From ab1cc2b46ca17838f6fa173a922a955b6ff7f5b1 Mon Sep 17 00:00:00 2001 From: Damion Dooley Date: Wed, 28 Jul 2021 16:01:07 -0700 Subject: [PATCH] vocabulary update --- script/main.js | 2 +- template/canada_covid19/data.js | 471 +++++++++++++++++++++++++++---- template/canada_covid19/data.tsv | 171 +++++------ 3 files changed, 504 insertions(+), 140 deletions(-) diff --git a/script/main.js b/script/main.js index 2e027fd3..c61d0ff5 100644 --- a/script/main.js +++ b/script/main.js @@ -11,7 +11,7 @@ * main.html?template=test_template * */ -const VERSION = '0.13.31'; +const VERSION = '0.13.32'; const VERSION_TEXT = 'DataHarmonizer provenance: v' + VERSION; const TEMPLATES = { 'CanCOGeN Covid-19': {'folder': 'canada_covid19', 'status': 'published'}, diff --git a/template/canada_covid19/data.js b/template/canada_covid19/data.js index 6b4fd389..edeb5ce9 100644 --- a/template/canada_covid19/data.js +++ b/template/canada_covid19/data.js @@ -329,6 +329,11 @@ var DATA = [ { "field": "GISAID_accession" } + ], + "VirusSeq_Portal": [ + { + "field": "GISAID accession" + } ] } } @@ -399,7 +404,7 @@ var DATA = [ "exportField": { "NML_LIMS": [ { - "value": "APL-C" + "value": "CANCOGEN_CALGARY_PROV_LAB" } ] } @@ -415,11 +420,20 @@ var DATA = [ ] } }, + "Dynacare (Manitoba)": { + "exportField": { + "NML_LIMS": [ + { + "value": "Dynacare Manitoba" + } + ] + } + }, "Eastern Ontario Regional Laboratory Association": { "exportField": { "NML_LIMS": [ { - "value": "Eastern Ontario Regional Laboratory Association" + "value": "CANCOGEN_EORLA" } ] } @@ -428,7 +442,16 @@ var DATA = [ "exportField": { "NML_LIMS": [ { - "value": "Hamilton Health Sciences" + "value": "CANCOGEN_HAMILTON_HS" + } + ] + } + }, + "The Hospital for Sick Children (SickKids)": { + "exportField": { + "NML_LIMS": [ + { + "value": "CANCOGEN_SICK_KIDS_HOSPITAL" } ] } @@ -473,7 +496,7 @@ var DATA = [ "exportField": { "NML_LIMS": [ { - "value": "Mount Sinai Hospital" + "value": "CANCOGEN_MOUNT_SINAI" } ] } @@ -527,7 +550,7 @@ var DATA = [ "exportField": { "NML_LIMS": [ { - "value": "Ontario Institute for Cancer Research (OICR)" + "value": "CANCOGEN_OICR" } ] } @@ -554,7 +577,7 @@ var DATA = [ "exportField": { "NML_LIMS": [ { - "value": "Queen's University / Kingston Health Sciences Centre" + "value": "CANCOGEN_KINGSTON" } ] } @@ -572,7 +595,7 @@ var DATA = [ "exportField": { "NML_LIMS": [ { - "value": "St. John's Rehab at Sunnybrook Hospital" + "value": "CANCOGEN_SJRH" } ] } @@ -581,7 +604,7 @@ var DATA = [ "exportField": { "NML_LIMS": [ { - "value": "Sunnybrook Health Sciences Centre" + "value": "CANCOGEN_SUNNYBROOK" } ] } @@ -590,7 +613,7 @@ var DATA = [ "exportField": { "NML_LIMS": [ { - "value": "Unity Health Toronto" + "value": "CANCOGEN_UNITY_HEALTH" } ] } @@ -599,7 +622,7 @@ var DATA = [ "exportField": { "NML_LIMS": [ { - "value": "William Osler Health System" + "value": "CANCOGEN_WILLIAM_OSLER" } ] } @@ -709,6 +732,24 @@ var DATA = [ "BCCDC Public Health Laboratory": {}, "Canadore College": {}, "The Centre for Applied Genomics (TCAG)": {}, + "Dynacare (Manitoba)": { + "exportField": { + "NML_LIMS": [ + { + "value": "Dynacare Manitoba" + } + ] + } + }, + "The Hospital for Sick Children (SickKids)": { + "exportField": { + "NML_LIMS": [ + { + "value": "CANCOGEN_SICK_KIDS_HOSPITAL" + } + ] + } + }, "Laboratoire de sant\u00e9 publique du Qu\u00e9bec (LSPQ)": {}, "Manitoba Cadham Provincial Laboratory": {}, "McMaster University": {}, @@ -2325,6 +2366,11 @@ var DATA = [ { "field": "description" } + ], + "VirusSeq_Portal": [ + { + "field": "purpose of sampling details" + } ] } }, @@ -2382,6 +2428,7 @@ var DATA = [ "ontology_id": "OBI:0002754" }, "Nucleic acid": { + "ontology_id": "OBI:0001010", "exportField": { "NML_LIMS": [ { @@ -2392,6 +2439,7 @@ var DATA = [ } }, "Not Applicable": { + "ontology_id": "GENEPIO:0001619", "exportField": { "NML_LIMS": [ { @@ -2427,10 +2475,14 @@ var DATA = [ ] }, "schema:ItemList": { - "Acute": {}, + "Acute": { + "ontology_id": "HP_0011009" + }, "Convalescent": {}, "Familial": {}, - "Follow-up": {}, + "Follow-up": { + "ontology_id": "EFO_0009642" + }, "Previously Submitted": {} } }, @@ -4352,7 +4404,9 @@ var DATA = [ "RNA (ribo-depleted)": { "ontology_id": "OBI:0002627" }, - "mRNA (messenger RNA)": {}, + "mRNA (messenger RNA)": { + "ontology_id": "OBI REQUEST" + }, "mRNA (cDNA)": { "ontology_id": "OBI:0002754" } @@ -5276,6 +5330,7 @@ var DATA = [ }, "schema:ItemList": { "Ageusia (complete loss of taste)": { + "ontology_id": "HP:0041051", "exportField": { "NML_LIMS": [ { @@ -5339,6 +5394,7 @@ var DATA = [ } }, "Acute Respiratory Distress Syndrome": { + "ontology_id": "HP:0033677", "exportField": { "CNPHI": [ { @@ -5480,7 +5536,9 @@ var DATA = [ ] } }, - "Conjunctival injection": {}, + "Conjunctival injection": { + "ontology_id": "HP:0030953" + }, "Conjunctivitis (pink eye)": { "ontology_id": "HP_0000509", "exportField": { @@ -5496,7 +5554,9 @@ var DATA = [ ] } }, - "Coryza": {}, + "Coryza (rhinitis)": { + "ontology_id": "MP:0001867" + }, "Cough": { "ontology_id": "HP_0012735", "exportField": { @@ -5550,6 +5610,7 @@ var DATA = [ }, "schema:ItemList": { "Circumoral cyanosis (bluish around mouth)": { + "ontology_id": "HP:0032556", "exportField": { "NML_LIMS": [ { @@ -5610,7 +5671,9 @@ var DATA = [ ] } }, - "Dry gangrene": {}, + "Dry gangrene": { + "ontology_id": "MP:0031127" + }, "Encephalitis (brain inflammation)": { "ontology_id": "HP_0002383", "exportField": { @@ -5626,7 +5689,9 @@ var DATA = [ ] } }, - "Encephalopathy": {}, + "Encephalopathy": { + "ontology_id": "HP:0001298" + }, "Fatigue (tiredness)": { "ontology_id": "HP_0012378", "exportField": { @@ -5751,6 +5816,7 @@ var DATA = [ } }, "Malaise (general discomfort/unease)": { + "ontology_id": "HP:0033834", "exportField": { "NML_LIMS": [ { @@ -5759,7 +5825,9 @@ var DATA = [ ] } }, - "Meningismus/nuchal rigidity": {}, + "Meningismus/nuchal rigidity": { + "ontology_id": "HP:0031179" + }, "Muscle weakness": { "ontology_id": "HP_0001324", "exportField": { @@ -5795,6 +5863,7 @@ var DATA = [ }, "Otitis": {}, "Pain": { + "ontology_id": "HP:0012531", "schema:ItemList": { "Abdominal pain": { "ontology_id": "HP:0002027", @@ -5826,7 +5895,9 @@ var DATA = [ ] }, "schema:ItemList": { - "Pleuritic chest pain": {} + "Pleuritic chest pain": { + "ontology_id": "HP:0033771" + } } }, "Myalgia (muscle pain)": { @@ -5852,12 +5923,15 @@ var DATA = [ } }, "Pharyngeal exudate": {}, - "Pleural effusion": {}, + "Pleural effusion": { + "ontology_id": "HP:0002202" + }, "Pneumonia": { "ontology_id": "HP:0002090" }, "Prostration": {}, "Pseudo-chilblains": { + "ontology_id": "HP:0033696", "schema:ItemList": { "Pseudo-chilblains on fingers (covid fingers)": { "exportField": { @@ -5941,8 +6015,12 @@ var DATA = [ ] } }, - "Sneezing": {}, - "Sputum Production": {}, + "Sneezing": { + "ontology_id": "HP:0025095" + }, + "Sputum Production": { + "ontology_id": "HP:0033709" + }, "Stroke": { "ontology_id": "HP:0001297", "exportField": { @@ -5953,7 +6031,9 @@ var DATA = [ ] } }, - "Swollen Lymph Nodes": {}, + "Swollen Lymph