Merge branch 'master' of https://github.com/cidgoh/DataHarmonizer

cidgoh · Jul 22, 2022 · b400699 · b400699
2 parents 1b9e85a + af77161
commit b400699
Show file tree

Hide file tree

Showing 6 changed files with 59 additions and 72 deletions.
diff --git a/...PX_validTestDataset_2-1-1_July202022.xlsx → ...PX_validTestDataset_2-2-1_July212022.xlsx b/...PX_validTestDataset_2-1-1_July202022.xlsx → ...PX_validTestDataset_2-2-1_July212022.xlsx
diff --git a/template/monkeypox/exampleInput/README.md b/template/monkeypox/exampleInput/README.md
@@ -1,7 +1,7 @@
 # Monkeypox Example Input Data
 This directory contains example input/test data for the Canadian Network for Public Health Intelligence (CNPHI) DataHarmonizer application template: `Monkeypox`. This data is appropriate for testing up to the version appended to the end of the file name, for example:
 
-- `DH_Canadian_MPX_validTestDataset_2-1-1_July202022.xlsx` is _valid_ for version `1-3-3` of the DataHarmonizer.
+- `DH_Canadian_MPX_validTestDataset_2-2-1_July212022.xlsx` is _valid_ for version `1-3-4` of the DataHarmonizer.
 
 ## Valid Test Data
 

diff --git a/template/monkeypox/schema.js b/template/monkeypox/schema.js
@@ -78,7 +78,7 @@ var SCHEMA = {
       "name": "time",
       "description": "A time object represents a (local) time of day, independent of any particular day",
       "notes": [
-        "URI is dateTime because OWL reasoners don't work with straight date or time"
+        "URI is dateTime because OWL reasoners do not work with straight date or time"
       ],
       "base": "XSDTime",
       "uri": "xsd:dateTime",
@@ -645,6 +645,11 @@ var SCHEMA = {
           "meaning": "UBERON:0006956",
           "is_a": "Head"
         },
+        "Cheek": {
+          "text": "Cheek",
+          "meaning": "UBERON:0001567",
+          "is_a": "Head"
+        },
         "Ear": {
           "text": "Ear",
           "meaning": "UBERON:0001690",
@@ -877,6 +882,11 @@ var SCHEMA = {
           "meaning": "UBERON:0006956",
           "is_a": "Head [UBERON:0000033]"
         },
+        "Cheek [UBERON:0001567]": {
+          "text": "Cheek [UBERON:0001567]",
+          "meaning": "UBERON:0001567",
+          "is_a": "Head [UBERON:0000033]"
+        },
         "Ear [UBERON:0001690]": {
           "text": "Ear [UBERON:0001690]",
           "meaning": "UBERON:0001690",
@@ -4625,50 +4635,29 @@ var SCHEMA = {
         }
       }
     },
-    "gene name 1 menu": {
-      "name": "gene name 1 menu",
+    "gene name menu": {
+      "name": "gene name menu",
       "from_schema": "https://example.com/monkeypox",
       "permissible_values": {
         "MPX (orf B6R)": {
           "text": "MPX (orf B6R)",
           "meaning": "GENEPIO:0100505"
-        }
-      }
-    },
-    "gene name 2 menu": {
-      "name": "gene name 2 menu",
-      "from_schema": "https://example.com/monkeypox",
-      "permissible_values": {
+        },
         "OVP (orf 17L)": {
           "text": "OVP (orf 17L)",
           "meaning": "GENEPIO:0100506"
-        }
-      }
-    },
-    "gene name 3 menu": {
-      "name": "gene name 3 menu",
-      "from_schema": "https://example.com/monkeypox",
-      "permissible_values": {
+        },
         "OPHA (orf B2R)": {
           "text": "OPHA (orf B2R)",
           "meaning": "GENEPIO:0100507"
-        }
-      }
-    },
-    "gene name 4 menu": {
-      "name": "gene name 4 menu",
-      "from_schema": "https://example.com/monkeypox",
-      "permissible_values": {
+        },
         "G2R_G (TNFR)": {
           "text": "G2R_G (TNFR)",
           "meaning": "GENEPIO:0100510"
-        }
-      }
-    },
-    "gene name 5 menu": {
-      "name": "gene name 5 menu",
-      "from_schema": "https://example.com/monkeypox",
-      "permissible_values": {
+        },
+        "G2R_G (WA)": {
+          "text": "G2R_G (WA)"
+        },
         "RNAse P gene (RNP)": {
           "text": "RNAse P gene (RNP)",
           "meaning": "GENEPIO:0100508"
@@ -9051,7 +9040,7 @@ var SCHEMA = {
       ],
       "any_of": [
         {
-          "range": "gene name 4 menu"
+          "range": "gene name menu"
         },
         {
           "range": "null value menu"
@@ -9105,7 +9094,7 @@ var SCHEMA = {
       ],
       "any_of": [
         {
-          "range": "gene name 5 menu"
+          "range": "gene name menu"
         },
         {
           "range": "null value menu"
@@ -10309,7 +10298,7 @@ var SCHEMA = {
           "slot_group": "Pathogen diagnostic testing",
           "any_of": [
             {
-              "range": "gene name 1 menu"
+              "range": "gene name menu"
             },
             {
               "range": "null value menu"
@@ -10330,7 +10319,7 @@ var SCHEMA = {
           "slot_group": "Pathogen diagnostic testing",
           "any_of": [
             {
-              "range": "gene name 2 menu"
+              "range": "gene name menu"
             },
             {
               "range": "null value menu"
@@ -10351,7 +10340,7 @@ var SCHEMA = {
           "slot_group": "Pathogen diagnostic testing",
           "any_of": [
             {
-              "range": "gene name 3 menu"
+              "range": "gene name menu"
             },
             {
               "range": "null value menu"
@@ -12250,7 +12239,7 @@ var SCHEMA = {
           "slot_group": "Pathogen diagnostic testing",
           "any_of": [
             {
-              "range": "gene name 1 menu"
+              "range": "gene name menu"
             },
             {
               "range": "null value menu"
@@ -12283,7 +12272,7 @@ var SCHEMA = {
           "slot_group": "Pathogen diagnostic testing",
           "any_of": [
             {
-              "range": "gene name 2 menu"
+              "range": "gene name menu"
             },
             {
               "range": "null value menu"
@@ -12316,7 +12305,7 @@ var SCHEMA = {
           "slot_group": "Pathogen diagnostic testing",
           "any_of": [
             {
-              "range": "gene name 3 menu"
+              "range": "gene name menu"
             },
             {
               "range": "null value menu"

