NML_LIMS export vocabulary update

cidgoh · Dec 22, 2021 · 3fcfb17 · 3fcfb17
1 parent f7b4910
commit 3fcfb17
Show file tree

Hide file tree

Showing 4 changed files with 14 additions and 6 deletions.
diff --git a/script/main.js b/script/main.js
@@ -11,7 +11,7 @@
  * main.html?template=test_template
  *
  */
-const VERSION = '0.14.6';
+const VERSION = '0.14.7';
 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
@@ -107,7 +107,7 @@ var DATA = [
         "exportField": {
           "NML_LIMS": [
             {
-              "field": "case ID"
+              "field": "PH_CASE_ID"
             }
           ]
         }
@@ -142,7 +142,7 @@ var DATA = [
           ],
           "NML_LIMS": [
             {
-              "field": "NML related specimen primary ID"
+              "field": "PH_RELATED_PRIMARY_ID"
             }
           ]
         }
@@ -1945,6 +1945,11 @@ var DATA = [
             {
               "field": "Related Specimen Relationship Type"
             }
+          ],
+          "NML_LIMS": [
+            {
+              "field": "PH_RELATED_RELATIONSHIP_TYPE"
+            }
           ]
         },
         "schema:ItemList": {

diff --git a/template/canada_covid19/data.tsv b/template/canada_covid19/data.tsv
@@ -4,8 +4,8 @@ GENEPIO:0001122			Database Identifiers
 GENEPIO:0001123		Database Identifiers	specimen collector sample ID	xs:unique		Not Applicable; Missing; Not Collected; Not Provided; Restricted Access	required					The user-defined name for the sample.	Store the collector sample ID. If this number is considered identifiable information, provide an alternative ID. Be sure to store the key that maps between the original and alternative IDs for traceability and follow up if necessary. Every collector sample ID from a single submitter must be unique. It can have any format, but we suggest that you make it concise, unique and consistent within your lab.	prov_rona_99	Sample ID given by the sample provider	Primary Specimen ID	TEXT_ID	sample_name	specimen collector sample ID
 GENEPIO:0001202		Database Identifiers	third party lab service provider name	xs:token								The name of the third party company or laboratory that provided services.	Store the sample identifier supplied by the third party services provider.	Switch Health			HC_TEXT5		
 GENEPIO:0001149		Database Identifiers	third party lab sample ID	xs:token								The identifier assigned to a sample by a third party service provider.		SHK123456			PH_ID_NUMBER_PRIMARY		
-GENEPIO:0100281		Database Identifiers	case ID	xs:unique			recommended					The identifier used to specify an epidemiologically detected case of disease.	Provide the case identifer. The case ID greatly facilitates linkage between laboratory and epidemiological data. The case ID may be considered identifiable information. Consult the data steward before sharing.	ABCD1234			case ID		
-GENEPIO:0001128		Database Identifiers	Related specimen primary ID	xs:token		Not Applicable; Missing; Not Collected; Not Provided; Restricted Access						The primary ID of a related specimen previously submitted to the repository.	Store the primary ID of the related specimen previously submitted to the National Microbiology Laboratory so that the samples can be linked and tracked through the system.	SR20-12345		Related Specimen ID;Related Specimen Relationship Type	NML related specimen primary ID		
+GENEPIO:0100281		Database Identifiers	case ID	xs:unique			recommended					The identifier used to specify an epidemiologically detected case of disease.	Provide the case identifer. The case ID greatly facilitates linkage between laboratory and epidemiological data. The case ID may be considered identifiable information. Consult the data steward before sharing.	ABCD1234			PH_CASE_ID		
+GENEPIO:0001128		Database Identifiers	Related specimen primary ID	xs:token		Not Applicable; Missing; Not Collected; Not Provided; Restricted Access						The primary ID of a related specimen previously submitted to the repository.	Store the primary ID of the related specimen previously submitted to the National Microbiology Laboratory so that the samples can be linked and tracked through the system.	SR20-12345		Related Specimen ID;Related Specimen Relationship Type	PH_RELATED_PRIMARY_ID		
