--- title: "Get a genome assembly data report by WGS accession" method: GET path: "/genome/wgs/{wgs_accessions}/dataset_report" tags: ["Genome"] --- # Get a genome assembly data report by WGS accession `GET /genome/wgs/{wgs_accessions}/dataset_report` Get a genome assembly data report by WGS (whole genome shotgun) accession. By default, in paged JSON format, but also available in tabular (accept: text/tab-separated-values) or JSON Lines (accept: application/x-ndjson) formats. ## Path parameters - `wgs_accessions` string[], required ## Query parameters - `filters.reference_only` boolean - `filters.assembly_source` 'all' | 'refseq' | 'genbank' - `filters.has_annotation` boolean - `filters.exclude_paired_reports` boolean - `filters.exclude_atypical` boolean - `filters.assembly_version` 'current' | 'all_assemblies' - `filters.assembly_level` V2reportsAssemblyLevel[] - `filters.first_release_date` string, date-time - `filters.last_release_date` string, date-time - `filters.search_text` string[] - `filters.is_metagenome_derived` 'METAGENOME_DERIVED_UNSET' | 'metagenome_derived_only' | 'metagenome_derived_exclude' - `filters.is_type_material` boolean - `filters.is_ictv_exemplar` boolean - `filters.exclude_multi_isolate` boolean - `filters.type_material_category` 'NONE' | 'TYPE_MATERIAL' | 'TYPE_MATERIAL_CLADE' | 'TYPE_MATERIAL_NEOTYPE' | 'TYPE_MATERIAL_REFTYPE' | 'PATHOVAR_TYPE' | 'TYPE_MATERIAL_SYN' - `tax_exact_match` boolean - `table_fields` string[] - `returned_content` 'COMPLETE' | 'ASSM_ACC' | 'PAIRED_ACC' - `page_size` integer - `page_token` string - `sort.field` string - `sort.direction` 'SORT_DIRECTION_UNSPECIFIED' | 'SORT_DIRECTION_ASCENDING' | 'SORT_DIRECTION_DESCENDING' - `include_tabular_header` 'INCLUDE_TABULAR_HEADER_FIRST_PAGE_ONLY' | 'INCLUDE_TABULAR_HEADER_ALWAYS' | 'INCLUDE_TABULAR_HEADER_NEVER' ## Response `200` A successful response - V2reportsAssemblyDataReportPage - `reports` V2reportsAssemblyDataReport[] - `accession` string - `current_accession` string - `paired_accession` string - `source_database` 'SOURCE_DATABASE_UNSPECIFIED' | 'SOURCE_DATABASE_GENBANK' | 'SOURCE_DATABASE_REFSEQ' - `organism` V2reportsOrganism - `tax_id` integer - `sci_name` string - `organism_name` string - `common_name` string - `lineage` V2reportsLineageOrganism[] - `tax_id` integer - `name` string - `strain` string - `pangolin_classification` string - `infraspecific_names` V2reportsInfraspecificNames - `breed` string - `cultivar` string - `ecotype` string - `isolate` string - `sex` string - `strain` string - `assembly_info` V2reportsAssemblyInfo - `assembly_level` string - `assembly_status` 'ASSEMBLY_STATUS_UNKNOWN' | 'current' | 'previous' | 'suppressed' | 'retired' - `paired_assembly` V2reportsPairedAssembly - `accession` string - `status` 'ASSEMBLY_STATUS_UNKNOWN' | 'current' | 'previous' | 'suppressed' | 'retired' - `annotation_name` string - `only_genbank` string - `only_refseq` string - `changed` string - `manual_diff` string - `refseq_genbank_are_different` boolean - `differences` string - `assembly_name` string - `assembly_long_name` string - `assembly_type` string - `bioproject_lineage` V2reportsBioProjectLineage[] - `bioprojects` V2reportsBioProject[] - `accession` string - `title` string - `parent_accession` string - `parent_accessions` string[] - `bioproject_accession` string - `submission_date` string - `release_date` string - `description` string - `submitter` string - `refseq_category` string - `synonym` string - `linked_assembly` string - `linked_assemblies` V2reportsLinkedAssembly[] - `linked_assembly` string - `assembly_type` '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` V2reportsAtypicalInfo - `is_atypical` boolean - `warnings` string[] - `genome_notes` string[] - `sequencing_tech` string - `assembly_method` string - `grouping_method` string - `biosample` V2reportsBioSampleDescriptor - `accession` string - `last_updated` string - `publication_date` string - `submission_date` string - `sample_ids` V2reportsBioSampleId[] - `db` string - `label` string - `value` string - `description` V2reportsBioSampleDescription - `title` string - `organism` V2reportsOrganism - `tax_id` integer - `sci_name` string - `organism_name` string - `common_name` string - `lineage` V2reportsLineageOrganism[] - … - `strain` string - `pangolin_classification` string - `infraspecific_names` V2reportsInfraspecificNames - … - `comment` string - `owner` V2reportsBioSampleOwner - `name` string - `contacts` V2reportsBioSampleContact[] - `lab` string - `models` string[] - `bioprojects` V2reportsBioProject[] - `accession` string - `title` string - `parent_accession` string - `parent_accessions` string[] - `package` string - `attributes` V2reportsBioSampleAttribute[] - `name` string - `value` string - `status` V2reportsBioSampleStatus - `status` string - `when` string - `age` string - `biomaterial_provider` string - `breed` string - `collected_by` string - `collection_date` string - `cultivar` string - `dev_stage` string - `ecotype` string - `geo_loc_name` string - `host` string - `host_disease` string - `identified_by` string - `ifsac_category` string - `isolate` string - `isolate_name_alias` string - `isolation_source` string - `lat_lon` string - `project_name` string - `sample_name` string - `serovar` string - `sex` string - `source_type` string - `strain` string - `sub_species` string - `tissue` string - `serotype` string - `blast_url` string - `comments` string - `suppression_reason` string - `diploid_role` '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` V2reportsAssemblyStats - `total_number_of_chromosomes` integer - `total_sequence_length` string, uint64 - `total_ungapped_length` string, uint64 - `number_of_contigs` integer - `contig_n50` integer - `contig_l50` integer - `number_of_scaffolds` integer - `scaffold_n50` integer - `scaffold_l50` integer - `gaps_between_scaffolds_count` integer - `number_of_component_sequences` integer - `atgc_count` string, uint64 - `gc_count` string, uint64 - `gc_percent` number, float - `genome_coverage` string - `number_of_organelles` integer - `organelle_info` V2reportsOrganelleInfo[] - `assembly_name` string - `infraspecific_name` string - `bioproject` string[] - `description` string - `total_seq_length` string, uint64 - `submitter` string - `additional_submitters` V2reportsAdditionalSubmitter[] - `genbank_accession` string - `refseq_accession` string - `chr_name` string - `molecule_type` string - `submitter` string - `bioproject_accession` string - `annotation_info` V2reportsAnnotationInfo - `name` string - `provider` string - `release_date` string - `report_url` string - `stats` V2reportsFeatureCounts - `gene_counts` V2reportsGeneCounts - `total` integer - `protein_coding` integer - `non_coding` integer - `pseudogene` integer - `other` integer - `busco` V2reportsBuscoStat - `busco_lineage` string - `busco_ver` string - `complete` number, float - `single_copy` number, float - `duplicated` number, float - `fragmented` number, float - `missing` number, float - `total_count` string, uint64 - `method` string - `pipeline` string - `software_version` string - `status` string - `release_version` string - `wgs_info` V2reportsWGSInfo - `wgs_project_accession` string - `master_wgs_url` string - `wgs_contigs_url` string - `type_material` V2reportsTypeMaterial - `type_label` string - `type_display_text` string - `checkm_info` V2reportsCheckM - `checkm_marker_set` string - `checkm_species_tax_id` integer - `checkm_marker_set_rank` string - `checkm_version` string - `completeness` number, float - `contamination` number, float - `completeness_percentile` number, float - `average_nucleotide_identity` V2reportsAverageNucleotideIdentity - `taxonomy_check_status` 'TAXONOMY_CHECK_STATUS_UNKNOWN' | 'OK' | 'Failed' | 'Inconclusive' - `match_status` '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` string - `submitted_species` string - `category` 'ANI_CATEGORY_UNKNOWN' | 'claderef' | 'category_na' | 'neotype' | 'no_type' | 'pathovar' | 'reftype' | 'suspected_type' | 'synonym' | 'type' - `submitted_ani_match` V2reportsANIMatch - `assembly` string - `organism_name` string - `category` 'ANI_CATEGORY_UNKNOWN' | 'claderef' | 'category_na' | 'neotype' | 'no_type' | 'pathovar' | 'reftype' | 'suspected_type' | 'synonym' | 'type' - `ani` number, float - `assembly_coverage` number, float - `type_assembly_coverage` number, float - `best_ani_match` V2reportsANIMatch - `assembly` string - `organism_name` string - `category` 'ANI_CATEGORY_UNKNOWN' | 'claderef' | 'category_na' | 'neotype' | 'no_type' | 'pathovar' | 'reftype' | 'suspected_type' | 'synonym' | 'type' - `ani` number, float - `assembly_coverage` number, float - `type_assembly_coverage` number, float - `comment` string - `content_type` 'COMPLETE' | 'ASSM_ACC' | 'PAIRED_ACC' - `total_count` integer - `next_page_token` string - `messages` V2reportsMessage[] - `error` V2reportsError - `assembly_error_code` 'UNKNOWN_ASSEMBLY_ERROR_CODE' | 'INVALID_BIOPROJECT_IDS' | 'NO_ASSEMBLIES_FOR_BIOPROJECTS' | 'INVALID_TAXON' | 'MISSING_SEARCH_FIELD' | 'INVALID_BIOSAMPLE_IDS' | 'NO_ASSEMBLIES_FOR_BIOSAMPLE_IDS' | 'NO_ASSEMBLIES_FOR_ASSEMBLY_NAMES' | 'INVALID_WGS_ACCESSIONS' | 'NO_ASSEMBLIES_FOR_WGS_ACCESSIONS' - `gene_error_code` 'UNKNOWN_GENE_ERROR_CODE' | 'INCOMPLETE_LOOKUP_SYMBOL' | 'INVALID_TAXON_GENE_ARGUMENT' - `organelle_error_code` 'UNKNOWN_ORGANELLE_ERROR_CODE' | 'INVALID_ORGANELLE_TAXON' | 'NO_ORGANELLES_FOR_ACCESSION' - `virus_error_code` 'UNKNOWN_VIRUS_ERROR_CODE' - `taxonomy_error_code` 'UNKNOWN_TAXONOMY_ERROR_CODE' | 'INVALID_TAXONOMY_TAXON' - `sequence_error_code` 'UNKNOWN_SEQUENCE_ERROR_CODE' | 'INVALID_SEQUENCE_ACCESSION' - `reason` string - `message` string - `invalid_identifiers` string[] - `warning` V2reportsWarning - `gene_warning_code` 'UNKNOWN_GENE_WARNING_CODE' | 'ACCESSION_VERSION_MISMATCH' | 'REPLACED_GENE_ID' | 'DISCONTINUED_GENE_ID' | 'UNRECOGNIZED_GENE_ID' | 'UNRECOGNIZED_GENE_SYMBOL' | 'UNRECOGNIZED_ACCESSION' | 'UNRECOGNIZED_TAX_TOKEN' | 'NO_GENE_ANNOTATION_FOUND' | 'ABOVE_SPECIES_TAXON' - `reason` string - `message` string - `replaced_id` V2reportsWarningReplacedId - `requested` string - `returned` string - `unrecognized_identifier` string ## Other responses - `default` — An unexpected error response. --- [API](https://skmtc.net/ncats/apis/ncbi-datasets-api.md) · [All operations](https://skmtc.net/ncats/apis/ncbi-datasets-api/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/ncats/ncbi-datasets-api/versions/e5d4400c8e5d/schema)