genome_annotation.mcf

# Classes
Node: dcid:Allele
typeOf: schema:Class
subClassOf: dcs:GenomeAnnotation
name: "Allele"

Node: dcid:BasePairs
typeOf: dcs:UnitOfMeasure
name: "BasePairs"
subClassOf: dcs:GenomeAnnotation
description: "The number of pairs of complementary bases in a double-stranded nucleic acid molecule (DNA), consisting of a purine in one strand linked by hydrogen bonds to a pyrimidine in the other."

Node: dcid:Chromosome
name: "Chromosome"
typeOf: schema:Class
subClassOf: dcs:GenomeAnnotation
description: "A threadlike structure of nucleic acids and protein found in the nucleus of most living cells, carrying genetic information in the form of genes."

Node: dcid:Gene
name: "Gene"
typeOf: schema:Class
subClassOf: dcs:GenomeAnnotation
description: "Gene symbol of a gene, which is the basic hereditary unit of life."
descriptionUrl: "https://bioportal.bioontology.org/ontologies/OGG"

Node: dcid:GeneGeneAssociation
name: "GeneGeneAssociation"
typeOf: schema:Class
subClassOf: dcs:GeneticAssociation
description: "The association between two genes."

Node: dcid:GeneGeneticVariantAssociation
name: "GeneGeneticVariantAssociation"
typeOf: schema:Class
subClassOf: dcs:GeneticAssoication
description: "The association between a gene and a genetic variant. This association is typically tissue-specific."

Node: dcid:GeneticAssociation
name: "GeneticAssociation"
typeOf: schema:Class
subClassOf: dcs:Association,dcs:GenomeAnnotation
description: "Association between a genome annotation and another entity type."

Node: dcid:GeneticVariant
name: "GeneticVariant"
typeOf: schema:Class
subClassOf: dcs:GenomeAnnotation
description:  "A single-nucleotide polymorphism, which is a substitution of a single nucleotide that occurs at a specific position in the genome, where each variation is present to some appreciable degree within a population. These are defined by dbSNP and includes small indels as well."
descriptionUrl: "http://rohsdb.usc.edu/GBshape/cgi-bin/hgTables?db=hg19&hgta_group=varRep&hgta_track=snp137&hgta_table=snp137&hgta_doSchema=describe+table+schema"

Node: dcid:GeneticVariantGeneticVariantAssociation
name: "GeneticVariantGeneticVariantAssociation"
typeOf: schema:Class
subClassOf: dcs:GeneticAssociation
description: "The association between two genetic variants."

Node: dcid:GenomeAnnotation
name: "GenomeAnnotation"
typeOf: schema:Class
subClassOf: dcs:BiologicalEntity
description: "Entities or properties of the genome."

Node: dcid:GenomeAssembly
name: "GenomeAssembly"
typeOf: schema:Class
subClassOf: dcs:GenomeAnnotation
description:  "The reference genome to which the associated nucleotides have been aligned."

Node: dcid:GenomeAssemblyUnit
name: "GenomeAssemblyUnit"
typeOf: schema:Class
subClassOf: dcs:GenomeAnnotation
description:  "The unit of assembling a reference genome to which the associated nucleotides have been aligned. Each unit is typically defined by the location of the cell from which the DNA is located such as the nucleus or an organelle."

Node: dcid:GeneMendelianInheritanceInManIdentifierAssociation
name: "GeneMendelianInheritanceInManIdentifierAssociation"
typeOf: schema:Class
subClassOf: dcs:GeneticAssociation
description: "Report of the relationship between MIM numbers (OMIM), GeneIDs, and Records in MedGen."
descriptionUrl: "https://ftp.ncbi.nlm.nih.gov/gene/README"

Node: dcid:GeneOntologyTerm
name: "GeneOntologyTerm"
typeOf: schema:Class
subClassOf: dcs:GenomeAnnotation
abbreviation: "GO Term"
description: "A Gene Ontology (GO) term is a controlled vocabulary term used to describe the functions of genes and gene products (proteins and RNA) in a standardized way. It provides a structured representation of biological knowledge, enabling researchers to annotate genes and gene products, compare and integrate data, and explore networks and pathways. It has a heirarchical structure and consists of three seperate ontologies: Biological Process (BP), Molecular Function (MF), and Cellular Component (CC)."

Node: dcid:GeneReferenceIntoFunction
name: "GeneReferenceIntoFunction"
typeOf: schema:Class
subClassOf: dcs:GenomeAnnotation
description: "A GeneRIF (Gene Reference Into Function) is a concise phrase describing the function of a gene. It provides a quick summary of the gene's role, linking the gene to its known or predicted biological function. GeneRIFs are manually curated from published literature and stored in the NCBI Gene database."

Node: dcid:GenomicCoordinates
name: "GenomicCoordinates"
typeOf: schema:Class
subClassOf: dcs:GenomeAnnotation
description: "The location in the genome or DNA conting of an element of interest. This is reported in the standardized format of [chrom, chromStart, chromEnd]. These coordinates are specific to any given genome assembly."

Node: dcid:GenomicPosition
name: "GenomicPosition"
typeOf: schema:Class
subClassOf: dcs:GenomeAnnotation
description: "The precise nucleotide location in thegenome or DNA contigof an element of interest. This is reported in the standardized format of [chrom position]. This position is specific to any given genome assembly. Genomic position is typically used to refer to genetic variants"

Node: dcid:GenomicRegion
name: "GenomicRegion"
typeOf: schema:Class
subClassOf: dcs:GenomeAnnotation
description: "A genomic region refers to a contiguous stretch of DNA within an organism's genome. It can encompass a single gene, a group of genes, regulatory elements, or any other segment of DNA with a defined start and end point."

Node: dcid:NonCodingRNA
name: "NonCodingRNA"
typeOf: schema:Class
subClassOf: dcs:Gene
description: "A non-coding RNA (ncRNA) is a functional RNA molecule that is not translated into a protein. The DNA sequence from which a functional non-coding RNA is transcribed is often called an RNA gene. Abundant and functionally important types of non-coding RNAs include transfer RNAs (tRNAs) and ribosomal RNAs (rRNAs), as well as small RNAs such as microRNAs, siRNAs, piRNAs, snoRNAs, snRNAs, exRNAs, scaRNAs and the long ncRNAs such as Xist and HOTAIR."
descriptionUrl: "https://en.wikipedia.org/wiki/Non-coding_RNA"

Node: dcid:Nucleotide
name: "Nucleotide"
typeOf: schema:Class
subClassOf: dcs:GenomeAnnotation
description: "A recorded nucleotide on the positive strand of a denoted genome assembly."

Node: dcid:MaturePeptide
name: "MaturePeptide"
typeOf: schema:Class
subClassOf: dcs:Protein
description: "A mature peptides represents the final, functional form of a protein after it has undergone post-translational modifications and processing. These modifications can include: cleavage, chemical modifications, and formation of disulfide bonds. It represents the active form of the protein that carries out its biological role. Mature peptides play crucial roles in various cellular processes, including signaling, enzymatic activity, structural support, and immune response."

Node: dcid:MendelianInheritanceInManEntity
name: "MendelianInheritanceInManEntity"
typeOf: schema:Class
subClassOf: dcs:GenomeAnnotation
description: "An entity representing a human gene or genetic phenotype in Online Mendelian Inheritance in Man (OMIM)."
url: "https://www.omim.org/"

Node: dcid:RnaTranscript
name: "RnaTranscript"
typeOf: schema:Class
subClassOf: dcs:GenomeAnnotation
description: "Recorded transcript. Unique identifier (GENCODE transcript ID for GENCODE Basic)."

Node: dcid:SequenceOntologyTerm
name: "SequenceOntologyTerm"
typeOf: schema:Class
subClassOf: dcs:GenomeAnnotation
description: "The Sequence Ontology (SO) is a set of terms and relationships used to describe the features and attributes of biological sequence. SO includes different kinds of features which can be located on the sequence. Biological features are those which are defined by their disposition to be involved in a biological process. Examples are binding_site and exon. Biomaterial features are those which are intended for use in an experiment such as aptamer and PCR_product. There are also experimental features which are the result of an experiment. SO also provides a rich set of attributes to describe these features such as polycistronic and maternally_imprinted."
descriptionUrl: "http://www.sequenceontology.org/"

Node: dcid:SequenceOntologyTermSynonym
name: "SequenceOntologyTermSynonym"
typeOf: schema:Class
subClassOf: dcs:SequenceOntologyTerm
description: "These are the synonyms for a SequenceOntologyTerm node. This includes information about the closeness of the match with the SequenceOntologyTerm, the source of the information, and a string value of the synonym itself."

Node: dcid:UmlsConceptUniqueIdentifier
name: "UmlsConceptUniqueIdentifier"
typeOf: schema:Class
subClassOf: dcs:BiomedicalEntity
synonym: "MedGen Concept ID", "CUI"
description: "A Concept Unique Identifer (CUI) for a entity in MedGen, which is NCBI's portal to information about conditions and phenotypes related to Medical Genetics. Terms from the NIH Genetic Testing Registry (GTR), UMLS, HPO, Orphanet, ClinVar and other sources are aggregated into concepts, each of which is assigned a unique identifier and a preferred name and symbol. The core content of the record may include names, identifiers used by other databases, mode of inheritance, clinical features, and map location of the loci affecting the disorder. The concept identifier (CUI) is used to aggregate information about that concept, similar to the way NCBI Gene serves as a gateway to gene-related information."
descriptionUrl: "https://www.ncbi.nlm.nih.gov/medgen/docs/help/"

# Properties
Node: dcid:agiLocusCode
name: "agiLocusCode"
typeOf: schema:Property
domainIncludes: dcs:Gene
rangeIncludes: schema:Text
synonym: "Arabidopsis Genome Initiative"
description: "The Arabidopsis Information Resource (TAIR) is a continuously updated, online database of genetic and molecular biology data for the model plant Arabidopsis thaliana that provides a global research community with centralized access to data for over 30,000 Arabidopsis genes. Each locus in Arabidopsis is assigned a unique identifier, termed the AGI locus code (AGI, Arabidopsis Genome Initiative) which consists of the prefix At, followed by the chromosome identifier (1-5 or M or C) followed by g for gene and then a unique 5 digit number (e.g. At2g46340). These AGI locus codes are used by other Arabidopsis resources in addition to TAIR, such as Araport."
descriptionUrl: "https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4545719/)."
url: "https://www.arabidopsis.org/"

Node: dcid:alleleOrigin
name: "alleleOrigin"
typeOf: schema:Property
rangeIncludes: dcs:VariantAlleleOriginEnum
domainIncludes: dcs:GeneticVariant
description: "Variant Allele Origin: unspecified, germline, somatic, both, inherited, paternal, maternal, uni-parental, bi-parental, not_tested, tested_inconclusive, de-novo, or other."

Node: dcid:alleleType
name: "alleleType"
typeOf: schema:Property
rangeIncludes: schema:Text
domainIncludes: dcs:GeneticVariant
description: "The allele of a genetic variant observed within a population."

Node: dcid:allianceOfGenomeResourcesId
name: "allianceOfGenomeResourcesId"
typeOf: schema:Property
domainIncludes: dcs:Gene
rangeIncludes: schema:Text
description: "The gene identifier used by the Alliance of Genome Resources, which is a consortium of seven model organism databases (MODs) and the Gene Ontology (GO) Consortium whose goal is to provide an integrated view of their data to all biologists, clinicians and other interested parties.The primary mission of the Alliance of Genome Resources (the Alliance) is to develop and maintain sustainable genome information resources that facilitate the use of diverse model organisms in understanding the genetic and genomic basis of human biology, health and disease. The seven model organism databases managed by the consortium is as follows: FlyBase, Mouse Genome Database (MGD), Rat Genome Database (RGD), Saccharomyces Genome Database (SGD), WormBase, XenBase, Zebrafish Information Network (ZFIN), and the Genome Ontology Consortium (GOC)."
url: "https://www.alliancegenome.org/"

Node: dcid:animalQuantitativeTraitLociId
name: "animalQuantitativeTraitLociId"
typeOf: schema:Property
domainIncludes: dcs:Gene
rangeIncludes: schema:Text
abbreviation: "animal QTL Id"
description: "The gene identifier used by The Animal Quantitative Trait Loci (QTL) Database (Animal QTLdb), a database that strives to collect all publicly available trait mapping data, i.e. QTL (phenotype/expression, eQTL), candidate gene and association data (GWAS), and copy number variations (CNV) mapped to livestock animal genomes, in order to facilitate locating and comparing discoveries within and between species. It supports information on cattle, chickens, horses, goats, pigs, rainbow trout, and sheep."
descriptionUrl: "https://www.animalgenome.org/cgi-bin/QTLdb/index"

Node: dcid:alternateGeneSymbol
name: "alternateGeneSymbol"
typeOf: schema:Property
rangeIncludes: schema:Text
domainIncludes: dcs:Gene
description: "Alternative or secondary symbol for a gene."