Nodes": { + "ontology_id": "HP:0002716" + }, "Tachypnea (accelerated respiratory rate)": { "ontology_id": "HP_0002789", "exportField": { @@ -5964,7 +6044,9 @@ var DATA = [ ] } }, - "Vertigo (dizziness)": {}, + "Vertigo (dizziness)": { + "ontology_id": "HP:0002321" + }, "Vomiting (throwing up)": { "ontology_id": "HP_0002013", "exportField": { @@ -7325,6 +7407,11 @@ var DATA = [ { "field": "PH_REASON_FOR_SEQUENCING_DETAILS" } + ], + "VirusSeq_Portal": [ + { + "field": "purpose of sequencing details" + } ] } }, @@ -7471,7 +7558,7 @@ var DATA = [ ], "NML_LIMS": [ { - "field": "ANALYSIS" + "field": "PH_INSTRUMENT_CGN" } ], "VirusSeq_Portal": [ @@ -7641,6 +7728,11 @@ var DATA = [ { "field": "PH_TESTING_PROTOCOL" } + ], + "VirusSeq_Portal": [ + { + "field": "sequencing protocol" + } ] } }, @@ -7709,6 +7801,11 @@ var DATA = [ { "field": "raw sequence data processing method" } + ], + "VirusSeq_Portal": [ + { + "field": "raw sequence data processing method" + } ] } }, @@ -7730,6 +7827,11 @@ var DATA = [ { "field": "dehosting method" } + ], + "VirusSeq_Portal": [ + { + "field": "dehosting method" + } ] } }, @@ -7876,6 +7978,11 @@ var DATA = [ { "field": "breadth of coverage value" } + ], + "VirusSeq_Portal": [ + { + "field": "breadth of coverage value" + } ] } }, @@ -7902,6 +8009,11 @@ var DATA = [ { "field": "depth of coverage value" } + ], + "VirusSeq_Portal": [ + { + "field": "depth of coverage value" + } ] } }, @@ -8133,6 +8245,11 @@ var DATA = [ { "field": "reference genome accession" } + ], + "VirusSeq_Portal": [ + { + "field": "reference genome accession" + } ] } }, @@ -8159,6 +8276,11 @@ var DATA = [ { "field": "bioinformatics protocol" } + ], + "VirusSeq_Portal": [ + { + "field": "bioinformatics protocol" + } ] } } @@ -8352,6 +8474,11 @@ var DATA = [ { "field": "gene_name_1" } + ], + "VirusSeq_Portal": [ + { + "field": "gene name" + } ] }, "schema:ItemList": { @@ -8367,100 +8494,325 @@ var DATA = [ { "value": "E gene" } + ], + "BIOSAMPLE": [ + { + "value": "E (orf4)" + } ] } }, "M gene (orf5)": { - "ontology_id": "PR:P0DTC5" + "ontology_id": "PR:P0DTC5", + "exportField": { + "BIOSAMPLE": [ + { + "value": "M (orf5)" + } + ] + } }, "N gene (orf9)": { - "ontology_id": "PR:P0DTC9" + "ontology_id": "PR:P0DTC9", + "exportField": { + "BIOSAMPLE": [ + { + "value": "N (orf9)" + } + ] + } }, "Spike gene (orf2)": { - "ontology_id": "PR:P0DTC2" + "ontology_id": "PR:P0DTC2", + "exportField": { + "BIOSAMPLE": [ + { + "value": "S (orf2)" + } + ] + } }, "orf1ab (rep)": { "ontology_id": "PR:000050281", + "exportField": { + "BIOSAMPLE": [ + { + "value": "orf1ab (rep)" + } + ] + }, "schema:ItemList": { "orf1a (pp1a)": { "ontology_id": "PR:P0DTC1-1", + "exportField": { + "BIOSAMPLE": [ + { + "value": "orf1a (pp1a)" + } + ] + }, "schema:ItemList": { "nsp11": { - "ontology_id": "PR:000050280" + "ontology_id": "PR:000050280", + "exportField": { + "BIOSAMPLE": [ + { + "value": "nsp11" + } + ] + } } } }, "nsp1": { - "ontology_id": "PR:000050270" + "ontology_id": "PR:000050270", + "exportField": { + "BIOSAMPLE": [ + { + "value": "nsp1" + } + ] + } }, "nsp2": { - "ontology_id": "PR:000050271" + "ontology_id": "PR:000050271", + "exportField": { + "BIOSAMPLE": [ + { + "value": "nsp2" + } + ] + } }, "nsp3": { - "ontology_id": "PR:000050272" + "ontology_id": "PR:000050272", + "exportField": { + "BIOSAMPLE": [ + { + "value": "nsp3" + } + ] + } }, "nsp4": { - "ontology_id": "PR:000050273" + "ontology_id": "PR:000050273", + "exportField": { + "BIOSAMPLE": [ + { + "value": "nsp4" + } + ] + } }, "nsp5": { - "ontology_id": "PR:000050274" + "ontology_id": "PR:000050274", + "exportField": { + "BIOSAMPLE": [ + { + "value": "nsp5" + } + ] + } }, "nsp6": { - "ontology_id": "PR:000050275" + "ontology_id": "PR:000050275", + "exportField": { + "BIOSAMPLE": [ + { + "value": "nsp6" + } + ] + } }, "nsp7": { - "ontology_id": "PR:000050276" + "ontology_id": "PR:000050276", + "exportField": { + "BIOSAMPLE": [ + { + "value": "nsp7" + } + ] + } }, "nsp8": { - "ontology_id": "PR:000050277" + "ontology_id": "PR:000050277", + "exportField": { + "BIOSAMPLE": [ + { + "value": "nsp8" + } + ] + } }, "nsp9": { - "ontology_id": "PR:000050278" + "ontology_id": "PR:000050278", + "exportField": { + "BIOSAMPLE": [ + { + "value": "nsp9" + } + ] + } }, "nsp10": { - "ontology_id": "PR:000050279" + "ontology_id": "PR:000050279", + "exportField": { + "BIOSAMPLE": [ + { + "value": "nsp10" + } + ] + } }, "RdRp gene (nsp12)": { - "ontology_id": "PR:000050284" + "ontology_id": "PR:000050284", + "exportField": { + "BIOSAMPLE": [ + { + "value": "nsp12 (RdRp)" + } + ] + } }, "hel gene (nsp13)": { - "ontology_id": "PR:000050285" + "ontology_id": "PR:000050285", + "exportField": { + "BIOSAMPLE": [ + { + "value": "nsp13 (Hel)" + } + ] + } }, "exoN gene (nsp14)": { - "ontology_id": "PR:000050286" + "ontology_id": "PR:000050286", + "exportField": { + "BIOSAMPLE": [ + { + "value": "nsp14 (ExoN)" + } + ] + } }, "nsp15": { - "ontology_id": "PR:000050287" + "ontology_id": "PR:000050287", + "exportField": { + "BIOSAMPLE": [ + { + "value": "nsp15" + } + ] + } }, "nsp16": { - "ontology_id": "PR:000050288" + "ontology_id": "PR:000050288", + "exportField": { + "BIOSAMPLE": [ + { + "value": "nsp16" + } + ] + } } } }, "orf3a": { - "ontology_id": "PR:P0DTC3" + "ontology_id": "PR:P0DTC3", + "exportField": { + "BIOSAMPLE": [ + { + "value": "orf3a" + } + ] + } + }, + "orf3b": { + "exportField": { + "BIOSAMPLE": [ + { + "value": "orf3b" + } + ] + } }, - "orf3b": {}, "orf6 (ns6)": { - "ontology_id": "PR:P0DTC6" + "ontology_id": "PR:P0DTC6", + "exportField": { + "BIOSAMPLE": [ + { + "value": "orf6 (ns6)" + } + ] + } }, "orf7a": { - "ontology_id": "PR:P0DTC7" + "ontology_id": "PR:P0DTC7", + "exportField": { + "BIOSAMPLE": [ + { + "value": "orf7a" + } + ] + } }, "orf7b (ns7b)": { - "ontology_id": "PR:P0DTD8" + "ontology_id": "PR:P0DTD8", + "exportField": { + "BIOSAMPLE": [ + { + "value": "orf7b (ns7b)" + } + ] + } }, "orf8 (ns8)": { - "ontology_id": "PR:P0DTC8" + "ontology_id": "PR:P0DTC8", + "exportField": { + "BIOSAMPLE": [ + { + "value": "orf8 (ns8)" + } + ] + } }, "orf9b": { - "ontology_id": "PR:P0DTD2" + "ontology_id": "PR:P0DTD2", + "exportField": { + "BIOSAMPLE": [ + { + "value": "orf9b" + } + ] + } + }, + "orf9c": { + "exportField": { + "BIOSAMPLE": [ + { + "value": "orf9c" + } + ] + } }, - "orf9c": {}, "orf10": { - "ontology_id": "PR:A0A663DJA2" + "ontology_id": "PR:A0A663DJA2", + "exportField": { + "BIOSAMPLE": [ + { + "value": "orf10" + } + ] + } + }, + "orf14": { + "exportField": { + "BIOSAMPLE": [ + { + "value": "orf14" + } + ] + } }, - "orf14": {}, "SARS-COV-2 5' UTR": {} } }, @@ -8482,7 +8834,7 @@ var DATA = [ "fieldName": "diagnostic pcr Ct value 1", "capitalize": "", "ontology_id": "GENEPIO_0001509", - "datatype": "xs:token", + "datatype": "xs:decimal", "source": "", "dataStatus": null, "xs:minInclusive": "", @@ -8506,6 +8858,11 @@ var DATA = [ { "field": "diagnostic_PCR_CT_value_1" } + ], + "VirusSeq_Portal": [ + { + "field": "diagnostic pcr Ct value" + } ] } }, @@ -8565,7 +8922,7 @@ var DATA = [ "fieldName": "diagnostic pcr Ct value 2", "capitalize": "", "ontology_id": "GENEPIO_0001512", - "datatype": "xs:token", + "datatype": "xs:decimal", "source": "", "dataStatus": null, "xs:minInclusive": "", @@ -8643,7 +9000,7 @@ var DATA = [ "fieldName": "diagnostic pcr Ct value 3", "capitalize": "", "ontology_id": "GENEPIO_0001515", - "datatype": "xs:token", + "datatype": "xs:decimal", "source": "", "dataStatus": null, "xs:minInclusive": "", diff --git a/template/canada_covid19/data.tsv b/template/canada_covid19/data.tsv index 5cb896e4..13d3e43d 100644 --- a/template/canada_covid19/data.tsv +++ b/template/canada_covid19/data.tsv @@ -12,7 +12,7 @@ GENEPIO_0001136 Database Identifiers bioproject accession xs:token UPPER T GENEPIO_0001139 Database Identifiers biosample accession xs:token UPPER The identifier assigned to a BioSample in INSDC archives. Store the accession returned from the BioSample submission. NCBI BioSamples will have the prefix SAMN. SAMN14180202 BioSample Accession PH_BIOSAMPLE_ACCESSION GENEPIO_0001142 Database Identifiers SRA accession xs:token UPPER The Sequence Read Archive (SRA) identifier linking raw read data, methodological metadata and quality control metrics submitted to the INSDC. Store the accession assigned to the submitted "run". NCBI-SRA accessions start with SRR. SRR11177792 SRA Accession PH_SRA_ACCESSION GENEPIO_0001145 Database Identifiers GenBank accession xs:token UPPER The GenBank identifier assigned to the sequence in the INSDC archives. Store the accession returned from a GenBank submission (viral genome assembly). MN908947.3 GenBank Accession GenBank accession -GENEPIO_0001147 Database Identifiers GISAID accession xs:token UPPER The GISAID accession number assigned to the sequence. Store the accession returned from the GISAID submission. EPI_ISL_436489 GISAID Accession (if known) SUBMISSIONS - GISAID Accession ID GISAID_accession +GENEPIO_0001147 Database Identifiers GISAID accession xs:token UPPER The GISAID accession number assigned to the sequence. Store the accession returned from the GISAID submission. EPI_ISL_436489 GISAID Accession (if known) SUBMISSIONS - GISAID Accession ID GISAID_accession GISAID accession GENEPIO_0001150 Sample collection and processing GENEPIO_0001153 Sample collection and processing sample collected by select Not Applicable; Missing; Not Collected; Not Provided; Restricted Access required The name of the agency that collected the original sample. The name of the sample collector should be written out in full, (with minor exceptions) and be consistent across multple submissions e.g. Public Health Agency of Canada, Public Health Ontario, BC Centre for Disease Control. The sample collector specified is at the discretion of the data provider (i.e. may be hospital, provincial public health lab, or other). BC Centre for Disease Control Originating lab Lab Name CUSTOMER collected_by sample collected by GENEPIO_0001156 Sample collection and processing sample collector contact email xs:token The email address of the contact responsible for follow-up regarding the sample. The email address can represent a specific individual or lab e.g. johnnyblogs@lab.ca, or RespLab@lab.ca RespLab@lab.ca sample collector contact email @@ -29,7 +29,7 @@ GENEPIO_0001189 Sample collection and processing geo_loc_name (city) xs:token GENEPIO_0001191 Sample collection and processing organism select Not Applicable; Missing; Not Collected; Not Provided; Restricted Access required Taxonomic name of the organism. Use "Severe acute respiratory syndrome coronavirus 2". This value is provided in the template. Severe acute respiratory syndrome coronavirus 2 Pathogen HC_CURRENT_ID organism organism GENEPIO_0001195 Sample collection and processing isolate xs:token Not Applicable; Missing; Not Collected; Not Provided; Restricted Access required Identifier of the specific isolate. Provide the GISAID virus name, which should be written in the format “hCov-19/CANADA/xxxxx/2020”. hCov-19/CANADA/prov_rona_99/2020 Virus name GISAID Virus Name RESULT - CANCOGEN_SUBMISSIONS isolate;GISAID_virus_name isolate GENEPIO_0001198 Sample collection and processing purpose of sampling select Not Applicable; Missing; Not Collected; Not Provided; Restricted Access required The reason that the sample was collected. The reason a sample was collected may provide information about potential biases in sampling strategy. Provide the purpose of sampling from the picklist in the template. Most likely, the sample was collected for Diagnostic testing. The reason why a sample was originally collected may differ from the reason why it was selected for sequencing, which should be indicated in the "purpose of sequencing" field. Diagnostic testing Reason for Sampling HC_SAMPLE_CATEGORY purpose_of_sampling purpose of sampling -GENEPIO_0001200 Sample collection and processing purpose of sampling details xs:token Not Applicable; Missing; Not Collected; Not Provided; Restricted Access required The description of why the sample was collected, providing specific details. Provide an expanded description of why the sample was collected using free text. The description may include the importance of the sample for a particular public health investigation/surveillance activity/research question. If details are not available, provide a null value. The sample was collected to investigate the prevalence of variants associated with mink-to-human transmission in Canada. Details on the Reason for Sampling PH_SAMPLING_DETAILS description +GENEPIO_0001200 Sample collection and processing purpose of sampling details xs:token Not Applicable; Missing; Not Collected; Not Provided; Restricted Access required The description of why the sample was collected, providing specific details. Provide an expanded description of why the sample was collected using free text. The description may include the importance of the sample for a particular public health investigation/surveillance activity/research question. If details are not available, provide a null value. The sample was collected to investigate the prevalence of variants associated with mink-to-human transmission in Canada. Details on the Reason for Sampling PH_SAMPLING_DETAILS description purpose of sampling details GENEPIO_0001204 Sample collection and processing NML submitted specimen type select required The type of specimen submitted to the National Microbiology Laboratory (NML) for testing. This information is required for upload through the CNPHI LaSER system. Select the specimen type from the pick list provided. If sequence data is being submitted rather than a specimen for testing, select “Not Applicable”. swab Specimen Type PH_SPECIMEN_TYPE GENEPIO_0001209 Sample collection and processing NML related specimen relationship type select The relationship of the related specimen to the previous National Microbiology Laboratory (NML) submission. Provide the specimen type of the original sample submitted from the pick list provided, so that additional specimen testing can