 GENEPIO:0001131		Database Identifiers	IRIDA sample name	xs:token								The identifier assigned to a sequenced isolate in IRIDA.	Store the IRIDA sample name. The IRIDA sample name will be created by the individual entering data into the IRIDA platform. IRIDA samples may be linked to metadata and sequence data, or just metadata alone. It is recommended that the IRIDA sample name be the same as, or contain, the specimen collector sample ID for better traceability. It is also recommended that the IRIDA sample name mirror the GISAID accession. IRIDA sample names cannot contain slashes. Slashes should be replaced by underscores. See IRIDA documentation for more information regarding special characters (https://irida.corefacility.ca/documentation/user/user/samples/#adding-a-new-sample). 	prov_rona_99			IRIDA sample name		
 GENEPIO:0001133		Database Identifiers	umbrella bioproject accession	select						UPPER		The INSDC accession number assigned to the umbrella BioProject for the Canadian SARS-CoV-2 sequencing effort.	Store the umbrella BioProject accession by selecting it from the picklist in the template. The umbrella BioProject accession will be identical for all CanCOGen submitters. Different provinces will have their own BioProjects, however these BioProjects will be linked under one umbrella BioProject.	PRJNA623807			umbrella bioproject accession		
 GENEPIO:0001136		Database Identifiers	bioproject accession	xs:token						UPPER		The INSDC accession number of the BioProject(s) to which the BioSample belongs.	Store the BioProject accession number. BioProjects are an organizing tool that links together raw sequence data, assemblies, and their associated metadata. Each province will be assigned a different bioproject accession number by the National Microbiology Lab. A valid NCBI BioProject accession has prefix PRJN e.g., PRJNA12345, and is created once at the beginning of a new sequencing project. 	PRJNA608651		BioProject Accession	PH_BIOPROJECT_ACCESSION	bioproject_accession	
@@ -31,7 +31,7 @@ GENEPIO:0001195		Sample collection and processing	isolate	xs:token		Not Applicab
 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	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	Related specimen relationship type	select								The relationship of the current specimen to the specimen/sample previously submitted to the repository.	Provide the tag that describes how the previous sample is related to the current sample being submitted from the pick list provided, so that the samples can be linked and tracked in the system.	Specimen sampling methods testing		Related Specimen ID;Related Specimen Relationship Type			
+GENEPIO:0001209		Sample collection and processing	Related specimen relationship type	select								The relationship of the current specimen to the specimen/sample previously submitted to the repository.	Provide the tag that describes how the previous sample is related to the current sample being submitted from the pick list provided, so that the samples can be linked and tracked in the system.	Specimen sampling methods testing		Related Specimen ID;Related Specimen Relationship Type	PH_RELATED_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
 GENEPIO:0001214		Sample collection and processing	anatomical part	select		Not Applicable; Missing; Not Collected; Not Provided; Restricted Access	required					An anatomical part of an organism e.g. oropharynx.	Provide a descriptor if an anatomical part 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. 	Nasopharynx (NP)	Specimen source	Anatomical Site	PH_ISOLATION_SITE	isolation_source;anatomical_part	anatomical part
 GENEPIO:0001216		Sample collection and processing	body product	select		Not Applicable; Missing; Not Collected; Not Provided; Restricted Access	required					A substance excreted/secreted from an organism e.g. feces, urine, sweat.	Provide a descriptor if a body product 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. 	Feces	Specimen source	Body Product	PH_SPECIMEN_SOURCE_DESC	isolation_source;body_product	body product

diff --git a/template/canada_covid19/export.js b/template/canada_covid19/export.js
@@ -374,6 +374,8 @@ var exportNML_LIMS = (baseName, hot, data, xlsx, fileType) => {
     ['TEXT_ID',                 []],
     ['HC_TEXT5',                []],
     ['PH_ID_NUMBER_PRIMARY',    []],
+    ['PH_CASE_ID',              []],
+    ['PH_RELATED_PRIMARY_ID',   []],
     ['PH_BIOPROJECT_ACCESSION', []],
     ['PH_BIOSAMPLE_ACCESSION',  []],
     ['PH_SRA_ACCESSION',        []],
@@ -389,6 +391,7 @@ var exportNML_LIMS = (baseName, hot, data, xlsx, fileType) => {
     ['HC_SAMPLE_CATEGORY',      []], 
     ['PH_SAMPLING_DETAILS',     []],
     ['PH_SPECIMEN_TYPE',        []],
+    ['PH_RELATED_RELATIONSHIP_TYPE', []],
     ['PH_ISOLATION_SITE_DESC',  []],
     ['PH_ISOLATION_SITE',       []],
     ['PH_SPECIMEN_SOURCE',      []], // Calculated field (not in import)