Node: dcid:aphidBaseId
name: "aphidBaseId"
typeOf: schema:Property
domainIncludes: dcs:Gene
rangeIncludes: schema:Text
description: "The gene identifier used by AphidBase, which is a reference information system providing genomic resources for the study of aphids. It hosts several reference aphid genomes, including the first aphid genome that was sequenced: Acyrthosiphon pisum."
descriptionUrl: "https://bipaa.genouest.org/is/aphidbase/"

Node: dcid:asapId
name: "asapId"
typeOf: schema:Property
domainIncludes: dcs:Gene
rangeIncludes: schema:Text
synonym: "A Systematic Annotation Package for Community Analysis of Genomes ID"
description: "The gene identifier used by ASAP (a systematic annotation package for community analysis of genomes), which is is a relational database and web interface developed to store, update and distribute genome sequence data and gene expression data collected by or in collaboration with researchers at the University of Wisconsin - Madison."
descriptionUrl: "http://asap.ahabs.wisc.edu/asap/ASAP1.htm"
url: "https://asap.ahabs.wisc.edu/"

Node: dcid:assemblyMethod
dcid: "assemblyMethod"
typeOf: schema:Property
rangeIncludes: schema:Text
domainIncludes: dcs:GenomeAssembly
description: "The alogrithm used to assemble the genome from sequencing reads."

Node: dcid:associationSource
name: "associationSource"
typeOf: schema:Property
domainIncludes: schema:Thing
rangeIncludes: schema:Text
description: "The organization that reported an association between two things."

Node: dcid:associationType
name: "associationType"
typeOf: schema:Property
domainIncludes: schema:Thing
rangeIncludes: dcs:AssociationTypeEnum
description: "The way by which an association between two entities is made."

Node: dcid:averageHeterozygosity
name: "averageHeterozygosity"
typeOf: schema:Property
rangeIncludes: schema:Number
domainIncludes: dcs:GeneticVariant
description: "Average heterozygosity from all observations. Note: may be computed on small number of samples."

Node: dcid:averageHeterozygositySE
name: "averageHeterozygositySE"
typeOf: schema:Property
rangeIncludes: schema:Number
domainIncludes: dcs:GeneticVariant
description: "Standard Error for the average heterozygosity."

Node: dcid:beetleBaseId
name: "beetleBaseId"
typeOf: schema:Property
domainIncludes: dcs:Gene
rangeIncludes: schema:Text
description: "The gene identifiers formatted as 'TC######' used by BeetleBase, which contains comprehensive genomic information for the red flour beetle Tribolium castaneum."
descriptionUrl: "https://www.ncbi.nlm.nih.gov/pmc/articles/PMC2808946/"

Node: dcid:betaDistributionShapes
name: "betaDistributionShapes"
typeOf: schema:Property
rangeIncludes: schema:Number
domainIncludes: dcs:GeneGeneticVariantAssociation
description: "The shape parameters of the fitted Beta distribution: B(shape1, shape2)."

Node: dcid:bovineGenomeDatabaseId
name: "bovineGenomeDatabaseId"
typeOf: schema:Property
domainIncludes: dcs:Gene
rangeIncludes: schema:Text
abbreviation: "BGD ID"
description: "The gene identifier used by the Bovine Genome Database (BGD), which supports the efforts of bovine genomics researchers by providing data mining, genome navigation and annotation tools for the bovine reference genome based on the hereford cow, L1 Dominette 01449."
descriptionUrl: "https://bovinegenome.elsiklab.missouri.edu/"

Node: dcid:chickenGeneNomenclatureConsortiumId
name: "chickenGeneNomenclatureConsortiumId"
typeOf: schema:Property
domainIncludes: dcs:Gene
rangeIncludes: schema:Text
abbreviation: "CGNC ID"
description: "The gene identifier used by the Chicken Gene Nomenclature Consortium (CGNC), which is an international group of researchers interested in providing standardized gene nomenclature for chicken genes."
descriptionUrl: "http://birdgenenames.org/cgnc/about.jsp"

Node: dcid:chrom
name: "chrom"
typeOf: schema:Property
domainIncludes: dcs:GenomeAnnotation
rangeIncludes: schema:Text,dcs:Chromosome
description: "Chromosome (e.g. chr3, chrY, chr2_random) or scaffold (e.g. scaffold10671) name."
descriptionUrl: "https://en.wikipedia.org/wiki/BED_(file_format)"

Node: dcid:chromosomeSize
name: "chromosomeSize"
typeOf: schema:Property
rangeIncludes: schema:Quantity
domainIncludes: dcs:Chromosome
description: "The number of nucleotides in a given chromosome."

Node: dcid:chromStart
name: "chromStart"
typeOf: schema:Property
domainIncludes: dcs:GenomeAnnotation
rangeIncludes: schema:Number
description: "Start coordinate on the chromosome or scaffold for the sequence considered (the first base on the chromosome is numbered 0)."
descriptionUrl: "https://en.wikipedia.org/wiki/BED_(file_format)"

Node: dcid:chromEnd
name: "chromEnd"
typeOf: schema:Property
domainIncludes: dcs:GenomeAnnotation
rangeIncludes: schema:Number
description: "End coordinate on the chromosome or scaffold for the sequence considered. This position is non-inclusive, unlike chromStart."
descriptionUrl: "https://en.wikipedia.org/wiki/BED_(file_format)"

Node: dcid:clinicalSignificance
name: "clinicalSignificance"
typeOf: schema:Property
rangeIncludes: dcs:ClinSigEnum
domainIncludes: dcs:GeneticVariant
description: "Clinical significance for this single variant: other, affects, uncertain_significance, pathogenic, risk_factor, benign, conflicting_interpretations_of_pathogenicity, association, likely_pathogenic, protective, likely_benign, not_provided, association_not_found, drug_response, pathogenic/likely_pathogenic,benign/likely_benign, unknown, untested, or histocompatibility."

Node: dcid:clinicalSource
name: "clinicalSource"
typeOf: schema:Property
rangeIncludes: schema:Text
domainIncludes: dcs:GeneticVariant
description: "The variant's clinical sources reported as tag-value pairs of database and variant identifier."

Node: dcid:clinVarAlleleID
name: "clinVarAlleleID"
typeOf: schema:Property
rangeIncludes: schema:Number
domainIncludes: dcs:GeneticVariant
description: "ClinVar Allele ID."

Node: dcid:clinicalSignificanceType
name: "clinicalSignificanceType"
typeOf: schema:Property
rangeIncludes: schema:Text
domainIncludes: dcs:GeneticVariant
description: "A type of clinical significance report observed for a genetic variant."

Node: dcid:clinVarFilterStatus
name: "clinVarFilterStatus"
typeOf: schema:Property
rangeIncludes: schema:Text
domainIncludes: dcs:GeneticVariant
description: "Filter status: PASS if this position has passed all filters, i.e., a call is made at this position. Otherwise, if the filters that the site failed are recorded."

Node: dcid:clinVarQualityScore
name: "clinVarQualityScore"
typeOf: schema:Property
rangeIncludes: schema:Number
domainIncludes: dcs:GeneticVariant
description: "Phred-scaled quality score for the assertion made in ALT. i.e. -10log10 prob(call in ALT is wrong)."

Node: dcid:clinVarReviewStatus
name: "clinVarReviewStatus"
typeOf: schema:Property
rangeIncludes: dcs:ClinVarReviewStatusEnum
domainIncludes: dcs:GeneticVariant
description: "ClinVar review status: no assertion criteria provided, reviewed by expert panel, conflicting interpretations, criteria provided, non interpretation for the single variant, practice guideline, no conflicts, multiple submitters, or single_submitter."

Node: codingCoordinates
dcid:codingCoordinates
name: "codingCoordinates"
typeOf: schema:Property
rangeIncludes: schema:Number
domainIncludes: dcs:RnaTranscript
description: "Specifies the genomic position of the genomic coordinates of the coding region associated with a given RefSeq Accession number."

Node: dcid:confidence
name: "confidence"
typeOf: schema:Property
domainIncludes: schema:Thing
rangeIncludes: schema:Text
description: "The level of confidence that a given result is accurate."

Node: dcid:contigCount
name: "contigCount"
typeOf: schema:Property
domainIncludes: dcs:GenomeAssembly
rangeIncludes: schema:Text
description: "The number of contigs in the primary assembly."
descriptionUrl: "https://ftp.ncbi.nlm.nih.gov/genomes/README_assembly_summary.txt"

Node: dcid:cytogeneticMapLocation
name: "cytogeneticMapLocation"
typeOf: schema:Property
rangeIncludes: schema:Text
domainIncludes: dcs:Gene
description: "The location of the gene on the chromosome. Each chromosome has a distinct banding pattern, and each band is numbered to help identify a particular region of a chromosome. This method of mapping a gene to a particular band of the chromosome is called cytogenetic mapping. For example, the hemoglobin beta gene (HBB) is found on chromosome 11p15.4. This means that the HBB gene lies on the short arm (p) of chromosome 11 and is found at the band labeled 15.4."
descriptionUrl: "https://www.ncbi.nlm.nih.gov/books/NBK22266/"

Node: dcid:dbSNPBuildID
name: "dbSNPBuildID"
typeOf: schema:Property
rangeIncludes: schema:Text
domainIncludes: dcs:GeneticVariant
description: "First dbSNP Build for RS."

Node: dcid:dbVarID
name: "dbVarID"
typeOf: schema:Property
rangeIncludes: schema:Text
domainIncludes: dcs:GeneticVariant
description: "Accessions from dbVar for the genetic variant"
descriptionUrl: "https://www.ncbi.nlm.nih.gov/dbvar/"

Node: dcid:dictyBaseGeneId
name: "dictyBaseGeneId"
typeOf: schema:Property
domainIncludes: dcs:Gene
rangeIncludes: schema:Text
description: "The gene identifier used by dictyBase, an online bioinformatics database dedicated to the model organism Dictyostelium discoideum."
url: "http://dictybase.org/"

Node: dcid:digitalObjectIdentifier
name: "digitalObjectIdentifier"
typeOf: schema:Property
domainIncludes: dcs:Thing
rangeIncludes: schema:Text
abbreviation: "DOI"
description: "A DOI name is a digital identifier of an object, any object - physical, digital, or abstract. DOIs solve a common problem: keeping track of things. Things can be matter, material, content, or activities. Designed to be used by humans as well as machines, DOIs identify objects persistently. They allow things to be uniquely identified and accessed reliably. You know what you have, where it is, and others can track it too."
descriptionUrl: "https://www.doi.org/"

Node: dcid:diseaseDescription
name: "diseaseDescription"
typeOf: schema:Property
rangeIncludes: schema:Text
domainIncludes: dcs:GeneticVariant
description: "ClinVar's preferred disease name for the concept specified by disease identifiers."

Node: dcid:diseaseName
name: "diseaseName"
typeOf: schema:Property
rangeIncludes: schema:Text
domainIncludes: dcs:GeneticVariant
description: "ClinVar's preferred disease name for the concept specified by disease identifiers."

Node: dcid:dnaSequenceRole
name: "dnaSequenceRole"
typeOf: schema:Property
rangeIncludes: dcs:DNASequenceRoleEnum
domainIncludes: dcs:Chromosome
description: "The role a defined sequence of DNA has in a genome assembly."

