-
Notifications
You must be signed in to change notification settings - Fork 3
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
* feat(aliquot-2): UNIPROT_ISOFORM * feat(aliquot-2): MANE, APPRIS, FLAGS * fix(aliquot-2): shift RefSeq * feat(aliquot-2): 100G columns * feat(aliquot-2): ESP columns * feat(aliquot-2): gnomAD columns * feat(aliquot-2): VEP max AF columns * feat(aliquot-2): non-cancer gnomAD columns * feat(aliquot-2): TF and miRNA columns * feat(aliquot-2): drop exac * feat(genie): genie 2.0.0 Co-authored-by: Charles Czysz <[email protected]>
- Loading branch information
Showing
2 changed files
with
227 additions
and
0 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,118 @@ | ||
| { | ||
| "version" : "gdc-1.0.0", | ||
| "annotation-spec" : "gdc-2.0.0-aliquot", | ||
| "extends" : "gdc-1.0.0", | ||
| "columns" : [ | ||
| [ "HGVSc", "NullableStringColumn", "The coding sequence of the variant in HGVS recommended format" ], | ||
| [ "HGVSp", "NullableStringColumn", "The protein sequence of the variant in HGVS recommended format. \"p.=\" signifies no change in the protein" ], | ||
| [ "HGVSp_Short", "NullableStringColumn", "Same as the HGVSp column, but using 1-letter amino-acid codes" ], | ||
| [ "Transcript_ID", "NullableStringColumn", "Ensembl ID of the transcript affected by the variant" ], | ||
| [ "Exon_Number", "NullableStringColumn", "The exon number (out of total number)" ], | ||
| [ "t_depth", "ZeroBasedIntegerColumn", "Read depth across this locus in tumor BAM" ], | ||
| [ "t_ref_count", "ZeroBasedIntegerColumn", "Read depth supporting the reference allele in tumor BAM" ], | ||
| [ "t_alt_count", "ZeroBasedIntegerColumn", "Read depth supporting the variant allele in tumor BAM" ], | ||
| [ "n_depth", "NullableZeroBasedIntegerColumn", "Read depth across this locus in normal BAM" ], | ||
| [ "n_ref_count", "NullableZeroBasedIntegerColumn", "Read depth supporting the reference allele in normal BAM (cleared in somatic MAF)" ], | ||
| [ "n_alt_count", "NullableZeroBasedIntegerColumn", "Read depth supporting the variant allele in normal BAM (cleared in somatic MAF)" ], | ||
| [ "all_effects", "SequenceOfStrings", "A semicolon delimited list of all possible variant effects, sorted by priority ([Symbol,Consequence,HGVSp_Short,Transcript_ID,RefSeq,HGVSc,Impact,Canonical,Sift,PolyPhen,Strand])" ], | ||
| [ "Allele", "StringColumn", "The variant allele used to calculate the consequence" ], | ||
| [ "Gene", "NullableStringColumn", "Stable Ensembl ID of affected gene" ], | ||
| [ "Feature", "NullableStringColumn", "Stable Ensembl ID of feature (transcript, regulatory, motif)" ], | ||
| [ "Feature_type", "FeatureType", "Type of feature. Currently one of Transcript, RegulatoryFeature, MotifFeature (or blank)" ], | ||
| [ "One_Consequence", "StringColumn", "The single consequence of the canonical transcript in sequence ontology terms" ], | ||
| [ "Consequence", "SequenceOfStrings", "Consequence type of this variant" ], | ||
| [ "cDNA_position", "NullableStringColumn", "Relative position of base pair in the cDNA sequence as a fraction. A \"-\" symbol is displayed as the numerator if the variant does not appear in cDNA" ], | ||
| [ "CDS_position", "NullableStringColumn", "Relative position of base pair in coding sequence. A \"-\" symbol is displayed as the numerator if the variant does not appear in coding sequence" ], | ||
| [ "Protein_position", "NullableStringColumn", "Relative position of affected amino acid in protein. A \"-\" symbol is displayed as the numerator if the variant does not appear in coding sequence" ], | ||
