{ "name": "consensus_sequence", "schema": { "type": "object", "required": [ "sample_collection", "host", "experiment", "sequence_analysis", "pathogen_diagnostic_testing" ], "properties": { "database_identifiers": { "type": "object", "properties": { "gisaid_accession": { "type": [ "string", "null" ] } }, "propertyNames": { "enum": [ "gisaid_accession" ] } }, "sample_collection": { "type": "object", "required": [ "sample_collected_by", "sequence_submitted_by", "sample_collection_date", "sample_collection_date_null_reason", "geo_loc_country", "geo_loc_province", "organism", "isolate", "fasta_header_name", "purpose_of_sampling", "purpose_of_sampling_details", "anatomical_material", "anatomical_part", "body_product", "environmental_material", "environmental_site", "collection_device", "collection_method" ], "properties": { "sample_collected_by": { "enum": [ "Alberta Precision Labs (APL)", "Alberta ProvLab North (APLN)", "Alberta ProvLab South (APLS)", "BCCDC Public Health Laboratory", "Dynacare (Brampton)", "Dynacare (Manitoba)", "Dynacare", "Eastern Ontario Regional Laboratory Association", "Hamilton Health Sciences", "Laboratoire de santé publique du Québec (LSPQ)", "Lake of the Woods District Hospital - Ontario", "LifeLabs", "LifeLabs (Ontario)", "Manitoba Cadham Provincial Laboratory", "McMaster University", "Mount Sinai Hospital", "National Microbiology Laboratory (NML)", "New Brunswick - Vitalité Health Network", "Newfoundland and Labrador - Eastern Health", "Newfoundland and Labrador - Newfoundland and Labrador Health Services", "Nova Scotia Health Authority", "Nunuvut", "Ontario Institute for Cancer Research (OICR)", "Prince Edward Island - Health PEI", "Public Health Ontario (PHO)", "Queen's University / Kingston Health Sciences Centre", "Saskatchewan - Roy Romanow Provincial Laboratory (RRPL)", "Shared Hospital Laboratory", "St. John's Rehab at Sunnybrook Hospital", "Sunnybrook Health Sciences Centre", "Switch Health", "The Hospital for Sick Children (SickKids)", "Unity Health Toronto", "William Osler Health System", "Not Applicable", "Missing", "Not Collected", "Not Provided", "Restricted Access" ] }, "sequence_submitted_by": { "enum": [ "Alberta Precision Labs (APL)", "Alberta ProvLab North (APLN)", "Alberta ProvLab South (APLS)", "BCCDC Public Health Laboratory", "Canadore College", "Dynacare (Manitoba)", "Laboratoire de santé publique du Québec (LSPQ)", "Manitoba Cadham Provincial Laboratory", "McGill University", "McMaster University", "National Microbiology Laboratory (NML)", "New Brunswick - Vitalité Health Network", "Newfoundland and Labrador - Eastern Health", "Newfoundland and Labrador - Newfoundland and Labrador Health Services", "Nova Scotia Health Authority", "Ontario Institute for Cancer Research (OICR)", "Prince Edward Island - Health PEI", "Public Health Ontario (PHO)", "Queen's University / Kingston Health Sciences Centre", "Saskatchewan - Roy Romanow Provincial Laboratory (RRPL)", "Sunnybrook Health Sciences Centre", "The Centre for Applied Genomics (TCAG)", "The Hospital for Sick Children (SickKids)", "Thunder Bay Regional Health Sciences Centre", "Not Applicable", "Missing", "Not Collected", "Not Provided", "Restricted Access" ] }, "sample_collection_date": { "anyOf": [ { "type": "string", "format": "date" }, { "type": "null" } ] }, "sample_collection_date_precision": { "enum": [ "year", "month", "day" ] }, "sample_collection_date_null_reason": { "enum": [ "Not Applicable", "Missing", "Not Collected", "Not Provided", "Restricted Access", null ] }, "geo_loc_country": { "enum": [ "Canada", "Not Applicable", "Missing", "Not Collected", "Not Provided", "Restricted Access" ] }, "geo_loc_province": { "enum": [ "Alberta", "British Columbia", "Manitoba", "New Brunswick", "Newfoundland and Labrador", "Northwest Territories", "Nova Scotia", "Nunavut", "Ontario", "Prince Edward Island", "Quebec", "Saskatchewan", "Yukon", "Not Applicable", "Missing", "Not Collected", "Not Provided", "Restricted Access" ] }, "geo_loc_city": { "type": [ "string", "null" ] }, "organism": { "enum": [ "Severe acute respiratory syndrome coronavirus 2", "RaTG13", "RmYN02", "Not Applicable", "Missing", "Not Collected", "Not Provided", "Restricted Access" ] }, "isolate": { "type": [ "string", "null" ] }, "fasta_header_name": { "type": "string", "pattern": "^hCoV-19/(?i)(canada)/[a-zA-Z0-9\\-_\\.:/]{1,99}/20[1-2][0-9]$" }, "purpose_of_sampling": { "enum": [ "Cluster/Outbreak investigation", "Diagnostic testing", "Research", "Surveillance", "Not Applicable", "Missing", "Not Collected", "Not Provided", "Restricted Access" ] }, "purpose_of_sampling_details": { "type": [ "string", "null" ] }, "anatomical_material": { "enum": [ "Blood", "Fluid", "Fluid (cerebrospinal (CSF))", "Fluid (pericardial)", "Fluid (pleural)", "Fluid (vaginal)", "Fluid (amniotic)", "Saliva", "Tissue", "Not Applicable", "Missing", "Not Collected", "Not Provided", "Restricted Access" ] }, "anatomical_part": { "type":"array", "items":{ "type":"string", "enum": [ "Alveolar sac", "Anterior Nares", "Anus", "Bronchiole", "Bronchus", "Buccal mucosa", "Duodenum", "Esophagus", "Ethmoid sinus", "Eye", "Inferior Nasal Turbinate", "Intestine", "Lower respiratory tract", "Lung", "Middle Nasal Turbinate", "Nasal Cavity", "Nasopharynx (NP)", "Oropharynx (OP)", "Pharynx (throat)", "Pleural cavity", "Pleural sac", "Rectum", "Skin", "Stomach", "Trachea", "Upper respiratory tract", "Not Applicable", "Missing", "Not Collected", "Not Provided", "Restricted Access" ] } }, "body_product": { "enum": [ "Breast Milk", "Feces", "Fluid (seminal)", "Mucus", "Sputum", "Sweat", "Tear", "Urine", "Not Applicable", "Missing", "Not Collected", "Not Provided", "Restricted Access" ] }, "environmental_material": { "enum": [ "Air vent", "Banknote", "Bed rail", "Building floor", "Cloth", "Control panel", "Door handle", "Door", "Face mask", "Face shield", "Food packaging", "Food", "Glass", "Handrail", "Hospital gown", "Light switch", "Locker", "N95 mask", "Nurse call button", "PPE gown", "Paper", "Particulate matter", "Plastic", "Sewage", "Sink", "Soil", "Stainless steel", "Tissue paper", "Toilet bowl", "Wastewater", "Water", "Window", "Wood", "Not Applicable", "Missing", "Not Collected", "Not Provided", "Restricted Access" ] }, "environmental_site": { "enum": [ "Acute care facility", "Animal house", "Bathroom", "Clinical assessment centre", "Conference venue", "Corridor", "Daycare", "Emergency room (ER)", "Family practice clinic", "Group home", "Homeless shelter", "Hospital", "Intensive Care Unit (ICU)", "Long Term Care Facility", "Patient room", "Prison", "Production Facility", "School", "Sewage Plant", "Subway train", "Wet market", "Not