Node: dcid:ecoCycAccessionId
name: "ecoCycAccessionId"
typeOf: schema:Property
domainIncludes: dcs:Gene
rangeIncludes: schema:Text
description: "The gene identifier used by BioCyc, which is a collection of 20,050 Pathway/Genome Databases (PGDBs) for model eukaryotes and for thousands of microbes, plus software tools for exploring them. BioCyc is an encyclopedic reference that contains curated data from 146,000 publications."
descriptionUrl: "https://biocyc.org/"

Node: dcid:echinoBaseGeneId
name: "echinoBaseGeneId"
typeOf: schema:Property
domainIncludes: dcs:Gene
rangeIncludes: schema:Text
description: "The gene identifier used by Echinobase, which supports the international research community by providing a centralized, integrated and easy to use web based resource to access the diverse and rich, functional genomics data of echinoderm species."
descriptionUrl: "https://www.echinobase.org/echinobase/"

Node: dcid:encodesGene
name: "encodesGene"
typeOf: schema:Property
domainIncludes: dcs:GenomicRegion
rangeIncludes: dcs:Gene
description: "Indicates the gene that the specific genomic region of DNA encodes."

Node: dcid:ensemblID
name: "ensemblID"
typeOf: schema:Property
rangeIncludes: schema:Text
domainIncludes: dcs:Gene,dcs:GeneGeneticVariantAssociation,dcs:Protein
description: "Ensembl ID, which describes a particular gene or protein."

Node: dcid:ensemblGeneId
name: "ensemblGeneId"
typeOf: schema:Property
domainIncludes: dcs:Gene, dcs:RnaTranscript, dcs:Protein
rangeIncludes: schema:Text
specializationOf: dcs:ensemblID
description: "Gene identifier used by Ensembl, which represents a specific genomic locus that is predicted to encode a protein or a functional RNA molecule. They are formatted starting with the prefix 'ENSG' followed by a unique number (e.g. ENSG00000139618 (Human BRCA2 gene)). This locus represents all known transcripts and protein products that originate from this locus, even if they have different splicing patterns or protein isoforms."

Node: dcid:ensemblProteinId
name: "ensemblProteinId"
typeOf: schema:Property
domainIncludes: dcs:Gene, dcs:RnaTranscript, dcs:Protein
rangeIncludes: schema:Text
specializationOf: dcs:ensemblID
description: "Protein identifier used by Ensembl, which represents a specific protein sequence translated from an mRNA transcript. They are formatted starting with the prefix 'ENSP' followed by a unique number (e.g.  ENSP00000369406 (One of the protein isoforms encoded by the Human BRCA2 gene)). This represents the amino acid sequence that results from the specific combination of exons in the corresponding mRNA."

Node: dcid:ensemblRapidReleaseId
name: "ensemblRapidReleaseId"
typeOf: schema:Property
domainIncludes: dcs:Gene, dcs:RnaTranscript, dcs:Protein
rangeIncludes: schema:Text
specializationOf: dcs:ensemblID

Node: dcid:ensemblRapidReleaseId
name: "ensemblRapidReleaseId"
typeOf: schema:Property
domainIncludes: dcs:Gene, dcs:RnaTranscript, dcs:Protein
rangeIncludes: schema:Text
specializationOf: dcs:ensemblID
description: "Ensembl Rapid Release IDs are unique identifiers assigned to genomic features (primarily genes, but also transcripts and proteins) in newly sequenced genomes that are made available quickly through Ensembl's Rapid Release pipeline. This program has a release cycle of two weeks and the identifiers provide early access to gene annotation for genomes that are not yet fully integrated into the main Ensembl database."

Node: dcid:ensemblRnaId
name: "ensemblRnaId"
typeOf: schema:Property
domainIncludes: dcs:Gene, dcs:RnaTranscript, dcs:Protein
rangeIncludes: schema:Text
specializationOf: dcs:ensemblID
description: "RNA sequence identifier used by Ensembl, which represents a specific RNA transcript produced from a gene. This could be a messenger RNA (mRNA) that encodes a protein or other types of RNA such as long non-coding RNAs (lncRNAs) or microRNAs (miRNAs). They are formatted starting with the prefix 'ENST' followed by a unique number (e.g. ENST00000380152 (One of the many transcripts of the Human BRCA2 gene). This represents the specific combination of exons included in the mature transcript due to alternative splicing."

Node: dcid:experimentalFactorOntologyID
name: "experimentalFactorOntologyID"
typeOf: schema:Property
rangeIncludes: schema:Text
domainIncludes: dcs:GeneticVariant
description: "The Experimental Factor Ontology (EFO) provides a systematic description of many experimental variables available in EBI databases, and for external projects such as the NHGRI GWAS catalog."
descriptionUrl: "https://www.ebi.ac.uk/efo/"
abbreviation: "EFO ID"

Node: dcid:flyBaseId
name: "flyBaseId"
typeOf: schema:Property
domainIncludes: dcs:Gene
rangeIncludes: schema:Text
specializationOf: dcs:allianceOfGenomeResourcesId
description: "The gene identifier used by FlyBase. The aim of the FlyBase project is to provide an openly accessible centralized resource for Drosophila genetic, genomic and functional data. FlyBase is a member of the Alliance of Genome Resources."
descriptionUrl:"https://wiki.flybase.org/wiki/FlyBase:About#FlyBase_Mission_Statement"
url:"https://flybase.org/"

Node: dcid:frequency
typeOf: schema:Property
domainIncludes: dcid:Allele
rangeIncludes: schema:Number
name: "frequency"

Node: dcid:fullName
name: "fullName"
typeOf: schema:Property
rangeIncludes: schema:Text
domainIncludes: dcs:Gene
description: "The full name of the gene."

Node: dcid:gcContent
name: "gcContent"
typeOf: schema:Property
domainIncludes: dcs:GenomeAnnotation
rangeIncludes: schema:Quantity
description: "Percent of nitrogenous bases (guanine or cytosine) in DNA submitted for the assembly, rounded to the nearest 0.5%."
descriptionUrl: "https://ftp.ncbi.nlm.nih.gov/genomes/README_assembly_summary.txt"

Node: dcid:genBankAssemblyAccession
name: "genBankAssemblyAccession"
typeOf: schema:Property
rangeIncludes: schema:Text
domainIncludes: dcs:BiologicalEntity
description: "The accession version of the GenBank assembly or sequence element."

Node: dcid:genBankNucleotideAccession
name: "genBankNucleotideAccession"
typeOf: schema:Property
domainIncludes dcs:GenomeAssembly
rangeIncludes: schema:Text
description: "WGS-master: the GenBank Nucleotide accession and version for the master record of the Whole Genome Shotgun (WGS) project for the genome assembly. The master record can be retrieved from the NCBI Nucleotide resource: https://www.ncbi.nlm.nih.gov/nuccore. Genome assemblies that are complete genomes, and those that are clone-based, do not have WGS-master records. GenBank uses a different format for accessions of sequences that are a part of the WGS project."
descriptionUrl: "https://ftp.ncbi.nlm.nih.gov/genomes/README_assembly_summary.txt"

Node: dcid:geneCount
name: "geneCount"
typeOf: schema:Property
domainIncludes: dcs:GenomeAnnotation
rangeIncludes: schema:Number
description: "The total number of genes (both protein coding and non-coding genes) within a consensus region of DNA."

Node: dcid:geneGeneOntologyTermRelationshipQualifier
name: "geneGeneOntologyTermRelationshipQualifier"
typeOf: schema:Property
domainIncludes: dcs:GeneOntologyTerm
rangeIncludes: dcs:GOTermQualifierEnum
description: "The nature of the association between the gene product and the GO term."

Node: dcid:geneID
name: "geneID"
typeOf: schema:Property
rangeIncludes: dcs:Gene
domainIncludes: dcs:GeneticAssociation,dcs:GeneticVariant,dcs:Protein
description: "Link out to the Gene node associated with the current node."

Node: dcid:geneOmimRelationshipComment
name: "geneOmimRelationshipComment"
typeOf: schema:Property
domainIncludes: dcs:GeneMendelianInheritanceInManIdentifierAssociation
rangeIncludes: dcs:GeneOmimRelationshipCommentEnum
description: "The qualifiers OMIM provides when reporting a gene/phenotype relationship."
descriptionUrl: "https://ftp.ncbi.nlm.nih.gov/gene/README"

Node: dcid:geneOmimRelationshipSource
name: "geneOmimRelationshipSource"
typeOf: schema:Property
domainIncludes: dcs:GeneMendelianInheritanceInManIdentifierAssociation
rangeIncludes: dcs:GeneOmimRelationshipSourceEnum
description: "The source of a report of a relationship between a MIM number that is a phenotype, and a Gene."
descriptionUrl: "https://ftp.ncbi.nlm.nih.gov/gene/README"

Node: dcid:geneOmimRelationshipType
name: "geneOmimRelationshipType"
typeOf: schema:Property
domainIncludes: dcs:GeneMendelianInheritanceInManIdentifierAssociation
rangeIncludes: dcs:GeneOmimRelationshipTypeEnum
description: "The type of relationship between the MIM number and the GeneID. The current values are 'gene' (the MIM number associated with a Gene, or a Gene that is assigned to a record where the molecular basis of the disease is not known) and 'phenotype' the MIM number associated with a disease that is associated with a gene."
descriptionUrl: "https://ftp.ncbi.nlm.nih.gov/gene/README"

Node: dcid:geneOntologyCategory
name: "geneOntologyCategory"
typeOf: schema:Property
domainIncludes: dcs:GeneOntologyTerm
rangeIncludes: dcs:GeneOntologyCategoryEnum
description: "Indicates which of the three ontologies to which the Gene Ontology Term belongs: Biological Process (BP), Cellular Component (CC), or Molecular Function (MF)."

Node: dcid:geneOntologyEvidenceCode
name: "geneOntologyEvidenceCode"
typeOf: schema:Property
domainIncludes: dcs:GeneOntologyTerm
rangeIncludes: dcs:GOTermEvidenceCodeEnum
description: "The evidence code that is associated with a Gene Ontology (GO) term. This indicates the type of evidence supporting the association between the gene product and the GO term (e.g., experimental, computational, or other evidence)."

Node: dcid:geneOntologyId
name: "geneOntologyId"
typeOf: schema:Property
domainIncludes: dcs:GeneOntologyTerm
rangeIncludes: dcs:GOTermEvidenceCodeEnum
description: "Every term has a human-readable term name - e.g. mitochondrion, glucose transmembrane transport, or amino acid building - and a GO ID, a unique seven digit identifier prefixed by GO:, e.g. GO:0005739, GO:1904659, or GO:0016597."
descriptionUrl: "https://geneontology.org/docs/GO-term-elements"

Node: dcid:geneOrtholog
name: "geneOrtholog"
typeOf: schema:Property
domainIncludes: dcs:Gene
rangeIncludes: dcs:Gene
description: "Orthologs are genes in different specise taht can be traced back to the sam gene in the most recent common ancestor."
descriptionUrl: "https://ftp.ncbi.nlm.nih.gov/gene/README"

Node: dcid:genePotentialReadthroughSibling
name: "genePotentialReadthroughSibling"
typeOf: schema:Property
domainIncludes: dcs:Gene
rangeIncludes: dcs:Gene
description: "A gene that is located close to another gene on the same DNA strand and might be transcribed together into a single RNA molecule due to the lack of a strong termination signal between them. Further analysis is needed to confirm if this readthrough actually occurs."

Node: dcid:geneReadthroughChild
name: "geneReadthroughChild"
typeOf: schema:Property
domainIncludes: dcs:Gene
rangeIncludes: dcs:Gene
description: "A gene that is formed when the transcription of an upstream gene (the 'parent') continues past its normal termination signal and into the downstream region, creating a longer RNA transcript that includes the sequence of the 'child' gene."

