/_filters/gnomad_total_af",
diap=(0., 1.),
default_value=0.)
with filters.viewGroup("GENCODE"):
filters.multiStatusUnit("GENCODE_Category",
"/_filters/gencode_category[]",
default_value="None")
filters.multiStatusUnit("GENCODE_Exonic_Category",
"/_filters/gencode_exonic_category",
compact_mode=True)
with filters.viewGroup("TOPMed"):
filters.multiStatusUnit("TOPMed_QC_Status",
"/_filters/top_med_qc_status[]",
default_value="None")
filters.floatValueUnit("TOPMed_Bravo_AF",
"/_filters/top_med_bravo_af",
default_value=0.)
with filters.viewGroup("Allele Frequencies"):
filters.floatValueUnit("ExAC03",
"/_filters/exac03",
render_mode="linear,<",
default_value=0.)
with filters.viewGroup("Variant Category"):
filters.multiStatusUnit("Disruptive_Missense",
"/_filters/disruptive_missense",
default_value="N/A")
filters.multiStatusUnit("CAGE_Promoter",
"/_filters/cage_promoter",
default_value="N/A")
filters.multiStatusUnit("CAGE_Enhancer",
"/_filters/cage_enhancer",
default_value="N/A")
filters.multiStatusUnit("Gene_Hancer",
"/_filters/gene_hancer",
default_value="N/A")
filters.multiStatusUnit("Super_Enhancer",
"/_filters/super_enhancer",
default_value="N/A")
with filters.viewGroup("Nucleotide Diversity"):
filters.floatValueUnit("bStatistics",
"/_filters/bstatistics",
default_value=0.)
with filters.viewGroup("Mutation Rate"):
filters.floatValueUnit("Freq1000bp",
"/_filters/freq1000bp",
default_value=0.)
filters.floatValueUnit("Rare1000bp",
"/_filters/rare1000bp",
default_value=0.)
with filters.viewGroup("Predictions"):
filters.multiStatusUnit("Clinvar",
"/_filters/clinvar[]",
default_value="N/A")
with filters.viewGroup("Protein Function"):
filters.multiStatusUnit("Polyphen_2_HVAR",
"/_filters/polyphen2_hvar",
default_value="N/A")
filters.multiStatusUnit("Polyphen_2_HDIV",
"/_filters/polyphen2_hdiv",
default_value="N/A")
filters.multiStatusUnit("PolyPhenCat",
"/_filters/polyphen_cat",
default_value="N/A")
filters.multiStatusUnit("SIFTcat",
"/_filters/sift_cat",
default_value="N/A")
with filters.viewGroup("Integrative Score"):
filters.floatValueUnit("GC", "/_filters/gc", default_value=0.)
filters.floatValueUnit("CpG", "/_filters/cpg", default_value=0.)
return filters
def defineFilterSchema(metadata_record):
data_schema = metadata_record.get("data_schema")
if data_schema == "FAVOR":
return FavorSchema.defineFilterSchema(metadata_record)
assert data_schema is None or data_schema == "CASE", (
"Bad data schema: " + data_schema)
filters = FilterPrepareSetH(metadata_record)
cohorts = metadata_record.get("cohorts")
with filters.viewGroup("Inheritance"):
if cohorts:
filters.multiStatusUnit("Variant_in",
"/_filters/cohort_has_variant[]")
filters.multiStatusUnit("Callers", "/_view/bioinformatics/called_by[]",
title = "Called by")
filters.statusUnit("Proband_Zygosity",
"/_view/bioinformatics/zygosity",
title = "Proband Zygosity")
filters.intValueUnit("Num_Samples", "/_filters/has_variant",
title = "Number of Samples",
conversion = ["len"], default_value = 0,
tooltip =
"Number of samples for which this variant has been called")
filters.multiStatusUnit("Has_Variant", "/_filters/has_variant[]")
if cohorts:
all_cohorts = ["ALL"] + [ch["name"] for ch in cohorts]
with filters.viewGroup("Cohorts"):
for ch_name in all_cohorts:
filters.floatValueUnit(ch_name + "_AF",
"/_view/cohorts/" + ch_name + "/AF",
default_value = 0)
filters.floatValueUnit(ch_name + "_AF2",
"/_view/cohorts/" + ch_name + "/AF2",
default_value = 0, title = "AF_Hom")
with filters.viewGroup("Variant"):
filters.statusUnit("Variant_Class", "/__data/variant_class",
tooltip = ("Variant class as returned by VEP. "
"The class of a variant is based on Sequence "
"Ontology and is called according to its component "
"alleles and its mapping to the reference genome. "
"https://useast.ensembl.org/info/genome/variation/"
"prediction/classification.html#classes"))
filters.statusUnit("Most_Severe_Consequence",
"/__data/most_severe_consequence",
variants = sConsequenceVariants,
default_value = "undefined")
filters.multiStatusUnit("Canonical_Annotation",
"/_view/general/canonical_annotation[]",
default_value = "undefined")
filters.statusUnit("Multiallelic", "/_filters/multiallelic",
title = "Multi-allelic?")
filters.statusUnit("Altered_VCF", "/_filters/altered_vcf",
title = "Has VCF been normalized?")