Applicable", "Missing", "Not Collected", "Not Provided", "Restricted Access" ] }, "collection_device": { "enum": [ "Air filter", "Blood Collection Tube", "Bronchoscope", "Collection Container", "Collection Cup", "Fibrobronchoscope Brush", "Filter", "Fine Needle", "Microcapillary tube", "Micropipette", "Needle", "Serum Collection Tube", "Sputum Collection Tube", "Suction Catheter", "Swab", "Urine Collection Tube", "Virus Transport Medium", "Not Applicable", "Missing", "Not Collected", "Not Provided", "Restricted Access" ] }, "collection_method": { "enum": [ "Air filtration", "Amniocentesis", "Aspiration", "Biopsy", "Bronchoalveolar lavage (BAL)", "Filtration", "Finger Prick", "Gastric Lavage", "Lavage", "Lumbar Puncture", "Necropsy", "Needle Biopsy", "Phlebotomy", "Rinsing", "Saline gargle (mouth rinse and gargle)", "Scraping", "Suprapubic Aspiration", "Swabbing", "Tracheal aspiration", "Vacuum Aspiration", "Wash", "Washout Tear Collection", "Not Applicable", "Missing", "Not Collected", "Not Provided", "Restricted Access" ] }, "nml_submitted_specimen_type": { "enum": [ "Swab", "RNA", "mRNA (cDNA)", "Nucleic acid", "Not Applicable" ] } }, "if": { "properties": { "sample_collection_date": { "const": null } } }, "then": { "properties": { "sample_collection_date_null_reason": { "enum": [ "Not Applicable", "Missing", "Not Collected", "Not Provided", "Restricted Access" ] } } }, "else": { "properties": { "sample_collection_date_null_reason": { "const": null } } }, "propertyNames": { "enum": [ "sample_collected_by", "sequence_submitted_by", "sample_collection_date", "sample_collection_date_precision", "sample_collection_date_null_reason", "geo_loc_country", "geo_loc_province", "geo_loc_city", "organism", "isolate", "fasta_header_name", "purpose_of_sampling", "purpose_of_sampling_details", "anatomical_material", "anatomical_part", "body_product", "environmental_material", "environmental_site", "collection_device", "collection_method", "nml_submitted_specimen_type" ] } }, "host": { "type": "object", "required": [ "host_scientific_name", "host_disease", "host_age", "host_age_null_reason", "host_age_bin", "host_age_unit", "host_gender" ], "properties": { "host_scientific_name": { "enum": [ "Homo sapiens", "Bos taurus", "Canis lupus familiaris", "Chiroptera", "Columbidae", "Felis catus", "Gallus gallus", "Manis", "Manis javanica", "Neovison vison", "Panthera leo", "Panthera tigris", "Rhinolophidae", "Rhinolophus affinis", "Sus scrofa domesticus", "Viverridae", "Not Applicable", "Missing", "Not Collected", "Not Provided", "Restricted Access" ] }, "host_disease": { "enum": [ "COVID-19", "Not Applicable", "Missing", "Not Collected", "Not Provided", "Restricted Access" ] }, "host_age": { "anyOf": [ { "type": "number", "minimum": 0, "maximum": 89 }, { "type": "null" } ] }, "host_age_null_reason": { "enum": [ "Not Applicable", "Missing", "Not Collected", "Not Provided", "Restricted Access", null ] }, "host_age_bin": { "enum": [ "0 - 9", "10 - 19", "20 - 29", "30 - 39", "40 - 49", "50 - 59", "60 - 69", "70 - 79", "80 - 89", "90+", "Not Applicable", "Missing", "Not Collected", "Not Provided", "Restricted Access" ] }, "host_gender": { "enum": [ "Female", "Male", "Non-binary gender", "Transgender (Male to Female)", "Transgender (Female to Male)", "Undeclared", "Unknown", "Not Applicable", "Missing", "Not Collected", "Not