Node: dcid:geneReadthroughParent
name: "geneReadthroughParent"
typeOf: schema:Property
domainIncludes: dcs:Gene
rangeIncludes: dcs:Gene
description: "The upstream gene in a readthrough relationship. It is the gene whose transcription continues past its normal termination point, leading to the formation of a readthrough child gene."

Node: dcid:geneReadthroughSibling
name: "geneReadthroughSibling"
typeOf: schema:Property
domainIncludes: dcs:Gene
rangeIncludes: dcs:Gene
description: "Genes located on the same DNA strand that are transcribed together into a single RNA molecule due to the lack of a strong termination signal between them. This is confirmed to occur."

Node: dcid:geneRegionMember
name: "geneRegionMember"
typeOf: schema:Property
domainIncludes: dcs:Gene
rangeIncludes: dcs:Gene
description: "A gene located within a defined genomic region. This region might be associated with a specific function, regulatory element, or evolutionary history."

Node: dcid:geneRegionParent
name: "geneRegionParent"
typeOf: schema:Property
domainIncludes: dcs:Gene
rangeIncludes: dcs:Gene
description: "A larger genomic region that encompasses multiple genes, including the 'region member'."

Node: dcid:geneReferenceIntoFunction
name: "geneReferenceIntoFunction"
typeOf: schema:Property
domainIncludes: dcs:GeneReferenceIntoFunction
rangeIncludes: schema:Text
description: "A short, specific summary of a gene's biological function, which is supported by citations from scientific literature."

Node: dcid:geneSymbol
name: "geneSymbol"
typeOf: schema:Property
rangeIncludes: schema:Text
domainIncludes: dcs:Gene,dcs:GeneticVariant,dcs:GeneticAssociation,dcs:Protein
description: "Original gene symbol."

Node: dcid:geneticRepliconCount
name: "geneticRepliconCount"
typeOf: schema:Property
domainIncludes dcs:GenomeAssembly
rangeIncludes: schema:Number
description: "The total number of chromosomes, organelle genomes, and plasmids in the primary assembly."
descriptionUrl: "https://ftp.ncbi.nlm.nih.gov/genomes/README_assembly_summary.txt"

Node: dcid:geneReviewsID
name: "geneReviewsID"
typeOf: schema:Property
rangeIncludes: schema:Number
domainIncludes: dcs:GeneticVariant
description: "GeneReviews, an international point-of-care resource for busy clinicians, provides clinically relevant and medically actionable information for inherited conditions in a standardized journal-style format, covering diagnosis, management, and genetic counseling for patients and their families. Each chapter in GeneReviews is written by one or more experts on the specific condition or disease and goes through a rigorous editing and peer review process before being published online."
descriptionUrl: "https://www.ncbi.nlm.nih.gov/books/NBK1116/"

Node: dcid:geneticScaffoldCount
name: "geneticScaffoldCount"
typeOf: schema:Property
domainIncludes dcs:GenomeAssembly
rangeIncludes: schema:Number
description: "The number of scaffolds including placed, unlocalized, unplaced, alternate loci and patch scaffolds in the primary assembly."
descriptionUrl: "https://ftp.ncbi.nlm.nih.gov/genomes/README_assembly_summary.txt"

Node: dcid:geneticsHomeReferenceID
name: "geneticsHomeReferenceID"
typeOf: schema:Property
rangeIncludes: schema:Number
domainIncludes: dcs:GeneticVariant
description: "Genetics Home Reference (GHR) provides consumer-friendly information about the effects of genetic variation on human health."
descriptionUrl: "https://ghr.nlm.nih.gov/"
abbreviation: "GHR ID"

Node: dcid:geneticTestingRegistryID
name: "geneticTestingRegistryID"
typeOf: schema:Property
rangeIncludes: schema:Number
domainIncludes: dcs:GeneticVariant
description: "The Genetic Testing Registry (GTR) provides a central location for voluntary submission of genetic test information by providers. The scope includes the test's purpose, methodology, validity, evidence of the test's usefulness, and laboratory contacts and credentials. The overarching goal of the GTR is to advance the public health and research into the genetic basis of health and disease."
descriptionUrl: "https://www.ncbi.nlm.nih.gov/gtr/"
abbreviation: "GTR ID"

Node: dcid:geneticVariantAlignmentQuality
name: "geneticVariantAlignmentQuality"
typeOf: schema:Property
rangeIncludes: dcs:GeneticVariantAlignmentQualityEnum
domainIncludes: dcs:GeneticVariant
description: "The quality of the alignment: unique mapping, non-unique, and many matches (1, 2, or 3+)."

Node: dcid:geneticVariantAttribute
name: "geneticVariantAttribute"
typeOf: schema:Property
rangeIncludes: dcs:GeneticVariantAttributeEnum
domainIncludes: dcs:GeneticVariant
description: "Genetic variant attributes extracted from dbSNP's SNP_bitfield table: clinically associated, MAF >5% in some populations, MAF >5% in all populations, has OMIM OMIA, microattribute tpa, submitted by locus-specific database, genotype conflict, rs cluster non-overlapping alleles, observed mismatch, pharmGKB, published, 3D structure, submitter link out, other variant with exact mapping, assembly specific,mutant, validated, included in high density kit, genotypes available, 1000 Genomes Phase 1, 1000 Genomes Phase 3, included in clinical diagnostic assay, withdrawn by some not all submitters, or common SNP."

Node: dcid:geneticVariantClass
name: "geneticVariantClass"
typeOf: schema:Property
rangeIncludes: dcs:GeneticVariantClassEnum
domainIncludes: dcs:GeneticVariant
description: "Class of variant: single_nucleotide_variant, deletion, insertion, in-del, named, mixed, mnp, het, microsatellite, inversion, copy_number_loss, variation, duplication, or copy_number_gain."

Node: dcid:geneticVariantExceptions
name: "geneticVariantExceptions"
typeOf: schema:Property
rangeIncludes: dcs:GeneticVariantExceptionEnum
domainIncludes: dcs:GeneticVariant
description: "Unusual conditions noted by UCSC that may indicate a problem with the data."

Node: dcid:geneticVariantFunctionalCategory
name: "geneticVariantFunctionalCategory"
typeOf: schema:Property
rangeIncludes: dcs:GeneticVariantFunctionalCategoryEnum
domainIncludes: dcs:GeneticVariant
description: "Functional category of the genetic variant (coding-synon, splice_5', missense, frameshift, near_gene_5', 3'_UTR, near_gene_3', nonsense, splice_3', intron, cds_reference, 5'_UTR, unknown, cds_indel, stop_loss, 5' UTR, or ncRNA.)"

Node: dcid:geneticVariantID
name: "geneticVariantID"
typeOf: schema:Property
rangeIncludes: dcs:GeneticVariant
domainIncludes: dcs:GeneGeneticVariantAssociation
description: "Link out to GeneticVariant node associated with the current node."

Node: dcid:geneticVariantImpercise
name: "geneticVariantImpercise"
typeOf: schema:Property
rangeIncludes: schema:Boolean
domainIncludes: dcs:GeneticVariant
description: "Boolean of whether a variant is flagged as an imprecise structural variation."

Node: dcid:geneticVariantLength
name: "geneticVariantLength"
typeOf: schema:Property
rangeIncludes: schema:Number
domainIncludes: dcs:GeneticVariant
description: "Difference in length between REF and ALT alleles (bp)."

Node: dcid:geneticVariantLocType
name: "geneticVariantLocType"
typeOf: schema:Property
rangeIncludes: dcs:GeneticVariantLocTypeEnum
domainIncludes: dcs:GeneticVariant
description: "Type of mapping inferred from size on reference; may not agree with class."

Node: dcid:geneticVariantSubmitterCount
name: "geneticVariantSubmitterCount"
typeOf: schema:Property
rangeIncludes: schema:Number
domainIncludes: dcs:GeneticVariant
description: "Number of distinct submitter handles for submitted SNPs for this ref SNP."

Node: dcid:geneticVariantValidationStatus
name: "geneticVariantValidationStatus"
typeOf: schema:Property
rangeIncludes: dcs:GeneticVariantValidationStatusEnum
domainIncludes: dcs:GeneticVariant
description: "Validation status of the SNP."

Node: dcid:genomeAnnotatedBy
name: "genomeAnnotatedBy"
typeOf: schema:Property
domainIncludes: dcs:GenomeAssembly
rangeIncludes: dcs:Lab,schema:Person,schema:Text
description: "The group that described the structure and identified functional elements of a genome sequence thereby by providing biological significance."

Node: dcid:genomeAssemblyDerivedFrom
name: "genomeAssemblyDerivedFrom"
typeOf: schema:Property
domainIncludes: dcs:GenomeAssembly
rangeIncludes: schema:Boolean
description: "Denotes the relation of the genome assembly with the type material from which it was derived."

Node: dcid:genomeAssemblyType
name: "genomeAssemblyType"
typeOf: schema:Property
rangeIncludes: dcs:GenomeAssemblyTypeEnum
domainIncludes: dcs:GenomeAssembly
description: "The type of sequence model data defined in this genome assembly."

Node: dcid:genomeAssemblyLevel
name: "genomeAssemblyLevel"
typeOf: schema:Property
rangeIncludes: dcs:GenomeAssemblyLevelEnum
domainIncludes: dcs:GenomeAssembly
description: "The highest level of assembly for any object in the assembly."
descriptionUrl: "https://www.ncbi.nlm.nih.gov/assembly/help/#level"

Node: dcid:genomeAssemblyReleaseType
name: "genomeAssemblyReleaseType"
typeOf: schema:Property
rangeIncludes: dcs:GenomeAssemblyReleaseTypeEnum
domainIncludes: dcs:GenomeAssembly
description: "Defines the update type of this genome assembly version release."

Node: dcid:genomeAssemblyYear
name: "genomeAssemblyYear"
typeOf: schema:Property
rangeIncludes: schema:Number
domainIncludes: dcs:GenomeAssembly
description: "The year in which the genome assembly was released."

Node: dcid:genomeCoverage
name: "genomeCoverage"
typeOf: schema:Property
rangeIncludes: schema:Number
domainIncludes: dcs:GenomeAssembly
description: "Genome coverage is the coverage depth of a sequencing run. This is calculated as the number of bases of all short reads that match a genome divided by the length of this genome, which represents the average number of times a base of a genome is sequenced."

Node: dcid:genomeReferenceConsortiumAssemblyName
name: "genomeReferenceConsortiumAssemblyName"
typeOf: schema:Property
rangeIncludes: schema:Text
domainIncludes: dcs:GenomeAssembly
description: "The Genome Refrence Consortium name for the genome assembly."
abbreviation: "GRC assembly name"

Node: dcid:genomeSize
name: "genomeSize"
typeOf: schema:Property
domainIncludes: dcs:GenomeAssembly
rangeIncludes: schema:Quantity
description: "Total length of all top-level sequences in the primary assembly."

Node: dcid:genomeSizeUngapped
name: "genomeSizeUngapped"
typeOf: schema:Property
domainIncludes: dcs:GenomeAssembly
rangeIncludes: schema:Quantity
description: "Total length of all top-level sequences in the primary assembly ignoring gaps. Any stretch of 10 or more Ns in asequence is treated like a gap."
descriptionUrl: "https://ftp.ncbi.nlm.nih.gov/genomes/README_assembly_summary.txt"

Node: dcid:genomicCoordinates
name: "genomicCoordinates"
typeOf: schema:Property
rangeIncludes: schema:Number
domainIncludes: dcs:Gene
description: "Start position (0 based). End position (non-inclusive). Represents the genomic coordinates of an object of interest."

Node: dcid:genomicPosition
name: "genomicPosition"
typeOf: schema:Property
rangeIncludes: schema:Number
domainIncludes: dcs:Nucleotide,dcs:GeneticVariant
description: "The genomic position of the nucleotide."

Node: dcid:gtexID
name: "gtexID"
typeOf: schema:Property
rangeIncludes: schema:Text
domainIncludes: dcs:GeneGeneticVariantAssociation
description: "An ID denoting a unique gene and genetic variant association within the GTEx database."

Node: dcid:hasGeneticVariantAnnotation
name: "hasGeneticVariantAnnotation"
typeOf: schema:Property
domainIncludes: dcs:Gene
rangeIncludes: schema:Boolean
description: "Indicates whether there are gene has genetic variants that are associated with it."