| [ "Amino_acids", "NullableStringColumn", "Only given if the variation affects the protein-coding sequence" ], | ||
| [ "Codons", "NullableStringColumn", "The alternative codons with the variant base in upper case" ], | ||
| [ "Existing_variation", "SequenceOfStrings", "Known identifier of existing variation" ], | ||
| [ "ALLELE_NUM", "ZeroBasedIntegerColumn", "Allele number from input; 0 is reference, 1 is first alternate etc." ], | ||
| [ "DISTANCE", "NullableIntegerColumn", "Shortest distance from the variant to transcript" ], | ||
| [ "TRANSCRIPT_STRAND", "TranscriptStrand", "The DNA strand (1 or -1) on which the transcript/feature lies" ], | ||
| [ "SYMBOL", "NullableStringColumn", "The gene symbol" ], | ||
| [ "SYMBOL_SOURCE", "NullableStringColumn", "The source of the gene symbol" ], | ||
| [ "HGNC_ID", "NullableStringColumn", "Gene identifier from the HUGO Gene Nomenclature Committee if applicable" ], | ||
| [ "BIOTYPE", "NullableStringColumn", "Biotype of transcript" ], | ||
| [ "CANONICAL", "Canonical", "A flag (YES) indicating that the VEP-based canonical transcript, the longest translation, was used for this gene. If not, the value is null" ], | ||
| [ "CCDS", "NullableStringColumn", "The CCDS identifier for this transcript, where applicable" ], | ||
| [ "ENSP", "NullableStringColumn", "The Ensembl protein identifier of the affected transcript" ], | ||
| [ "SWISSPROT", "SequenceOfStrings", "UniProtKB/Swiss-Prot accession" ], | ||
| [ "TREMBL", "SequenceOfStrings", "UniProtKB/TrEMBL identifier of protein product" ], | ||
| [ "UNIPARC", "SequenceOfStrings", "UniParc identifier of protein product" ], | ||
| [ "UNIPROT_ISOFORM", "SequenceOfStrings", "Direct mappings to UniProtKB isoforms" ], | ||
| [ "RefSeq", "SequenceOfStrings", "RefSeq identifier for this transcript" ], | ||
| [ "MANE", "SequenceOfStrings", "MANE (Matched Annotation by NCBI and EMBL-EBI) Transcript" ], | ||
| [ "APPRIS", "NullableStringColumn", "Annotates alternatively spliced transcripts as primary or alternate based on a range of computational methods" ], | ||
| [ "FLAGS", "SequenceOfStrings", "Transcript quality flags" ], | ||
| [ "SIFT", "NullableStringColumn", "The SIFT prediction and/or score, with both given as prediction (score)" ], | ||
| [ "PolyPhen", "NullableStringColumn", "The PolyPhen prediction and/or score" ], | ||
| [ "EXON", "NullableStringColumn", "The exon number (out of total number)" ], | ||
| [ "INTRON", "NullableStringColumn", "The intron number (out of total number)" ], | ||
| [ "DOMAINS", "SequenceOfStrings", "The source and identifier of any overlapping protein domains" ], | ||
| [ "1000G_AF", "NullableFloatColumn", "Non-reference allele and frequency of existing variant in 1000 Genomes" ], | ||
| [ "1000G_AFR_AF", "NullableFloatColumn", "Non-reference allele and frequency of existing variant in 1000 Genomes combined African population" ], | ||
| [ "1000G_AMR_AF", "NullableFloatColumn", "Non-reference allele and frequency of existing variant in 1000 Genomes combined American population" ], | ||
| [ "1000G_EAS_AF", "NullableFloatColumn", "Non-reference allele and frequency of existing variant in 1000 Genomes combined East Asian population" ], | ||
| [ "1000G_EUR_AF", "NullableFloatColumn", "Non-reference allele and frequency of existing variant in 1000 Genomes combined European population" ], | ||
| [ "1000G_SAS_AF", "NullableFloatColumn", "Non-reference allele and frequency of existing variant in 1000 Genomes combined South Asian population" ], | ||
| [ "ESP_AA_AF", "NullableFloatColumn", "Non-reference allele and frequency of existing variant in NHLBI-ESP African American population" ], | ||