Provided", "Restricted Access" ] }, "host_age_unit": { "enum": [ "year", "month", "Not Applicable", "Missing", "Not Collected", "Not Provided", "Restricted Access" ] } }, "allOf": [ { "if": { "properties": { "host_age": { "const": null } } }, "then": { "properties": { "host_age_null_reason": { "enum": [ "Not Applicable", "Missing", "Not Collected", "Not Provided", "Restricted Access" ] } } }, "else": { "properties": { "host_age_null_reason": { "const": null }, "host_age_bin": { "enum": [ "0 - 9", "10 - 19", "20 - 29", "30 - 39", "40 - 49", "50 - 59", "60 - 69", "70 - 79", "80 - 89" ] } } } }, { "if": { "properties": { "host_age_bin": { "const": "0 - 9" } } }, "then": { "properties": { "host_age": { "anyOf": [ { "type": "number", "minimum": 0, "maximum": 9 }, { "type": "null" } ] } } } }, { "if": { "properties": { "host_age_bin": { "const": "10 - 19" } } }, "then": { "properties": { "host_age": { "anyOf": [ { "type": "number", "minimum": 10, "maximum": 19 }, { "type": "null" } ] } } } }, { "if": { "properties": { "host_age_bin": { "const": "20 - 29" } } }, "then": { "properties": { "host_age": { "anyOf": [ { "type": "number", "minimum": 20, "maximum": 29 }, { "type": "null" } ] } } } }, { "if": { "properties": { "host_age_bin": { "const": "30 - 39" } } }, "then": { "properties": { "host_age": { "anyOf": [ { "type": "number", "minimum": 30, "maximum": 39 }, { "type": "null" } ] } } } }, { "if": { "properties": { "host_age_bin": { "const": "40 - 49" } } }, "then": { "properties": { "host_age": { "anyOf": [ { "type": "number", "minimum": 40, "maximum": 49 }, { "type": "null" } ] } } } }, { "if": { "properties": { "host_age_bin": { "const": "50 - 59" } } }, "then": { "properties": { "host_age": { "anyOf": [ { "type": "number", "minimum": 50, "maximum": 59 }, { "type": "null" } ] } } } }, { "if": { "properties": { "host_age_bin": { "const": "60 - 69" } } }, "then": { "properties": { "host_age": { "anyOf": [ { "type": "number", "minimum": 60, "maximum": 69 }, { "type": "null" } ] } } } }, { "if": { "properties": { "host_age_bin": { "const": "70 - 79" } } }, "then": { "properties": { "host_age": { "anyOf": [ { "type": "number", "minimum": 70, "maximum": 79 }, { "type": "null" } ] } } } }, { "if": { "properties": { "host_age_bin": { "const": "80 - 89" } } }, "then": { "properties": { "host_age": { "anyOf": [ { "type": "number", "minimum": 80, "maximum": 89 }, { "type": "null" } ] } } } }, { "if": { "properties": { "host_age_bin": { "const": "90+" } } }, "then": { "properties": { "host_age": { "const": null }, "host_age_null_reason": { "const": "Restricted Access" } } } } ], "propertyNames": { "enum": [ "host_scientific_name", "host_disease", "host_age", "host_age_null_reason", "host_age_bin", "host_age_unit", "host_gender" ] } }, "experiment": { "type": "object", "required": [ "purpose_of_sequencing", "purpose_of_sequencing_details", "sequencing_instrument", "sequencing_protocol" ], "properties": { "purpose_of_sequencing": { "type":"array", "items":{ "type":"string", "enum": [ "Baseline surveillance (random sampling)", "Chronic (prolonged) infection surveillance", "Cluster/Outbreak investigation", "Domestic travel surveillance", "International travel surveillance", "Interstate/ interprovincial travel surveillance", "Intra-jurisdictional outbreak investigation", "Intra-state/ intra-provincial