Node: dcid:hasGenomicCoordinates
name: "hasGenomicCoordinates"
typeOf: schema:Property
domainIncludes: dcs:GenomeAnnotation
rangeIncludes: dcs:GenomicCoordinates
description: "Genomic coordinates specify the location of the position of an element within a defined DNA contig. It is a specified set of chromosome start_position end_position within a specified genome assembly."

Node: dcid:hasGenomicPosition
name: "hasGenomicPosition"
typeOf: schema:Property
domainIncludes: dcs:GenomeAnnotation
rangeIncludes: dcs:GenomicPosition
description: "Genomic position specify the precise nucleotide location within a defined DNA contig. It is a specified set of chromosome and position within a specified genome assembly."

Node: dcid:hgncID
name: "hgncID"
typeOf: schema:Property
rangeIncludes: schema:Text
domainIncludes: dcs:Gene
description: "HUGO Gene Nomenclature Committee identifier."
synonym: "HUGO Gene Nomenclature Committee ID"

Node: dcid:hg38DistanceFromTranscriptionStartSite
name: "hg38DistanceFromTranscriptionStartSite"
typeOf: schema:Property
rangeIncludes: schema:Number
domainIncludes: dcs:GeneGeneticVariantAssociation
description: "In the hg38 genome assembly, the distance in base pairs between the associated genetic variant and gene."
abbreviation: "hg38 distance from TSS"

Node: dcid:hg19DistanceFromTranscriptionStartSite
name: "hg19DistanceFromTranscriptionStartSite"
typeOf: schema:Property
rangeIncludes: schema:Number
domainIncludes: dcs:GeneGeneticVariantAssociation
description: "In the hg19 genome assembly, the distance in base pairs between the associated genetic variant and gene."
abbreviation: "hg19 distance from TSS"

Node: dcid:humanGenomeVariationSocietyNomenclature
name: "humanGenomeVariationSocietyNomenclature"
typeOf: schema:Property
rangeIncludes: schema:Number
domainIncludes: dcs:GeneticVariant
description: "Variant names from the Human Genome Variation Society"
descriptionUrl: "https://varnomen.hgvs.org/"

Node: dcid:humanPhenotypeOntologyID
name: "humanPhenotypeOntologyID"
typeOf: schema:Property
rangeIncludes: schema:Text
domainIncludes: dcs:GeneticVariant
description: "The Human Phenotype Ontology (HPO)"
descriptionUrl: "https://hpo.jax.org/app/"

Node: dcid:inChromosome
name: "inChromosome"
typeOf: schema:Property
rangeIncludes: dcs:Chromosome,schema:Text
domainIncludes: dcs:GenomeAnnotation,dcs:Chromosome
description: "A threadlike structure of nucleic acids and protein found in the nucleus of most living cells, carrying genetic information in the form of genes."

Node: dcid:inGenomeAssembly
name: "inGenomeAssembly"
typeOf: schema:Property
rangeIncludes: dcs:GenomeAssembly, schema:Text
domainIncludes: dcs:GenomeAnnotation
description: "Genome assembly."

Node: dcid:internationalImMunoGeneTicsGeneId
name: "internationalImMunoGeneTicsGeneId"
typeOf: schema:Property
domainIncludes: dcs:Gene
rangeIncludes: schema:Text
description: "The gene identifier used by the international ImMunoGeneTics (IMGT), which is a pioneering international information system in immunogenetics and immunoinformatics. It provides databases and tools based on the IMGT-ONTOLOGY to the scientific community for in-depth exploration of the adaptive immune response."
descriptionUrl: "https://www.imgt.org/"

Node: dcid:interProAccession
name: "interProAccession"
typeOf: schema:Property
domainIncludes: dcs:Gene, dcs:Protein
rangeIncludes: schema:Text
description: "The identifier for a protein domain that's used by InterPro, which provides functional analysis of proteins by classifying them into families and predicting domains and important sites. To classify proteins in this way, InterPro uses predictive models, known as signatures, provided by several different databases (referred to as member databases) that make up the InterPro consortium. We combine protein signatures from these member databases into a single searchable resource, capitalising on their individual strengths to produce a powerful integrated database and diagnostic tool."
descriptionUrl: "https://www.ebi.ac.uk/interpro/"

Node: dcid:internationalStandardBookNumber
name: "internationalStandardBookNumber"
typeOf: schema:Property
domainIncludes: dcs:Thing
rangeIncludes: schema:Text
abbreviation: "ISBN"
description: "The International Standard Book Number (ISBN) is a numeric commercial book identifier that is intended to be unique. Publishers purchase or receive ISBNs from an affiliate of the International ISBN Agency."
descriptionUrl: "https://en.wikipedia.org/wiki/ISBN"

Node: dcid:internationalStandardSerialNumber
name: "internationalStandardSerialNumber"
typeOf: schema:Property
domainIncludes: dcs:Thing
rangeIncludes: schema:Text
abbreviation: "ISSN"
description: "An International Standard Serial Number is an eight-digit serial number used to uniquely identify a serial publication, such as a magazine. The ISSN is especially helpful in distinguishing between serials with the same title."
descriptionUrl: "https://en.wikipedia.org/wiki/ISSN"

Node: dcid:isDeprecated
name: "isDeprecated"
typeOf: schema:Property
domainIncludes: dcs:Thing
rangeIncludes: schema:Boolean
description: "A term is considered deprecated and is no longer in use."

Node: dcid:isGenomeRepresentationFull
name: "isGenomeRepresentationFull"
typeOf: schema:Property
rangeIncludes: schema:Boolean
domainIncludes: dcs:GenomeAssembly
description: "Whether the goal for the assembly was to represent the whole genome or only part of it."
descriptionUrl: "https://www.ncbi.nlm.nih.gov/assembly/help/#representation"

Node: dcid:isRefSeqGenBankAssembliesIdentical
name: "isRefSeqGenBankAssembliesIdentical"
typeOf: schema:Property
rangeIncludes: schema:Boolean
domainIncludes: dcs:GenomeAssembly
description: "Indicate whether the RefSeq and GenBank assemblies are identical."

Node: dcid:isVeryImportantPharmacogene
name: "isVeryImportantPharmacogene"
typeOf: schema:Property
domainIncludes: dcs:Gene
rangeIncludes: schema:Boolean
description: "The gene is signficantly involved in metabolism of, or response to, one or several drugs. Often, the gene either plays a role in the metabolism of many drugs (e.g. CYP2D6), or contain variants which potentially contribute to a severe drug response (e.g. HLA-B)."
descriptionUrl: "https://www.pharmgkb.org/vips"

Node: dcid:iupharTargetId
name: "iupharTargetId"
typeOf: schema:Property
domainIncludes: dcs:Gene
rangeIncludes: schema:Number
description: "The target id specified by the International Union of Basic and Clinical Pharmacology (IUPHAR), which represents the receptor of a gene targeted by one or more drugs. The IUPHAR is a voluntary, non-profit association representing the interests of pharmacologists around the world through promoting international cooperation, sponsoring regional activities, encouraging free exchange of scientists and ideas, developing public awareness, the Nomenclature and Standards Committee of IUPHAR (NC-IUPHAR), and the GUIDE TO PHARMCOLOGY."
synonym: "International Union of Basic and Clinical Pharmacology Target ID"

Node: dcid:log2AllelicFoldChange
name: "log2AllelicFoldChange"
typeOf: schema:Property
rangeIncludes: schema:Number
domainIncludes: dcs:GeneGeneticVariantAssociation
description: "The allelic Fold Change in log2 of the change in gene expression of samples with or without the minor allele."

Node: dcid:log2AllelicFoldChangeConfidenceInterval
name: "log2AllelicFoldChangeConfidenceInterval"
typeOf: schema:Property
rangeIncludes: schema:Number
domainIncludes: dcs:GeneGeneticVariantAssociation
description: "The 95% confidence interval of the allelic Fold Change in log2 of the change in gene expression of samples with or without the minor allele: [lowerCI upperCI]."

Node: dcid:loincCode
name: "loincCode"
typeOf: schema:Property
domainIncludes: dcs:BiomedicalEntity
rangeIncludes: schema:Text
description: "A code for Logical Observation Identifiers Names and Codes (LOINC), which is clinical terminology that is important for laboratory test orders and results, and is one of a suite of designated standards for use in U.S. Federal Government systems for the electronic exchange of clinical health information."
descriptionUrl: "https://www.mayocliniclabs.com/test-catalog/appendix/LOINC-Codes#:~:text=Logical%20Observation%20Identifiers%20Names%20and,exchange%20of%20clinical%20health%20information."

Node: dcid:makesProtein
name: "makesProtein"
typeOf: schema:Property
rangeIncludes: schema:Text
domainIncludes: dcs:RnaTranscript,dcs:Protein
description: "UniProt display ID, UniProt accession, or RefSeq protein ID representing the protein made by the corresponding gene or RNA transcript."

Node: dcid:mapLocation
name: "mapLocation"
typeOf: schema:Property
rangeIncludes: schema:Text
domainIncludes: dcs:Gene
description: "The location of the gene on the chromosome."

Node: dcid:maturedFromProtein
name: "maturedFromProtein"
typeOf: schema:Property
domainIncludes: dcs:MaturePeptide
rangeIncludes: dcs:Protein
description: "Indicates the initial, full-length protein from which a mature peptide has derived after post-translational modifications and processing".

Node: dcid:medGenID
name: "medGenID"
typeOf: schema:Property
rangeIncludes: schema:Number
domainIncludes: dcs:GeneticVariant
description: "ID for organized information related to human medical genetics, such as attributes of conditions with a genetic contribution."
descriptionUrl: "https://www.ncbi.nlm.nih.gov/medgen/"

Node: dcid:medicalGeneticSummariesID
name: "medicalGeneticSummariesID"
typeOf: schema:Property
rangeIncludes: schema:Number
domainIncludes: dcs:GeneticVariant
description: "Medical Genetics Summaries is a growing collection of summaries which describe the impact that specific sequence variations have on health. The summaries review genetic variants that underlie inherited conditions, affect the risk of developing a disease in the future, or influence how an individual may respond to a specific drug."
descriptionUrl: "https://www.ncbi.nlm.nih.gov/books/NBK61999/"

Node: dcid:medicalSubjectHeadingID
name: "medicalSubjectHeadingID"
typeOf: schema:Property
rangeIncludes: schema:Text,dcs:MeSHRecordType
domainIncludes: dcs:GeneticVariant,dcs:Disease
description: "Medical Subject Heading"
descriptionUrl: "https://meshb.nlm.nih.gov/search"
abbreviation: "MeSH ID"

Node: dcid:minimalPValueNominal
name: "minimalPValueNominal"
typeOf: schema:Property
rangeIncludes: schema:Number
domainIncludes: dcs:GeneGeneticVariantAssociation
description: "The smallest nominal p-value for the gene."

Node: dcid:minorAlleleCount
name: "minorAlleleCount"
typeOf: schema:Property
rangeIncludes: schema:Number
domainIncludes: dcs:GeneGeneticVariantAssociation
description: "Total number of minor alleles across individuals."

Node: dcid:minorAlleleSampleNumber
name: "minorAlleleSampleNumber"
typeOf: schema:Property
rangeIncludes: schema:Number
domainIncludes: dcs:GeneGeneticVariantAssociation
description: "The number of samples carrying the minor allele."

Node: dcid:miRBaseId
name: "miRBaseId"
typeOf: schema:Property
domainIncludes: dcs:Gene
rangeIncludes: schema:Text
description: "The identifier used by miRBase, which is a public online database that contains information about microRNAs (miRNAs) in plants and animals. It's the world's largest collection of miRNA data and is the primary resource for miRNA research."
url: "https://www.mirbase.org/"

Node: dcid:modificationDate
name: "modificationDate"
typeOf: schema:Property
rangeIncludes: schema:Text
domainIncludes: dcs:Gene
description: "The date of last modification on the NCBI database."