diff --git a/template/monkeypox/schema.yaml b/template/monkeypox/schema.yaml
@@ -729,7 +729,7 @@ classes:
         comments: Select the name of the gene used for the diagnostic PCR from the
           standardized pick list.
         any_of:
-        - range: gene name 1 menu
+        - range: gene name menu
         - range: null value menu
       diagnostic pcr Ct value 1:
         rank: 105
@@ -740,7 +740,7 @@ classes:
         comments: Select the name of the gene used for the diagnostic PCR from the
           standardized pick list.
         any_of:
-        - range: gene name 2 menu
+        - range: gene name menu
         - range: null value menu
       diagnostic pcr Ct value 2:
         rank: 107
@@ -751,7 +751,7 @@ classes:
         comments: Select the name of the gene used for the diagnostic PCR from the
           standardized pick list.
         any_of:
-        - range: gene name 3 menu
+        - range: gene name menu
         - range: null value menu
       diagnostic pcr Ct value 3:
         rank: 109
@@ -2953,7 +2953,7 @@ slots:
     examples:
     - value: G2R_G (TNFR)
     any_of:
-    - range: gene name 4 menu
+    - range: gene name menu
     - range: null value menu
     exact_mappings:
     - CNPHI:Gene Target 4
@@ -2983,7 +2983,7 @@ slots:
     examples:
     - value: RNAse P
     any_of:
-    - range: gene name 5 menu
+    - range: gene name menu
     - range: null value menu
     exact_mappings:
     - CNPHI:Gene Target 5
@@ -3407,6 +3407,10 @@ enums:
         text: Buccal mucosa
         meaning: UBERON:0006956
         is_a: Head
+      Cheek:
+        text: Cheek
+        meaning: UBERON:0001567
+        is_a: Head
       Ear:
         text: Ear
         meaning: UBERON:0001690
@@ -3587,6 +3591,10 @@ enums:
         text: Buccal mucosa [UBERON:0006956]
         meaning: UBERON:0006956
         is_a: Head [UBERON:0000033]
+      Cheek [UBERON:0001567]:
+        text: Cheek [UBERON:0001567]
+        meaning: UBERON:0001567
+        is_a: Head [UBERON:0000033]
       Ear [UBERON:0001690]:
         text: Ear [UBERON:0001690]
         meaning: UBERON:0001690
@@ -6417,33 +6425,23 @@ enums:
         text: Unity Health Toronto
       William Osler Health System:
         text: William Osler Health System
-  gene name 1 menu:
-    name: gene name 1 menu
+  gene name menu:
+    name: gene name menu
     permissible_values:
       MPX (orf B6R):
         text: MPX (orf B6R)
         meaning: GENEPIO:0100505
-  gene name 2 menu:
-    name: gene name 2 menu
-    permissible_values:
       OVP (orf 17L):
         text: OVP (orf 17L)
         meaning: GENEPIO:0100506
-  gene name 3 menu:
-    name: gene name 3 menu
-    permissible_values:
       OPHA (orf B2R):
         text: OPHA (orf B2R)
         meaning: GENEPIO:0100507
-  gene name 4 menu:
-    name: gene name 4 menu
-    permissible_values:
       G2R_G (TNFR):
         text: G2R_G (TNFR)
         meaning: GENEPIO:0100510
-  gene name 5 menu:
-    name: gene name 5 menu
-    permissible_values:
+      G2R_G (WA):
+        text: G2R_G (WA)
       RNAse P gene (RNP):
         text: RNAse P gene (RNP)
         meaning: GENEPIO:0100508

