{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"title": "datasetReport",
"type": "object",
"properties": {
"accession": {
"type": "string",
"title": "The GenColl assembly accession"
},
"current_accession": {
"type": "string",
"title": "The latest GenColl assembly accession for this revision chain"
},
"paired_accession": {
"type": "string",
"title": "The GenBank or RefSeq assembly accession paired with this assembly"
},
"source_database": {
"title": "Source of the accession. The paired accession, if it exists, is from the other database.",
"type": "string",
"default": "SOURCE_DATABASE_UNSPECIFIED",
"enum": [
"SOURCE_DATABASE_UNSPECIFIED",
"SOURCE_DATABASE_GENBANK",
"SOURCE_DATABASE_REFSEQ"
]
},
"organism": {
"type": "object",
"properties": {
"tax_id": {
"type": "integer",
"title": "NCBI Taxonomy identifier"
},
"sci_name": {
"type": "string",
"title": "Scientific name"
},
"organism_name": {
"type": "string",
"title": "Scientific name"
},
"common_name": {
"type": "string",
"title": "Common name"
},
"lineage": {
"type": "array",
"items": {
"type": "object",
"properties": {
"tax_id": {
"type": "integer",
"title": "NCBI Taxonomy identifier"
},
"name": {
"type": "string",
"title": "Scientific name"
}
}
}
},
"strain": {
"type": "string"
},
"pangolin_classification": {
"type": "string"
},
"infraspecific_names": {
"type": "object",
"properties": {
"breed": {
"type": "string",
"title": "A homogenous group of animals within a domesticated species"
},
"cultivar": {
"type": "string",
"title": "A variety of plant within a species produced and maintained by cultivation"
},
"ecotype": {
"type": "string",
"title": "A population or subspecies occupying a distinct habitat"
},
"isolate": {
"type": "string",
"title": "The individual isolate from which the sequences in the genome assembly were derived"
},
"sex": {
"type": "string",
"title": "Physical sex of sampled organism"
},
"strain": {
"type": "string",
"title": "A genetic variant, subtype or culture within a species"
}
}
}
}
},
"assembly_info": {
"title": "Metadata for the genome assembly submission",
"type": "object",
"properties": {
"assembly_level": {
"type": "string",
"title": "The level at which a genome has been assembled"
},
"assembly_status": {
"title": "The GenColl assembly status",
"type": "string",
"default": "ASSEMBLY_STATUS_UNKNOWN",
"enum": [
"ASSEMBLY_STATUS_UNKNOWN",
"current",
"previous",
"suppressed",
"retired"
]
},
"paired_assembly": {
"title": "Metadata from the GenBank or RefSeq assembly paired with this one",
"type": "object",
"properties": {
"accession": {
"type": "string",
"title": "The GenColl assembly accession of the GenBank or RefSeq assembly paired with this one"
},
"status": {
"title": "GenColl Assembly status from paired record",
"type": "string",
"default": "ASSEMBLY_STATUS_UNKNOWN",
"enum": [
"ASSEMBLY_STATUS_UNKNOWN",
"current",
"previous",
"suppressed",
"retired"
]
},
"annotation_name": {
"type": "string",
"title": "Annotation name from paired record"
},
"only_genbank": {
"type": "string",
"title": "Sequences that are only included in the GenBank assembly"
},
"only_refseq": {
"type": "string",
"title": "Sequences that are only included in the RefSeq assembly"
},
"changed": {
"type": "string",
"title": "Sequences present on both the GenBank and the RefSeq assemblies that have been changed, e.g., contaminated sequence in the GenBank assembly has been replaced with a gap"
},
"manual_diff": {
"type": "string",
"title": "Manually curated description of differences between the GenBank and RefSeq assemblies"
},
"refseq_genbank_are_different": {
"type": "boolean",
"title": "boolean indication on whether there are any differences between the GenBank and RefSeq assemblies"
},
"differences": {
"type": "string",
"title": "Concatenation of all differences between the GenBank and RefSeq assemblies, including manually curated description and other fields"
}
}
},
"assembly_name": {
"type": "string",
"title": "The assembly submitter's name for the genome assembly, when provided. Otherwise, a default name in the form ASM#####v# is assigned"
},
"assembly_long_name": {
"type": "string"
},
"assembly_type": {
"type": "string",
"title": "Chromosome content of the submitted genome assembly"
},
"bioproject_lineage": {
"type": "array",
"items": {
"type": "object",
"properties": {
"bioprojects": {
"type": "array",
"items": {
"type": "object",
"properties": {
"accession": {
"type": "string",
"title": "BioProject accession"
},
"title": {
"type": "string",
"title": "Title of the BioProject provided by the submitter"
},
"parent_accession": {
"type": "string"
},
"parent_accessions": {
"type": "array",
"items": {
"type": "string"
}
}
}
}
}
}
}
},
"bioproject_accession": {
"type": "string"
},
"submission_date": {
"type": "string",
"title": "Date the assembly was submitted to NCBI (being replaced by release date - should maintain until most CLI users upgrade)"
},
"release_date": {
"type": "string",
"title": "Date the assembly was made available by NCBI. This field is not returned by versions of the datasets Command Line Interface (CLI) program < 15."
