Merge pull request #37 from UW-GAC/phenotype/update-diabetes-dprism-v…

…ariables Update diabetes dprism variables
UW-GAC · Jun 11, 2024 · d34285e · d34285e
2 parents 6835393 + 585dbe5
commit d34285e
Show file tree

Hide file tree

Showing 5 changed files with 45 additions and 29 deletions.
diff --git a/PRIMED_phenotype_data_model.json b/PRIMED_phenotype_data_model.json
@@ -1,7 +1,7 @@
 {
   "name": "PRIMED Phenotype Data Model",
   "description": "Data model for phenotype data in the PRIMED consortium",
-  "version": "1.8",
+  "version": "1.9",
   "tables": [
     {
       "table": "subject",
@@ -865,7 +865,7 @@
     {
       "table": "diabetes_diabetes",
       "url": "https://docs.google.com/spreadsheets/d/1Zc1ALFmFI8kD_bn0n-u_HfRpZjOpSf10nM-lOuTiS6s/edit#gid=597696160",
-      "version": "1.1",
+      "version": "1.2",
       "columns": [
         {
           "column": "subject_id",
@@ -909,18 +909,32 @@
           "notes": "0 = 'no' 1 = 'yes' Missing values can either be left blank or set to NA."
         },
         {
-          "column": "t1d_dprism_1",
+          "column": "t1d_dprism_ehr_1",
           "description": "indicator of Type 1 Diabetes",
           "data_type": "enumeration",
           "enumerations": ["0", "1"],
           "notes": "0 = 'no' 1 = 'yes' Missing values can either be left blank or set to NA."
         },
         {
-          "column": "t2d_dprism_1",
+          "column": "t1d_dprism_ehr_plus_1",
+          "description": "indicator of Type 1 Diabetes, including self-report",
+          "data_type": "enumeration",
+          "enumerations": ["0", "1"],
+          "notes": "0 = 'no' 1 = 'yes' Missing values can either be left blank or set to NA."
+        },
+        {
+          "column": "t2d_dprism_ehr_1",
           "description": "indicator of Type 2 Diabetes",
           "data_type": "enumeration",
           "enumerations": ["0", "1"],
           "notes": "0 = 'no' 1 = 'yes' Missing values can either be left blank or set to NA."
+        },
+        {
+          "column": "t2d_dprism_ehr_plus_1",
+          "description": "indicator of Type 2 Diabetes, including self-report",
+          "data_type": "enumeration",
+          "enumerations": ["0", "1"],
+          "notes": "0 = 'no' 1 = 'yes' Missing values can either be left blank or set to NA."
         }
       ]
     },

diff --git a/sheets_to_JSON_phenotype.R b/sheets_to_JSON_phenotype.R
@@ -9,7 +9,7 @@ library(jsonlite)
 url <- "https://docs.google.com/spreadsheets/d/1kpWz-6QfjMPVtm62fQwm4hoxzXhR0dnKxVt02fbx9ks"
 model_name <- "PRIMED Phenotype Data Model"
 model_description <- "Data model for phenotype data in the PRIMED consortium"
-model_version <-"1.8"
+model_version <-"1.9"
 