# filters.intValueUnit("Number_ALTs",
# "/_filters/alts",
# title = "Number of Alternative alleles",
# conversion = ["len"], default_value = 0)
#filters.intValueUnit("zyg_len", "/__data/zygosity",
# conversion = ["len"], default_value = 0)
with filters.viewGroup("Genes"):
genes_unit = filters.multiStatusUnit("Symbol",
"/_view/general/genes[]",
compact_mode = True)
filters.panelsUnit("Panels", genes_unit, "Symbol",
view_path = "/_view/general/gene_panels")
filters.multiStatusUnit("EQTL_Gene", "/_filters/eqtl_gene[]",
title = "EQTL Gene", default_value = "None")
#filters.multiStatusUnit("Transcripts",
# "/__data/transcript_consequences[]", compact_mode = True,
# conversion = [["property", transcript_id"]])
filters.intValueUnit("Num_Genes", "/_view/general/genes",
title = "Number of overlapping genes",
conversion = ["len"], default_value = 0)
filters.intValueUnit("Num_Transcripts",
"/__data/transcript_consequences",
title = "Number of transcripts at the position",
conversion = ["len"], default_value = 0)
with filters.viewGroup("Transcripts"):
filters.transcriptMultisetUnit("Transcript_consequence",
"transcript_annotations", variants = sConsequenceVariants,
default_value = "undefined")
filters.transcriptStatusUnit("Transcript_canonical", "is_canonical",
bool_check_value = "True", default_value = "False")
filters.transcriptStatusUnit("Transcript_GENCODE_Basic",
"gencode_basic", bool_check_value = "True",
default_value = "False")
filters.transcriptStatusUnit("Transcript_biotype", "biotype",
default_value = "undefined")
filters.transcriptStatusUnit("Transcript_worst", "is_worst",
bool_check_value = "True", default_value = "False")
filters.transcriptStatusUnit("Transcript_id", "id",
default_value = "undefined")
tr_genes_unit = filters.transcriptStatusUnit("Transctript_Gene",
"gene", default_value = "undefined")
filters.transcriptPanelsUnit("Transcript_Gene_Panels",
tr_genes_unit, "Symbol", view_name = "tr_gene_panels")
filters.transcriptStatusUnit("Transcript_source", "transcript_source",
default_value = "undefined")
filters.transcriptStatusUnit("Transcript_codon_pos", "codonpos",
default_value = "undefined")
filters.transcriptStatusUnit("Transcript_region", "region",
title= "Gene Region", default_value = "undefined")
filters.transcriptStatusUnit("Transcript_CDS", "cds",
title= "CDS?", default_value = "-")
filters.transcriptStatusUnit("Transcript_masked", "masked_region",
title= "Masked", default_value = "No")
filters.transcriptIntValueUnit("Transcript_dist_from_exon",
"dist_from_exon",
title = "Distance from Exon Boundary", default_value = -1)
# filters.transcriptStatusUnit("Transcript_strand", "strand",
# default_value = "undefined")
with filters.viewGroup("Transcript_Predictions"):
filters.transcriptStatusUnit(
"Transcript_PolypPhen_HDIV", "polyphen2_hdiv_prediction")
filters.transcriptStatusUnit(
"Transcript_PolyPhen_HVAR", "polyphen2_hvar_prediction")
filters.transcriptStatusUnit(
"Transcript_SIFT", "sift_prediction")
filters.transcriptStatusUnit(
"Transcript_SIFT_4G", "sift_4g_prediction")
filters.transcriptStatusUnit(
"Transcript_FATHMM", "fathmm_prediction")
# with filters.viewGroup("Transcripts"):
# filters.transcriptMultisetUnit("Transcript_consequence",
# "consequence_terms", variants = sConsequenceVariants,
# default_value = "undefined")
# filters.transcriptStatusUnit("Transcript_canonical", "canonical",
# bool_check_value = "1", default_value = "False")
# filters.transcriptStatusUnit("Transcript_biotype", "biotype",
# default_value = "undefined")
# filters.transcriptStatusUnit("Transcript_worst", "consequence_terms",
# bool_check_value = "${Most_Severe_Consequence}",
# default_value = "False")
# filters.transcriptStatusUnit("Transcript_id", "transcript_id",
# default_value = "undefined")
# filters.transcriptStatusUnit("Transctript_gene_id", "gene_id",
# default_value = "undefined")
# filters.transcriptStatusUnit("Transcript_source", "source",
# default_value = "undefined")
# filters.transcriptStatusUnit("Transcript_strand", "strand",
# default_value = "undefined")
with filters.viewGroup("Coordinates"):
filters.statusUnit("Chromosome", "/_filters/chromosome",
variants = ["chr1", "chr2", "chr3", "chr4", "chr5",
"chr6", "chr7", "chr8", "chr9", "chr10",
"chr11", "chr12", "chr13", "chr14", "chr15",
"chr16", "chr17", "chr18", "chr19", "chr20",
"chr21", "chr22", "chr23", "chrX", "chrY", "undefined"],
default_value = "undefined")
filters.intValueUnit("Start_Pos", "/__data/start",
title = "Start Position",
render_mode = "neighborhood", default_value = sys.maxsize)
filters.intValueUnit("End_Pos", "/__data/end",
title = "End Position", default_value = 0,
render_mode = "neighborhood")
filters.intValueUnit("Dist_from_Exon", "/_filters/dist_from_exon",
title = "Distance From Intron/Exon Boundary (Canonical)",
default_value = 0, render_mode = "log,<")
filters.intValueUnit("Dist_from_Exon_Canonical",
"/_filters/dist_from_exon_canonical",
title = "Distance From Intron/Exon Boundary (Canonical)",
default_value = 0, render_mode = "log,<", conversion = ["min"])
filters.intValueUnit("Dist_from_Exon_Worst",
"/_filters/dist_from_exon_worst",
title = "Distance From Intron/Exon Boundary (Canonical)",
default_value = 0, render_mode = "log,<", conversion = ["min"])
filters.multiStatusUnit("Region_Canonical",
"/__data/region_canonical[]",
title = "Region (Canonical)", default_value = "Other")
filters.multiStatusUnit("Region_Worst", "/__data/region_worst[]",
title = "Region (Canonical)", default_value = "Other")
filters.statusUnit("Region", "/__data/region_canonical",
title = "Region (Legacy)", default_value = "Other", )
filters.statusUnit("hg19", "/_view/general/hg19", title = "HG19",
conversion = [["filter", "is_none"]],
value_map= {"None": "Unmapped"}, default_value = "Mapped")
with filters.viewGroup("gnomAD"):
filters.floatValueUnit("gnomAD_AF",
"/_filters/gnomad_af_fam",
diap = (0., 1.), default_value = 0.,
title = "gnomAD Allele Frequency (family)",
tooltip = "gnomAD Overall Allele Frequency",
render_mode = "log,<")
filters.floatValueUnit("gnomAD_AF_Exomes",
"/_filters/gnomad_db_exomes_af",
diap = (0., 1.), default_value = 0.,
title = "gnomAD Exome Allele Frequency (family)",
render_mode = "log,<")
filters.floatValueUnit("gnomAD_AF_Genomes",
"/_filters/gnomad_db_genomes_af",
diap = (0., 1.), default_value = 0.,
title = "gnomAD Genome Allele Frequency (family)",
render_mode = "log,<")
filters.floatValueUnit("gnomAD_AF_Proband",
"/_filters/gnomad_af_pb",
diap = (0., 1.), default_value = 0.,
title = "gnomAD Allele Frequency (proband)",
tooltip = "gnomAD Overall Allele Frequency "
"for the allele present in proband",
render_mode = "log,<")
filters.floatValueUnit("gnomAD_PopMax_AF",
"/_filters/gnomad_popmax_af",
tooltip = "Maximum allele frequency across outbred populations",
diap = (0., 1.), default_value = 0.,
title = "PopMax Allele Frequency",
render_mode = "log,<")
filters.statusUnit("gnomAD_PopMax",
"/_filters/gnomad_popmax", default_value = "None",
title = "PopMax Ancestry",
tooltip =
"Outbred population that has the maximum allele frequency")
filters.intValueUnit("gnomAD_PopMax_AN",
"/_filters/gnomad_popmax_an",
default_value = 0,
title = "Number of alleles in outbred PopMax Ancestry",
render_mode = "log,>")
filters.floatValueUnit("gnomAD_PopMax_AF_Inbred",
"/_filters/gnomad_raw_popmax_af",
tooltip = "Maximum allele frequency across all populations "
+ "(including inbred)",
diap = (0., 1.), default_value = 0.,
title = "PopMax Allele Frequency (including inbred)",
render_mode = "log,<")
filters.statusUnit("gnomAD_PopMax_Inbred",
"/_filters/gnomad_raw_popmax", default_value = "None",
title = "PopMax Ancestry (including inbred)",
tooltip = "Population, including inbred, that has the maximum "
+ "allele frequency")
filters.intValueUnit("gnomAD_PopMax_AN_Inbred",
"/_filters/gnomad_raw_popmax_an",
default_value = 0, render_mode = "log,>",