| [ "ESP_EA_AF", "NullableFloatColumn", "Non-reference allele and frequency of existing variant in NHLBI-ESP European American population" ], | ||
| [ "gnomAD_AF", "NullableFloatColumn", "Frequency of existing variant in gnomAD exomes combined population" ], | ||
| [ "gnomAD_AFR_AF", "NullableFloatColumn", "Frequency of existing variant in gnomAD exomes African/American population" ], | ||
| [ "gnomAD_AMR_AF", "NullableFloatColumn", "Frequency of existing variant in gnomAD exomes American population" ], | ||
| [ "gnomAD_ASJ_AF", "NullableFloatColumn", "Frequency of existing variant in gnomAD exomes Ashkenazi Jewish population" ], | ||
| [ "gnomAD_EAS_AF", "NullableFloatColumn", "Frequency of existing variant in gnomAD exomes East Asian population" ], | ||
| [ "gnomAD_FIN_AF", "NullableFloatColumn", "Frequency of existing variant in gnomAD exomes Finnish population" ], | ||
| [ "gnomAD_NFE_AF", "NullableFloatColumn", "Frequency of existing variant in gnomAD exomes Non-Finnish European population" ], | ||
| [ "gnomAD_OTH_AF", "NullableFloatColumn", "Frequency of existing variant in gnomAD exomes other combined population" ], | ||
| [ "gnomAD_SAS_AF", "NullableFloatColumn", "Frequency of existing variant in gnomAD exomes South Asian population" ], | ||
| [ "MAX_AF", "NullableFloatColumn", "Maximum observed allele frequency in 1000 Genomes, ESP and ExAC/gnomAD" ], | ||
| [ "MAX_AF_POPS", "SequenceOfStrings", "Populations in which maximum allele frequency was observed" ], | ||
| [ "gnomAD_non_cancer_AF", "NullableFloatColumn", "Frequency of exisiting variant in gnomAD genomes combined non-cancer population" ], | ||
| [ "gnomAD_non_cancer_AFR_AF", "NullableFloatColumn", "Frequency of exisiting variant in gnomAD genomes non-cancer African/American population" ], | ||
| [ "gnomAD_non_cancer_AMI_AF", "NullableFloatColumn", "Frequency of exisiting variant in gnomAD genomes non-cancer Amish population" ], | ||
| [ "gnomAD_non_cancer_AMR_AF", "NullableFloatColumn", "Frequency of exisiting variant in gnomAD genomes non-cancer Latino population" ], | ||
| [ "gnomAD_non_cancer_ASJ_AF", "NullableFloatColumn", "Frequency of exisiting variant in gnomAD genomes non-cancer Ashkenazi Jewish population" ], | ||
| [ "gnomAD_non_cancer_EAS_AF", "NullableFloatColumn", "Frequency of exisiting variant in gnomAD genomes non-cancer East Asian population" ], | ||
| [ "gnomAD_non_cancer_FIN_AF", "NullableFloatColumn", "Frequency of exisiting variant in gnomAD genomes non-cancer Finnish population" ], | ||
| [ "gnomAD_non_cancer_MID_AF", "NullableFloatColumn", "Frequency of exisiting variant in gnomAD genomes non-cancer Middle Eastern population" ], | ||
| [ "gnomAD_non_cancer_NFE_AF", "NullableFloatColumn", "Frequency of exisiting variant in gnomAD genomes non-cancer Non-Finnish European population" ], | ||
| [ "gnomAD_non_cancer_OTH_AF", "NullableFloatColumn", "Frequency of exisiting variant in gnomAD genomes non-cancer Other population" ], | ||
| [ "gnomAD_non_cancer_SAS_AF", "NullableFloatColumn", "Frequency of exisiting variant in gnomAD genomes non-cancer South Asian population" ], | ||
| [ "gnomAD_non_cancer_MAX_AF_adj", "NullableFloatColumn", "Maximum observed allele frequency in non-cancer gnomAD genomes populations after removing subpopulations with less than 2 allele counts" ], | ||
| [ "gnomAD_non_cancer_MAX_AF_POPS_adj", "SequenceOfStrings", "Non-cancer gnomAD genomes populations in which the maximum allele frequency was observed after removing those with less than 2 allele counts" ], | ||
| [ "CLIN_SIG", "SequenceOfStrings", "Clinical significance of variant from dbSNP" ], | ||
