From 50f672077bbd58cea838729ae70b55e7946d0b80 Mon Sep 17 00:00:00 2001 From: Nalika Palayoor Date: Fri, 17 Jan 2025 17:18:12 -0500 Subject: [PATCH 1/5] Update seed to be seed.subsystems --- src/bioregistry/data/bioregistry.json | 204 +++++++++++++++++--------- 1 file changed, 131 insertions(+), 73 deletions(-) diff --git a/src/bioregistry/data/bioregistry.json b/src/bioregistry/data/bioregistry.json index 6e38d6bae..2ee5af964 100644 --- a/src/bioregistry/data/bioregistry.json +++ b/src/bioregistry/data/bioregistry.json @@ -661,6 +661,41 @@ "database": "Q111134507" } }, + "absd": { + "contact": { + "email": "nicolas.maillet@pasteur.fr", + "name": "Nicolas Maillet", + "orcid": "0000-0003-1611-5243" + }, + "contributor": { + "email": "palayoor.n@northeastern.edu", + "github": "nalikapalayoor", + "name": "Nalika Palayoor", + "orcid": "0009-0008-8406-631X" + }, + "description": "The AntiBody Sequence Database is a public dataset for antibody sequence data. It provides unique identifiers for antibody sequences, including both immunoglobulin and single-chain variable fragment sequences. These are are critical for immunological studies, and allows users to search and retrieve antibody sequences based on sequence similarity and specificity, and other biological properties.", + "example": "81d0ea69a9ab134f6ba68314e982171a367d3ab739c85c5ba49701dd02170ed3", + "github_request_issue": 1362, + "homepage": "https://absd.pasteur.cloud", + "name": "AntiBody Sequence Database", + "pattern": "^[a-f0-9]{64}$", + "publications": [ + { + "doi": "10.1093/nargab/lqae171", + "pmc": "PMC11655285", + "pubmed": "39703430", + "title": "AntiBody Sequence Database", + "year": 2024 + } + ], + "reviewer": { + "email": "b.gyori@northeastern.edu", + "github": "bgyori", + "name": "Benjamin M. Gyori", + "orcid": "0000-0001-9439-5346" + }, + "uri_format": "https://absd.pasteur.cloud/antibody/$1" + }, "ac": { "contributor": { "email": "cthoyt@gmail.com", @@ -37448,6 +37483,29 @@ "https://genomebiology.biomedcentral.com/articles/10.1186/gb-2007-8-10-r229" ] }, + "evr": { + "contact": { + "email": "cthoyt@gmail.com", + "github": "cthoyt", + "name": "Charles Tapley Hoyt", + "orcid": "0000-0003-4423-4370" + }, + "contributor": { + "email": "cthoyt@gmail.com", + "github": "cthoyt", + "name": "Charles Tapley Hoyt", + "orcid": "0000-0003-4423-4370" + }, + "description": "An open, community-driven registry of conference and event venues.\n\nEVR assigns persistent identifiers (PIDs) to make referencing venues FAIR. This is similar to how ORCID assigns PIDs to researchers and ROR assigns PIDs to research organizations.\n\nThis benefits researchers assembling information about in-person conferences and events by enabling them to refer in an unambiguous way to the venue where it takes place.\n\nThis repository follows the [Open Data, Open Code, Open Infrastructure (O3) principles](https://www.nature.com/articles/s41597-024-03406-w), meaning that the data and code are all in one repository that anyone can contribute to.", + "example": "0000001", + "github_request_issue": 1363, + "homepage": "https://cthoyt.com/evr", + "license": "CC0-1.0", + "name": "Event Venue Registry", + "pattern": "^\\d{7}$", + "repository": "https://github.com/cthoyt/evr", + "uri_format": "https://cthoyt.com/evr/$1" + }, "exac.gene": { "biocontext": { "prefix": "EXAC.GENE" @@ -104334,79 +104392,6 @@ "uri_format": "https://sed-ml.org/urns.html#language:$1" } }, - "seed": { - "biocontext": { - "prefix": "SEED" - }, - "contributor_extras": [ - { - "email": "aireland@lbl.gov", - "github": "ialarmedalien", - "name": "AJ Ireland", - "orcid": "0000-0003-1982-9065" - }, - { - "email": "seaver@anl.gov", - "github": "samseaver", - "name": "Sam