[
{
"id": "agr",
"description": "The primary mission of the Alliance of Genome Resources (the Alliance) is to develop and maintain sustainable genome information resources that facilitate the use of diverse model organisms in understanding the genetic and genomic basis of human biology, health and disease.",
"last-curated": "2022-06-10",
"source": "Alliance of Genome Resources (AGR)",
"source-link": "https://www.alliancegenome.org",
"source-type": "integrator",
"status": "complete",
"data-field": "biology",
"data-type": "MOD",
"data-categories": [
"functional annotation",
"disease-gene association",
"orthology",
"phenotype and disease models"
],
"data-access": [
{
"type": "download",
"location": "https://www.alliancegenome.org/downloads"
}
],
"license": "CC-BY-4.0",
"license-type": "permissive",
"license-link": "https://www.alliancegenome.org/privacy-warranty-licensing",
"license-hat-used": "false",
"license-issues": [],
"license-commentary": [
"The licensing page easily linked through footer.",
"The licensing page makes a distinction between ontologies used in annotation and other data; we will focus on the data portion.",
"For this re-evaluation, the API was not persued as the downloads were straightforward and did not seem to include ontology repackaging."
],
"was-controversial": "false",
"provisional": "true",
"contacts": [
"help@alliancegenome.org"
],
"grants": [
{
"label": "The Alliance is supported by NIH NHGRI and NHLBI: U24HG010859"
},
{
"label": "...additional support from: NIH NHGRI U41HG000739 (FlyBase), NIH NHGRI HG000330 (MGD), NIH NHLBI HL64541 (RGD), NIH NHGRI U24HG001315 (SGD), NIH NHGRI U24HG002223 (WormBase), NIH NHGRI P41HG002659 (ZFIN), NIH NHGRI U41HG002273 (GOC[...])"
}
],
"license-commentary-embeddable": "The licensing page easily linked through footer.
The licensing page makes a distinction between ontologies used in annotation and other data; we will focus on the data portion.
For this re-evaluation, the API was not persued as the downloads were straightforward and did not seem to include ontology repackaging.",
"data-tags": "biology, MOD, functional annotation, disease-gene association, orthology, phenotype and disease models",
"grade-automatic": 5
},
{
"id": "arrayexpress",
"description": "ArrayExpress Archive of Functional Genomics Data stores data from high-throughput functional genomics experiments, and provides these data for reuse to the research community.",
"last-curated": "2018-02-09",
"source": "ArrayExpress",
"source-link": "https://www.ebi.ac.uk/arrayexpress",
"source-type": "repository",
"status": "complete",
"data-field": "biology",
"data-type": "microarray experiments",
"data-categories": [
"functional genomics",
"high-throughput",
"microarray",
"sequencing"
],
"data-access": [
{
"type": "download",
"location": "ftp://ftp.ebi.ac.uk/pub/databases/arrayexpress/data/"
},
{
"type": "api",
"location": "https://www.ebi.ac.uk/arrayexpress/help/programmatic_access.html"
}
],
"license": "custom",
"license-type": "permissive",
"license-link": "https://www.ebi.ac.uk/arrayexpress/help/FAQ.html#data_restrictions",
"license-hat-used": "false",
"license-issues": [
{
"criteria": "A.2.2",
"comment": "Minimal custom permissive terms."
}
],
"license-commentary": [
"The entirety of the license appears to be: \"No restrictions, all public data from ArrayExpress can be used by anyone and our services are completely free of charge.\"",
"Otherwise, ArrayExpress seems to defer its licensing and ToS to the EBI terms; e.g.: https://www.ebi.ac.uk/about/terms-of-use; while these are similarly permissive, we take the ArrayExpress terms at face value.",
"While there are distinctions occasionally made between \"private\" and \"public\" data, it seems that \"private\" is just staging data before publication and does not affect evaluation.",
"There is an interesting section (https://www.ebi.ac.uk/arrayexpress/help/data_availability.html#removal) that describes situations where data needs to be retracted. This section, while alarmingly titled, is has no effect on the license determination."
],
"was-controversial": "false",
"contacts": [
"arrayexpress@ebi.ac.uk",
"https://www.ebi.ac.uk/arrayexpress/help/contact_us.html"
],
"grants": [
{
"label": "ArrayExpress and related activities are supported by member states of the European Molecular Biology Laboratory; European Commission: ENGAGE [201413], EurocanPlatform [260791], GEUVADIS [261123], SLING [226073], SYBARIS [242220], EUROCANPLATFORM [260791], CAGEKID [241669], BioMedBridges [284209] and Gen2Phen [200754]; US National Institutes of Health (the National Human Genome Research Institute, National Institute of Biomedical Imaging and Bioengineering and the National Cancer Institute) [P41 HG003619]; National Center for Biomedical Ontology (one of the National Centers for Biomedical Computing supported by the National Human Genome Research Institute, the National Heart, Lung, and Blood Institute, and National Institutes of Health Common Fund [U54-HG004028]); National Science Foundation Award Number [1127112]."