Node: dcid:mondoID
name: "mondoID"
typeOf: schema:Property
rangeIncludes: schema:Text
domainIncludes: dcs:GeneticVariant
description: "MONDO database identifier."

Node: dcid:molecularType
name: "molecularType"
typeOf: schema:Property
rangeIncludes: dcs:GeneticVariantMolTypeEnum
domainIncludes: dcs:GeneticVariant
description: "Sample type from exemplar submitted GeneticVariants (cDNA, genomic, mitochondrial, or unknown)."

Node: dcid:mouseGenomeInformaticsId
name: "mouseGenomeInformaticsId"
typeOf: schema:Property
domainIncludes: dcs:Gene
rangeIncludes: schema:Text
abbreviation: "MGI ID"
specializationOf: dcs:allianceOfGenomeResourcesId
description: "The gene identifier used by Mouse Genome Informatics (MGI) and the Mouse GenomeDatabase (MGD). MGI is the international database resource for the laboratory mouse, providing integrated genetic, genomic, and biological data to facilitate the study of human health and disease. MGD is the database resource for the laboratory mouse, and provides integrated biological data to facilitate the study of human health and disease. MGD is a core database in the Mouse Genome Informatics (MGI) consortium and founding member of the Alliance of Genome Resources Project."
descriptionUrl: "https://www.informatics.jax.org/mgihome/projects/aboutmgi.shtml"
descriptionUrl: "https://www.alliancegenome.org/members/mgd"

Node: dcid:nasioniaBaseId
name: "nasioniaBaseId"
typeOf: schema:Property
domainIncludes: dcs:Gene
rangeIncludes: schema:Text
description: "The gene identifier used by NasoniaBase, an informatics data repository for the Nasonia Species Complex Genome Projects. Currently, NasoniaBase provides a graphical interface to the assembly of the Nasonia vitripennis genome. Assembly Nvit_1.0 was released by the Baylor College of Medicine Human Genome Sequencing Center in March, 2007. It was generated from small whole genome shotgun (WGS) sequencing reads (3-5kb), fosmids reads (36kb) and BAC end reads (130kb - 150kb) and includes repetitive reads. NasoniaBase is an archive and will not be updated. The most up-to-date Nasonia genome data is now available through the navigation bar on the HGD Home page."
descriptionUrl: "https://hymenoptera.elsiklab.missouri.edu/nasonia"

Node: dcid:ncbiBioProject
name: "ncbiBioProject"
typeOf: schema:Property
rangeIncludes: schema:Text
domainIncludes: dcs:GenomeAssembly
description: "A BioProject is a collection of biological data related to a single initiative originating from a single organization or from a consortium. A BioProject record provides users a single place to find links to the diverse data generated for that project and deposited into the archival databases maintained by members of the International Nucleotide Sequence Database Collaboration (INSDC). Typical examples of a BioProject include a multiisolate project for sequencing multiple strains of a bacterial species, or a monoisolate project for the genome and transcriptome of a particular organism."
descriptionUrl: "https://www.ncbi.nlm.nih.gov/bioproject/docs/faq/"

Node: dcid:ncbiBioSample
name: "ncbiBioSample"
typeOf: schema:Property
rangeIncludes: schema:Text
domainIncludes: dcs:GenomeAssembly
description: "A BioSample contains descriptive information about the physical biological specimen from which your experimental data are derived. Typical examples of a BioSample include a cell line, a tissue biopsy or an environmental isolate. The information you supply about the biological materials are critical for providing context to your experimental data."
descriptionUrl: "https://www.ncbi.nlm.nih.gov/biosample/docs/submission/faq/"

Node: dcid:ncbiGeneID
name: "ncbiGeneID"
typeOf: schema:Property
rangeIncludes: schema:Text
domainIncludes: dcs:Gene,dcs:GeneticVariant
description: "NCBI Entrez Gene database identifier."

Node: dcid:ncbiLocusTag
name: "ncbiLocusTag"
typeOf: schema:Property
rangeIncludes: schema:Text
domainIncludes: dcs:Gene
description: "Identifiers that are systematically applied to every gene in a genome."

Node: dcid:ncbiMaturePeptideGiNumber
name: "ncbiMaturePeptideGiNumber"
typeOf: schema:Property
domainIncludes: dcs:Gene, dcs:MaturePeptide, dcs:Protein, dcs:RnaTranscript
rangeIncludes: schema:Text
synonym: "Mature Peptide GI", "Mature Peptide GenInfo Identifier"
description: "GI number (sometimes written in lower case, 'gi') is simply a series of digits that are assigned consecutively to each mature peptide record processed by NCBI. The GI number bears no resemblance to the Accession number of the smature peptide record and are version specific. The mature peptide GI number represents the final, processed form of a protein after post-translational modifications like cleavage or removal of signal peptides. It identifies the functional protein sequence, distinct from the initial translation product. It is associated with protein records derived from mature peptides."

Node: dcid:ncbiProteinAccessionNumber
name: "ncbiProteinAccessionNumber"
typeOf: schema:Property
rangeIncludes: schema:Text
domainIncludes: dcs:Gene,dcs:Protein
description: "NCBI protein accession number."

Node: dcid:ncbiProteinGiNumber
name: "ncbiProteinGiNumber"
typeOf: schema:Property
domainIncludes: dcs:Gene, dcs:MaturePeptide, dcs:Protein, dcs:RnaTranscript
rangeIncludes: schema:Text
synonym: "Protein GI", "Protein GenInfo Identifier"
description: "GI number (sometimes written in lower case, 'gi') is simply a series of digits that are assigned consecutively to each mature peptide record processed by NCBI. The GI number bears no resemblance to the Accession number of the smature peptide record and are version specific. The protein GI number represents the amino acid sequence of a protein, either directly submitted or translated from a coding sequence (CDS) within a nucleotide record. It identifies a specific version of a protein sequence."

Node: dcid:ncbiRnaNucleotideGiNumber
name: "ncbiRnaNucleotideGiNumber"
typeOf: schema:Property
domainIncludes: dcs:Gene, dcs:MaturePeptide, dcs:Protein, dcs:RnaTranscript
rangeIncludes: schema:Text
synonym: "RNA GI", "RNA GenInfo Identifier"
description: "GI number (sometimes written in lower case, 'gi') is simply a series of digits that are assigned consecutively to each mature peptide record processed by NCBI. The GI number bears no resemblance to the Accession number of the smature peptide record and are version specific. The RNA nucleotide GI number represents the final, processed form of a protein after post-translational modifications like cleavage or removal of signal peptides. It identifies the functional protein sequence, distinct from the initial translation product. It is associated with protein records derived from mature peptides."

Node: dcid:ncbiSequenceGiNumber
name: "ncbiSequenceGiNumber"
typeOf: schema:Property
domainIncludes: dcs:Gene, dcs:GenomicRegion
rangeIncludes: schema:Text
synonym: "Sequence GI", "SequencdeGenInfo Identifier"
description: "GI number (sometimes written in lower case, 'gi') is simply a series of digits that are assigned consecutively to each sequence record processed by NCBI. The GI number bears no resemblance to the Accession number of the sequence record and are version specific. They are formatted as follows: nucleotide sequence GI number is shown in the VERSION field of the database record and protein sequence GI number is shown in the CDS/db_xref field of a nucleotide database record, and the VERSION field of a protein database record This identification system runs in parallel to the VERSION."
descriptionUrl: "https://www.ncbi.nlm.nih.gov/Sitemap/sequenceIDs.html"

Node: dcid:ncbiTaxonID
name: "ncbiTaxonID"
typeOf: schema:Property
rangeIncludes: schema:Text
domainIncludes: dcs:GenomeAnnotation,dcs:Protein
description: "NCBI Taxonomy database identifier."

Node: dcid:nomenclatureStatus
name: "nomenclatureStatus"
typeOf: schema:Property
rangeIncludes:  dcs:NomenclatureStatusEnum
domainIncludes: dcs:Gene
description: "The status of the name from the nomenclature committee: official, interim, or NCBI-supplied."

Node: dcid:nonCodingGeneCount
name: "nonCodingGeneCount"
typeOf: schema:Property
domainIncludes dcs:GenomeAnnotation
rangeIncludes: schema:Number
description: "The number of non-coding genes within a consensus region of DNA."

Node: dcid:nonCodingRNAType
name: "nonCodingRNAType"
typeOf: schema:Property
domainIncludes: dcs:NonCodingRNA
rangeIncludes: dcs:NonCodingRNATypeEnum
description: "A non-coding RNA (ncRNA) is a functional RNA molecule that is not translated into a protein. The DNA sequence from which a functional non-coding RNA is transcribed is often called an RNA gene. Abundant and functionally important types of non-coding RNAs include transfer RNAs (tRNAs) and ribosomal RNAs (rRNAs), as well as small RNAs such as microRNAs, siRNAs, piRNAs, snoRNAs, snRNAs, exRNAs, scaRNAs and the long ncRNAs such as Xist and HOTAIR."
descriptionUrl: "https://en.wikipedia.org/wiki/Non-coding_RNA"

Node: dcid:numberOfAllelesWithFreq
name: "numberOfAllelesWithFreq"
typeOf: schema:Property
rangeIncludes: schema:Number
domainIncludes: dcs:GeneticVariant
description: "Number of observed alleles with frequency data."

Node: dcid:numberOfAlternativeAlleles
name: "numberOfAlternativeAlleles"
typeOf: schema:Property
rangeIncludes: schema:Number
domainIncludes: dcs:GeneGeneticVariantAssociation
description: "The number of alternative alleles observed at the genetic variant site."

Node: dcid:observedAllele
name: "observedAllele"
typeOf: schema:Property
rangeIncludes: schema:Text
domainIncludes: dcs:GeneticVariant,dcs:GeneGeneticVariantAssociation
description: "The sequences of the observed alleles from rs-fasta files. This is formated as major allele/minor allele."

Node: dcid:omimID
name: "omimID"
typeOf: schema:Property
rangeIncludes: schema:Text
domainIncludes: dcs:Disease,dcs:Gene,dcs:GeneticVariant
description: "OMIM database identifier."
synonym: "Online Mendelian Inheritance in Man ID"
sameAs: dcs:onlineMendelianInheritanceInManID

Node: dcid:onlineMendelianInheritanceInManID
name: "onlineMendelianInheritanceInManID"
typeOf: schema:Property
rangeIncludes: schema:Text
domainIncludes: dcs:Disease,dcs:Gene,dcs:GeneticVariant
description: "Online Mendelian Inheritance in Man (OMIM) database identifier. Omim is /"an online catalog of human genes and genetic disorders/"."
descriptionUrl: "https://www.omim.org/"
abbreviation: "OMIM ID"
sameAs: "omimID"

Node: dcid:orphaNumber
name: "orphaNumber"
typeOf: schema:Property
rangeIncludes: schema:Text
domainIncludes: dcs:Disease,dcs:GeneticVariant
description: "Orphanet rare disease nomenclature"
descriptionUrl: "https://www.orpha.net/consor/cgi-bin/index.php"
synonym: "orphanet rare disease ontology number"

Node: dcid:pfamAccession
name: "pfamAccession"
typeOf: schema:Property
domainIncludes: dcs:Gene
rangeIncludes: schema:Text
description: "The accession used by the Pfam database to refer to a protin family. The Pfam database is a large collection of protein families, each represented by multiple sequence alignments and hidden Markov models (HMMs). The Pfam database is now hosted by InterPro."
descriptionUrl: "http://pfam.xfam.org/"

Node: dcid:pharmacogeneVariationConsortiumId
name: "pharmacogeneVariationConsortiumId"
typeOf: schema:Property
domainIncludes: dcs:Gene
rangeIncludes: schema:Text
description: "The identifier representing a gene in the Pharmacogene Variation (PharmVar) Consortium database. THe PharmVar Consortium is a central repository for pharmacogene (PGx) variation that focuses on haplotype structure and allelic variation. The information in this resource facilitates basic and clinical research as well as the interpretation of pharmacogenetic test results to guide precision medicine."
descriptionUrl: "https://www.pharmvar.org/"
abbreviation: "PharmVar ID"

Node: dcid:pharmGKBID
name: "pharmGKBID"
typeOf: schema:Property
rangeIncludes: schema:Number,dcs:Text
domainIncludes: dcs:GeneticVariant,dcs:ChemicalCompound,dcs:Gene
description: "PharmGKB is a comprehensive resource that curates knowledge about the impact of genetic variation on drug response for clinicians and researchers."
descriptionUrl: "https://www.pharmgkb.org/"

Node: dcid:phytozomeGeneId
name: "phytozomeGeneId"
typeOf: schema:Property
domainIncludes: dcs:Gene
rangeIncludes: schema:Text
description: "The gene id used by Phytozome, the Plant Comparative Genomics portal of the Department of Energy's Joint Genome Institute, which provides JGI users and the broader plant science community a hub for accessing, visualizing and analyzing JGI-sequenced plant genomes, as well as selected genomes and datasets that have been sequenced elsewhere. By integrating this large collection of plant genomes into a single resource and performing comprehensive and uniform annotation and analyses, Phytozome facilitates accurate and insightful comparative genomics studies."
descriptionUrl: "https://phytozome-next.jgi.doe.gov/"

Node: dcid:pomBaseId
name: "pomBaseId"
typeOf: schema:Property
domainIncludes: dcs:GenomeAnnotation
rangeIncludes: schema:Text
description: "An identifier for a term in PomBase, a comprehensive knowledgebase for the fission yeast Schizosaccharomyces pombe, providing iterature curation, analysis tools, genome annotation and access to large-scale data sets."
descriptionUrl: "https://www.pombase.org/"

Node: dcid:proteinCodingGeneCount
name: "proteinCodingGeneCount"
typeOf: schema:Property
domainIncludes dcs:GenomeAnnotation
rangeIncludes: schema:Number
description: "The number of protein coding genes within a consensus region of DNA."