Seaver", - "orcid": "0000-0002-7674-5194" - } - ], - "go": { - "description": "Project to annotate the first 1000 sequenced genomes, develop detailed metabolic reconstructions, and construct the corresponding stoichiometric matrices", - "homepage": "http://www.theseed.org", - "name": "The SEED;", - "prefix": "SEED", - "uri_format": "http://www.theseed.org/linkin.cgi?id=$1" - }, - "mappings": { - "biocontext": "SEED", - "go": "SEED", - "miriam": "seed", - "n2t": "seed", - "ncbi": "SEED" - }, - "miriam": { - "deprecated": true, - "description": "This cooperative effort, which includes Fellowship for Interpretation of Genomes (FIG), Argonne National Laboratory, and the University of Chicago, focuses on the development of the comparative genomics environment called the SEED. It is a framework to support comparative analysis and annotation of genomes, and the development of curated genomic data (annotation). Curation is performed at the level of subsystems by an expert annotator, across many genomes, and not on a gene by gene basis. This collection references subsystems.", - "id": "00000552", - "name": "SEED Subsystem", - "namespaceEmbeddedInLui": false, - "pattern": "^\\w+$", - "prefix": "seed", - "sampleId": "Biotin_biosynthesis" - }, - "n2t": { - "description": "This cooperative effort, which includes Fellowship for Interpretation of Genomes (FIG), Argonne National Laboratory, and the University of Chicago, focuses on the development of the comparative genomics environment called the SEED. It is a framework to support comparative analysis and annotation of genomes, and the development of curated genomic data (annotation). Curation is performed at the level of subsystems by an expert annotator, across many genomes, and not on a gene by gene basis. This collection references subsystems.", - "example": "Biotin_biosynthesis", - "homepage": "http://seed-viewer.theseed.org/seedviewer.cgi", - "name": "SEED Subsystem at Argonne National Laboratory", - "namespaceEmbeddedInLui": false, - "pattern": "^\\w+$", - "prefix": "seed", - "uri_format": "http://seed-viewer.theseed.org/seedviewer.cgi?page=Subsystems&subsystem=$1" - }, - "name": "SEED Subsystem", - "ncbi": { - "example": "fig|83331.1.peg.1", - "homepage": "http://www.theseed.org", - "name": "The SEED Database", - "prefix": "SEED" - }, - "publications": [ - { - "doi": "10.1093/nar/gki866", - "pmc": "PMC1251668", - "pubmed": "16214803", - "title": "The Subsystems Approach to Genome Annotation and its Use in the Project to Annotate 1000 Genomes", - "year": 2005 - } - ], - "repository": "https://github.com/TheSEED", - "synonyms": [ - "seed.subsystem" - ] - }, "seed.compound": { "biocontext": { "prefix": "SEED.COMPOUND" @@ -104475,6 +104460,79 @@ "uri_format": "http://modelseed.org/biochem/reactions/$1" } }, + "seed.subsystems": { + "biocontext": { + "prefix": "SEED.SUBSYSTEMS" + }, + "contributor_extras": [ + { + "email": "aireland@lbl.gov", + "github": "ialarmedalien", + "name": "AJ Ireland", + "orcid": "0000-0003-1982-9065" + }, + { + "email": "seaver@anl.gov", + "github": "samseaver", + "name": "Sam Seaver", + "orcid": "0000-0002-7674-5194" + } + ], + "go": { + "description": "Project to annotate the first 1000 sequenced genomes, develop detailed metabolic reconstructions, and construct the corresponding stoichiometric matrices", + "homepage": "http://www.theseed.org", + "name": "The SEED;", + "prefix": "SEED.SUBSYSTEMS", + "uri_format": "http://www.theseed.org/linkin.cgi?id=$1" + }, + "mappings": { + "biocontext": "SEED.SUBSYSTEMS", + "go": "SEED.SUBSYSTEMS", + "miriam": "seed.subsystems", + "n2t": "seed.subsystems", + "ncbi": "SEED.SUBSYSTEMS" + }, + "miriam": { + "deprecated": true, + "description": "This