}
],
"license-commentary-embeddable": "The entirety of the license appears to be: \"No restrictions, all public data from ArrayExpress can be used by anyone and our services are completely free of charge.\"
Otherwise, ArrayExpress seems to defer its licensing and ToS to the EBI terms; e.g.: https://www.ebi.ac.uk/about/terms-of-use; while these are similarly permissive, we take the ArrayExpress terms at face value.
While there are distinctions occasionally made between \"private\" and \"public\" data, it seems that \"private\" is just staging data before publication and does not affect evaluation.
There is an interesting section (https://www.ebi.ac.uk/arrayexpress/help/data_availability.html#removal) that describes situations where data needs to be retracted. This section, while alarmingly titled, is has no effect on the license determination.",
"data-tags": "biology, microarray experiments, functional genomics, high-throughput, microarray, sequencing",
"grade-automatic": 4.5
},
{
"id": "bgee",
"source": "Bgee",
"source-link": "http://bgee.org",
"source-type": "integrator",
"status": "complete",
"description": "Bgee is a database to retrieve and compare gene expression patterns in multiple animal species, produced from multiple data types (RNA-Seq, Affymetrix, in situ hybridization, and EST data).",
"data-field": "biomedical",
"data-type": "x-species",
"data-categories": [
"expression data"
],
"data-access": [
{
"type": "download",
"location": "ftp://ftp.bgee.org/"
}
],
"license": "inconsistent",
"license-type": "unknown",
"license-issues": [
{
"criteria": "A.1.1",
"comment": "While the CC0 tool is explicitly being invoked in main areas, there is some inconsistency, i.e. different ontology licensing and downloads that obviously encompass non-CC0 data."
}
],
"license-commentary": [
"Evaluated as a single cohesive product.",
"Noting CC0 label in footer explicit terms info at https://bgee.org/?page=about",
"https://bgee.org/?page=download from \"About\" page is 404; once an access method for download was determined (looking at various download URLs), one star was awarded accordingly for C.",
"Data sources: https://bgee.org/?page=source",
"Some clarifying information taken from direct communication (https://github.com/reusabledata/reusabledata/issues/126)."
],
"was-controversial": "true",
"provisional": "true",
"last-curated": "2019-07-02",
"grants": [],
"contacts": [
"Bgee@sib.swiss"
],
"license-commentary-embeddable": "Evaluated as a single cohesive product.
Noting CC0 label in footer explicit terms info at https://bgee.org/?page=about
https://bgee.org/?page=download from \"About\" page is 404; once an access method for download was determined (looking at various download URLs), one star was awarded accordingly for C.
Data sources: https://bgee.org/?page=source
Some clarifying information taken from direct communication (https://github.com/reusabledata/reusabledata/issues/126).",
"data-tags": "biomedical, x-species, expression data",
"grade-automatic": 1
},
{
"id": "biocyc-open",
"description": "BioCyc is a collection of 20,028 Pathway/Genome Databases (PGDBs) for model eukaryotes and for thousands of microbes, plus software tools for exploring them. BioCyc is an encyclopedic reference that contains curated data from 130,000 publications.",
"last-curated": "2023-03-08",
"source": "BioCyc Database Collection (BioCyc, public)",
"source-link": "https://www.biocyc.org/",
"source-type": "source",
"status": "complete",
"data-field": "biology",
"data-type": "genomic resource",
"data-categories": [
"sequence",
"gene structure",
"pathways",
"reactions",
"functional annotation"
],
"data-access": [
{
"type": "download",
"location": "https://biocyc.org/download.shtml"
}
],
"license": "custom",
"license-type": "restrictive",
"license-link": "http://biocyc.org/all-reg.shtml",
"license-hat-used": "false",
"license-issues": [
{
"criteria": "A.2.2",
"comment": "Non-standard/custom license."
},
{
"criteria": "B.1",
"comment": "One term of the license is that you must \"Notify SRI that you are making BIOCYC DATABASES available in this manner\"; this, combined with somewhat bulky access (see comments), I believe rises to a barrier to reuse as a manual step invloving people has been added."
},
{
"criteria": "D.1.2",
"comment": "The license specifically notes that it is being licensed to you and you do not have rights betond that; I believe that this puts second-hand reuse in question: you may remix, but a downstream party from you would have to register and comply directly with BioCyc."
}
],
"license-commentary": [
"This curation is for the post two-year embargo window data, excluding EcoCyc and MetaCyc which are current and supported by the NIH; data within that window is available with a subscription.",
"All data access to the downloads is mediated by an individual URL/password/login combination that is obtained by filling out a form and waiting for a response. The curator waited a little over two business days for their response. I do not believe this constitutes a violation of C.2 by itself.",
"The core of the license seems to be essentially: \"...you may use, modify and redistribute the BIOCYC DATABASES on a royalty-free basis, worldwide, and for any purpose; provided that[...]\" changes are identified and BioCyc is credited in a couple of specific ways, including branding.",
"The terms are very interesting. I believe the D.1.2 violation could also be interpreted as a D.1.1 violation."