title = "Number of alleles in (inbred) PopMax Ancestry")
filters.intValueUnit("gnomAD_Hom",
"/_filters/gnomad_hom",
default_value = 0, render_mode = "log,>",
title = "gnomAD: Number of homozygous")
filters.intValueUnit("gnomAD_Hem",
"/_filters/gnomad_hem",
default_value = 0, render_mode = "log,>",
title = "gnomAD: Number of hemizygous")
with filters.viewGroup("Databases"):
presence_in_db = [
("ClinVar", "/_view/databases/clinVar"),
("GnomAD", "/_filters/gnomad_af_fam"),
("HGMD", "/__data/hgmd_pmids[]"),
("OMIM", "/_view/databases/omim")]
for submitter in sorted(filters.getStdItem(
"item-dict", "Clinvar_Trusted_Submitters").getData().values()):
presence_in_db.append((submitter,
"/_view/databases/clinvar_trusted/%s" % submitter))
filters.presenceUnit("Presence_in_Databases", presence_in_db,
title = "Presence in Databases")
filters.multiStatusUnit("ClinVar_Submitters",
"/_view/databases/clinVar_submitters[]",
title = "ClinVar Submitters", compact_mode = True)
filters.intValueUnit("Number_submitters",
"/_view/databases/clinVar_submitters",
title = "Number of ClinVar Submitters",
conversion = ["len"], default_value = 0)
filters.multiStatusUnit("PMIDs",
"/_view/databases/references[]",
title = "PMIDs", compact_mode = True)
filters.intValueUnit("Number_pmid",
"/_view/databases/references",
title = "Number of PMIDs",
conversion = ["len"], default_value = 0)
# filters.multiStatusUnit("beacons",
# "/__data/beacon_names",
# title = "Observed at")
with filters.viewGroup("Call_Quality"):
filters.floatValueUnit("Proband_GQ", "/_filters/proband_gq",
title = "Genotype Quality (GQ) for Proband",
render_mode = "linear,>", default_value = -1,
tooltip = "GQ tells you how confident we are that "
"the genotype we assigned to a particular sample is correct. "
"It is simply the second lowest PL, because it is the "
"difference between the second lowest PL and the lowest PL "
"(always 0).")
filters.floatValueUnit("Min_GQ", "/_filters/min_gq",
title = "Minimum GQ for the family", render_mode = "linear,>",
default_value = -1,
tooltip = "GQ tells you how confident we are that "
"the genotype we assigned to a particular sample is correct. "
"It is simply the second lowest PL, because it is the "
"difference between the second lowest PL and the lowest PL "
"(always 0).")
filters.intValueUnit("Max_GQ", "/_view/quality_samples",
title = "The highest GQ",
tooltip= "Max(GQ) for those samples that have the variant",
render_mode = "linear,=", default_value = 0,
conversion = [
["filter", "has_variant"],
["property", "genotype_quality"],
"max"])
filters.intValueUnit("Num_NO_CALL", "/_view/quality_samples",
title = "Number of NO_CALL samples",
tooltip= "Number of samples with NO_CALL in the current site",
render_mode = "linear,=", default_value = 0,
conversion = [
["skip", 1],
["property", "genotype_quality"],
"negative", "len"])
filters.intValueUnit("QUAL", "/_filters/qual",
title = "Variant Call Quality",
default_value = -1)
filters.floatValueUnit("QD", "/_filters/qd",
title = "Quality by Depth",
render_mode = "linear,>", default_value = -1.,
tooltip = "The QUAL score normalized by allele depth (AD) "
"for a variant. This annotation puts the variant confidence "
"QUAL score into perspective by normalizing for the amount "
"of coverage available. Because each read contributes a little "
"to the QUAL score, variants in regions with deep coverage "
"can have artificially inflated QUAL scores, giving the "
"impression that the call is supported by more evidence "
"than it really is. To compensate for this, we normalize "
"the variant confidence by depth, which gives us a more "
"objective picture of how well supported the call is.")
filters.floatValueUnit("FS", "/_filters/fs",
title = "Fisher Strand Bias",
render_mode = "linear,<", default_value = 0.,
tooltip = "Phred-scaled probability that there is strand bias "
"at the site. Strand Bias tells us whether the alternate "
"allele was seen more or less often on the forward or "
"reverse strand than the reference allele. When there "
"little to no strand bias at the site, the FS value "
"will be close to 0.")
filters.multiStatusUnit("FT", "/_filters/filters[]", title = "FILTER",
tooltip = "This field contains the name(s) of any filter(s) "
"that the variant fails to pass, or the value PASS if the "
"variant passed all filters. If the FILTER value is ., "
"then no filtering has been applied to the records.")
with filters.viewGroup("Predictions"):
# research_only = True
filters.statusUnit("HGMD_Benign", "/_filters/hgmd_benign",
title = "Categorized Benign in HGMD",
default_value = "Not in HGMD",
value_map = {"True": "Benign", "False": "VUS or Pathogenic"})
filters.multiStatusUnit("HGMD_Tags", "/_view/databases/hgmd_tags[]",
default_value = "None")
# research_only = True
filters.statusUnit("Clinvar_Benign", "/_filters/clinvar_benign",
default_value = "Not in ClinVar",
title = "Categorized Benign in ClinVar by all submitters",
value_map = {"True": "Benign", "False": "VUS or Pathogenic"})
filters.multiStatusUnit("ClinVar_Significance",
"/__data/clinvar_significance[]",
title = "Clinical Significance in ClinVar")
filters.regPreTransform(lambda rec_no, rec_data:
clinvarPreTransform(rec_data, filters.getStdItem(
"item-dict", "Clinvar_Trusted_Submitters").getData()))
filters.multiStatusUnit("Clinvar_Trusted_Significance",
"/_view/databases/clinvar_trusted",
title = "ClinVar significance by trusted submitters only",
tooltip =
"Clinical Significance by ClinVar trusted submitters only",
conversion = ["values", ["split", ','], "clear", "uniq"])
filters.multiStatusUnit("Clinvar_Trusted_Simplified",
"/_view/databases/clinvar_trusted_simplified",
tooltip =
"Simplified Clinical Significance by trusted submitters only",
conversion = ["values", ["split", ','], "clear", "uniq"])
filters.statusUnit("Clinvar_stars", "/_filters/clinvar_stars",
default_value = "No data", title = "ClinVar Stars")
filters.intValueUnit("Number_of_clinvar_submitters",
"/_filters/num_clinvar_submitters", render_mode = "log,>",
default_value = 0, title = "ClinVar: Number of Submitters")
filters.statusUnit("Clinvar_review_status",
"/_filters/clinvar_review_status",
default_value = "No data", title = "ClinVar Review Status")
filters.statusUnit("Clinvar_criteria_provided",
"/_filters/clinvar_criteria_provided",
default_value = "Not Provided", title = "ClinVar Criteria")
filters.statusUnit("Clinvar_conflicts",
"/_filters/clinvar_conflicts",
default_value = "Criteria not Provided",
title = "ClinVar Conflicts")
filters.multiStatusUnit("Clinvar_acmg_guidelines",
"/_filters/clinvar_acmg_guidelines[]",
default_value = "None")
for submitter in sorted(filters.getStdItem(
"item-dict", "Clinvar_Trusted_Submitters").getData().values()):
filters.statusUnit("%s_Significance" % submitter,
"/_view/databases/clinvar_trusted",
title = "Clinical Significance by %s" % submitter,
conversion = [["property", submitter]],
default_value = "None")
#filters.statusUnit("Clinvar_Trusted_Benign",
# "/_filters/clinvar_trusted_benign",
# default_value = "No data",
# title = "Categorized Benign by Clinvar Trusted Submitters",
# value_map = {"True": "Benign by Trusted submitters",
# "False": "Unknown"})
filters.statusUnit("splice_altering", "/_filters/splice_altering",
title = "Splice AI splice altering",
default_value = "No altering")
filters.floatValueUnit("splice_ai_dsmax", "/_filters/splice_ai_dsmax",
title = "Splice AI splice altering score",
render_mode = "linear,>", default_value = 0)
# filters.multiStatusUnit("Polyphen", "/_view/predictions/polyphen[]",
# default_value = "N/A")
# This is an obsolete filter replaced by Polyphen 2
filters.multiStatusUnit("Polyphen_2_HVAR",
"/_view/predictions/polyphen2_hvar[]",
title = "Polyphen",
conversion = [["split_re", r"[\s\,]"], "clear", "uniq"],
default_value = "N/A",
tooltip = "HumVar (HVAR) is PolyPhen-2 classifier "
"trained on known human variation (disease mutations vs."