diff --git a/template/monkeypox/schema_enums.tsv b/template/monkeypox/schema_enums.tsv
@@ -115,6 +115,7 @@ anatomical part menu	UBERON:0001245	Anus
 	FMA:24920		      Hand (palm)									
 	UBERON:0000033	Head										
 	UBERON:0006956		      Buccal mucosa									
+	UBERON:0001567		      Cheek									
 	UBERON:0001690		      Ear									
 	NCIT:C103848			Preauricular region								
 	UBERON:0000970		      Eye									
@@ -168,6 +169,7 @@ anatomical part international menu	UBERON:0001245	Anus [UBERON:0001245]
 	FMA:24920		      Hand (palm) [FMA:24920]									
 	UBERON:0000033	Head [UBERON:0000033]										
 	UBERON:0006956		      Buccal mucosa [UBERON:0006956]									
+	UBERON:0001567		      Cheek [UBERON:0001567]									
 	UBERON:0001690		      Ear [UBERON:0001690]									
 	NCIT:C103848			Preauricular region [NCIT:C103848]								
 	UBERON:0000970		      Eye [UBERON:0000970]									
@@ -1006,15 +1008,13 @@ sequenced by menu		Alberta Precision Labs (APL)
 		Unity Health Toronto										
 		William Osler Health System										
 
-gene name 1 menu	GENEPIO:0100505	MPX (orf B6R)										
+gene name menu	GENEPIO:0100505	MPX (orf B6R)										
+	GENEPIO:0100506	OVP (orf 17L)										
+	GENEPIO:0100507	OPHA (orf B2R)										
+	GENEPIO:0100510	G2R_G (TNFR)										
+		G2R_G (WA)										
+	GENEPIO:0100508	RNAse P gene (RNP)										
 
-gene name 2 menu	GENEPIO:0100506	OVP (orf 17L)										
-
-gene name 3 menu	GENEPIO:0100507	OPHA (orf B2R)										
-
-gene name 4 menu	GENEPIO:0100510	G2R_G (TNFR)										
-
-gene name 5 menu	GENEPIO:0100508	RNAse P gene (RNP)										
 
 geo_loc_name (country) menu	GAZ:00006882	Afghanistan										
 	GAZ:00002953	Albania										

diff --git a/template/monkeypox/schema_slots.tsv b/template/monkeypox/schema_slots.tsv
@@ -168,18 +168,18 @@ Monkeypox	Bioinformatics and QC metrics	GENEPIO:0001489	bioinformatics protocol
 Monkeypox_international	Bioinformatics and QC metrics	GENEPIO:0001489	bioinformatics protocol		WhitespaceMinimizedString										A description of the overall bioinformatics strategy used.	Further details regarding the methods used to process raw data, and/or generate assemblies, and/or generate consensus sequences can. This information can be provided in an SOP or protocol or pipeline/workflow. Provide the name and version number of the protocol, or a GitHub link to a pipeline or workflow.	https://github.com/phac-nml/monkeypox-nf		Bioinformatics Protocol	PH_BIOINFORMATICS_PROTOCOL		bioinformatics protocol
 