},
"description": {
"type": "string",
"title": "Long description for this genome"
},
"submitter": {
"type": "string",
"title": "The submitting consortium or organization. Full submitter information is available in the BioProject"
},
"refseq_category": {
"type": "string",
"title": "The RefSeq Category, if present, indicates whether the assembly is a reference genome"
},
"synonym": {
"type": "string",
"title": "Genome name ascribed to this assembly by the UC Santa Cruz genome browser"
},
"linked_assembly": {
"type": "string",
"title": "The accession.version and designation (principal or alternate pseudohaplotype) of a paired genome assembly derived from the same diploid individual"
},
"linked_assemblies": {
"type": "array",
"items": {
"type": "object",
"properties": {
"linked_assembly": {
"type": "string",
"title": "The linked assembly accession"
},
"assembly_type": {
"title": "The linked assembly type",
"type": "string",
"default": "LINKED_ASSEMBLY_TYPE_UNKNOWN",
"enum": [
"LINKED_ASSEMBLY_TYPE_UNKNOWN",
"alternate_pseudohaplotype_of_diploid",
"principal_pseudohaplotype_of_diploid",
"maternal_haplotype_of_diploid",
"paternal_haplotype_of_diploid",
"haplotype_1",
"haplotype_2",
"haplotype_3",
"haplotype_4",
"haploid"
]
}
}
}
},
"atypical": {
"title": "Information on atypical genomes - genomes that have assembly issues or are otherwise atypical",
"type": "object",
"properties": {
"is_atypical": {
"type": "boolean",
"title": "If true there are assembly issues or the assembly is in some way non-standard"
},
"warnings": {
"type": "array",
"items": {
"type": "string"
}
}
}
},
"genome_notes": {
"type": "array",
"items": {
"type": "string"
}
},
"sequencing_tech": {
"type": "string",
"title": "Sequencing technology used to sequence this genome"
},
"assembly_method": {
"type": "string",
"title": "Genome assembly method"
},
"grouping_method": {
"type": "string",
"title": "Version of the NCBI Virus segmented genome grouping pipeline, which groups nucleotide sequences for segmented viruses into a single genome assembly. For more information, see the [NCBI Virus Help Documentation](https://www.ncbi.nlm.nih.gov/labs/virus/vssi/docs/help/#virus_segment_grouping)"
},
"biosample": {
"title": "NCBI BioSample from which the sequences in the genome assembly were obtained.",
"type": "object",
"properties": {
"accession": {
"type": "string"
},
"last_updated": {
"type": "string"
},
"publication_date": {
"type": "string"
},
"submission_date": {
"type": "string"
},
"sample_ids": {
"type": "array",
"items": {
"type": "object",
"properties": {
"db": {
"type": "string"
},
"label": {
"type": "string"
},
"value": {
"type": "string"
}
}
}
},
"description": {
"type": "object",
"properties": {
"title": {
"type": "string"
},
"organism": {
"type": "object",
"properties": {
"tax_id": {
"type": "integer",
"title": "NCBI Taxonomy identifier"
},
"sci_name": {
"type": "string",
"title": "Scientific name"
},
"organism_name": {
"type": "string",
"title": "Scientific name"
},
"common_name": {
"type": "string",
"title": "Common name"
},
"lineage": {
"type": "array",
"items": {
"type": "object",
"properties": {
"tax_id": {
"type": "integer",
"title": "NCBI Taxonomy identifier"
},
"name": {
"type": "string",
"title": "Scientific name"
}
}
}
},
"strain": {
"type": "string"
},
"pangolin_classification": {
"type": "string"
},
"infraspecific_names": {
"type": "object",
"properties": {