be tracked in the system. Follow-up Related Specimen ID;Related Specimen Relationship Type GENEPIO_0001211 Sample collection and processing anatomical material select Not Applicable; Missing; Not Collected; Not Provided; Restricted Access required A substance obtained from an anatomical part of an organism e.g. tissue, blood. Provide a descriptor if an anatomical material was sampled. Use the picklist provided in the template. If a desired term is missing from the picklist, contact emma.griffiths@bccdc.ca. If not applicable, do not leave blank. Choose a null value. Blood Specimen source Anatomical Material PH_ISOLATION_SITE_DESC isolation_source;anatomical_material anatomical material @@ -95,29 +95,29 @@ GENEPIO_0001440 Host reinfection information prior SARS-CoV-2 antiviral treatme GENEPIO_0001441 Sequencing GENEPIO_0001445 Sequencing purpose of sequencing multiple Not Applicable; Missing; Not Collected; Not Provided; Restricted Access required The reason that the sample was sequenced. The reason why a sample was originally collected may differ from the reason why it was selected for sequencing. The reason a sample was sequenced may provide information about potential biases in sequencing strategy. Provide the purpose of sequencing from the picklist in the template. The reason for sample collection should be indicated in the "purpose of sampling" field. Baseline surveillance (random sampling) Reason for Sequencing PH_REASON_FOR_SEQUENCING purpose_of_sequencing purpose of sequencing -GENEPIO_0001446 Sequencing purpose of sequencing details xs:token Not Applicable; Missing; Not Collected; Not Provided; Restricted Access required The description of why the sample was sequenced providing specific details. Provide an expanded description of why the sample was sequenced using free text. The description may include the importance of the sequences for a particular public health investigation/surveillance activity/research question. Suggested standardized descriotions include: Screened for S gene target failure (S dropout), Screened for mink variants, Screened for B.1.1.7 variant, Screened for B.1.135 variant, Screened for P.1 variant, Screened due to travel history, Screened due to close contact with infected individual, Assessing public health control measures, Determining early introductions and spread, Investigating airline-related exposures, Investigating temporary foreign worker, Investigating remote regions, Investigating health care workers, Investigating schools/universities, Investigating reinfection. Screened for S gene target failure (S dropout) Details on the Reason for Sequencing PH_REASON_FOR_SEQUENCING_DETAILS +GENEPIO_0001446 Sequencing purpose of sequencing details xs:token Not Applicable; Missing; Not Collected; Not Provided; Restricted Access required The description of why the sample was sequenced providing specific details. Provide an expanded description of why the sample was sequenced using free text. The description may include the importance of the sequences for a particular public health investigation/surveillance activity/research question. Suggested standardized descriotions include: Screened for S gene target failure (S dropout), Screened for mink variants, Screened for B.1.1.7 variant, Screened for B.1.135 variant, Screened for P.1 variant, Screened due to travel history, Screened due to close contact with infected individual, Assessing public health control measures, Determining early introductions and spread, Investigating airline-related exposures, Investigating temporary foreign worker, Investigating remote regions, Investigating health care workers, Investigating schools/universities, Investigating reinfection. Screened for S gene target failure (S dropout) Details on the Reason for Sequencing PH_REASON_FOR_SEQUENCING_DETAILS purpose of sequencing details GENEPIO_0001447 Sequencing sequencing date xs:date Not Applicable; Missing; Not Collected; Not Provided; Restricted Access The date the sample was sequenced. ISO 8601 standard "YYYY-MM-DD". 2020-06-22 sequencing date GENEPIO_0001448 Sequencing library ID xs:token recommended The user-specified identifier for the library prepared for sequencing. The library name should be unique, and can be an autogenerated ID from your LIMS, or modification of the isolate ID. XYZ_123345 library ID GENEPIO_0001449 Sequencing amplicon size xs:token The length of the amplicon generated by PCR amplification. Provide the amplicon size, including the units. 300bp amplicon size GENEPIO_0001450 Sequencing library preparation kit xs:token The name of the DNA library preparation kit used to generate the library being sequenced. Provide the name of the library preparation kit used. Nextera XT library preparation kit GENEPIO_0001451 Sequencing flow cell barcode xs:token The barcode of the flow cell used for sequencing. Provide the barcode of the flow cell used for sequencing the sample. FAB06069 flow cell barcode -GENEPIO_0001452 Sequencing sequencing instrument multiple Not Applicable; Missing; Not Collected; Not Provided; Restricted Access required The model of the sequencing instrument used. Select a sequencing instrument from the picklist provided in the template. MinIon Sequencing technology Sequencing Instrument ANALYSIS sequencing instrument +GENEPIO_0001452 Sequencing sequencing instrument multiple Not Applicable; Missing; Not Collected; Not Provided; Restricted Access required The model of the sequencing instrument used. Select a sequencing instrument from the picklist provided in the template. MinIon Sequencing technology Sequencing Instrument PH_INSTRUMENT_CGN sequencing instrument GENEPIO_0001453 Sequencing sequencing protocol name xs:token recommended The name and version number of the sequencing protocol used. Provide the name and version of the sequencing protocol e.g. 1D_DNA_MinION https://www.protocols.io/view/covid-19-artic-v3-illumina-library-construction-an-bibtkann Sequencing Protocol Name sequencing protocol name -GENEPIO_0001454 Sequencing sequencing protocol xs:token The protocol used to generate the sequence. Provide a free text description of the methods and materials used to generate the sequence. Suggested text, fill in information where indicated.: "Viral sequencing was performed following a tiling amplicon strategy using the primer scheme. Sequencing was performed using a sequencing instrument. Libraries were prepared using library kit. " Genomes were generated through amplicon sequencing of 1200 bp amplicons with Freed schema primers. Libraries were created using Illumina DNA Prep kits, and sequence data was produced using Miseq Micro v2 (500 cycles) sequencing kits. PH_TESTING_PROTOCOL +GENEPIO_0001454 Sequencing sequencing protocol xs:token The protocol used to generate the sequence. Provide a free text description of the methods and materials used to generate the sequence. Suggested text, fill in information where indicated.: "Viral sequencing was performed following a tiling amplicon strategy using the primer