 Monkeypox;Monkeypox_international		GENEPIO:0001506	Pathogen diagnostic testing																			
-Monkeypox	Pathogen diagnostic testing	GENEPIO:0001507	gene name 1		gene name 1 menu	null value menu									The name of the gene used in the diagnostic RT-PCR test.	Select the name of the gene used for the diagnostic PCR from the standardized pick list.	MPX (orf B6R)		Gene Target 1	SUBMITTED_RESLT - Gene Target #1	gene_name_1	gene name
+Monkeypox	Pathogen diagnostic testing	GENEPIO:0001507	gene name 1		gene name menu	null value menu									The name of the gene used in the diagnostic RT-PCR test.	Select the name of the gene used for the diagnostic PCR from the standardized pick list.	MPX (orf B6R)		Gene Target 1	SUBMITTED_RESLT - Gene Target #1	gene_name_1	gene name
 Monkeypox_international	Pathogen diagnostic testing	GENEPIO:0001507	gene name 1		WhitespaceMinimizedString	null value menu									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	MPX (orf B6R)		Gene Target 1	SUBMITTED_RESLT - Gene Target #1	gene_name_1	gene name
 Monkeypox;Monkeypox_international	Pathogen diagnostic testing	GENEPIO:0001509	diagnostic pcr Ct value 1		decimal	null value menu									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 
-Monkeypox	Pathogen diagnostic testing	GENEPIO:0001510	gene name 2		gene name 2 menu	null value menu									The name of the gene used in the diagnostic RT-PCR test.	Select the name of the gene used for the diagnostic PCR from the standardized pick list.	OVP (orf 17L)		Gene Target 2	SUBMITTED_RESLT - Gene Target #2	gene_name_2	
+Monkeypox	Pathogen diagnostic testing	GENEPIO:0001510	gene name 2		gene name menu	null value menu									The name of the gene used in the diagnostic RT-PCR test.	Select the name of the gene used for the diagnostic PCR from the standardized pick list.	OVP (orf 17L)		Gene Target 2	SUBMITTED_RESLT - Gene Target #2	gene_name_2	
 Monkeypox_international	Pathogen diagnostic testing	GENEPIO:0001510	gene name 2		WhitespaceMinimizedString	null value menu									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	OVP (orf 17L)		Gene Target 2	SUBMITTED_RESLT - Gene Target #2	gene_name_2	
 Monkeypox;Monkeypox_international	Pathogen diagnostic testing	GENEPIO:0001512	diagnostic pcr Ct value 2		decimal	null value menu									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	
-Monkeypox	Pathogen diagnostic testing	GENEPIO:0001513	gene name 3		gene name 3 menu	null value menu									The name of the gene used in the diagnostic RT-PCR test.	Select the name of the gene used for the diagnostic PCR from the standardized pick list.	OPHA (orf B2R)		Gene Target 3	SUBMITTED_RESLT - Gene Target #3	gene_name_3	
+Monkeypox	Pathogen diagnostic testing	GENEPIO:0001513	gene name 3		gene name menu	null value menu									The name of the gene used in the diagnostic RT-PCR test.	Select the name of the gene used for the diagnostic PCR from the standardized pick list.	OPHA (orf B2R)		Gene Target 3	SUBMITTED_RESLT - Gene Target #3	gene_name_3	
 Monkeypox_international	Pathogen diagnostic testing	GENEPIO:0001513	gene name 3		WhitespaceMinimizedString	null value menu									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	OPHA (orf B2R)		Gene Target 3	SUBMITTED_RESLT - Gene Target #3	gene_name_3	
 Monkeypox;Monkeypox_international	Pathogen diagnostic testing	GENEPIO:0001515	diagnostic pcr Ct value 3		decimal	null value menu									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.	19		Gene Target 3 CT Value	SUBMITTED_RESLT - Gene Target #3 CT Value	diagnostic_PCR_CT_value_3	
-Monkeypox	Pathogen diagnostic testing		gene name 4		gene name 4 menu	null value menu									The name of the gene used in the diagnostic RT-PCR test.	Select the name of the gene used for the diagnostic PCR from the standardized pick list.	G2R_G (TNFR)		Gene Target 4	SUBMITTED_RESLT - Gene Target #4	gene_name_4	
+Monkeypox	Pathogen diagnostic testing		gene name 4		gene name menu	null value menu									The name of the gene used in the diagnostic RT-PCR test.	Select the name of the gene used for the diagnostic PCR from the standardized pick list.	G2R_G (TNFR)		Gene Target 4	SUBMITTED_RESLT - Gene Target #4	gene_name_4	
 Monkeypox	Pathogen diagnostic testing		diagnostic pcr Ct value 4		decimal	null value menu									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.	27		Gene Target 4 CT Value	SUBMITTED_RESLT - Gene Target #4 CT Value	diagnostic_PCR_CT_value_4	
-Monkeypox	Pathogen diagnostic testing		gene name 5		gene name 5 menu	null value menu									The name of the gene used in the diagnostic RT-PCR test.	Select the name of the gene used for the diagnostic PCR from the standardized pick list.	RNAse P		Gene Target 5	SUBMITTED_RESLT - Gene Target #5	gene_name_5	
+Monkeypox	Pathogen diagnostic testing		gene name 5		gene name menu	null value menu									The name of the gene used in the diagnostic RT-PCR test.	Select the name of the gene used for the diagnostic PCR from the standardized pick list.	RNAse P		Gene Target 5	SUBMITTED_RESLT - Gene Target #5	gene_name_5	
 Monkeypox	Pathogen diagnostic testing		diagnostic pcr Ct value 5		decimal	null value menu									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 5 CT Value	SUBMITTED_RESLT - Gene Target #5 CT Value	diagnostic_PCR_CT_value_5	
 
 		GENEPIO:0001516	Contributor acknowledgement