"breed": {
"type": "string",
"title": "A homogenous group of animals within a domesticated species"
},
"cultivar": {
"type": "string",
"title": "A variety of plant within a species produced and maintained by cultivation"
},
"ecotype": {
"type": "string",
"title": "A population or subspecies occupying a distinct habitat"
},
"isolate": {
"type": "string",
"title": "The individual isolate from which the sequences in the genome assembly were derived"
},
"sex": {
"type": "string",
"title": "Physical sex of sampled organism"
},
"strain": {
"type": "string",
"title": "A genetic variant, subtype or culture within a species"
}
}
}
}
},
"comment": {
"type": "string"
}
}
},
"owner": {
"type": "object",
"properties": {
"name": {
"type": "string"
},
"contacts": {
"type": "array",
"items": {
"type": "object",
"properties": {
"lab": {
"type": "string",
"title": "Submitter lab name."
}
}
}
}
}
},
"models": {
"type": "array",
"items": {
"type": "string"
}
},
"bioprojects": {
"type": "array",
"items": {
"type": "object",
"properties": {
"accession": {
"type": "string",
"title": "BioProject accession"
},
"title": {
"type": "string",
"title": "Title of the BioProject provided by the submitter"
},
"parent_accession": {
"type": "string"
},
"parent_accessions": {
"type": "array",
"items": {
"type": "string"
}
}
}
}
},
"package": {
"type": "string"
},
"attributes": {
"type": "array",
"items": {
"type": "object",
"properties": {
"name": {
"type": "string"
},
"value": {
"type": "string"
}
}
}
},
"status": {
"type": "object",
"properties": {
"status": {
"type": "string"
},
"when": {
"type": "string"
}
}
},
"age": {
"type": "string",
"title": "Age at the time of sampling"
},
"biomaterial_provider": {
"type": "string",
"title": "Name and address of the lab or PI"
},
"breed": {
"type": "string",
"title": "Breed name"
},
"collected_by": {
"type": "string",
"title": "Name of persons or institute who collected the sample"
},
"collection_date": {
"type": "string",
"title": "Date on which the sample was collected"
},
"cultivar": {
"type": "string",
"title": "Cultivated variety of plant"
},
"dev_stage": {
"type": "string",
"title": "Developmental stage at the time of sampling"
},
"ecotype": {
"type": "string",
"title": "Population within a given species adapted to a local habitat"
},
"geo_loc_name": {
"type": "string",
"title": "Geographical origin of the sample"
},
"host": {
"type": "string",
"title": "The natural host to the organism"
},
"host_disease": {
"type": "string",
"title": "Name of relevant disease"
},
"identified_by": {
"type": "string",
"title": "Name of the taxonomist who identified the specimen"
},
"ifsac_category": {
"type": "string",
"title": "Interagency Food Safety Analytics Collaboration (IFSAC) category"
},
"isolate": {
"type": "string",
"title": "Description of the specific individual from which the sample was derived"
},
"isolate_name_alias": {
"type": "string",
"title": "Other IDs associated with this isolate"
},
"isolation_source": {
"type": "string",
"title": "Source of the sample"
},
"lat_lon": {
"type": "string",
"title": "Geographic coordinates of the location where the sample was collected"
},
"project_name": {
"type": "string",
"title": "Name of the project"
},
"sample_name": {
"type": "string",
"title": "Sample name in source database"
},
"serovar": {
"type": "string",
"title": "Taxonomic name below subspecies. Same as serotype."