" common neutral variants)")
filters.multiStatusUnit("Polyphen_2_HDIV",
"/_view/predictions/polyphen2_hdiv[]",
title = "Polyphen HDIV (High sensitivity)",
conversion = [["split_re", r"[\s\,]"], "clear", "uniq"],
default_value = "N/A",
tooltip = "HumDiv (HDIV) classifier is trained on a smaller "
"number of select extreme effect disease mutations vs. "
"divergence with close homologs (e.g. primates), which is "
"supposed to consist of mostly neutral mutations.")
filters.multiStatusUnit("SIFT", "/_view/predictions/sift[]",
default_value = "N/A",
tooltip = "Sort intolerated from tolerated (An amino acid at a "
"position is tolerated | The most frequentest amino acid "
"being tolerated). D: Deleterious T: tolerated")
filters.multiStatusUnit("FATHMM", "/_view/predictions/fathmm[]",
default_value = "N/A",
tooltip = "Functional analysis through hidden markov model HMM."
"D: Deleterious; T: Tolerated")
filters.multiStatusUnit("PrimateAI",
"/_view/predictions/primate_ai_pred[]",
default_value = "N/A",
tooltip = "Prediction of PrimateAI score based on the authors "
"recommendation, “T(olerated)” or “D(amaging)”. "
"The score cutoff between “D” and “T” is 0.803.")
filters.floatValueUnit("GERP_score", "/_view/bioinformatics/gerp_rs",
render_mode = "linear,>", default_value = 0, title = "GERP Score")
with filters.viewGroup("Pharmacogenomics"):
filters.multiStatusUnit("Diseases",
"/_filters/pharmacogenomics_diseases[]", default_value = "N/A")
filters.multiStatusUnit("Chemicals",
"/_filters/pharmacogenomics_chemicals[]", default_value = "N/A")
with filters.viewGroup("Expression"):
filters.multiStatusUnit("Mostly_Expressed_in",
"/_filters/top_tissues[]", default_value = "N/A")
# required = {"debug"}
with filters.viewGroup("Debug_Info"):
filters.intValueUnit("Severity", "/_filters/severity",
default_value = -1)
return filters
s_value = "other"
clinvar_trusted_simplified[trusted_map[submitter]] = s_value
rec_data["_view"]["databases"]["clinvar_trusted"] = clinvar_trusted
rec_data["_view"]["databases"]["clinvar_trusted_simplified"] = (
clinvar_trusted_simplified)
#===============================================
def sample_has_variant(sample):
genotype = sample.get("genotype")
return genotype and not ("HOM_REF" in genotype or "NO_CALL" in genotype)
def is_none(value):
return value == "None"
FilterPrepareSetH.regNamedFunction("has_variant", sample_has_variant)
FilterPrepareSetH.regNamedFunction("is_none", is_none)
#===============================================
def defineFilterSchema(metadata_record):
data_schema = metadata_record.get("data_schema")
if data_schema == "FAVOR":
return FavorSchema.defineFilterSchema(metadata_record)
assert data_schema is None or data_schema == "CASE", (
"Bad data schema: " + data_schema)
filters = FilterPrepareSetH(metadata_record)
cohorts = metadata_record.get("cohorts")
with filters.viewGroup("Inheritance"):
if cohorts:
filters.multiStatusUnit("Variant_in",
def defineFilterSchema(metadata_record):
data_schema = metadata_record.get("data_schema")
if data_schema == "FAVOR":
return FavorSchema.defineFilterSchema(metadata_record)
assert data_schema is None or data_schema == "CASE", (
"Bad data schema: " + data_schema)
filters = FilterPrepareSetH(metadata_record, anfisaVariables)
cohorts = metadata_record.get("cohorts")
with filters.viewGroup("Inheritance"):
if cohorts:
filters.multiStatusUnit("Variant_in",
"/_filters/cohort_has_variant[]")
filters.multiStatusUnit("Callers",
"/_view/bioinformatics/called_by[]")
filters.statusUnit("Proband_Zygosity",
"/_view/bioinformatics/zygosity")
filters.intValueUnit("Num_Samples", "/_filters/has_variant",
conversion = ["len"], default_value = 0)
filters.multiStatusUnit("Has_Variant", "/_filters/has_variant[]")
if cohorts:
with filters.viewGroup("Cohorts"):
filters.floatValueUnit("ALL_AF",
"/_view/cohorts/ALL", default_value = 0)
filters.floatValueUnit("ALL_AF2",
"/_view/cohorts/ALL2", default_value = 0)
for ch_info in cohorts:
ch_name = ch_info["name"]
filters.floatValueUnit(f"Cohort_{ch_name}_AF",
f"/_view/cohorts/{ch_name}/AF",
default_value = 0)
filters.floatValueUnit(f"Cohort_{ch_name}_AF2",
f"/_view/cohorts/{ch_name}/AF2",
default_value = 0)
with filters.viewGroup("Variant"):
filters.statusUnit("Variant_Class", "/__data/variant_class")
filters.statusUnit("Most_Severe_Consequence",
"/__data/most_severe_consequence",
variants = sConsequenceVariants,
default_value = "undefined")
filters.multiStatusUnit("Canonical_Annotation",
"/_view/general/canonical_annotation[]",
default_value = "undefined")
filters.statusUnit("Multiallelic", "/_filters/multiallelic")
filters.statusUnit("Altered_VCF", "/_filters/altered_vcf")
# filters.intValueUnit("Number_ALTs",
# "/_filters/alts",
# conversion = ["len"], default_value = 0)
#filters.intValueUnit("zyg_len", "/__data/zygosity",
# conversion = ["len"], default_value = 0)
with filters.viewGroup("Genes"):
genes_unit = filters.multiStatusUnit("Symbol",
"/_view/general/genes[]", compact_mode = True)
filters.panelsUnit("Panels", genes_unit, "Symbol",
view_path = "/_view/general/gene_panels")
filters.multiStatusUnit("EQTL_Gene", "/_filters/eqtl_gene[]",
default_value = "None")
filters.intValueUnit("Num_Genes", "/_view/general/genes",
conversion = ["len"], default_value = 0)
filters.intValueUnit("Num_Transcripts",
"/__data/transcript_consequences",
conversion = ["len"], default_value = 0)
with filters.viewGroup("Transcripts"):
filters.transcriptMultisetUnit("Transcript_consequence",
"transcript_annotations", variants = sConsequenceVariants,
default_value = "undefined")
filters.transcriptStatusUnit("Transcript_canonical", "is_canonical",
bool_check_value = "True", default_value = "False")
filters.transcriptStatusUnit("Transcript_GENCODE_Basic",
