Merge branch 'main' into 1.4.0

# Changes to be committed: # new file: Best_Practices # new file: VERSION.py # modified: docs/io-domain.md # modified: docs/provenance-domain.md # modified: examples/HCV1a.json # modified: examples/HIVE_metagenomics.json # modified: examples/glycosylation-sites-UniCarbKB.json # modified: scripts/validate.py
biocompute-objects · Jul 16, 2020 · 6e9e18d · 6e9e18d
2 parents 88b9426 + 5c7f83d
commit 6e9e18d
Show file tree

Hide file tree

Showing 8 changed files with 47 additions and 34 deletions.
diff --git a/Best_Practices b/Best_Practices
@@ -0,0 +1 @@
+
diff --git a/VERSION.py b/VERSION.py
@@ -0,0 +1,3 @@
+VERSION_MAJOR = "1.4"
+VERSION_MINOR = ".0"
+VERSION = VERSION_MAJOR + ('.' + VERSION_MINOR if VERSION_MINOR else '')
diff --git a/docs/io-domain.md b/docs/io-domain.md
@@ -12,8 +12,8 @@ Condensed exampled:
 
 ```json
 "io_domain": {
-        "input_subdomain": {
-        }, 
+        "input_subdomain": [
+        ], 
         "output_subdomain": [
         ]
 }, 

diff --git a/docs/provenance-domain.md b/docs/provenance-domain.md
@@ -93,6 +93,7 @@ The fields from the `contributor` object (described in [section 2.1.9](/provenan
 ### 2.1.4 Inheritance/derivation "derived_from"
 
 If the object is derived from another, this field will specify the parent object, in the form of the ‘object_id’. If the object is novel than the field is not included. 
+=======
 
 ```json
 "derived_from" : "https://github.com/biocompute-objects/BCO_Specification/blob/1.2.1-beta/HCV1a.json"
@@ -159,7 +160,7 @@ This is a list to hold contributor identifiers and a description of their type o
 
