Manually update MIRIAM

biopragmatics · Oct 30, 2023 · 98527c7 · 98527c7
1 parent 6490261
commit 98527c7
Show file tree

Hide file tree

Showing 3 changed files with 175 additions and 9 deletions.
diff --git a/src/bioregistry/data/bioregistry.json b/src/bioregistry/data/bioregistry.json
@@ -50097,9 +50097,9 @@
       "description": "The genome assembly database contains detailed information about genome assemblies for eukaryota, bacteria and archaea. The scope of the genome collections database does not extend to viruses, viroids and bacteriophage.",
       "homepage": "https://www.ebi.ac.uk/ena/browse/genome-assembly-database",
       "id": "00000607",
-      "name": "Genome assembly database",
+      "name": "Genome assembly database - INSDC accessions",
       "namespaceEmbeddedInLui": false,
-      "pattern": "^GC[AF]_[0-9]{9}\\.[0-9]+$",
+      "pattern": "^GCA_[0-9]{9}(\\.[0-9]+)?$",
       "prefix": "insdc.gca",
       "providers": [
         {
@@ -50124,6 +50124,23 @@
       "uri_format": "https://www.ncbi.nlm.nih.gov/assembly/$1"
     }
   },
+  "insdc.gcf": {
+    "mappings": {
+      "miriam": "insdc.gcf"
+    },
+    "miriam": {
+      "deprecated": false,
+      "description": "The genome assembly database contains detailed information about genome assemblies for eukaryota, bacteria and archaea. The scope of the genome collections database RefSeq accessions does not extend to viroids and bacteriophage.",
+      "homepage": "https://www.ncbi.nlm.nih.gov/",
+      "id": "00001030",
+      "name": "Genome assembly database - RefSeq accessions",
+      "namespaceEmbeddedInLui": false,
+      "pattern": "^GCF_[0-9]{9}(\\.[0-9]+)?$",
+      "prefix": "insdc.gcf",
+      "sampleId": "GCF_000001405",
+      "uri_format": "https://www.ncbi.nlm.nih.gov/datasets/genome/$1"
+    }
+  },
   "insdc.run": {
     "comment": "https://www.insdc.org/ is the authoritative source for INSDC. However, confusingly, they don't mention runs in this table. I think we should ask them to include. ENA is a partner and they have documentation [here](https://ena-docs.readthedocs.io/en/latest/submit/general-guide/accessions.html). Runs | (E\\|D\\|S)RR[0-9]{6,} | ERR123456 -- | -- | --",
     "contributor": {
@@ -50208,9 +50225,9 @@
         {
           "code": "ddbj",
           "description": "DDBJ Sequence Read Archive (DRA)",
-          "homepage": "http://trace.ddbj.nig.ac.jp/dra/",
+          "homepage": "https://www.ddbj.nig.ac.jp/dra/index-e.html",
           "name": "DDBJ Sequence Read Archive (DRA)",
-          "uri_format": "http://trace.ddbj.nig.ac.jp/DRASearch/experiment?acc=$1"
+          "uri_format": "https://ddbj.nig.ac.jp/resource/sra-experiment/$1"
         }
       ],
       "sampleId": "SRX000007",
@@ -56189,10 +56206,23 @@
       "aberowl": "MAXO",
       "biolink": "MAXO",
       "bioportal": "MAXO",
+      "miriam": "maxo",
       "obofoundry": "maxo",
       "ols": "maxo",
       "ontobee": "MAXO"
     },
+    "miriam": {
+      "deprecated": false,
+      "description": "An ontology to represent medically relevant actions, procedures, therapies, interventions, and recommendations.",
+      "homepage": "https://www.ebi.ac.uk/ols4/ontologies/maxo",
+      "id": "00001032",
+      "name": "Medical Action Ontology",
+      "namespaceEmbeddedInLui": false,
+      "pattern": "\\d{7}",
+      "prefix": "maxo",
+      "sampleId": "0001073",
+      "uri_format": "https://www.ebi.ac.uk/ols4/ontologies/maxo/terms?obo_id=MAXO:$1"
+    },
     "obofoundry": {
       "appears_in": [
         "ecto"