"gencode_basic", bool_check_value = "True",
default_value = "False")
filters.transcriptStatusUnit("Transcript_biotype", "biotype",
default_value = "undefined")
filters.transcriptStatusUnit("Transcript_worst", "is_worst",
bool_check_value = "True", default_value = "False")
filters.transcriptStatusUnit("Transcript_id", "id",
default_value = "undefined", transcript_id_mode = True)
tr_genes_unit = filters.transcriptStatusUnit("Transctript_Gene",
"gene", default_value = "undefined")
filters.transcriptPanelsUnit("Transcript_Gene_Panels",
tr_genes_unit, "Symbol", view_name = "tr_gene_panels")
filters.transcriptStatusUnit("Transcript_source", "transcript_source",
default_value = "undefined")
filters.transcriptStatusUnit("Transcript_codon_pos", "codonpos",
default_value = "undefined")
filters.transcriptStatusUnit("Transcript_region", "region",
default_value = "undefined")
filters.transcriptStatusUnit("Transcript_CDS", "cds",
default_value = "-")
filters.transcriptStatusUnit("Transcript_masked", "masked_region",
default_value = "No")
filters.transcriptIntValueUnit("Transcript_dist_from_exon",
"dist_from_exon", default_value = -1)
# filters.transcriptStatusUnit("Transcript_strand", "strand",
# default_value = "undefined")
with filters.viewGroup("Transcript_Predictions"):
filters.transcriptStatusUnit(
"Transcript_PolypPhen_HDIV", "polyphen2_hdiv_prediction")
filters.transcriptStatusUnit(
"Transcript_PolyPhen_HVAR", "polyphen2_hvar_prediction")
filters.transcriptStatusUnit(
"Transcript_SIFT", "sift_prediction")
filters.transcriptStatusUnit(
"Transcript_SIFT_4G", "sift_4g_prediction")
filters.transcriptStatusUnit(
"Transcript_FATHMM", "fathmm_prediction")
with filters.viewGroup("Coordinates"):
filters.statusUnit("Chromosome", "/_filters/chromosome",
variants = ["chr1", "chr2", "chr3", "chr4", "chr5",
"chr6", "chr7", "chr8", "chr9", "chr10",
"chr11", "chr12", "chr13", "chr14", "chr15",
"chr16", "chr17", "chr18", "chr19", "chr20",
"chr21", "chr22", "chr23", "chrX", "chrY", "undefined"],
default_value = "undefined")
filters.intValueUnit("Start_Pos", "/__data/start",
default_value = sys.maxsize)
filters.intValueUnit("End_Pos", "/__data/end",
default_value = 0)
filters.intValueUnit("Dist_from_Exon", "/_filters/dist_from_exon",
default_value = 0)
filters.intValueUnit("Dist_from_Exon_Canonical",
"/_filters/dist_from_exon_canonical",
default_value = 0, conversion = ["min"])
filters.intValueUnit("Dist_from_Exon_Worst",
"/_filters/dist_from_exon_worst",
default_value = 0, conversion = ["min"])
filters.multiStatusUnit("Region_Canonical",
"/__data/region_canonical[]",
default_value = "Other")
filters.multiStatusUnit("Region_Worst", "/__data/region_worst[]",
default_value = "Other")
filters.transcriptStatusUnit("Region", "region",
default_value = "undefined")
filters.statusUnit("In_hg19", "/_view/general/hg19",
conversion = [["filter", "is_none"]],
value_map= {"None": "Unmapped"}, default_value = "Mapped")
with filters.viewGroup("gnomAD"):
filters.floatValueUnit("gnomAD_AF",
"/_filters/gnomad_af_fam",
diap = (0., 1.), default_value = 0.)
filters.floatValueUnit("gnomAD_AF_Exomes",
"/_filters/gnomad_db_exomes_af",
diap = (0., 1.), default_value = 0.)
filters.floatValueUnit("gnomAD_AF_Genomes",
"/_filters/gnomad_db_genomes_af",
diap = (0., 1.), default_value = 0.)
filters.floatValueUnit("gnomAD_AF_Proband",
"/_filters/gnomad_af_pb",
diap = (0., 1.), default_value = 0.)
filters.floatValueUnit("gnomAD_PopMax_AF",
"/_filters/gnomad_popmax_af",
diap = (0., 1.), default_value = 0.)
filters.statusUnit("gnomAD_PopMax",
"/_filters/gnomad_popmax", default_value = "None")
filters.intValueUnit("gnomAD_PopMax_AN",
"/_filters/gnomad_popmax_an", default_value = 0)
filters.floatValueUnit("gnomAD_PopMax_AF_Inbred",
"/_filters/gnomad_raw_popmax_af",
diap = (0., 1.), default_value = 0.)
filters.statusUnit("gnomAD_PopMax_Inbred",
"/_filters/gnomad_raw_popmax", default_value = "None")
filters.intValueUnit("gnomAD_PopMax_AN_Inbred",
"/_filters/gnomad_raw_popmax_an", default_value = 0)
filters.intValueUnit("gnomAD_Hom",
"/_filters/gnomad_hom", default_value = 0)
filters.intValueUnit("gnomAD_Hem",
"/_filters/gnomad_hem", default_value = 0)
with filters.viewGroup("Databases"):
presence_in_db = [
("ClinVar", "/_view/databases/clinVar"),
("GnomAD", "/_filters/gnomad_af_fam"),
("HGMD", "/__data/hgmd_pmids[]"),
("OMIM", "/_view/databases/omim")]
for submitter in sorted(filters.getStdItem(
"item-dict", "Clinvar_Trusted_Submitters").getData().values()):
presence_in_db.append((submitter,
"/_view/databases/clinvar_trusted/%s" % submitter))
filters.presenceUnit("Presence_in_Databases", presence_in_db)
filters.multiStatusUnit("ClinVar_Submitters",
"/_view/databases/clinVar_submitters[]", compact_mode = True)
filters.intValueUnit("Number_submitters",
"/_view/databases/clinVar_submitters",
conversion = ["len"], default_value = 0)
filters.multiStatusUnit("PMIDs",
"/_view/databases/references[]", compact_mode = True)
filters.intValueUnit("Number_pmid",
"/_view/databases/references",
conversion = ["len"], default_value = 0)
# filters.multiStatusUnit("beacons",
# "/__data/beacon_names")
with filters.viewGroup("Call_Quality"):
filters.floatValueUnit("Proband_GQ", "/_filters/proband_gq",
default_value = -1)
filters.floatValueUnit("Min_GQ", "/_filters/min_gq",
default_value = -1)
filters.intValueUnit("Max_GQ", "/_view/quality_samples",
default_value = 0,
conversion = [
["filter", "has_variant"],
["property", "genotype_quality"],
"max"])
filters.intValueUnit("Num_NO_CALL", "/_view/quality_samples",
default_value = 0,
conversion = [
["skip", 1],
["property", "genotype_quality"],
"negative", "len"])
filters.intValueUnit("QUAL", "/_filters/qual",
default_value = -1)
filters.floatValueUnit("QD", "/_filters/qd",
default_value = -1.)