cooperative effort, which includes Fellowship for Interpretation of Genomes (FIG), Argonne National Laboratory, and the University of Chicago, focuses on the development of the comparative genomics environment called the SEED. It is a framework to support comparative analysis and annotation of genomes, and the development of curated genomic data (annotation). Curation is performed at the level of subsystems by an expert annotator, across many genomes, and not on a gene by gene basis. This collection references subsystems.", + "id": "00000552", + "name": "SEED Subsystem", + "namespaceEmbeddedInLui": false, + "pattern": "^\\w+$", + "prefix": "seed.subsystems", + "sampleId": "Biotin_biosynthesis" + }, + "n2t": { + "description": "This cooperative effort, which includes Fellowship for Interpretation of Genomes (FIG), Argonne National Laboratory, and the University of Chicago, focuses on the development of the comparative genomics environment called the SEED. It is a framework to support comparative analysis and annotation of genomes, and the development of curated genomic data (annotation). Curation is performed at the level of subsystems by an expert annotator, across many genomes, and not on a gene by gene basis. This collection references subsystems.", + "example": "Biotin_biosynthesis", + "homepage": "https://modelseed.org/", + "name": "SEED Subsystem at Argonne National Laboratory", + "namespaceEmbeddedInLui": false, + "pattern": "^\\w+$", + "prefix": "seed.subsystems", + "uri_format": "https://pubseed.theseed.org/SubsysEditor.cgi?page=ShowSubsystem&subsystem=$1" + }, + "name": "SEED Subsystem", + "ncbi": { + "example": "fig|83331.1.peg.1", + "homepage": "http://www.theseed.org", + "name": "The SEED Database", + "prefix": "SEED.SUBSYSTEMS" + }, + "publications": [ + { + "doi": "10.1093/nar/gki866", + "pmc": "PMC1251668", + "pubmed": "16214803", + "title": "The Subsystems Approach to Genome Annotation and its Use in the Project to Annotate 1000 Genomes", + "year": 2005 + } + ], + "repository": "https://github.com/TheSEED", + "synonyms": [ + "seed" + ] + }, "seinet": { "contributor": { "email": "cthoyt@gmail.com", From 05359559d2d738b701addc687135ce14139f8767 Mon Sep 17 00:00:00 2001 From: Nalika Palayoor Date: Fri, 17 Jan 2025 18:38:32 -0500 Subject: [PATCH 2/5] Reverted mistaken updates in seed.subsystem prefix --- src/bioregistry/data/bioregistry.json | 25 +++++++++++++------------ 1 file changed, 13 insertions(+), 12 deletions(-) diff --git a/src/bioregistry/data/bioregistry.json b/src/bioregistry/data/bioregistry.json index 2ee5af964..fe99f0846 100644 --- a/src/bioregistry/data/bioregistry.json +++ b/src/bioregistry/data/bioregistry.json @@ -104460,9 +104460,10 @@ "uri_format": "http://modelseed.org/biochem/reactions/$1" } }, - "seed.subsystems": { + "seed.subsystem": { "biocontext": { - "prefix": "SEED.SUBSYSTEMS" + "prefix": "SEED.SUBSYSTEM", + "uri_format": "https://pubseed.theseed.org/SubsysEditor.cgi?page=ShowSubsystem&subsystem=$1" }, "contributor_extras": [ { @@ -104482,15 +104483,15 @@ "description": "Project to annotate the first 1000 sequenced genomes, develop detailed metabolic reconstructions, and construct the corresponding stoichiometric matrices", "homepage": "http://www.theseed.org", "name": "The SEED;", - "prefix": "SEED.SUBSYSTEMS", + "prefix": "SEED", "uri_format": "http://www.theseed.org/linkin.cgi?id=$1" }, "mappings": { - "biocontext": "SEED.SUBSYSTEMS", - "go": "SEED.SUBSYSTEMS", - "miriam": "seed.subsystems", - "n2t": "seed.subsystems", - "ncbi": "SEED.SUBSYSTEMS" + "biocontext": "SEED", + "go": "SEED", + "miriam": "seed", + "n2t": "seed", + "ncbi": "SEED" }, "miriam": { "deprecated": true, @@ -104499,7 +104500,7 @@ "name": "SEED Subsystem", "namespaceEmbeddedInLui": false, "pattern": "^\\w+$", - "prefix": "seed.subsystems", + "prefix": "seed", "sampleId": "Biotin_biosynthesis" }, "n2t": { @@ -104509,15 +104510,15 @@ "name": "SEED Subsystem at Argonne National Laboratory", "namespaceEmbeddedInLui": false, "pattern": "^\\w+$", - "prefix": "seed.subsystems", - "uri_format": "https://pubseed.theseed.org/SubsysEditor.cgi?page=ShowSubsystem&subsystem=$1" + "prefix": "seed", + "uri_format": "http://seed-viewer.theseed.org/seedviewer.cgi?page=Subsystems&subsystem=$1" }, "name": "SEED Subsystem", "ncbi": { "example": "fig|83331.1.peg.1", "homepage": "http://www.theseed.org", "name": "The SEED Database", - "prefix": "SEED.SUBSYSTEMS" + "prefix": "SEED" }, "publications": [ { From fadab01e1521f9e988c08839cacd52d6d2fd161d Mon Sep 17 00:00:00 2001 From: Ben Gyori Date: Sat, 18 Jan 2025 10:23:52 -0500 Subject: [PATCH 3/5] Update prefix in mismatch.json --- src/bioregistry/data/mismatch.json | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/bioregistry/data/mismatch.json b/src/bioregistry/data/mismatch.json index 65da6b416..b87cd0016 100644 --- a/src/bioregistry/data/mismatch.json +++ b/src/bioregistry/data/mismatch.json @@ -207,7 +207,7 @@ "bartoc": "1756", "lov": "sao" }, - "seed": { + "seed.subsystem": { "fairsharing": "FAIRsharing.68b03f" }, "string": { From 6a6b88585d95e35fcb9f16b7d14f5508e77e9dba Mon Sep 17 00:00:00 2001 From: Ben Gyori Date: Sat, 18 Jan 2025 10:26:53 -0500 Subject: [PATCH 4/5] Override URI format for seed --- src/bioregistry/data/bioregistry.json | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/src/bioregistry/data/bioregistry.json b/src/bioregistry/data/bioregistry.json index 415b7fb6f..abd293fa9 100644 --- a/src/bioregistry/data/bioregistry.json +++ b/src/bioregistry/data/bioregistry.json @@ -104579,7 +104579,8 @@ "repository": "https://github.com/TheSEED", "synonyms": [ "seed" - ] + ], + "uri_format": "https://pubseed.theseed.org/SubsysEditor.cgi?page=ShowSubsystem&subsystem=$1" }, "seinet": { "contributor": { From 62e6ec2563bd27c194636b7069530e1ce4244d97 Mon Sep 17 00:00:00 2001 From: Ben Gyori Date: Sat, 18 Jan 2025 11:25:25 -0500 Subject: [PATCH 5/5] Revert more changes in mapped content --- src/bioregistry/data/bioregistry.json | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/src/bioregistry/data/bioregistry.json b/src/bioregistry/data/bioregistry.json index abd293fa9..8ee82a33f 100644 --- a/src/bioregistry/data/bioregistry.json +++ b/src/bioregistry/data/bioregistry.json @@ -104509,8 +104509,7 @@ }, "seed.subsystem": { "biocontext": { - "prefix": "SEED.SUBSYSTEM", - "uri_format": "https://pubseed.theseed.org/SubsysEditor.cgi?page=ShowSubsystem&subsystem=$1" + "prefix": "SEED" }, "contributor_extras": [ { @@ -104553,7 +104552,7 @@ "n2t": { "description": "This cooperative effort, which includes Fellowship for Interpretation of Genomes (FIG), Argonne National Laboratory, and the University of Chicago, focuses on the development of the comparative genomics environment called the SEED. It is a framework to support comparative analysis and annotation of genomes, and the development of curated genomic data (annotation). Curation is performed at the level of subsystems by an expert annotator, across many genomes, and not on a gene by gene basis. This collection references subsystems.", "example": "Biotin_biosynthesis", - "homepage": "https://modelseed.org/", + "homepage": "http://seed-viewer.theseed.org/seedviewer.cgi", "name": "SEED Subsystem at Argonne National Laboratory", "namespaceEmbeddedInLui": false, "pattern": "^\\w+$",