scheme. Sequencing was performed using a sequencing instrument. Libraries were prepared using library kit. " Genomes were generated through amplicon sequencing of 1200 bp amplicons with Freed schema primers. Libraries were created using Illumina DNA Prep kits, and sequence data was produced using Miseq Micro v2 (500 cycles) sequencing kits. PH_TESTING_PROTOCOL sequencing protocol GENEPIO_0001455 Sequencing sequencing kit number xs:token The manufacturer's kit number. Alphanumeric value. AB456XYZ789 sequencing kit number GENEPIO_0001456 Sequencing amplicon pcr primer scheme xs:token The specifications of the primers (primer sequences, binding positions, fragment size generated etc) used to generate the amplicons to be sequenced. Provide the name and version of the primer scheme used to generate the amplicons for sequencing. https://github.com/joshquick/artic-ncov2019/blob/master/primer_schemes/nCoV-2019/V3/nCoV-2019.tsv amplicon pcr primer scheme GENEPIO_0001457 Bioinformatics and QC metrics -GENEPIO_0001458 Bioinformatics and QC metrics raw sequence data processing method xs:token recommended The names of the software and version number used for raw data processing such as removing barcodes, adapter trimming, filtering etc. Provide the software name followed by the version e.g. Trimmomatic v. 0.38, Porechop v. 0.2.3 Porechop 0.2.3 raw sequence data processing method -GENEPIO_0001459 Bioinformatics and QC metrics dehosting method xs:token The method used to remove host reads from the pathogen sequence. Provide the name and version number of the software used to remove host reads. Nanostripper dehosting method +GENEPIO_0001458 Bioinformatics and QC metrics raw sequence data processing method xs:token recommended The names of the software and version number used for raw data processing such as removing barcodes, adapter trimming, filtering etc. Provide the software name followed by the version e.g. Trimmomatic v. 0.38, Porechop v. 0.2.3 Porechop 0.2.3 raw sequence data processing method raw sequence data processing method +GENEPIO_0001459 Bioinformatics and QC metrics dehosting method xs:token The method used to remove host reads from the pathogen sequence. Provide the name and version number of the software used to remove host reads. Nanostripper dehosting method dehosting method GENEPIO_0001460 Bioinformatics and QC metrics consensus sequence name xs:token The name of the consensus sequence. Provide the name and version number of the consensus sequence. ncov123assembly3 consensus sequence name GENEPIO_0001461 Bioinformatics and QC metrics consensus sequence filename xs:token The name of the consensus sequence file. Provide the name and version number of the consensus sequence FASTA file. ncov123assembly.fasta consensus sequence filename GENEPIO_0001462 Bioinformatics and QC metrics consensus sequence filepath xs:token The filepath of the consesnsus sequence file. Provide the filepath of the consensus sequence FASTA file. /User/Documents/RespLab/Data/ncov123assembly.fasta consensus sequence filepath GENEPIO_0001463 Bioinformatics and QC metrics consensus sequence software name xs:token required The name of software used to generate the consensus sequence. Provide the name of the software used to generate the consensus sequence. Ivar consensus sequence PH_CONSENSUS_SEQUENCE consensus sequence software name GENEPIO_0001469 Bioinformatics and QC metrics consensus sequence software version xs:token required The version of the software used to generate the consensus sequence. Provide the version of the software used to generate the consensus sequence. 1.3 consensus sequence PH_CONSENSUS_SEQUENCE_VERSION consensus sequence software version -GENEPIO_0001472 Bioinformatics and QC metrics breadth of coverage value xs:token The percentage of the reference genome covered by the sequenced data, to a prescribed depth. Provide value as a percent. 95% breadth of coverage value -GENEPIO_0001474 Bioinformatics and QC metrics depth of coverage value xs:token The average number of reads representing a given nucleotide in the reconstructed sequence. Provide value as a fold of coverage. 400x Coverage depth of coverage value +GENEPIO_0001472 Bioinformatics and QC metrics breadth of coverage value xs:token The percentage of the reference genome covered by the sequenced data, to a prescribed depth. Provide value as a percent. 95% breadth of coverage value breadth of coverage value +GENEPIO_0001474 Bioinformatics and QC metrics depth of coverage value xs:token The average number of reads representing a given nucleotide in the reconstructed sequence. Provide value as a fold of coverage. 400x Coverage depth of coverage value depth of coverage value GENEPIO_0001475 Bioinformatics and QC metrics depth of coverage threshold xs:token The threshold used as a cut-off for the depth of coverage. Provide the threshold fold coverage. 100x depth of coverage threshold GENEPIO_0001476 Bioinformatics and QC metrics r1 fastq filename xs:token recommended The user-specified filename of the r1 FASTQ file. Provide the r1 FASTQ filename. ABC123_S1_L001_R1_001.fastq.gz r1 fastq filename GENEPIO_0001477 Bioinformatics and QC metrics r2 fastq filename xs:token recommended The user-specified filename of the r2 FASTQ file. Provide the r2 FASTQ filename. ABC123_S1_L001_R2_001.fastq.gz r2 fastq filename @@ -128,8 +128,8 @@ GENEPIO_0001481 Bioinformatics and QC metrics fast5 filepath xs:token The GENEPIO_0001482 Bioinformatics and QC metrics number of base pairs sequenced xs:nonNegativeInteger The number of total base pairs generated by the sequencing process. Provide a numerical value (no need to include units). 387566 number of base pairs sequenced GENEPIO_0001483 Bioinformatics and QC metrics consensus genome length xs:nonNegativeInteger Size of the reconstructed genome described as the number of base pairs. Provide a numerical value (no need to include units). 38677 consensus genome length GENEPIO_0001484 Bioinformatics and QC metrics Ns per 100 kbp xs:decimal 0 The number of N symbols present in the consensus fasta sequence, per 100kbp of sequence. Provide a numerical value (no need to include units). 