Node: dcid:proteinModificationOntology
name: "proteinModificationOntology"
typeOf: schema:Property
domainIncludes: dcs:BioChemEntity
rangeIncludes: schema:Text
description: "An identifier for The Proteomics Standards Initiative modification ontology (PSI-MOD), which aims to define a concensus nomenclature and ontology reconciling, in a hierarchical representation, the complementary descriptions of residue modifications."
descriptionUrl: "https://bioregistry.io/registry/mod"

Node: dcid:pseudoCapLocusTag
name: "pseudoCapLocusTag"
typeOf: schema:Property
domainIncludes: dcs:Gene
rangeIncludes: schema:Text
description: "The gene locus tag used to identify genes by the Pseudomonas Genome Database, which collaborates with an international panel of expert Pseudomonas researchers to provide high quality updates to the PAO1 genome annotation and make cutting edge genome analysis data available."
descriptionUrl: "https://www.pseudomonas.com/"

Node: dcid:pubMedCentralId
name: "pubMedCentralId"
typeOf: schema:Property
domainIncludes: dcs:BiomedicalEntity
rangeIncludes: schema:Text
description: "An identifier that references an article stored in PubMed Central (PMC). PMC is a free full-text archive of biomedical and life sciences journal literature at the U.S. National Institutes of Health's National Library of Medicine (NIH/NLM). In keeping with NLM's legislative mandate to collect and preserve the biomedical literature, PMC is part of the NLM collection, which also includes NLM's extensive print and licensed electronic journal holdings and supports contemporary biomedical and health care research and practice as well as future scholarship. Available to the public online since 2000, PMC was developed and is maintained by the National Center for Biotechnology Information (NCBI) at NLM."
descriptionUrl: "https://www.ncbi.nlm.nih.gov/pmc/about/intro/"

Node: dcid:pValueBeta
name: "pValueBeta"
typeOf: schema:Property
rangeIncludes: schema:Number
domainIncludes: dcs:GeneGeneticVariantAssociation
description: "The beta-approximated permutation p-value."

Node: dcid:pValueNominal
name: "pValueNominal"
typeOf: schema:Property
rangeIncludes: schema:Number
domainIncludes: dcs:GeneGeneticVariantAssociation
description: "The nominal p-value associated with the most significant variant for this gene."

Node: dcid:pValueNominalThreshold
name: "pValueNominalThreshold"
typeOf: schema:Property
rangeIncludes: schema:Number
domainIncludes: dcs:GeneGeneticVariantAssociation
description: "The nominal p-value threshold for calling a variant-gene pair significant for the gene."

Node: dcid:pValuePermutation
name: "pValuePermutation"
typeOf: schema:Property
rangeIncludes: schema:Number
domainIncludes: dcs:GeneGeneticVariantAssociation
description: "The permutation p-value."

Node: dcid:pValueTrueDegreesOfFreedom
name: "pValueTrueDegreesOfFreedom"
typeOf: schema:Property
rangeIncludes: schema:Number
domainIncludes: dcs:GeneGeneticVariantAssociation
description: "The p-value of the effective degrees of freedom the Beta distribution approximation."

Node: dcid:qValue
name: "qValue"
typeOf: schema:Property
rangeIncludes: schema:Number
domainIncludes: dcs:GeneGeneticVariantAssociation
description: "The Storey q-value derived from pval_beta."

Node: dcid:ratGenomeDatabaseId
name: "ratGenomeDatabaseId"
typeOf: schema:Property
domainIncludes: dcs:Gene
rangeIncludes: schema:Text
abbreviation: "RGD ID"
specializationOf: dcs:allianceOfGenomeResourcesId
description: "The gene identifier used by the Rat Genome Database (RGD), which is the primary site for genetic, genomic, phenotype, and disease-related data generated from rat research. The data is the result of both manual curation work by RGD curators and imported data from other databases through custom ELT (Extract, Load and Transform) pipelines. RGD has expanded to include structured and standardized data for additional species (human, mouse, chinchilla, bonobo, 13-lined ground squirrel, dog and pig). RGD is a founding member of the Alliance of Genome Resources Project."
descriptionUrl: "https://www.alliancegenome.org/members/rgd"

Node: dcid:referenceAlleleNCBI
name: "referenceAlleleNCBI"
typeOf: schema:Property
rangeIncludes: schema:Text
domainIncludes: dcs:GeneticVariant
description: "Reference genomic sequence from dbSNP."

Node: dcid:referenceAlleleUCSC
name: "referenceAlleleUCSC"
typeOf: schema:Property
rangeIncludes: schema:Text
domainIncludes: dcs:GeneticVariant
description: "Reference genomic sequence from UCSC."

Node: dcid:referenceSNPClusterID
name: "referenceSNPClusterID"
typeOf: schema:Property
rangeIncludes: schema:Text
domainIncludes: dcs:GeneticVariant,dcs:GeneGeneticVariantAssociation
description: "The referenceSNPClusterID or rsID number is a unique label ("rs" followed by a number) used by researchers and databases to identify a specific SNP (Single Nucleotide Polymorphism). It stands for Reference SNP cluster ID and is the naming convention used for most SNPs."
descriptionUrl: "https://customercare.23andme.com/hc/en-us/articles/212196908-What-Are-RS-Numbers-Rsid-"
abbreviation: "rsID", "refSNP cluster ID"
synonym: "reference SNP ID number"
sameAs: dcs:rsID

Node: dcid:refSeqAssemblyAccession
name: "refSeqAssemblyAccession"
typeOf: schema:Property
rangeIncludes: schema:Text
domainIncludes: dcs:BiologicalEntity
description: "The accession version of the RefSeq assembly or sequence element."

Node: dcid:refSeqCategory
name: "refSeqCategory"
typeOf: schema:Property
rangeIncludes: dcs:RefSeqCategoryEnum
domainIncludes: dcs:GenomeAssembly
description: "Denotes that the assembly is a reference or representative genome in the NCBI Reference Sequence ( RefSeq ) project classification."
descriptionUrl: "https://www.ncbi.nlm.nih.gov/assembly/help/"

Node: dcid:refSeqFunctionElementFeatureAnnotation
name: "refSeqFunctionElementFeatureAnnotation"
typeOf: schema:Property
domainIncludes: dcs:Gene, dcs:GenomicRegion, dcs:RnaTranscript
rangeIncludes: dcs:GeneFeatureTypeEnum
description: "RefSeq Functional Element sequences include manually curated features in accordance with International Nucleotide Sequence Database Collaboration (INSDC) standards. Features that are supported by direct experimental evidence include at least one '/experiment' qualifier with an evidence code (ECO ID) from the Evidence & Conclusion Ontology, and at least one citation from PubMed. It is important to note that annotated sequence ranges may be approximate depending on the experimental evidence type, and that features may include extraneous sequences that are not necessary for function."
descriptionUrl: "https://www.ncbi.nlm.nih.gov/refseq/functionalelements/"

Node: dcid:refSeqGenomicAccession
name: "refSeqGenomicAccession"
typeOf: schema:Property
domainIncludes: dcs:Gene, dcs:GenomicRegion, dcs:Protein, dcs:RnaTranscript
rangeIncludes: schema:Text
synonym: "VERSION", "Genomic accession.version"
specializationOf: dcs:refSeqID
description: "This is a sequence identifier that is made of the accession number of the RefSeq database record followed by a dot and a version number (and is therefore sometimes referred to as the "accession.version"). They are formatted as follows nucleotide sequence version contains two letters followed by six digits, a dot, and a version number (or for older nucleotide sequence records, the format is one letter followed by five digits, a dot, and a version number). The VERSION system of identifiers was adopted in February 1999 by the International Nucleotide Sequence Database Collaboration (GenBank, EMBL, and DDBJ). This identification system runs in parallel to the GI number."
descriptionUrl: "https://www.ncbi.nlm.nih.gov/Sitemap/sequenceIDs.html"

Node: dcid:refSeqID
name: "refSeqID"
typeOf: schema:Property
rangeIncludes: schema:Text
domainIncludes: dcs:Gene, dcs:GenomicRegion, dcs:MaturePeptide, dcs:Protein, dcs:RnaTranscript
description: "A nucleotide sequence or protein annotated and curated by the National Center for Biotechnology Information."

Node: dcid:refSeqMaturePeptideAccession
name: "refSeqMaturePeptideAccession"
typeOf: schema:Property
domainIncludes: dcs:Gene, dcs:MaturePeptide, dcs:Protein, dcs:RnaTranscript
rangeIncludes: schema:Text
synonym: "Mature Peptide accession.version"
specializationOf: dcs:refSeqID
description: "This is a mature peptide identifier that is made of the accession number of the RefSeq database record followed by a dot and a version number (and is therefore sometimes referred to as the "accession.version"). They represent the final, processed form of a protein after post-translational modifications like cleavage or removal of signal peptide."

Node: dcid:refSeqProteinAccession
name: "refSeqProteinAccession"
typeOf: schema:Property
domainIncludes: dcs:Gene, dcs:MaturePeptide, dcs:Protein, dcs:RnaTranscript
rangeIncludes: schema:Text
synonym: "Protein accession.version"
specializationOf: dcs:refSeqID
description: "This is a protein identifier that is made of the accession number of the RefSeq database record followed by a dot and a version number (and is therefore sometimes referred to as the "accession.version"). They represent the amino acid sequence of a protein product translated from an mRNA. The prefixes indicate how these amino acid sequences were derived, such as: NP_, which are curated protein sequences derived from the translation of NM_ (mRNA) sequences, and XM_, which are model protein sequences predicted from XM_ (model mRNA) sequences."

Node: dcid:refSeqRnaNucleotideAccession
name: "refSeqRnaNucleotideAccession"
typeOf: schema:Property
domainIncludes: dcs:Gene, dcs:MaturePeptide, dcs:Protein, dcs:RnaTranscript
rangeIncludes: schema:Text
synonym: "RNA accession.version"
specializationOf: dcs:refSeqID
description: "This is a RNA nucleotide identifier that is made of the accession number of the RefSeq database record followed by a dot and a version number (and is therefore sometimes referred to as the "accession.version"). They represent RNA transcript sequences, reflecting the processed product of a gene after transcription and splicing (for mRNAs). Prefixes indicate the type of gene product: NM_ (mRNA sequences that are fully curated and supported by experimental evidence), NR_ (Non-coding RNA sequences (rRNAs, tRNAs, etc.) that are curated), XM_ (Model mRNA sequences predicted from the genome annotation pipeline, may have varying levels of support), and XR_ (Model non-coding RNA sequences predicted from the genome)."