filters.floatValueUnit("FS", "/_filters/fs",
default_value = 0.)
filters.multiStatusUnit("FT", "/_filters/filters[]")
with filters.viewGroup("Predictions"):
# research_only = True
filters.statusUnit("HGMD_Benign", "/_filters/hgmd_benign",
default_value = "Not in HGMD",
value_map = {"True": "Benign", "False": "VUS or Pathogenic"})
filters.multiStatusUnit("HGMD_Tags", "/_view/databases/hgmd_tags[]",
default_value = "None")
# research_only = True
filters.statusUnit("Clinvar_Benign", "/_filters/clinvar_benign",
default_value = "Not in ClinVar",
value_map = {"True": "Benign", "False": "VUS or Pathogenic"})
filters.multiStatusUnit("ClinVar_Significance",
"/__data/clinvar_significance[]")
filters.regPreTransform(lambda rec_no, rec_data:
clinvarPreTransform(rec_data, filters.getStdItem(
"item-dict", "Clinvar_Trusted_Submitters").getData()))
filters.multiStatusUnit("Clinvar_Trusted_Significance",
"/_view/databases/clinvar_trusted",
conversion = ["values", ["split", ','], "clear", "uniq"])
filters.multiStatusUnit("Clinvar_Trusted_Simplified",
"/_view/databases/clinvar_trusted_simplified",
conversion = ["values", ["split", ','], "clear", "uniq"])
filters.statusUnit("Clinvar_stars", "/_filters/clinvar_stars",
default_value = "No data")
filters.intValueUnit("Number_of_clinvar_submitters",
"/_filters/num_clinvar_submitters",
default_value = 0)
filters.statusUnit("Clinvar_review_status",
"/_filters/clinvar_review_status",
default_value = "No data")
filters.statusUnit("Clinvar_criteria_provided",
"/_filters/clinvar_criteria_provided",
default_value = "Not Provided")
filters.statusUnit("Clinvar_conflicts",
"/_filters/clinvar_conflicts",
default_value = "Criteria not Provided")
filters.multiStatusUnit("Clinvar_acmg_guidelines",
"/_filters/clinvar_acmg_guidelines[]",
default_value = "None")
for submitter in sorted(filters.getStdItem(
"item-dict", "Clinvar_Trusted_Submitters").getData().values()):
filters.statusUnit(f"ClinVar_Significance_{submitter}",
"/_view/databases/clinvar_trusted",
conversion = [["property", submitter]],
default_value = "None")
#filters.statusUnit("Clinvar_Trusted_Benign",
# "/_filters/clinvar_trusted_benign",
# default_value = "No data",
# value_map = {"True": "Benign by Trusted submitters",
# "False": "Unknown"})
filters.statusUnit("splice_altering", "/_filters/splice_altering",
default_value = "No altering")
filters.floatValueUnit("splice_ai_dsmax", "/_filters/splice_ai_dsmax",
default_value = 0)
filters.multiStatusUnit("Polyphen_2_HVAR",
"/_view/predictions/polyphen2_hvar[]",
conversion = [["split_re", r"[\s\,]"], "clear", "uniq"],
default_value = "N/A")
filters.multiStatusUnit("Polyphen_2_HDIV",
"/_view/predictions/polyphen2_hdiv[]",
conversion = [["split_re", r"[\s\,]"], "clear", "uniq"],
default_value = "N/A")
filters.multiStatusUnit("SIFT", "/_view/predictions/sift[]",
default_value = "N/A")
filters.multiStatusUnit("FATHMM", "/_view/predictions/fathmm[]",
default_value = "N/A")
filters.multiStatusUnit("PrimateAI",
"/_view/predictions/primate_ai_pred[]",
default_value = "N/A")
filters.floatValueUnit("GERP_score", "/_view/bioinformatics/gerp_rs",
default_value = 0)
with filters.viewGroup("Pharmacogenomics"):
filters.multiStatusUnit("Diseases",
"/_filters/pharmacogenomics_diseases[]", default_value = "N/A")
filters.multiStatusUnit("Chemicals",
"/_filters/pharmacogenomics_chemicals[]", default_value = "N/A")
with filters.viewGroup("Expression"):
filters.multiStatusUnit("Mostly_Expressed_in",
"/_filters/top_tissues[]", default_value = "N/A")
# required = {"debug"}
with filters.viewGroup("Debug_Info"):
filters.intValueUnit("Severity", "/_filters/severity",
default_value = -1)
assert filters.getTranscriptIdUnitName() is not None, (
"Transcript ID unit is not set")
return filters
def defineFilterSchema():
filters = FilterPrepareSetH()
with filters.viewGroup("Inheritance"):
filters.statusUnit("Proband_Zygosity",
"/view/bioinformatics/zygosity",
title="Proband Zygosity")
filters.zygositySpecialUnit(
"Inheritance_Mode",
"/data/zygosity",
config={"x_cond": ConditionMaker.condEnum("Chromosome", ["chrX"])},
title="Inheritance Mode")
filters.multiStatusUnit("Callers",
"/view/bioinformatics/called_by[]",
title="Called by")
filters.multiStatusUnit("Has_Variant", "/_filters/has_variant[]")
with filters.viewGroup("Variant"):
filters.statusUnit(
"Variant_Class",
"/data/variant_class",
tooltip=("Variant class as returned by VEP. "
"The class of a variant is based on Sequence "
"Ontology and is called according to its component "
"alleles and its mapping to the reference genome. "
"https://useast.ensembl.org/info/genome/variation/"
"prediction/classification.html#classes"))
filters.statusUnit("Most_Severe_Consequence",
"/data/most_severe_consequence",
variants=sConsequenceVariants,
default_value="undefined")
filters.statusUnit("Canonical_Annotation",
"/view/general/canonical_annotation",
default_value="undefined")
filters.intValueUnit("Number_ALTs",
"/_filters/alts",
title="Number of Alternative alleles",
conversion=_conv_len,
default_value=0)
#filters.intValueUnit("zyg_len", "/data/zygosity",
# conversion = _conv_len, default_value = 0)
with filters.viewGroup("Genes"):
genes_unit = filters.multiStatusUnit("Symbol",
"/view/general/genes[]",
compact_mode=True)
filters.panelStatusUnit("Panels",
genes_unit,
view_path="/view/general/gene_panels")