travel surveillance", "Longitudinal surveillance (repeat sampling of individuals)", "Multi-jurisdictional outbreak investigation", "Priority surveillance project", "Protocol testing experiment", "Re-infection surveillance", "Research", "Retrospective sequencing", "Sample has epidemiological link to Omicron Variant", "Sample has epidemiological link to Variant of Concern (VoC)", "Screening for Variants of Concern (VoC)", "Surveillance from international worker testing", "Surveillance of international border crossing by air travel or ground transport", "Surveillance of international border crossing by air travel", "Surveillance of international border crossing by ground transport", "Targeted surveillance (non-random sampling)", "Travel-associated surveillance", "Vaccine escape surveillance", "Viral passage experiment", "Not Applicable", "Missing", "Not Collected", "Not Provided", "Restricted Access" ] } }, "purpose_of_sequencing_details": { "type": [ "string", "null" ] }, "sequencing_instrument": { "enum": [ "BGI Genomics BGISEQ-500", "BGI Genomics", "Illumina Genome Analyzer II", "Illumina Genome Analyzer IIx", "Illumina Genome Analyzer", "Illumina HiScanSQ", "Illumina HiSeq 1000", "Illumina HiSeq 1500", "Illumina HiSeq 2000", "Illumina HiSeq 2500", "Illumina HiSeq 3000", "Illumina HiSeq 4000", "Illumina HiSeq X Five", "Illumina HiSeq X Ten", "Illumina HiSeq X", "Illumina HiSeq", "Illumina MiSeq", "Illumina MiniSeq", "Illumina NextSeq 2000", "Illumina NextSeq 500", "Illumina NextSeq 550", "Illumina NextSeq", "Illumina NovaSeq 6000", "Illumina NovaSeq", "Illumina iSeq 100", "Illumina iSeq", "Illumina", "Ion Torrent PGM", "Ion Torrent Proton", "Ion Torrent S5 XL", "Ion Torrent S5", "Ion Torrent", "MGI DNBSEQ-G400 FAST", "MGI DNBSEQ-G400", "MGI DNBSEQ-G50", "MGI DNBSEQ-T7", "MGI", "Oxford Nanopore GridION", "Oxford Nanopore MinION", "Oxford Nanopore PromethION", "Oxford Nanopore", "PacBio RS II", "PacBio RS", "PacBio Sequel II", "PacBio Sequel", "Pacific Biosciences", "Not Applicable", "Missing", "Not Collected", "Not Provided", "Restricted Access" ] }, "sequencing_protocol": { "type": [ "string", "null" ] }, "sequencing_date": { "anyOf": [ { "type": "string", "format": "date" }, { "type": "null" } ] }, "library_id": { "type": [ "string", "null" ] } }, "propertyNames": { "enum": [ "sequencing_instrument", "sequencing_date", "library_id", "purpose_of_sequencing", "purpose_of_sequencing_details", "sequencing_protocol" ] } }, "sequence_analysis": { "type": "object", "required": [ "consensus_sequence_software_name", "consensus_sequence_software_version", "raw_sequence_data_processing_method", "dehosting_method" ], "properties": { "consensus_sequence_software_name": { "type": [ "string", "null" ] }, "consensus_sequence_software_version": { "type": [ "string", "null" ] }, "raw_sequence_data_processing_method": { "type": [ "string", "null" ] }, "dehosting_method": { "type": [ "string", "null" ] }, "metrics": { "type": "object", "properties": { "breadth_of_coverage": { "anyOf": [ { "type": "string", "pattern": "^(100|\\d{1,2}(\\.\\d+)?)%$", "minLength": 2, "description": "The percentage of the reference genome covered by the sequenced data, to a prescribed depth.", "examples": [ "95%" ] }, { "enum": [ "Not Applicable", "Missing", "Not Collected", "Not Provided", "Restricted Access", null ] } ] }, "depth_of_coverage": { "anyOf": [ { "type": "string", "pattern": "^\\d+(\\.