},
"sex": {
"type": "string",
"title": "Physical sex of sampled organism"
},
"source_type": {
"type": "string",
"title": "Controlled vocabulary describing the isolation source"
},
"strain": {
"type": "string",
"title": "Strain name"
},
"sub_species": {
"type": "string",
"title": "Sub-species taxonomic name"
},
"tissue": {
"type": "string",
"title": "Type of tissue from which the sample was derived"
},
"serotype": {
"type": "string",
"title": "Taxonomic name below subspecies. Same as serovar"
}
}
},
"blast_url": {
"type": "string",
"title": "URL to blast page for this assembly"
},
"comments": {
"type": "string",
"title": "Freeform comments"
},
"suppression_reason": {
"type": "string",
"title": "The reason for the assembly is suppressed, for suppressed assemblies"
},
"diploid_role": {
"type": "string",
"default": "LINKED_ASSEMBLY_TYPE_UNKNOWN",
"enum": [
"LINKED_ASSEMBLY_TYPE_UNKNOWN",
"alternate_pseudohaplotype_of_diploid",
"principal_pseudohaplotype_of_diploid",
"maternal_haplotype_of_diploid",
"paternal_haplotype_of_diploid",
"haplotype_1",
"haplotype_2",
"haplotype_3",
"haplotype_4",
"haploid"
]
}
}
},
"assembly_stats": {
"title": "Global statistics for the genome assembly",
"type": "object",
"properties": {
"total_number_of_chromosomes": {
"type": "integer",
"title": "Count of nuclear chromosomes, organelles and plasmids in a submitted genome assembly"
},
"total_sequence_length": {
"type": "string",
"format": "integer",
"title": "Total sequence length of the nuclear genome including unplaced and unlocalized sequences"
},
"total_ungapped_length": {
"type": "string",
"format": "integer",
"title": "Total length of all top-level sequences ignoring gaps. Any stretch of 10 or more Ns in a sequence is treated like a gap"
},
"number_of_contigs": {
"type": "integer",
"title": "Total number of sequence contigs in the assembly. Any stretch of 10 or more Ns in a sequence is treated as a gap between two contigs in a scaffold when counting contigs and calculating contig N50 & L50 values"
},
"contig_n50": {
"type": "integer",
"title": "Length such that sequence contigs of this length or longer include half the bases of the assembly"
},
"contig_l50": {
"type": "integer",
"title": "Number of sequence contigs that are longer than, or equal to, the N50 length and therefore include half the bases of the assembly"
},
"number_of_scaffolds": {
"type": "integer",
"title": "Number of scaffolds including placed, unlocalized, unplaced, alternate loci and patch scaffolds"
},
"scaffold_n50": {
"type": "integer",
"title": "Length such that scaffolds of this length or longer include half the bases of the assembly"
},
"scaffold_l50": {
"type": "integer",
"title": "Number of scaffolds that are longer than, or equal to, the N50 length and therefore include half the bases of the assembly"
},
"gaps_between_scaffolds_count": {
"type": "integer",
"title": "Number of unspanned gaps between scaffolds"
},
"number_of_component_sequences": {
"type": "integer",
"title": "Total number of component WGS or clone sequences in the assembly"
},
"atgc_count": {
"type": "string",
"format": "integer",
"title": "The number of AT and GC base-pairs in the assembly"
},
"gc_count": {
"type": "string",
"format": "integer",
"title": "The number of GC base-pairs in the assembly"
},
"gc_percent": {
"type": "number",
"format": "float",
"title": "The percentage of GC base-pairs in the assembly"
},
"genome_coverage": {
"type": "string",
"title": "Genome assembly coverage"
},
"number_of_organelles": {
"type": "integer",
"title": "number of organelles"
}
}
},
"organelle_info": {
"type": "array",
"items": {
"type": "object",
"properties": {
"assembly_name": {
"type": "string",
"title": "Name of associated nuclear assembly"
},
"infraspecific_name": {
"type": "string",
"title": "The strain, breed, cultivar or ecotype of the organism from which the sequences in the assembly were derived"
},
"bioproject": {
"type": "array",
"items": {
"type": "string"
}
},
"description": {
"type": "string",
"title": "Long description of the organelle genome"
},
"total_seq_length": {
"type": "string",
"format": "integer",
"title": "Sequence length of the organelle genome"
},
"submitter": {
"type": "string",
"title": "Name of submitter"
}
}
}
},
"additional_submitters": {
"type": "array",
"items": {
"type": "object",
"properties": {