330 Ns per 100 kbp -GENEPIO_0001485 Bioinformatics and QC metrics reference genome accession xs:token A persistent, unique identifier of a genome database entry. Provide the accession number of the reference genome. NC_045512.2 reference genome accession -GENEPIO_0001489 Bioinformatics and QC metrics bioinformatics protocol xs:token The name and version number of the bioinformatics protocol used. Further details regarding the methods used to process raw data, and/or generate assemblies, and/or generate consensus sequences can be provided in an SOP or protocol. Provide the name and version number of the protocol. https://www.protocols.io/groups/cphln-sarscov2-sequencing-consortium/members Bioinformatics Protocol bioinformatics protocol +GENEPIO_0001485 Bioinformatics and QC metrics reference genome accession xs:token A persistent, unique identifier of a genome database entry. Provide the accession number of the reference genome. NC_045512.2 reference genome accession reference genome accession +GENEPIO_0001489 Bioinformatics and QC metrics bioinformatics protocol xs:token The name and version number of the bioinformatics protocol used. Further details regarding the methods used to process raw data, and/or generate assemblies, and/or generate consensus sequences can be provided in an SOP or protocol. Provide the name and version number of the protocol. https://www.protocols.io/groups/cphln-sarscov2-sequencing-consortium/members Bioinformatics Protocol bioinformatics protocol bioinformatics protocol GENEPIO_0001498 Lineage and Variant information GENEPIO_0001500 Lineage and Variant information lineage/clade name xs:token The name of the lineage or clade. Provide the Pangolin or Nextstrain lineage/clade name. B.1.1.7 PH_LINEAGE_CLADE_NAME GENEPIO_0001501 Lineage and Variant information lineage/clade analysis software name xs:token The name of the software used to determine the lineage/clade. Provide the name of the software used to determine the lineage/clade. Pangolin PH_LINEAGE_CLADE_SOFTWARE @@ -138,15 +138,15 @@ GENEPIO_0001503 Lineage and Variant information variant designation select Not GENEPIO_0001504 Lineage and Variant information variant evidence select Not Applicable; Missing; Not Collected; Not Provided; Restricted Access The evidence used to make the variant determination. Select whether the sample was screened using RT-qPCR or by sequencing from the pick list. RT-qPCR PH_VARIANT_EVIDENCE GENEPIO_0001505 Lineage and Variant information variant evidence details xs:token Details about the evidence used to make the variant determination. Provide the assay and list the set of lineage-defining mutations used to make the variant determination. If there are mutations of interest/concern observed in addition to lineage-defining mutations, describe those here. Lineage-defining mutations: ORF1ab (K1655N), Spike (K417N, E484K, N501Y, D614G, A701V), N (T205I), E (P71L). PH_VARIANT_EVIDENCE_DETAILS GENEPIO_0001506 Pathogen diagnostic testing -GENEPIO_0001507 Pathogen diagnostic testing gene name 1 select Not Applicable; Missing; Not Collected; Not Provided; Restricted Access The name of the gene used in the diagnostic RT-PCR test. Provide the full name of the gene used in the test. The gene symbol (short form of gene name) can also be provided. Standardized gene names and symbols can be found in the Gene Ontology using this look-up service: https://bit.ly/2Sq1LbI E gene (orf4) Gene Target 1 SUBMITTED_RESLT - Gene Target #1 gene_name_1 +GENEPIO_0001507 Pathogen diagnostic testing gene name 1 select Not Applicable; Missing; Not Collected; Not Provided; Restricted Access The name of the gene used in the diagnostic RT-PCR test. Provide the full name of the gene used in the test. The gene symbol (short form of gene name) can also be provided. Standardized gene names and symbols can be found in the Gene Ontology using this look-up service: https://bit.ly/2Sq1LbI E gene (orf4) Gene Target 1 SUBMITTED_RESLT - Gene Target #1 gene_name_1 gene name GENEPIO_0001508 Pathogen diagnostic testing diagnostic pcr protocol 1 xs:token The name and version number of the protocol used for diagnostic marker amplification. The name and version number of the protocol used for carrying out a diagnostic PCR test. This information can be compared to sequence data for evaluation of performance and quality control. EGenePCRTest 2 -GENEPIO_0001509 Pathogen diagnostic testing diagnostic pcr Ct value 1 xs:token The Ct value result from a diagnostic SARS-CoV-2 RT-PCR test. Provide the CT value of the sample from the diagnostic RT-PCR test. 21 Gene Target 1 CT Value SUBMITTED_RESLT - Gene Target #1 CT Value diagnostic_PCR_CT_value_1 +GENEPIO_0001509 Pathogen diagnostic testing diagnostic pcr Ct value 1 xs:decimal The Ct value result from a diagnostic SARS-CoV-2 RT-PCR test. Provide the CT value of the sample from the diagnostic RT-PCR test. 21 Gene Target 1 CT Value SUBMITTED_RESLT - Gene Target #1 CT Value diagnostic_PCR_CT_value_1 diagnostic pcr Ct value GENEPIO_0001510 Pathogen diagnostic testing gene name 2 select gene name 1 Not Applicable; Missing; Not Collected; Not Provided; Restricted Access The name of the gene used in the diagnostic RT-PCR test. Provide the full name of another gene used in an RT-PCR test. The gene symbol (short form of gene name) can also be provided. Standardized gene names and symbols can be found in the Gene Ontology using this look-up service: https://bit.ly/2Sq1LbI RdRp gene (nsp12) Gene Target 2 SUBMITTED_RESLT - Gene Target #2 gene_name_2 GENEPIO_0001511 Pathogen diagnostic testing diagnostic pcr protocol 2 xs:token The name and version number of the protocol used for diagnostic marker amplification. The name and version number of the protocol used for carrying out a second diagnostic PCR test. This information can be compared to sequence data for evaluation of performance and quality control. RdRpGenePCRTest 3 -GENEPIO_0001512 Pathogen diagnostic testing diagnostic pcr Ct value 2 xs:token The Ct value result from a diagnostic SARS-CoV-2 RT-PCR test. Provide the CT value of the sample from the second diagnostic RT-PCR test. 36 Gene Target 2 CT Value SUBMITTED_RESLT - Gene Target #2 CT Value diagnostic_PCR_CT_value_2 +GENEPIO_0001512 Pathogen diagnostic testing diagnostic pcr Ct value 2 xs:decimal The Ct value result from a diagnostic SARS-CoV-2 RT-PCR test. Provide the CT value of the sample from the second diagnostic RT-PCR test. 36 Gene Target 2 CT Value SUBMITTED_RESLT - Gene Target #2 CT Value diagnostic_PCR_CT_value_2 GENEPIO_0001513 Pathogen diagnostic testing gene name 3 select gene name 1 Not Applicable; Missing; Not Collected; Not Provided; Restricted Access The name of the gene used in the diagnostic RT-PCR test. Provide the full name of another gene used in an RT-PCR test. The gene symbol (short form of gene name) can also be provided. Standardized gene names and symbols can be found in the Gene Ontology using this look-up service: https://bit.ly/2Sq1LbI RdRp gene (nsp12) Gene Target 3 SUBMITTED_RESLT - Gene Target #3 GENEPIO_0001514 Pathogen diagnostic testing diagnostic pcr protocol 3 xs:token The name and version number of the protocol used for diagnostic marker amplification. The name and version number of the protocol used for carrying out a second diagnostic PCR test. This information can be compared to sequence data for evaluation of performance and quality control. RdRpGenePCRTest 3 -GENEPIO_0001515 Pathogen diagnostic testing diagnostic pcr Ct value 3 xs:token The Ct value result from a diagnostic SARS-CoV-2 RT-PCR test. Provide the CT value of the sample from the second diagnostic RT-PCR test. 30 Gene Target 3 CT Value SUBMITTED_RESLT - Gene Target #3 CT Value +GENEPIO_0001515 Pathogen diagnostic testing diagnostic pcr Ct value 3 xs:decimal The Ct value result from a diagnostic SARS-CoV-2 RT-PCR test. Provide the CT value of the sample