diff --git a/src/bioregistry/data/external/miriam/processed.json b/src/bioregistry/data/external/miriam/processed.json
@@ -4812,9 +4812,9 @@
     "description": "The genome assembly database contains detailed information about genome assemblies for eukaryota, bacteria and archaea. The scope of the genome collections database does not extend to viruses, viroids and bacteriophage.",
     "homepage": "https://www.ebi.ac.uk/ena/browse/genome-assembly-database",
     "id": "00000607",
-    "name": "Genome assembly database",
+    "name": "Genome assembly database - INSDC accessions",
     "namespaceEmbeddedInLui": false,
-    "pattern": "^GC[AF]_[0-9]{9}\\.[0-9]+$",
+    "pattern": "^GCA_[0-9]{9}(\\.[0-9]+)?$",
     "prefix": "insdc.gca",
     "providers": [
       {
@@ -4828,6 +4828,18 @@
     "sampleId": "GCA_000155495.1",
     "uri_format": "https://www.ebi.ac.uk/ena/data/view/$1"
   },
+  "insdc.gcf": {
+    "deprecated": false,
+    "description": "The genome assembly database contains detailed information about genome assemblies for eukaryota, bacteria and archaea. The scope of the genome collections database RefSeq accessions does not extend to viroids and bacteriophage.",
+    "homepage": "https://www.ncbi.nlm.nih.gov/",
+    "id": "00001030",
+    "name": "Genome assembly database - RefSeq accessions",
+    "namespaceEmbeddedInLui": false,
+    "pattern": "^GCF_[0-9]{9}(\\.[0-9]+)?$",
+    "prefix": "insdc.gcf",
+    "sampleId": "GCF_000001405",
+    "uri_format": "https://www.ncbi.nlm.nih.gov/datasets/genome/$1"
+  },
   "insdc.sra": {
     "deprecated": false,
     "description": "The Sequence Read Archive (SRA) stores raw sequencing data from the next generation of sequencing platforms Data submitted to SRA. It is organized using a metadata model consisting of six objects: study, sample, experiment, run, analysis and submission. The SRA study contains high-level information including goals of the study and literature references, and may be linked to the INSDC BioProject database.",
@@ -5646,6 +5658,18 @@
     "sampleId": "P00747__P07355",
     "uri_format": "http://matrixdb.univ-lyon1.fr//cgi-bin/current/newPort?type=association&value=$1&class=Association"
   },
+  "maxo": {
+    "deprecated": false,
+    "description": "An ontology to represent medically relevant actions, procedures, therapies, interventions, and recommendations.",
+    "homepage": "https://www.ebi.ac.uk/ols4/ontologies/maxo",
+    "id": "00001032",
+    "name": "Medical Action Ontology",
+    "namespaceEmbeddedInLui": false,
+    "pattern": "\\d{7}",
+    "prefix": "maxo",
+    "sampleId": "0001073",
+    "uri_format": "https://www.ebi.ac.uk/ols4/ontologies/maxo/terms?obo_id=MAXO:$1"
+  },
   "mdm": {
     "deprecated": false,
     "description": "The MDM (Medical Data Models) Portal is a meta-data registry for creating, analysing, sharing and reusing medical forms. Electronic forms are central in numerous processes involving data, including the collection of data through electronic health records (EHRs), Electronic Data Capture (EDC), and as case report forms (CRFs) for clinical trials. The MDM Portal provides medical forms in numerous export formats, facilitating the sharing and reuse of medical data models and exchange between information systems.",