 ### 2.1.10 License "license"
 
-A space for Creative Commons licence or other licence information (text). The default or recommended licence can be _Creative Commons Attribution 4.0 International_ identified as https://spdx.org/licenses/CC-BY-4.0.html
+A space for Creative Commons licence or other license information (text). The default or recommended licence can be _Creative Commons Attribution 4.0 International_ identified as https://spdx.org/licenses/CC-BY-4.0.html
 
 ```json
 "license": "https://spdx.org/licenses/CC-BY-4.0.html"

diff --git a/examples/HCV1a.json b/examples/HCV1a.json
@@ -1,7 +1,7 @@
 {
     "object_id": "https://w3id.org/biocompute/1.3.0/examples/HCV1a.json",
     "etag": "8e03f6f65e2caae86770a64a9ebef3e0651d4675a96687e5b148fda181c9cdc0",
-    "spec_version": "https://w3id.org/biocompute/1.3.0/",
+    "spec_version": "https://w3id.org/ieee/ieee-2791-schema/",
     "provenance_domain": {
         "name": "HCV1a ledipasvir resistance SNP detection",
         "version": "2.9",
@@ -71,7 +71,7 @@
     ],
     "extension_domain": [
         {
-            "extension_schema": "https://github.com/biocompute-objects/BCO_Specification/blob/1.4.0/schemas/extension_domain/fhir_extension.json",
+            "extension_schema": "https://raw.githubusercontent.com/biocompute-objects/extension_domain/master/FHIR/fhir_extension.json",
             "fhir_extension": [
                 {
                     "fhir_endpoint": "http://fhirtest.uhn.ca/baseDstu3",
@@ -102,7 +102,7 @@
             ]
         }, 
         {
-            "extension_schema": "https://github.com/biocompute-objects/BCO_Specification/blob/1.4.0/schemas/extension_domain/fhir_extension.json",
+            "extension_schema": "https://raw.githubusercontent.com/biocompute-objects/extension_domain/master/SCM/scm_extension.json",
             "scm_extension": {
                 "scm_repository": "https://github.com/example/repo1",
                 "scm_type": "git",

diff --git a/examples/HIVE_metagenomics.json b/examples/HIVE_metagenomics.json
@@ -1,7 +1,7 @@
 {
     "object_id": "https://w3id.org/biocompute/1.3.0/examples/HIVE_metagenomics.json",
-    "checksum": "09d55a44601184330b05dae6c3d49e9c3821f528a93f958edec92504fef41970",
-    "spec_version" : "https://w3id.org/biocompute/1.3.0/",
+    "etag": "09d55a44601184330b05dae6c3d49e9c3821f528a93f958edec92504fef41970",
+    "spec_version" : "https://w3id.org/ieee/ieee-2791-schema/",
     "provenance_domain": {
         "name": "Healthy human fecal metagenomic diversity", 
         "version": "1.0.0",
@@ -48,15 +48,18 @@
         "Identify the general community composition of organisms in a human [taxID:9606] fecal [UBERON:0001988] sample, ", 
         "CensuScope is used to do a census of the composition of the read files. Based on a user-defined threshold, organisms identified are used for alignment in the Hexagon alignment."
     ],
-    "extension_domain":{
-        "scm_extension": {
-            "scm_repository": "https://github.com/biocompute-objects/HIVE_metagenomics",
-            "scm_type": "git",
-            "scm_commit": "e4620f642fb20557f6c679397696614305ed07b1",
-            "scm_path": "biocompute-objects/HIVE_metagenomics",
-            "scm_preview": "https://github.com/example/repo1/blob/c9ffea0b60fa3bcf8e138af7c99ca141a6b8fb21/workflow/hive-viral-mutation-detection.cwl"
-      }
-    },
+    "extension_domain":[
+        {
+            "extension_schema": "https://raw.githubusercontent.com/biocompute-objects/extension_domain/master/SCM/scm_extension.json",
+            "scm_extension": {
+                "scm_repository": "https://github.com/biocompute-objects/HIVE_metagenomics",
+                "scm_type": "git",
+                "scm_commit": "e4620f642fb20557f6c679397696614305ed07b1",
+                "scm_path": "biocompute-objects/HIVE_metagenomics",
+                "scm_preview": "https://github.com/example/repo1/blob/c9ffea0b60fa3bcf8e138af7c99ca141a6b8fb21/workflow/hive-viral-mutation-detection.cwl"
+                }
+        }
+    ],
     "description_domain": {
         "keywords": [
             "metagenome", 

diff --git a/examples/glycosylation-sites-UniCarbKB.json b/examples/glycosylation-sites-UniCarbKB.json
@@ -1,7 +1,7 @@
 {
     "object_id": "https://w3id.org/biocompute/1.3.0/examples/glycosylation-sites-UniCarbKB",
-    "checksum": "c0b41938a47f7b7689a34f5d89707f039e210f3cc22857b80070f73cbcd2e669",
-    "spec_version" : "https://w3id.org/biocompute/1.3.0/",
+    "etag": "c0b41938a47f7b7689a34f5d89707f039e210f3cc22857b80070f73cbcd2e669",
+    "spec_version" : "https://w3id.org/ieee/ieee-2791-schema/",
     "provenance_domain":{
         "name": "glycosylation-sites-UniCarbKB",
         "version": "1.0",
@@ -44,18 +44,26 @@
     "usability_domain":[
         "List of human [taxid:9606] proteins with information on glycosylation sites from UniCarbKB database [https://academic.oup.com/nar/article/42/D1/D215/1052197, https://doi.org/10.1093/nar/gkt1128]"
     ],
-    "extension_domain":{
-        "license":{
-            "data_license": "https://creativecommons.org/licenses/by/4.0/",
-            "scripts_license": "https://www.gnu.org/licenses/gpl-3.0.en.html"
+    "extension_domain":[
+        {
+            "extension_schema": "https://raw.githubusercontent.com/biocompute-objects/extension_domain/master/License/license_extension.json",
+            "license_extension":{
+                "data_license": "https://creativecommons.org/licenses/by/4.0/",
+                "scripts_license": "https://www.gnu.org/licenses/gpl-3.0.en.html"
+            }
         },
-        "scm_extension":{  
-            "scm_repository": "https://github.com/GW-HIVE/glygen-backend-integration/",
-            "scm_type": "git",
-            "scm_commit": "d34b85553e775dd5452005d786fe6e47d6048ee0",
-            "scm_path": "/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_unicarbkb_glytoucan.readme.txt"
+        {
+
+            "extension_schema": "https://raw.githubusercontent.com/biocompute-objects/extension_domain/master/SCM/scm_extension.json",
+            "scm_extension":{  
+                "scm_repository": "https://github.com/GW-HIVE/glygen-backend-integration/",
+                "scm_type": "git",
+                "scm_commit": "d34b85553e775dd5452005d786fe6e47d6048ee0",
+                "scm_path": "/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_unicarbkb_glytoucan.readme.txt"
+            }
         }
-    },
+
+    ],
     "description_domain":{
         "keywords":[
            "protein", 
@@ -214,10 +222,8 @@
     },
     "error_domain":{
         "empirical_error":{
+            "comment": "Unique value statistics for the dataset",
             "statistics":[
-                {
-                    "comment": "Unique value statistics for the dataset"
-                },
                 {
                     "key": "uniprotkb_canonical_ac",
                     "value":92,
@@ -251,7 +257,7 @@
                 {
                     "key": "glycosylation_type",
                     "value":3,
-                    "description": "Type of glycosylation [linkage type]"
+                    "description": "Type of glycosylation linkage type"
                 }
             ]
         },

diff --git a/scripts/validate.py b/scripts/validate.py
@@ -6,7 +6,6 @@
 """Used to test a BCO against the schema. The following commands were used to run the script:
 
     cd BCO_specification/
-    python -m venv env
     source env/bin/activate
     pip install jsonschema jsonref
     python validate.py HCV1a.json $PWD/schemas/biocomputeobject.json