from the second diagnostic RT-PCR test. 30 Gene Target 3 CT Value SUBMITTED_RESLT - Gene Target #3 CT Value GENEPIO_0001516 Contributor acknowledgement GENEPIO_0001517 Contributor acknowledgement authors xs:token recommended Names of individuals contributing to the processes of sample collection, sequence generation, analysis, and data submission. Include the first and last names of all individuals that should be attributed, separated by a comma. Tejinder Singh, Fei Hu, Joe Blogs Authors Authors PH_CANCOGEN_AUTHORS GENEPIO_0001518 Contributor acknowledgement DataHarmonizer provenance provenance The DataHarmonizer software version provenance. The current software version information will be automatically generated in this field after the user utilizes the "validate" function. This information will be generated regardless as to whether the row is valid of not. DataHarmonizer provenance: v0.13.21 DataHarmonizer provenance Additional Comments HC_COMMENTS @@ -185,19 +185,19 @@ UO:0000033 sample collection date precision day Day OBI:0000895 biomaterial extracted RNA (total) OBI:0000869 biomaterial extracted RNA (poly-A) OBI:0002627 biomaterial extracted RNA (ribo-depleted) - biomaterial extracted mRNA (messenger RNA) +OBI REQUEST biomaterial extracted mRNA (messenger RNA) OBI:0002754 biomaterial extracted mRNA (cDNA) signs and symptoms Abnormal lung auscultation HP:0000223 signs and symptoms Abnormality of taste sensation SENSE_OF_TASTE - Abnormality of taste sensation Ageusia (complete loss of taste) AGEUSIA +HP:0041051 Abnormality of taste sensation Ageusia (complete loss of taste) AGEUSIA HP:0031249 Abnormality of taste sensation Parageusia (distorted sense of taste) PARAGEUSIA HP_0000224 Abnormality of taste sensation Hypogeusia (reduced sense of taste) HYPOGEUSIA HP:0004408 signs and symptoms Abnormality of the sense of smell SENSE_OF_SMELL HP_0000458 Abnormality of the sense of smell Anosmia (lost sense of smell) ANOSMIA HP_0004409 Abnormality of the sense of smell Hyposmia (reduced sense of smell) HYPOSMIA - signs and symptoms Acute Respiratory Distress Syndrome ARDS +HP:0033677 signs and symptoms Acute Respiratory Distress Syndrome ARDS HP:0011446 signs and symptoms Altered mental status ALTERED_CONSCIOUS HP:0011675 signs and symptoms Arrhythmia HP:0100543 Altered mental status Cognitive impairment COGNITIVE @@ -211,24 +211,24 @@ HP_0025406 signs and symptoms Asthenia (generalized weakness) ASTHE HP:0031352 signs and symptoms Chest tightness or pressure CHEST_TIGHT HP:0025145 Chest tightness or pressure Rigors (fever shakes) RIGORS HP_0025143 signs and symptoms Chills (sudden cold sensation) Chills CHILLS - signs and symptoms Conjunctival injection +HP:0030953 signs and symptoms Conjunctival injection HP_0000509 signs and symptoms Conjunctivitis (pink eye) Conjunctivitis CONJUNCTIVITIS - signs and symptoms Coryza +MP:0001867 signs and symptoms Coryza (rhinitis) HP_0012735 signs and symptoms Cough COUGH HP:0031246 Cough Nonproductive cough (dry cough) NONPRODUCT_COUGH HP:0031245 Cough Productive cough (wet cough) PRODUCTIVE_COUGH HP:0000961 signs and symptoms Cyanosis (blueish skin discolouration) CYANOSIS HP:0001063 Cyanosis (blueish skin discolouration) Acrocyanosis ACROCYANOS - Acrocyanosis Circumoral cyanosis (bluish around mouth) CIRCUMORAL_CYANOSIS +HP:0032556 Acrocyanosis Circumoral cyanosis (bluish around mouth) CIRCUMORAL_CYANOSIS Acrocyanosis Cyanotic face (bluish face) CYANOTIC_FACE Cyanosis (blueish skin discolouration) Central Cyanosis Central Cyanosis Cyanotic lips (bluish lips) CYANOTIC_LIPS Cyanosis (blueish skin discolouration) Peripheral Cyanosis HP_0002094 signs and symptoms Dyspnea (breathing difficulty) DYSPNEA HP_0002014 signs and symptoms Diarrhea (watery stool) Diarrhea, watery DIARRHEA - signs and symptoms Dry gangrene +MP:0031127 signs and symptoms Dry gangrene HP_0002383 signs and symptoms Encephalitis (brain inflammation) Encephalitis ENCEPHALITIS - signs and symptoms Encephalopathy +HP:0001298 signs and symptoms Encephalopathy HP_0012378 signs and symptoms Fatigue (tiredness) Fatigue FATIGUE HP_0001945 signs and symptoms Fever FEVER Fever Fever (>=38°C) Fever @@ -243,25 +243,25 @@ HP_0012418 signs and symptoms Hypoxemia (low blood oxygen) HYPOXEMI HP:0011029 signs and symptoms Internal hemorrhage (internal bleeding) INTERNAL_HEMORRHAGE NCIT:C121416 signs and symptoms Loss of Fine Movements LOSS_OF_FINE_MOVE HP_0004396 signs and symptoms Low appetite LOW_APPETITE - signs and symptoms Malaise (general discomfort/unease) MALAISE - signs and symptoms Meningismus/nuchal rigidity +HP:0033834 signs and symptoms Malaise (general discomfort/unease) MALAISE +HP:0031179 signs and symptoms Meningismus/nuchal rigidity HP_0001324 signs and symptoms Muscle weakness MUSCLE_WEAK HP_0001742 signs and symptoms Nasal obstruction (stuffy nose) NASAL_OBSTRUCT HP_0002018 signs and symptoms Nausea NAUSEA HP_0000421 signs and symptoms Nose bleed signs and symptoms Otitis - signs and symptoms Pain +HP:0012531 signs and symptoms Pain HP:0002027 Pain Abdominal pain ABDOMINAL HP_0002829 Pain Arthralgia (painful joints) ARTHRALGIA HP_0100749 Pain Chest pain CHEST_PAIN - Chest pain Pleuritic chest pain +HP:0033771 Chest pain Pleuritic chest pain HP_0003326 Pain Myalgia (muscle pain) MYALGIA HP_0025439 signs and symptoms Pharyngitis (sore throat) PHARYNGITIS signs and symptoms Pharyngeal exudate - signs and symptoms Pleural effusion +HP:0002202 signs and symptoms Pleural effusion HP:0002090 signs and symptoms Pneumonia signs and symptoms Prostration - signs and symptoms Pseudo-chilblains +HP:0033696 signs and symptoms Pseudo-chilblains Pseudo-chilblains Pseudo-chilblains on fingers (covid fingers) PSEUDO-CHIBLAINS_F Pseudo-chilblains Pseudo-chilblains on toes (covid toes) PSEUDO-CHIBLAINS_T HP_0000988 signs and symptoms Rash RASH @@ -270,12 +270,12 @@ HP_0001250 signs and symptoms Seizure SEIZURE HP:0020219 Seizure Motor seizure MOTOR_SEIZURE HP:0025144 signs and symptoms Shivering (involuntary muscle twitching) SHIVERING HP_0001350 signs and symptoms Slurred speech SLURRED_SPEECH - signs and symptoms Sneezing - signs and symptoms Sputum Production +HP:0025095 signs and symptoms Sneezing +HP:0033709 signs and symptoms Sputum Production HP:0001297 signs and symptoms Stroke STROKE - signs and symptoms Swollen Lymph Nodes +HP:0002716 signs and symptoms Swollen Lymph Nodes HP_0002789 signs and symptoms Tachypnea (accelerated respiratory rate) TACHYPNEA - signs and symptoms Vertigo (dizziness) +HP:0002321 signs and symptoms Vertigo (dizziness) HP_0002013 signs and symptoms Vomiting (throwing up) VOMITING host vaccination status Fully Vaccinated @@ -289,14 +289,14 @@ HP_0002013 signs and symptoms Vomiting (throwing up) VOMITING OBI_0002600 NML submitted specimen type Swab PH_SPECIMEN_TYPE:SWAB OBI_0000880 NML submitted specimen type RNA PH_SPECIMEN_TYPE:RNA OBI:0002754 NML submitted specimen type mRNA (cDNA) - NML submitted specimen type Nucleic acid PH_SPECIMEN_TYPE:NUCLEIC_ACID - NML submitted specimen type Not