 # table metadata
 meta <- read_sheet(url, sheet="Description", skip=1, col_types="c") %>%

diff --git a/test_data/diabetes_diabetes.tsv b/test_data/diabetes_diabetes.tsv
@@ -1,21 +1,21 @@
-subject_id	age_at_obs	visit	t1d_1	t2d_1	t1d_dprism_1	t2d_dprism_1
-subject1	59	visit_1	0	0	0	0
-subject2	46	visit_1	0	1	0	0
-subject3	55	visit_1	0	0	0	0
-subject4	55	visit_1	0	0	0	0
-subject5	62	visit_1	0	0	0	0
-subject6	55	visit_1	0	0	0	0
-subject7	61	visit_1	0	0	0	0
-subject8	65	visit_1	0	0	0	0
-subject9	66	visit_1	0	0	0	0
-subject10	51	visit_1	0	0	0	1
-subject11	61	visit_1	0	0	0	0
-subject12	55	visit_1	0	0	0	0
-subject13	52	visit_1	0	0	0	0
-subject14	66	visit_1	1	0	0	0
-subject15	57	visit_1	0	0	0	0
-subject16	57	visit_1	0	1	0	0
-subject17	67	visit_1	1	0	0	0
-subject18	59	visit_1	0	0	0	0
-subject19	67	visit_1	1	0	0	0
-subject20	62	visit_1	0	0	0	0
+subject_id	age_at_obs	visit	t1d_1	t2d_1	t1d_dprism_ehr_1	t1d_dprism_ehr_plus_1	t2d_dprism_ehr_1	t2d_dprism_ehr_plus_1
+subject1	59	visit_1	0	0	0	0	0	0
+subject2	46	visit_1	0	1	0	0	0	0
+subject3	55	visit_1	0	0	0	0	0	0
+subject4	55	visit_1	0	0	0	0	0	0
+subject5	62	visit_1	0	0	0	0	0	0
+subject6	55	visit_1	0	0	0	0	0	0
+subject7	61	visit_1	0	0	0	0	0	0
+subject8	65	visit_1	0	0	0	0	1	0
+subject9	66	visit_1	0	0	0	0	0	1
+subject10	51	visit_1	0	0	0	1	0	0
+subject11	61	visit_1	0	0	0	0	0	0
+subject12	55	visit_1	0	0	0	0	0	0
+subject13	52	visit_1	0	0	0	0	0	0
+subject14	66	visit_1	1	0	0	0	0	0
+subject15	57	visit_1	0	0	0	0	0	0
+subject16	57	visit_1	0	1	0	0	0	0
+subject17	67	visit_1	1	0	0	0	0	0
+subject18	59	visit_1	0	0	0	0	0	0
+subject19	67	visit_1	1	0	0	0	0	0
+subject20	62	visit_1	0	0	0	0	0	0
diff --git a/test_data/phenotype_harmonized.tsv b/test_data/phenotype_harmonized.tsv
@@ -7,7 +7,7 @@ cmqt_lipids	17ce825be3d94425e26c08987fa78cd9	gs://fc-e3b6ff37-761e-4e53-89c0-fb2
 cmqt_hematology	155f8eac3c84a91fdb17eff3739e7799	gs://fc-e3b6ff37-761e-4e53-89c0-fb243b8bd8e5/test_data/cmqt_hematology.tsv	gs://fc-e3b6ff37-761e-4e53-89c0-fb243b8bd8e5/test_data/readme.tsv	20	20
 cmqt_glycemic	4af06300bac223b5462356532fa98729	gs://fc-e3b6ff37-761e-4e53-89c0-fb243b8bd8e5/test_data/cmqt_glycemic.tsv	gs://fc-e3b6ff37-761e-4e53-89c0-fb243b8bd8e5/test_data/readme.tsv	20	20
 cmqt_kidney_function	35962811d3e9c081de82e4f3f8e4bfb5	gs://fc-e3b6ff37-761e-4e53-89c0-fb243b8bd8e5/test_data/cmqt_kidney_function.tsv	gs://fc-e3b6ff37-761e-4e53-89c0-fb243b8bd8e5/test_data/readme.tsv	20	20
-diabetes_diabetes	bf4ff29e1312614c66a08a27b4d129c5	gs://fc-e3b6ff37-761e-4e53-89c0-fb243b8bd8e5/test_data/diabetes_diabetes.tsv	gs://fc-e3b6ff37-761e-4e53-89c0-fb243b8bd8e5/test_data/readme.tsv	20	20
+diabetes_diabetes	cc22b4c190d773f5c9f27065ce6e32ce	gs://fc-e3b6ff37-761e-4e53-89c0-fb243b8bd8e5/test_data/diabetes_diabetes.tsv	gs://fc-e3b6ff37-761e-4e53-89c0-fb243b8bd8e5/test_data/readme.tsv	20	20
 cvd_cad	26439afc298880695450a008d3f92290	gs://fc-e3b6ff37-761e-4e53-89c0-fb243b8bd8e5/test_data/cvd_cad.tsv	gs://fc-e3b6ff37-761e-4e53-89c0-fb243b8bd8e5/test_data/readme.tsv	20	20
 cancer_breast	322959303fc4c173f503aaea46fbccbf	gs://fc-e3b6ff37-761e-4e53-89c0-fb243b8bd8e5/test_data/cancer_breast.tsv	gs://fc-e3b6ff37-761e-4e53-89c0-fb243b8bd8e5/test_data/readme.tsv	20	20
 cancer_prostate	af65adca42868373afc81bef2dd2cd2b	gs://fc-e3b6ff37-761e-4e53-89c0-fb243b8bd8e5/test_data/cancer_prostate.tsv	gs://fc-e3b6ff37-761e-4e53-89c0-fb243b8bd8e5/test_data/readme.tsv	20	20

diff --git a/test_data/test_files.R b/test_data/test_files.R
@@ -169,8 +169,10 @@ diabetes_diabetes <- tibble(
   visit=rep("visit_1", n),
   t1d_1=sample(x = c(0, 1), size = n, replace = TRUE, prob = c(0.95, 0.05)),
   t2d_1=sample(x = c(0, 1), size = n, replace = TRUE, prob = c(0.95, 0.05)),
-  t1d_dprism_1=sample(x = c(0, 1), size = n, replace = TRUE, prob = c(0.95, 0.05)),
-  t2d_dprism_1=sample(x = c(0, 1), size = n, replace = TRUE, prob = c(0.95, 0.05)),
+  t1d_dprism_ehr_1=sample(x = c(0, 1), size = n, replace = TRUE, prob = c(0.95, 0.05)),
+  t1d_dprism_ehr_plus_1=sample(x = c(0, 1), size = n, replace = TRUE, prob = c(0.95, 0.05)),
+  t2d_dprism_ehr_1=sample(x = c(0, 1), size = n, replace = TRUE, prob = c(0.95, 0.05)),
+  t2d_dprism_ehr_plus_1=sample(x = c(0, 1), size = n, replace = TRUE, prob = c(0.95, 0.05)),
 )
 
 set.seed(4)