diff --git a/src/bioregistry/data/external/miriam/raw.json b/src/bioregistry/data/external/miriam/raw.json
@@ -24576,10 +24576,10 @@
         "id": 1685,
         "infoOnPostmortemAccess": null,
         "mirId": "MIR:00000607",
-        "modified": "2020-03-31T12:32:16.941+0000",
-        "name": "Genome assembly database",
+        "modified": "2023-10-30T09:41:30.572+0000",
+        "name": "Genome assembly database - INSDC accessions",
         "namespaceEmbeddedInLui": false,
-        "pattern": "^GC[AF]_[0-9]{9}\\.[0-9]+$",
+        "pattern": "^GCA_[0-9]{9}(\\.[0-9]+)?$",
         "prefix": "insdc.gca",
         "renderDeprecatedLanding": false,
         "resources": [
@@ -24657,6 +24657,62 @@
         "sampleId": "GCA_000155495.1",
         "successor": null
       },
+      {
+        "created": "2023-10-30T09:39:26.272+0000",
+        "deprecated": false,
+        "deprecationDate": null,
+        "deprecationOfflineDate": null,
+        "deprecationStatement": null,
+        "description": "The genome assembly database contains detailed information about genome assemblies for eukaryota, bacteria and archaea. The scope of the genome collections database RefSeq accessions does not extend to viroids and bacteriophage.",
+        "id": 3719,
+        "infoOnPostmortemAccess": null,
+        "mirId": "MIR:00001030",
+        "modified": "2023-10-30T10:34:56.198+0000",
+        "name": "Genome assembly database - RefSeq accessions",
+        "namespaceEmbeddedInLui": false,
+        "pattern": "^GCF_[0-9]{9}(\\.[0-9]+)?$",
+        "prefix": "insdc.gcf",
+        "renderDeprecatedLanding": false,
+        "resources": [
+          {
+            "authHelpDescription": null,
+            "authHelpUrl": null,
+            "deprecated": false,
+            "deprecationDate": null,
+            "deprecationOfflineDate": null,
+            "deprecationStatement": null,
+            "description": "The National Center for Biotechnology Information advances science and health by providing access to biomedical and genomic information.",
+            "id": 3720,
+            "institution": {
+              "description": "The National Center for Biotechnology Information advances science and health by providing access to biomedical and genomic information.",
+              "homeUrl": "https://www.ncbi.nlm.nih.gov/",
+              "id": 26,
+              "location": {
+                "countryCode": "US",
+                "countryName": "United States"
+              },
+              "name": "National Center for Biotechnology Information",
+              "rorId": "https://ror.org/02meqm098"
+            },
+            "location": {
+              "countryCode": "US",
+              "countryName": "United States"
+            },
+            "mirId": "MIR:00001029",
+            "name": "National Center for Biotechnology Information",
+            "official": true,
+            "protectedUrls": false,
+            "providerCode": "ncbi",
+            "renderDeprecatedLanding": false,
+            "renderProtectedLanding": false,
+            "resourceHomeUrl": "https://www.ncbi.nlm.nih.gov/",
+            "sampleId": "GCF_000001405",
+            "urlPattern": "https://www.ncbi.nlm.nih.gov/datasets/genome/{$id}"
+          }
+        ],
+        "sampleId": "GCF_000001405",
+        "successor": null
+      },
       {
         "created": "2019-06-11T14:16:35.560+0000",
         "deprecated": false,
@@ -28514,6 +28570,62 @@
         "sampleId": "P00747__P07355",
         "successor": null
       },
+      {
+        "created": "2023-10-30T09:40:47.492+0000",
+        "deprecated": false,
+        "deprecationDate": null,
+        "deprecationOfflineDate": null,
+        "deprecationStatement": null,
+        "description": "An ontology to represent medically relevant actions, procedures, therapies, interventions, and recommendations.",
+        "id": 3723,
+        "infoOnPostmortemAccess": null,
+        "mirId": "MIR:00001032",
+        "modified": "2023-10-30T09:40:47.492+0000",
+        "name": "Medical Action Ontology",
+        "namespaceEmbeddedInLui": false,
+        "pattern": "\\d{7}",
+        "prefix": "maxo",
+        "renderDeprecatedLanding": false,
+        "resources": [
+          {
+            "authHelpDescription": null,
+            "authHelpUrl": null,
+            "deprecated": false,
+            "deprecationDate": null,
+            "deprecationOfflineDate": null,
+            "deprecationStatement": null,
+            "description": "The Ontology Lookup Service (OLS) is a repository for biomedical ontologies that aims to provide a single point of access to the latest ontology versions. You can browse the ontologies through the website as well as programmatically via the OLS API. OLS is developed and maintained by the Samples, Phenotypes and Ontologies Team (SPOT)  at EMBL-EBI.",
+            "id": 3724,
+            "institution": {
+              "description": "The Monarch Initiative is an integrative data and analytic platform connecting phenotypes to genotypes across species, bridging basic and applied research with semantics-based analysis. We have created or currently contribute to many essential bio-ontologies that together enable sophisticated and semantically integrated computational analysis across gene, genotype, variant, disease, and phenotype data. ",
+              "homeUrl": "https://monarchinitiative.org/",
+              "id": 3722,
+              "location": {
+                "countryCode": "US",
+                "countryName": "United States"
+              },
+              "name": "Monarch Initiative",
+              "rorId": null
+            },
+            "location": {
+              "countryCode": "US",
+              "countryName": "United States"
+            },
+            "mirId": "MIR:00001031",
+            "name": "MAXO via OLS",
+            "official": true,
+            "protectedUrls": false,
+            "providerCode": "ols",
+            "renderDeprecatedLanding": false,
+            "renderProtectedLanding": false,
+            "resourceHomeUrl": "https://www.ebi.ac.uk/ols4/ontologies/maxo",
+            "sampleId": "0001073",
+            "urlPattern": "https://www.ebi.ac.uk/ols4/ontologies/maxo/terms?obo_id=MAXO:{$id}"
+          }
+        ],
+        "sampleId": "0001073",
+        "successor": null
+      },
       {
         "created": "2019-06-11T14:17:52.138+0000",
         "deprecated": false,