| [ "SOMATIC", "SequenceOfNullableYesOrNo", "Somatic status of each ID reported under Existing_variation (0, 1, or null)" ], | ||
| [ "PUBMED", "SequenceOfIntegers", "Pubmed ID(s) of publications that cite existing variant" ], | ||
| [ "TRANSCRIPTION_FACTORS", "SequenceOfStrings", "List of transcription factors which bind to the transcription factor binding profile" ], | ||
| [ "MOTIF_NAME", "NullableStringColumn", "The stable identifier of a transcription factor binding profile (TFBP) aligned at this position" ], | ||
| [ "MOTIF_POS", "NullableIntegerColumn", "The relative position of the variation in the aligned TFBP" ], | ||
| [ "HIGH_INF_POS", "NullableYOrN", "A flag indicating if the variant falls in a high information position of a transcription factor binding profile (TFBP) (Y, N, or null)" ], | ||
| [ "MOTIF_SCORE_CHANGE", "NullableFloatColumn", "The difference in motif score of the reference and variant sequences for the TFBP" ], | ||
| [ "miRNA", "SequenceOfStrings", "SO terms of overlapped miRNA secondary structure feature(s)" ], | ||
| [ "IMPACT", "Impact", "The impact modifier for the consequence type" ], | ||
| [ "PICK", "PickColumn", "Indicates if this block of consequence data was picked by VEP's pick feature (1 or null)" ], | ||
| [ "VARIANT_CLASS", "NullableStringColumn", "Sequence Ontology variant class" ], | ||
| [ "TSL", "NullableIntegerColumn", "Transcript support level, which is based on independent RNA analyses" ], | ||
| [ "HGVS_OFFSET", "NullableIntegerColumn", "Indicates by how many bases the HGVS notations for this variant have been shifted" ], | ||
| [ "PHENO", "SequenceOfNullableYesOrNo", "Indicates if existing variant is associated with a phenotype, disease or trait (0, 1, or null)" ], | ||
| [ "MINIMISED", "PickColumn", "Alleles in this variant have been converted to minimal representation before consequence calculation (1 or null)" ], | ||
| [ "GENE_PHENO", "NullableYesOrNo", "Indicates if gene that the variant maps to is associated with a phenotype, disease or trait (0, 1, or null)" ], | ||
| [ "FILTER", "SequenceOfStrings", "Copied from input VCF. This includes filters implemented directly by the variant caller and other external software used in the DNA-Seq pipeline. See below for additional details." ], | ||
| [ "CONTEXT", "StringColumn", "The reference allele per VCF specs, and its five flanking base pairs" ], | ||
| [ "src_vcf_id", "UUIDColumn", "GDC UUID for the input VCF file" ], | ||
| [ "tumor_bam_uuid", "UUIDColumn", "GDC UUID for the tumor bam file" ], | ||
| [ "normal_bam_uuid", "NullableUUIDColumn", "GDC UUID for the normal bam file" ], | ||
| [ "case_id", "UUIDColumn", "GDC UUID for the case" ], | ||
| [ "GDC_FILTER", "SequenceOfStrings", "GDC filters applied universally across all MAFs" ], | ||
| [ "COSMIC", "SequenceOfStrings", "Overlapping COSMIC variants" ], | ||
| [ "hotspot", "NullableYOrN", "A flag indicating if the variant is a known hotspot (Y, N, or null)" ], | ||
| [ "vcf_region", "StringColumn", "Colon separated string containing the CHROM, POS, ID, REF, and ALT columns from the VCF file (e.g., chrZ:20:rs1234:A:T) (not in somatic MAF)" ], | ||
| [ "vcf_info", "NullableStringColumn", "INFO column from VCF (not in somatic MAF)" ], | ||
| [ "vcf_format", "StringColumn", "FORMAT column from VCF (not in somatic MAF)" ], | ||
| [ "vcf_tumor_gt", "StringColumn", "Tumor sample genotype column from VCF (not in somatic MAF)" ], | ||
| [ "vcf_normal_gt", "NullableStringColumn", "Normal sample genotype column from VCF (not in somatic MAF)" ] | ||
| ], | ||
| "filtered" : "None" | ||
| } |
Oops, something went wrong.