"genbank_accession": {
"type": "string",
"title": "genbank accession of extra sequence"
},
"refseq_accession": {
"type": "string",
"title": "genbank accession of extra sequence"
},
"chr_name": {
"type": "string",
"title": "chromosome name"
},
"molecule_type": {
"type": "string",
"title": "molecule type"
},
"submitter": {
"type": "string",
"title": "Name of submitter"
},
"bioproject_accession": {
"type": "string",
"title": "Bioproject accession"
}
}
}
},
"annotation_info": {
"title": "Metadata and statistics for the genome assembly annotation, when available",
"type": "object",
"properties": {
"name": {
"type": "string",
"title": "Annotation name"
},
"provider": {
"type": "string",
"title": "Source of the annotation"
},
"release_date": {
"type": "string",
"title": "Annotation release date"
},
"report_url": {
"type": "string",
"title": "Annotation report web address"
},
"stats": {
"type": "object",
"properties": {
"gene_counts": {
"title": "Counts of gene types",
"type": "object",
"properties": {
"total": {
"type": "integer",
"title": "Total number of annotated genes"
},
"protein_coding": {
"type": "integer",
"title": "Count of annotated genes that encode a protein"
},
"non_coding": {
"type": "integer",
"title": "Count of transcribed non-coding genes (e.g. lncRNAs, miRNAs, rRNAs, etc...) excludes transcribed pseudogenes"
},
"pseudogene": {
"type": "integer",
"title": "Count of transcribed and non-transcribed pseudogenes"
},
"other": {
"type": "integer",
"title": "Count of genic region GeneIDs and non-genic regulatory GeneIDs"
}
}
}
}
},
"busco": {
"type": "object",
"properties": {
"busco_lineage": {
"type": "string",
"title": "BUSCO Lineage"
},
"busco_ver": {
"type": "string",
"title": "BUSCO Version"
},
"complete": {
"type": "number",
"format": "float",
"title": "BUSCO score: Complete"
},
"single_copy": {
"type": "number",
"format": "float",
"title": "BUSCO score: Single Copy"
},
"duplicated": {
"type": "number",
"format": "float",
"title": "BUSCO score: Duplicated"
},
"fragmented": {
"type": "number",
"format": "float",
"title": "BUSCO score: Fragmented"
},
"missing": {
"type": "number",
"format": "float",
"title": "BUSCO score: Missing"
},
"total_count": {
"type": "string",
"format": "integer",
"title": "BUSCO score: Total Count"
}
}
},
"method": {
"type": "string",
"title": "Software tools used to calculate annotation"
},
"pipeline": {
"type": "string",
"title": "NCBI annotation pipeline used to calculate annotation"
},
"software_version": {
"type": "string",
"title": "NCBI annotation pipeline software version"
},
"status": {
"type": "string",
"title": "Type of annotation"
},
"release_version": {
"type": "string"
}
}
},
"wgs_info": {
"title": "Metadata pertaining to the Whole Genome Shotgun (WGS) record for the genome assemblies that are complete genomes. Those that are clone-based do not have WGS-master records.",
"type": "object",
"properties": {
"wgs_project_accession": {
"type": "string",
"title": "WGS project accession"
},
"master_wgs_url": {
"type": "string",
"title": "WGS project Nucleotide web address"
},
"wgs_contigs_url": {
"type": "string",
"title": "WGS project Sequence set browser web address"
}
}
},
"type_material": {
"type": "object",
"properties": {
"type_label": {
"type": "string"
},
"type_display_text": {
"type": "string"
}
}
},
"checkm_info": {
"title": "Metadata on the completeness and contamination of this assembly",
"type": "object",
"properties": {
"checkm_marker_set": {
"type": "string",
"title": "What taxonomic group is used as the basis for comparison with this assembly with regards to checkM values"
},
"checkm_species_tax_id": {
"type": "integer",
"title": "The species-level taxid for this assemblies checkM dataset"
},
"checkm_marker_set_rank": {
"type": "string",
"title": "CheckM taxonomic rank of checkm_marker_set"
},
"checkm_version": {
"type": "string",
"title": "CheckM software version"
},
"completeness": {
"type": "number",
"format": "float",
"title": "What percent complete is this assembly"
},
"contamination": {
"type": "number",
"format": "float",
"title": "What is the contamination percentage for this assembly"
},
"completeness_percentile": {
"type": "number",
"format": "float",
"title": "The percent of assemblies under the taxonomic grouping 'checkm_marker_set' that this assembly is as-or-more complete than."