#filters.multiStatusUnit("Transcripts",
# "/data/transcript_consequences[]", compact_mode = True,
# conversion = lambda arr:
# [el["transcript_id"] for el in arr] if arr else [])
filters.intValueUnit("Num_Genes",
"/view/general/genes",
title="Number of overlapping genes",
conversion=_conv_len,
default_value=0)
filters.intValueUnit("Num_Transcripts",
"/data/transcript_consequences",
title="Number of transcripts at the position",
conversion=_conv_len,
default_value=0)
with filters.viewGroup("Transcripts"):
filters.transctiptMultisetUnit("Transctipt_consequence",
"consequence_terms",
variants=sConsequenceVariants)
filters.transctiptStatusUnit("Transcript_canonical",
"canonical",
bool_check_value="1",
default_value="False")
filters.transctiptStatusUnit("Transcript_biotype",
"biotype",
default_value="undefined")
filters.transctiptStatusUnit(
"Transcript_worst",
"consequence_terms",
bool_check_value="${Most_Severe_Consequence}",
default_value="False")
filters.transctiptStatusUnit("Transcript_id",
"transcript_id",
default_value="undefined")
filters.transctiptStatusUnit("Transctript_gene_id",
"gene_id",
default_value="undefined")
filters.transctiptStatusUnit("Transcript_source",
"source",
default_value="undefined")
filters.transctiptStatusUnit("Transcript_strand",
"strand",
default_value="undefined")
with filters.viewGroup("Coordinates"):
filters.statusUnit("Chromosome",
"/_filters/chromosome",
variants=[
"chr1", "chr2", "chr3", "chr4", "chr5", "chr6",
"chr7", "chr8", "chr9", "chr10", "chr11",
"chr12", "chr13", "chr14", "chr15", "chr16",
"chr17", "chr18", "chr19", "chr20", "chr21",
"chr22", "chr23", "chrX", "chrY", "undefined"
],
default_value="undefined")
filters.intValueUnit("Start_Pos",
"/data/start",
title="Start Position",
render_mode="neighborhood",
default_value=sys.maxsize)
filters.intValueUnit("End_Pos",
"/data/end",
title="End Position",
default_value=0,
render_mode="neighborhood")
filters.intValueUnit(
"Dist_from_Exon",
"/_filters/dist_from_exon",
title="Distance From Intron/Exon Boundary (Canonical)",
default_value=0,
render_mode="log,<")
filters.statusUnit("Region",
"/data/region_canonical",
title="Region (Canonical)",
default_value="Other")
with filters.viewGroup("gnomAD"):
filters.floatValueUnit("gnomAD_AF",
"/_filters/gnomad_af_fam",
diap=(0., 1.),
default_value=0.,
title="gnomAD Allele Frequency (family)",
tooltip="gnomAD Overall Allele Frequency",
render_mode="log,<")
filters.floatValueUnit("gnomAD_AF_Exomes",
"/_filters/gnomad_db_exomes_af",
diap=(0., 1.),
default_value=0.,
title="gnomAD Exome Allele Frequency (family)",
render_mode="log,<")
filters.floatValueUnit("gnomAD_AF_Genomes",
"/_filters/gnomad_db_genomes_af",
diap=(0., 1.),
default_value=0.,
title="gnomAD Genome Allele Frequency (family)",
render_mode="log,<")
filters.floatValueUnit("gnomAD_AF_Proband",
"/_filters/gnomad_af_pb",
diap=(0., 1.),
default_value=0.,
title="gnomAD Allele Frequency (proband)",
tooltip="gnomAD Overall Allele Frequency "
"for the allele present in proband",
render_mode="log,<")
filters.floatValueUnit(
"gnomAD_PopMax_AF",
"/_filters/gnomad_popmax_af",
tooltip="Maximum allele frequency across all populations",
diap=(0., 1.),
default_value=0.,
title="gnomAD PopMax Allele Frequency",
render_mode="log,<")
filters.statusUnit(
"gnomAD_PopMax",
"/_filters/gnomad_popmax",
default_value="None",
title="gnomAD PopMax Ancestry",
tooltip="Population that has the maximum allele frequency")
filters.intValueUnit(
"gnomAD_PopMax_AN",
"/_filters/gnomad_popmax_an",
default_value=0,
title="gnomAD: Number of alleles in PopMax Ancestry",
render_mode="log,>")
filters.intValueUnit("gnomAD_Hom",
"/_filters/gnomad_hom",
default_value=0,
title="gnomAD: Number of homozygous",
render_mode="log,>")
filters.intValueUnit("gnomAD_Hem",
"/_filters/gnomad_hem",
default_value=0,
title="gnomAD: Number of hemizygous",
render_mode="log,>")
with filters.viewGroup("Databases"):
filters.presenceUnit(
"Presence_in_Databases",
[("ClinVar", "/view/databases/clinVar"),
("LMM", "/view/databases/lmm_significance"),
("GeneDx", "/view/databases/gene_dx_significance"),
("GnomAD", "/_filters/gnomad_af_fam"),
("HGMD", "/view/databases/hgmd_pmids[]"),
("OMIM", "/view/databases/omim")],
title="Presence in Databases")
filters.multiStatusUnit("ClinVar_Submitters",
"/view/databases/clinVar_submitters[]",
title="ClinVar Submitters",
compact_mode=True)
filters.intValueUnit("Number_submitters",
"/view/databases/clinVar_submitters",
title="Number of ClinVar Submitters",
conversion=_conv_len,
default_value=0)
filters.intValueUnit("Number_pmid",
"/view/databases/hgmd_pmids",
title="Number of PMIDs in HGMD",
conversion=_conv_len,
default_value=0)
# filters.multiStatusUnit("beacons",
# "/data/beacon_names",
# title = "Observed at")
with filters.viewGroup("Call_Quality"):
filters.floatValueUnit("Proband_GQ",
"/_filters/proband_gq",
title="Genotype Quality (GQ) for Proband",
render_mode="linear,>",
default_value=1000)
filters.floatValueUnit("Min_GQ",
"/_filters/min_gq",
title="Minimum GQ for the family)",
render_mode="linear,>",
default_value=1000)
filters.floatValueUnit("QD",
"/_filters/qd",
title="Quality by Depth",
render_mode="linear,>",
default_value=100000.)
filters.floatValueUnit("FS",
"/_filters/fs",
"Fisher Strand Bias",
render_mode="linear,<",
default_value=0.)