\\d+)?[xX]$", "minLength": 2, "description": "The average number of reads representing a given nucleotide in the reconstructed sequence.Provide value as a fold of coverage.", "examples": [ "400X" ] }, { "enum": [ "Not Applicable", "Missing", "Not Collected", "Not Provided", "Restricted Access", null ] } ] }, "consensus_genome_length": { "type": [ "integer", "null" ] }, "Ns_per_100kbp": { "type": [ "number", "null" ] } } }, "reference_genome_accession": { "type": [ "string", "null" ] }, "bioinformatics_protocol": { "type": [ "string", "null" ] } }, "propertyNames": { "enum": [ "consensus_sequence_software_name", "consensus_sequence_software_version", "raw_sequence_data_processing_method", "dehosting_method", "metrics", "reference_genome_accession", "bioinformatics_protocol" ] } }, "pathogen_diagnostic_testing": { "type": "object", "required": [ "gene_name", "diagnostic_pcr_ct_value", "diagnostic_pcr_ct_value_null_reason" ], "properties": { "gene_name": { "enum": [ "E gene (orf4)", "M gene (orf5)", "N gene (orf9)", "RdRp gene (nsp12)", "SARS-COV-2 5' UTR", "Spike gene (orf2)", "exoN gene (nsp14)", "hel gene (nsp13)", "nsp1 ", "nsp10 ", "nsp11", "nsp15", "nsp16", "nsp2 ", "nsp3 ", "nsp4 ", "nsp5 ", "nsp6 ", "nsp7 ", "nsp8 ", "nsp9 ", "orf10", "orf14", "orf1a (pp1a)", "orf1ab (rep)", "orf3a", "orf3b", "orf6 (ns6)", "orf7a", "orf7b (ns7b)", "orf8 (ns8)", "orf9b", "orf9c", "Not Applicable", "Missing", "Not Collected", "Not Provided", "Restricted Access" ] }, "diagnostic_pcr_ct_value": { "anyOf": [ { "type": "number", "minimum": 0 }, { "type": "null" } ] }, "diagnostic_pcr_ct_value_null_reason": { "enum": [ "Not Applicable", "Missing", "Not Collected", "Not Provided", "Restricted Access", null ] } }, "if": { "properties": { "diagnostic_pcr_ct_value": { "const": null } } }, "then": { "properties": { "diagnostic_pcr_ct_value_null_reason": { "enum": [ "Not Applicable", "Missing", "Not Collected", "Not Provided", "Restricted Access" ] } } }, "else": { "properties": { "diagnostic_pcr_ct_value_null_reason": { "const": null } } }, "propertyNames": { "enum": [ "gene_name", "diagnostic_pcr_ct_value", "diagnostic_pcr_ct_value_null_reason" ] } }, "lineage_analysis": { "type": "object", "properties": { "lineage_name": { "type": [ "string", "null" ] }, "lineage_analysis_software_name": { "type": [ "string", "null" ] }, "lineage_analysis_software_version": { "type": [ "string", "null" ] }, "lineage_analysis_software_data_version": { "type": [ "string", "null" ] }, "scorpio_call": { "type": [ "string", "null" ] }, "scorpio_version": { "type": [ "string", "null" ] }, "variant_designation": { "enum": [ "Variant of Concern (VOC)", "Variant of Interest (VOI)", "Not Applicable", "Missing", "Not Collected", "Not Provided", "Restricted Access", null ] }, "variant_evidence": { "enum": [ "RT-qPCR", "Sequencing", "Not Applicable", "Missing", "Not Collected", "Not Provided", "Restricted Access", null ] }, "variant_evidence_details": { "type": [ "string", "null" ] } }, "propertyNames": { "enum": [ "lineage_name", "lineage_analysis_software_name", "lineage_analysis_software_version", "lineage_analysis_software_data_version", "scorpio_call", "scorpio_version", "variant_designation", "variant_evidence", "variant_evidence_details" ] } } } } }