}
}
},
"average_nucleotide_identity": {
"type": "object",
"properties": {
"taxonomy_check_status": {
"title": "Indicates whether the ANI result is consistent with the submitted organism",
"type": "string",
"default": "TAXONOMY_CHECK_STATUS_UNKNOWN",
"enum": [
"TAXONOMY_CHECK_STATUS_UNKNOWN",
"OK",
"Failed",
"Inconclusive"
]
},
"match_status": {
"title": "Indicates the specific type of ANI result that supports the Taxonomy check status",
"type": "string",
"default": "BEST_MATCH_STATUS_UNKNOWN",
"enum": [
"BEST_MATCH_STATUS_UNKNOWN",
"approved_mismatch",
"below_threshold_match",
"below_threshold_mismatch",
"best_match_status",
"derived_species_match",
"genus_match",
"low_coverage",
"mismatch",
"status_na",
"species_match",
"subspecies_match",
"synonym_match",
"lineage_match",
"below_threshold_lineage_match"
]
},
"submitted_organism": {
"type": "string",
"title": "Taxonomic name of the query assembly"
},
"submitted_species": {
"type": "string",
"title": "Species name of the query assembly"
},
"category": {
"title": "Category of type or validated assembly",
"type": "string",
"default": "ANI_CATEGORY_UNKNOWN",
"enum": [
"ANI_CATEGORY_UNKNOWN",
"claderef",
"category_na",
"neotype",
"no_type",
"pathovar",
"reftype",
"suspected_type",
"synonym",
"type"
]
},
"submitted_ani_match": {
"type": "object",
"properties": {
"assembly": {
"type": "string",
"title": "Accession of the submitted organism best match type-strain assembly or best match type-strain assembly"
},
"organism_name": {
"type": "string",
"title": "Taxonomic name of the submitted organism or best match type-strain organism"
},
"category": {
"title": "Type category",
"type": "string",
"default": "ANI_CATEGORY_UNKNOWN",
"enum": [
"ANI_CATEGORY_UNKNOWN",
"claderef",
"category_na",
"neotype",
"no_type",
"pathovar",
"reftype",
"suspected_type",
"synonym",
"type"
]
},
"ani": {
"type": "number",
"format": "float",
"title": "Percent average nucleotide identity"
},
"assembly_coverage": {
"type": "number",
"format": "float",
"title": "Percent coverage of the query assembly by the submitted organism or best match type assembly"
},
"type_assembly_coverage": {
"type": "number",
"format": "float",
"title": "Percent coverage of the submitted organism or best match type assembly by the query assembly"
}
}
},
"best_ani_match": {
"type": "object",
"properties": {
"assembly": {
"type": "string",
"title": "Accession of the submitted organism best match type-strain assembly or best match type-strain assembly"
},
"organism_name": {
"type": "string",
"title": "Taxonomic name of the submitted organism or best match type-strain organism"
},
"category": {
"title": "Type category",
"type": "string",
"default": "ANI_CATEGORY_UNKNOWN",
"enum": [
"ANI_CATEGORY_UNKNOWN",
"claderef",
"category_na",
"neotype",
"no_type",
"pathovar",
"reftype",
"suspected_type",
"synonym",
"type"
]
},
"ani": {
"type": "number",
"format": "float",
"title": "Percent average nucleotide identity"
},
"assembly_coverage": {
"type": "number",
"format": "float",
"title": "Percent coverage of the query assembly by the submitted organism or best match type assembly"
},
"type_assembly_coverage": {
"type": "number",
"format": "float",
"title": "Percent coverage of the submitted organism or best match type assembly by the query assembly"
}
}
},
"comment": {
"type": "string",
"title": "Additional information about the ANI result"
}
}
}
}
}