filters.multiStatusUnit("FT", "/_filters/filters[]", title="FILTER")
with filters.viewGroup("Predictions"):
filters.statusUnit(
"HGMD_Benign",
"/_filters/hgmd_benign",
title="Categorized Benign in HGMD",
default_value="Not in HGMD",
research_only=True,
render_mode="replace(True/Benign, False/Not Benign)")
filters.multiStatusUnit("HGMD_Tags",
"/view/databases/hgmd_tags[]",
default_value="None")
filters.statusUnit(
"Clinvar_Benign",
"/_filters/clinvar_benign",
default_value="Not in ClinVar",
title="Categorized Benign in ClinVar by all submitters",
research_only=True)
filters.multiStatusUnit("ClinVar_Significance",
"/data/clinvar_significance[]",
title="Clinical Significance in ClinVar")
filters.statusUnit("Clinvar_stars",
"/_filters/clinvar_stars",
default_value="No data",
title="ClinVar Stars")
filters.intValueUnit("Number_of_clinvar_submitters",
"/_filters/num_clinvar_submitters",
render_mode="log,>",
default_value=0,
title="ClinVar: Number of Submitters")
filters.statusUnit("Clinvar_review_status",
"/_filters/clinvar_review_status",
default_value="No data",
title="ClinVar Review Status")
filters.statusUnit("Clinvar_criteria_provided",
"/_filters/clinvar_criteria_provided",
default_value="Not Provided",
title="ClinVar Criteria")
filters.statusUnit("Clinvar_conflicts",
"/_filters/clinvar_conflicts",
default_value="Criteria not Provided",
title="ClinVar Conflicts")
filters.multiStatusUnit("Clinvar_acmg_guidelines",
"/_filters/clinvar_acmg_guidelines[]",
default_value="None")
filters.statusUnit(
"Clinvar_Trusted_Benign",
"/_filters/clinvar_trusted_benign",
default_value="No data",
title="Categorized Benign by Clinvar Trusted Submitters")
filters.multiStatusUnit("LMM_Significance",
"/data/lmm",
title="Clinical Significance by LMM")
filters.multiStatusUnit("GeneDx_Significance",
"/data/gene_dx",
title="Clinical Significance by GeneDx")
filters.statusUnit("splice_altering",
"/_filters/splice_altering",
default_value="No altering",
title="Splice AI splice altering")
filters.floatValueUnit("splice_ai_dsmax",
"/_filters/splice_ai_dsmax",
render_mode="linear,>",
default_value=0,
title="Splice AI splice altering score")
filters.multiStatusUnit("Polyphen",
"/view/predictions/polyphen[]",
default_value="N/A")
filters.multiStatusUnit("SIFT",
"/view/predictions/sift[]",
default_value="N/A")
filters.multiStatusUnit("Polyphen_2_HVAR",
"/view/predictions/polyphen2_hvar[]",
separators="[\s\,]",
default_value="N/A")
filters.multiStatusUnit("Polyphen_2_HDIV",
"/view/predictions/polyphen2_hdiv[]",
separators="[\s\,]",
default_value="N/A")
filters.floatValueUnit("GERP_score",
"/view/bioinformatics/gerp_rs",
render_mode="linear,>",
default_value=0,
title="GERP Score")
with filters.viewGroup("Debug_Info"):
filters.intValueUnit("Severity",
"/_filters/severity",
research_only=True,
default_value=-1)
return filters
def execIt(self):
if not self.correctWSName(self.mWSName):
self.setStatus("Incorrect derived dataset name")
return None
self.setStatus("Preparing to create derived dataset")
logging.info("Prepare dataset derivation: %s" % self.mWSName)
receipt = {
"kind": self.mEval.getSolKind(),
"base": self.mDS.getName(),
"root": self.mDS.getRootDSName()
}
if self.mEval.getSolKind() == "filter":
if self.mEval.getFilterName():
receipt["filter-name"] = self.mEval.getFilterName()
condition = self.mEval.getCondition()
rec_count = self.mDS.getEvalSpace().evalTotalCounts(condition)[0]
if (rec_count < 1
or rec_count >= AnfisaConfig.configOption("max.ws.size")):
self.setStatus("Size is incorrect: %d" % rec_count)
return None
rec_no_seq = self.mDS.getEvalSpace().evalRecSeq(
condition, rec_count)
receipt["f-presentation"] = self.mEval.getPresentation()
receipt["conditions"] = self.mEval.getCondDataSeq()
else:
if self.mEval.getDTreeName():
receipt["dtree-name"] = self.mEval.getDTreeName()
rec_no_seq, point_seq = self.mEval.collectRecSeq()
receipt["p-presentation"] = point_seq
receipt["dtree-code"] = self.mEval.getCode()
receipt["eval-update-info"] = self.mEval.getUpdateInfo()
rec_no_seq = sorted(rec_no_seq)
ws_dir = self.mDS.getDataVault().getDir() + "/" + self.mWSName
if os.path.exists(ws_dir) and self.mForceMode:
if self.mDS.getDataVault().getDS(self.mWSName):
self.mDS.getDataVault().unloadDS(self.mWSName, "ws")
shutil.rmtree(ws_dir)
if os.path.exists(ws_dir):
self.setStatus("Dataset already exists")
return None
view_schema = deepcopy(self.mDS.getViewSchema())
flt_schema = deepcopy(self.mDS.getFltSchema())
meta_rec = deepcopy(self.mDS.getDataInfo().get("meta"))
filter_set = FilterPrepareSetH(meta_rec, anfisaVariables)
filter_set.setupFromInfo(flt_schema)
trans_prep = TransformPreparator_WS(flt_schema, self.mDS, False)
os.mkdir(ws_dir)
logging.info("Fill dataset %s datafiles..." % self.mWSName)
with DataDiskStorageWriter(False,
ws_dir, filter_set, trans_prep) as ws_out:
for _, rec_data in self.mDS.getRecStorage().iterRecords(
rec_no_seq):
ws_out.saveRecord(rec_data)
if ws_out.getTotal() % self.mReportLines == 0:
self.setStatus("Extracting records: %d/%d" %
(ws_out.getTotal(), len(rec_no_seq)))
self.setStatus("Finishing...")
logging.info("Finalizing derivation %s" % self.mWSName)
total_item_count = trans_prep.finishUp()
date_loaded = datetime.now().isoformat()
mongo_agent = self.mDS.getApp().getMongoConnector().getDSAgent(
self.mWSName, "ws")
mongo_agent.updateCreationDate(date_loaded)
if "versions" in meta_rec:
meta_rec["versions"][
"Anfisa load"] = self.mDS.getApp().getVersionCode()
receipts = self.mDS.getDataInfo().get("receipts")
if receipts is not None:
receipts = [receipt] + receipts[:]
else:
receipts = [receipt]
ds_info = {
"name": self.mWSName,
"kind": "ws",
"view_schema": view_schema,
"flt_schema": flt_schema,
"total": len(rec_no_seq),
"total_items": total_item_count,
"mongo": self.mWSName,
"base": self.mDS.getName(),
"root": self.mDS.getRootDSName(),
"modes": ["secondary"],
"meta": meta_rec,
"doc": [],
"zygosity_var": self.mDS.getDataInfo()["zygosity_var"],
"receipts": receipts,
"date_loaded": date_loaded}
with open(ws_dir + "/dsinfo.json", "w", encoding = "utf-8") as outp:
print(json.dumps(ds_info, sort_keys = True, indent = 4),
file = outp)
os.mkdir(ws_dir + "/doc")
with open(ws_dir + "/doc/info.html", "w", encoding = "utf-8") as outp:
reportDS(outp, ds_info, mongo_agent, self.mDS.getDataInfo())
with open(ws_dir + "/active", "w", encoding = "utf-8") as outp:
print("", file = outp)
self.mDS.getDataVault().loadDS(self.mWSName, "ws")
self.setStatus("Done")
return {"ws": self.mWSName}