Applicable PH_SPECIMEN_TYPE:NA +OBI:0001010 NML submitted specimen type Nucleic acid PH_SPECIMEN_TYPE:NUCLEIC_ACID +GENEPIO:0001619 NML submitted specimen type Not Applicable PH_SPECIMEN_TYPE:NA - NML related specimen relationship type Acute +HP_0011009 NML related specimen relationship type Acute NML related specimen relationship type Convalescent NML related specimen relationship type Familial - NML related specimen relationship type Follow-up +EFO_0009642 NML related specimen relationship type Follow-up NML related specimen relationship type Previously Submitted @@ -948,38 +948,38 @@ GENEPIO_0001935 Ion Torrent Ion Torrent PGM MGI MGI DNBSEQ-G50 -PR:P0DTC4 gene name 1 E gene (orf4) E gene E gene -PR:P0DTC5 gene name 1 M gene (orf5) -PR:P0DTC9 gene name 1 N gene (orf9) -PR:P0DTC2 gene name 1 Spike gene (orf2) -PR:000050281 gene name 1 orf1ab (rep) -PR:P0DTC1-1 orf1ab (rep) orf1a (pp1a) -PR:000050280 orf1a (pp1a) nsp11 -PR:000050270 orf1ab (rep) nsp1 -PR:000050271 orf1ab (rep) nsp2 -PR:000050272 orf1ab (rep) nsp3 -PR:000050273 orf1ab (rep) nsp4 -PR:000050274 orf1ab (rep) nsp5 -PR:000050275 orf1ab (rep) nsp6 -PR:000050276 orf1ab (rep) nsp7 -PR:000050277 orf1ab (rep) nsp8 -PR:000050278 orf1ab (rep) nsp9 -PR:000050279 orf1ab (rep) nsp10 -PR:000050284 orf1ab (rep) RdRp gene (nsp12) -PR:000050285 orf1ab (rep) hel gene (nsp13) -PR:000050286 orf1ab (rep) exoN gene (nsp14) -PR:000050287 orf1ab (rep) nsp15 -PR:000050288 orf1ab (rep) nsp16 -PR:P0DTC3 gene name 1 orf3a - gene name 1 orf3b -PR:P0DTC6 gene name 1 orf6 (ns6) -PR:P0DTC7 gene name 1 orf7a -PR:P0DTD8 gene name 1 orf7b (ns7b) -PR:P0DTC8 gene name 1 orf8 (ns8) -PR:P0DTD2 gene name 1 orf9b - gene name 1 orf9c -PR:A0A663DJA2 gene name 1 orf10 - gene name 1 orf14 +PR:P0DTC4 gene name 1 E gene (orf4) E gene E gene E (orf4) +PR:P0DTC5 gene name 1 M gene (orf5) M (orf5) +PR:P0DTC9 gene name 1 N gene (orf9) N (orf9) +PR:P0DTC2 gene name 1 Spike gene (orf2) S (orf2) +PR:000050281 gene name 1 orf1ab (rep) orf1ab (rep) +PR:P0DTC1-1 orf1ab (rep) orf1a (pp1a) orf1a (pp1a) +PR:000050280 orf1a (pp1a) nsp11 nsp11 +PR:000050270 orf1ab (rep) nsp1 nsp1 +PR:000050271 orf1ab (rep) nsp2 nsp2 +PR:000050272 orf1ab (rep) nsp3 nsp3 +PR:000050273 orf1ab (rep) nsp4 nsp4 +PR:000050274 orf1ab (rep) nsp5 nsp5 +PR:000050275 orf1ab (rep) nsp6 nsp6 +PR:000050276 orf1ab (rep) nsp7 nsp7 +PR:000050277 orf1ab (rep) nsp8 nsp8 +PR:000050278 orf1ab (rep) nsp9 nsp9 +PR:000050279 orf1ab (rep) nsp10 nsp10 +PR:000050284 orf1ab (rep) RdRp gene (nsp12) nsp12 (RdRp) +PR:000050285 orf1ab (rep) hel gene (nsp13) nsp13 (Hel) +PR:000050286 orf1ab (rep) exoN gene (nsp14) nsp14 (ExoN) +PR:000050287 orf1ab (rep) nsp15 nsp15 +PR:000050288 orf1ab (rep) nsp16 nsp16 +PR:P0DTC3 gene name 1 orf3a orf3a + gene name 1 orf3b orf3b +PR:P0DTC6 gene name 1 orf6 (ns6) orf6 (ns6) +PR:P0DTC7 gene name 1 orf7a orf7a +PR:P0DTD8 gene name 1 orf7b (ns7b) orf7b (ns7b) +PR:P0DTC8 gene name 1 orf8 (ns8) orf8 (ns8) +PR:P0DTD2 gene name 1 orf9b orf9b + gene name 1 orf9c orf9c +PR:A0A663DJA2 gene name 1 orf10 orf10 + gene name 1 orf14 orf14 gene name 1 SARS-COV-2 5' UTR @@ -989,6 +989,8 @@ PR:A0A663DJA2 gene name 1 orf10 sequence submitted by BCCDC Public Health Laboratory sequence submitted by Canadore College sequence submitted by The Centre for Applied Genomics (TCAG) + sequence submitted by Dynacare (Manitoba) Dynacare Manitoba + sequence submitted by The Hospital for Sick Children (SickKids) CANCOGEN_SICK_KIDS_HOSPITAL sequence submitted by Laboratoire de santé publique du Québec (LSPQ) sequence submitted by Manitoba Cadham Provincial Laboratory sequence submitted by McMaster University @@ -1008,29 +1010,36 @@ PR:A0A663DJA2 gene name 1 orf10 sample collected by Alberta Precision Labs (APL) Alberta Precision Labs (APL) Alberta ProvLab North (APLN) CANCOGEN_EDMONTON_PROV_LAB - Alberta Precision Labs (APL) Alberta ProvLab South (APLS) APL-C + Alberta Precision Labs (APL) Alberta ProvLab South (APLS) CANCOGEN_CALGARY_PROV_LAB sample collected by BCCDC Public Health Laboratory CANCOGEN_BCCDC - sample collected by Eastern Ontario Regional Laboratory Association Eastern Ontario Regional Laboratory Association - sample collected by Hamilton Health Sciences Hamilton Health Sciences + sample collected by Dynacare (Manitoba) Dynacare Manitoba + sample collected by Eastern Ontario Regional Laboratory Association CANCOGEN_EORLA + sample collected by Hamilton Health Sciences " +CANCOGEN_HAMILTON_HS" + sample collected by The Hospital for Sick Children (SickKids) CANCOGEN_SICK_KIDS_HOSPITAL sample collected by Laboratoire de santé publique du Québec (LSPQ) CANCOGEN_LSPQ sample collected by Lake of the Woods District Hospital - Ontario CANCOGEN_LAKE_OF_THE_WOODS sample collected by Manitoba Cadham Provincial Laboratory CANCOGEN_CADHAM_LAB sample collected by McMaster University CANCOGEN_MCMASTER_UNIVERSITY - sample collected by Mount Sinai Hospital Mount Sinai Hospital + sample collected by Mount Sinai Hospital " +CANCOGEN_MOUNT_SINAI" sample collected by National Microbiology Laboratory (NML) CANCOGEN_NML_IRV sample collected by New Brunswick - Vitalité Health Network CANCOGEN_G_L_DUMONT sample collected by Newfoundland and Labrador - Eastern Health CANCOGEN_STJOHNS_PHL sample collected by Nova Scotia Health Authority CANCOGEN_QEII_HSC sample collected by Nunuvut CANCOGEN_NUNAVUT_ - sample collected by Ontario Institute for Cancer Research (OICR) Ontario Institute for Cancer Research (OICR) + sample collected by Ontario Institute for Cancer Research (OICR) CANCOGEN_OICR sample collected by Prince Edward Island - Health PEI CANCOGEN_QEH sample collected by Public Health Ontario (PHO) CANCOGEN_ONTARIO_PHO - sample collected by Queen's University / Kingston Health Sciences Centre Queen's University / Kingston Health Sciences Centre + sample collected by Queen's University / Kingston Health Sciences Centre CANCOGEN_KINGSTON sample collected by Saskatchewan - Roy Romanow Provincial Laboratory (RRPL) CANCOGEN_ROMANOW_PROV_LAB - sample collected by St. John's Rehab at Sunnybrook Hospital St. John's Rehab at Sunnybrook Hospital - sample collected by Sunnybrook Health Sciences Centre Sunnybrook Health Sciences Centre - sample collected by Unity Health Toronto Unity Health Toronto - sample collected by William Osler Health System William Osler Health System + sample collected by St. John's Rehab at Sunnybrook Hospital " +CANCOGEN_SJRH" + sample collected by Sunnybrook Health Sciences Centre CANCOGEN_SUNNYBROOK + sample collected by Unity Health Toronto " +CANCOGEN_UNITY_HEALTH" + sample collected by William Osler Health System " +CANCOGEN_WILLIAM_OSLER" GAZ_00006882 geo_loc_name (country) Afghanistan @@ -1303,6 +1312,4 @@ GAZ_00009572 geo_loc_name (country) West Bank GAZ_00000564 geo_loc_name (country) Western Sahara GAZ_00005284 geo_loc_name (country) Yemen GAZ_00001107 geo_loc_name (country) Zambia -GAZ_00001106 geo_loc_name (country) Zimbabwe - - \ No newline at end of file +GAZ_00001106 geo_loc_name (country) Zimbabwe \ No newline at end of file