Node: dcid:refSeqStatus
name: "refSeqStatus"
typeOf: schema:Property
domainIncludes: dcs:RnaTranscript
rangeIncludes: dcs:RefSeqStatusEnum
description: "A status is a designation assigned to each RefSeq record in the NCBI RefSeq database that indicates the level of review, curation, and confidence associated with the sequence data. It provides valuable information about the quality and reliability of the sequence."

Node: dcid:regressionSlope
name: "regressionSlope"
typeOf: schema:Property
rangeIncludes: schema:Number
domainIncludes: dcs:StatisticalVariable

Node: dcid:relatedFunctionalGene
name: "relatedFunctionalGene"
typeOf: schema:Property
domainIncludes: dcs:Gene
rangeIncludes: dcs:Gene
description: "Genes that are related by sequence similarity and are presumed to have similar or related functions. These could be paralogs (genes that arose from a duplication event within a species) or orthologs (genes in different species that evolved from a common ancestral gene)."

Node: dcid:relatedPseudogene
name: "relatedPseudogene"
typeOf: schema:Property
domainIncludes: dcs:Gene
rangeIncludes: dcs:Gene
description: "A non-functional copy of a gene that has accumulated mutations over time. It is related to a functional gene by sequence similarity but is no longer capable of producing a functional protein."

Node: dcid:rnaModId
name: "rnaModId"
typeOf: schema:Property
domainIncludes: dcs:GenomeAnnotation
rangeIncludes: schema:Text
description: "An identifier for RNAmod, a resource that annotates RNA modification across 21 species."

Node: dcid:rsID
name: "rsID"
typeOf: schema:Property
rangeIncludes: schema:Text
domainIncludes: dcs:GeneticVariant,dcs:GeneGeneticVariantAssociation
description: "The referenceSNPClusterID or rsID number is a unique label ("rs" followed by a number) used by researchers and databases to identify a specific SNP (Single Nucleotide Polymorphism). It stands for Reference SNP cluster ID and is the naming convention used for most SNPs."
descriptionUrl: "https://customercare.23andme.com/hc/en-us/articles/212196908-What-Are-RS-Numbers-Rsid-"
synonym: "reference SNP ID number","reference SNP Cluster ID","refSNP cluster ID"
sameAs: dcs:referenceSNPClusterID

Node: dcid:saccharomycesGenomeDatabaseId
name: "saccharomycesGenomeDatabaseId"
typeOf: schema:Property
domainIncludes: dcs:Gene
rangeIncludes: schema:Text
abbreviation: "SGD Id"
specializationOf: dcs:allianceOfGenomeResourcesId
description: "The gene identifier used by the Saccharomyces Genome Database (SGD), which provides comprehensive integrated biological information for the budding yeast Saccharomyces cerevisiae. SGD is a member of the Alliance of Genome Resources Project."
descriptionUrl: "https://www.yeastgenome.org/"

Node: dcid:sequenceOntologyID
name: "sequenceOntologyID"
typeOf: schema:Property
rangeIncludes: schema:Text
domainIncludes: dcs:GeneticVariant
description: "Sequence Ontology ID: http://www.sequenceontology.org/"

Node: dcid:sequenceOntologySubset
name: "sequenceOntologySubset"
typeOf: schema:Property
domainIncludes: dcs:SequenceOntologyTerm
rangeIncludes: dcs:SequenceOntologySubsetEnum
description: "A subset of terms from The Sequence Ontology that can be useful for defined activities."

Node: dcid:sequencingTechnology
name: "sequencingTechnology"
typeOf: schema:Property
rangeIncludes: schema:Text
domainIncludes: dcs:GenomeAssembly
description: "The manufacturer and model of the sequencing machine used to generate the GenomeAssembly."

Node: dcid:snomedCT
name: "snomedCT"
typeOf: schema:Property
rangeIncludes: schema:Number
domainIncludes: dcs:Disease,dcs:GeneticVariant
description: "SNOMED CT (Systematized Nomenclature of Medicine -- Clinical Terms) is a standardized, multilingual vocabulary of clinical terminology that is used by physicians and other health care providers for the electronic exchange of clinical health information."
descriptionUrl: "https://www.snomed.org"

Node: strandOrientation
dcid:strandOrientation
name: "strandOrientation"
typeOf: schema:Property
rangeIncludes: dcs:StrandOrientationEnum
domainIncludes: dcs:GenomeAnnotation
description: "The strand on which a given annotation is located."

Node: dcid:submitter
name: "submitter"
typeOf: schema:Property
rangeIncludes: schema:Text
domainIncludes: schema:Thing
description: "List of submitter handles."

Node: dcid:suspectReasonCode
name: "suspectReasonCode"
typeOf: schema:Property
rangeIncludes: dcs:VariantSuspectReasonCodesEnum
domainIncludes: dcs:GeneticVariant
description: "Variant Suspect Reason Codes: unspecified, Paralog, byEST, oldAlign, Para_EST, 1kg_failed, or other."

Node: dcid:synonym
name: "synonym"
typeOf: schema:Property
domainIncludes: schema:Thing
rangeIncludes: schema:Text, dcs:SequenceOntologyTerm
description: "Alternative names for the given entity."

Node: dcid:synonymType
name: "synonymType"
typeOf: schema:Property
domainIncludes: dcs:SequenceOntologyTermSynonym
rangeIncludes: dcs:SynonymTypeEnum
description: "How two terms are related to each other."

Node: dcid:tissue
name: "tissue"
typeOf: schema:Property
rangeIncludes: schema:Text
domainIncludes: dcs:GeneGeneticVariantAssociation
description: "The tissue in which the association between the genetic variant and the gene was made."

Node: dcid:transcribedFromGene
name: "transcribedFromGene"
typeOf: schema:Property
domainIncludes: dcs:RnaTranscript, dcs:MaturePeptide, dcs:Protein
rangeIncludes: dcs:Gene
description: "The gene from which the RNA transcript is a direct product."

Node: dcid:transcriptionCoordinates
name: "transcriptionCoordinates"
typeOf: schema:Property
rangeIncludes: schema:Number
domainIncludes: dcs:RnaTranscript
description: "Specifies the genomic coordinates associated with the transcription of a given RefSeq Accession number."

Node: dcid:translatedFromRna
name: "translatedFromRna"
typeOf: schema:Property
domainIncludes: dcs:MaturePeptide, dcs:Protein
rangeIncludes: dcs:RnaTranscript
description: "Indicates the specified mRNA transcript from which a protein is translated into a sequence of amino acids."

Node: dcid:translocationToChromosome
name: "translocationToChromosome"
typeOf: schema:Property
rangeIncludes: dcs:Chromosome
domainIncludes: dcs:GeneticVariant
description: "Second (To) Chromosome in a translocation pair."

Node: dcid:trueDegreesOfFreedom
name: "trueDegreesOfFreedom"
typeOf: schema:Property
rangeIncludes: schema:Number
domainIncludes: dcs:GeneGeneticVariantAssociation
description: "The effective degrees of freedom the Beta distribution approximation."

Node: dcid:typeOfGene
name: "typeOfGene"
typeOf: schema:Property
rangeIncludes: dcs:TypeOfGeneEnum
domainIncludes: dcs:Gene
description: "The type of gene."

Node: dcid:variantNumber
name: "variantNumber"
typeOf: schema:Property
rangeIncludes: schema:Number
domainIncludes: dcs:GeneGeneticVariantAssociation
description: "The number of variants in cis-window (1 Mbp) with the associated gene."

Node: dcid:variationEndCI
name: "variationEndCI"
typeOf: schema:Property
rangeIncludes: schema:Number
domainIncludes: dcs:GeneticVariant
description: "Confidence interval around END for imprecise variants."
synonym: "variation end confidence interval"

Node: dcid:variationPositionCI
name: "variationPositionCI"
typeOf: schema:Property
rangeIncludes: schema:Number
domainIncludes: dcs:GeneticVariant
description: "Confidence interval around POS for imprecise variants."
synonym: "variation position confidence interval"
abbreviation: "variation pos CI"

Node: dcid:variationType
name: "variationType"
typeOf: schema:Property
rangeIncludes: dcs:VariationTypeEnum
domainIncludes: dcs:GeneticVariant
description: "Variation type of alternate allele."

Node: dcid:vertebrateGeneNomenclatureCommitteeId
name: "vertebrateGeneNomenclatureCommitteeId"
typeOf: schema:Property
domainIncludes: dcs:Gene
rangeIncludes: schema:Text
abbreviation: "VGNC ID"
description: "The gene identifier used by the Vertebrate Gene Nomenclature Committee (VGNC), which is an extension of the established HGNC (HUGO Gene Nomenclature Committee) project that names human genes. VGNC is responsible for assigning standardized names to genes in vertebrate species that currently lack a nomenclature committee."
descriptionUrl: "https://vertebrate.devgenenames.cloud/about/"
url: "https://vertebrate.devgenenames.cloud/"

Node: dcid:vEuPathDBId
name: "vEuPathDBId"
typeOf: schema:Property
domainIncludes: dcs:Gene
rangeIncludes: schema:Text
description: "The gene identifier used by VEuPathDB. The VEuPathDB Bioinformatics Resource Center makes genomic, phenotypic, and population-centric data accessible to the scientific community. There are multiple projects that under the VEuPathDB Project umbrella including AmoebaDB, CryptoDB, FungiDB, GiardiaDB, MicrosporidiaDB, PlasmoDB, PiroplasmaDB, ToxoDB, TrichDB, TriTrypDB, VectorBase, and VEuPathDB. This was formally known as ApiDB. The funding supporting this effort terminated on September 14, 2024."
url: "https://veupathdb.org/veupathdb/app"

Node: dcid:wormBaseId
name: "wormBaseId"
typeOf: schema:Property
domainIncludes: dcs:Gene
rangeIncludes: schema:Text
specializationOf: dcs:allianceOfGenomeResourcesId
description: "The gene identifier used by WormBase, an international consortium of biologists and computer scientists providing the research community with accurate, current, accessible information concerning the genetics, genomics and biology of C. elegans and related nematodes. Founded in 2000, the WormBase Consortium is led by Paul Sternberg (CalTech), Matt Berriman (The Wellcome Trust Sanger Institute), Sarah Dyer (EBI), and Lincoln Stein (The Ontario Institute for Cancer Research). WormBase is a founding member of the Alliance of Genome Resources Project."
descriptionUrl: "https://wormbase.org/about#01--10"

Node: dcid:xenbaseId
name: "xenbaseId"
typeOf: schema:Property
domainIncludes: dcs:Gene
rangeIncludes: schema:Text
specializationOf: dcs:allianceOfGenomeResourcesId
synonym: "Zebrafish Information Network ID"
description: "The gene identifier used by Xenbase, which is a web-accessible resource that integrates all the diverse biological, genomic, genotype and phenotype data available from Xenopus research. Xenbase is a member of the Alliance of Genome Resources Project."
descriptionUrl: "https://www.xenbase.org/xenbase/"

Node: dcid:zfinId
name: "zfinId"
typeOf: schema:Property
domainIncludes: dcs:Gene
rangeIncludes: schema:Text
specializationOf: dcs:allianceOfGenomeResourcesId
synonym: "Zebrafish Information Network ID"
description: "The gene identifier used by the Zebrafish Information Network (ZFIN), which is the database of genetic and genomic data for the zebrafish (Danio rerio) as a model organism. ZFIN provides a wide array of expertly curated, organized and cross-referenced zebrafish research data. ZFIN is a member of the Alliance of Genome Resources Project."
descriptionUrl: "https://zfin.org/"

Node: dcid:zScore
name: "zScore"
typeOf: schema:Property
domainIncludes: schema:Thing
rangeIncludes: schema:Text
description: "A statistical measurement that describes a value's relationship to the mean of a group of values in a normal distribution curve."