],
"was-controversial": "true",
"provisional": "true",
"contacts": [
"biocyc-support@sri.com",
"https://www.biocyc.org/contact.shtml"
],
"grants": [],
"license-commentary-embeddable": "This curation is for the post two-year embargo window data, excluding EcoCyc and MetaCyc which are current and supported by the NIH; data within that window is available with a subscription.
All data access to the downloads is mediated by an individual URL/password/login combination that is obtained by filling out a form and waiting for a response. The curator waited a little over two business days for their response. I do not believe this constitutes a violation of C.2 by itself.
The core of the license seems to be essentially: \"...you may use, modify and redistribute the BIOCYC DATABASES on a royalty-free basis, worldwide, and for any purpose; provided that[...]\" changes are identified and BioCyc is credited in a couple of specific ways, including branding.
The terms are very interesting. I believe the D.1.2 violation could also be interpreted as a D.1.1 violation.",
"data-tags": "biology, genomic resource, sequence, gene structure, pathways, reactions, functional annotation",
"grade-automatic": 3
},
{
"id": "biogrid",
"source": "BioGRID",
"source-link": "https://thebiogrid.org",
"status": "complete",
"description": "BioGRID is an interaction repository with data compiled through comprehensive curation efforts. Our current index is version 3.4.155 and searches 63,959 publications for 1,507,991 protein and genetic interactions, 27,785 chemical associations and 38,559 post translational modifications from major model organism species. All data are freely provided via our search index and available for download in standardized formats.",
"data-field": "biology",
"data-type": "cross-species",
"data-categories": [
"protein-protein interaction"
],
"data-access": [
{
"type": "download",
"location": "https://downloads.thebiogrid.org/BioGRID"
}
],
"license": "MIT",
"license-type": "permissive",
"license-link": "https://downloads.thebiogrid.org/BioGRID",
"license-commentary": [
"Please note the somewhat quirky use of the MIT software license.",
"We are considering the terms on the downloads page to be the most specific and correct ones. While there are additional terms as http://wiki.thebiogrid.org/doku.php/terms_and_conditions, these appear to belikely related to the wiki and non-data content.",
"Please use the file navigator below to browse and download archived BioGRID project files. All data provided are 100% freely available to both academic and commercial users under the MIT License, and are provided WITHOUT ANY WARRANTY. If you have any questions, please feel free to contact us. Publications are requested to please cite the original contributing authors (where applicable) and also: Stark C, Breitkreutz BJ, Reguly T, Boucher L, Breitkreutz A, Tyers M. Biogrid: A General Repository for Interaction Datasets. Nucleic Acids Res. Jan 1, 2006; 34:D535-9."
],
"license-issues": [],
"last-curated": "2017-12-03",
"contacts": [
"biogridadmin@gmail.com"
],
"license-commentary-embeddable": "Please note the somewhat quirky use of the MIT software license.
We are considering the terms on the downloads page to be the most specific and correct ones. While there are additional terms as http://wiki.thebiogrid.org/doku.php/terms_and_conditions, these appear to belikely related to the wiki and non-data content.
Please use the file navigator below to browse and download archived BioGRID project files. All data provided are 100% freely available to both academic and commercial users under the MIT License, and are provided WITHOUT ANY WARRANTY. If you have any questions, please feel free to contact us. Publications are requested to please cite the original contributing authors (where applicable) and also: Stark C, Breitkreutz BJ, Reguly T, Boucher L, Breitkreutz A, Tyers M. Biogrid: A General Repository for Interaction Datasets. Nucleic Acids Res. Jan 1, 2006; 34:D535-9.",
"data-tags": "biology, cross-species, protein-protein interaction",
"grade-automatic": 5
},
{
"id": "bto",
"description": "A structured controlled vocabulary for the source of an enzyme. It comprises terms of tissues, cell lines, cell types and cell cultures from uni- and multicellular organisms.",
"last-curated": "2017-12-03",
"source": "BRENDA Tissue Ontology",
"source-link": "http://bto.brenda-enzymes.org/",
"source-type": "source",
"status": "complete",
"data-field": "biology",
"data-type": "ontology",
"data-categories": [
"enzyme sources"
],
"data-access": [
{
"type": "download",
"location": "http://www.brenda-enzymes.info/ontology/tissue/tree/update/update_files/BrendaTissueOBO"
}
],
"license": "custom",
"license-type": "permissive",
"license-link": "http://www.brenda-enzymes.info/ontology/tissue/tree/update/update_files/BrendaTissueOBO",
"license-hat-used": "false",
"license-issues": [
{
"criteria": "A.2.2",
"comment": "While they are obviously attempting to be permissive by listing \\\"CC-BY\\\", this does not map onto any of the number CC-BY versions (e.g. 3.0 or 4.0), thereby, breaking the reference and meaning that we would have to contact for them for terms)."
},
{
"criteria": "C.2",
"comment": "Once one knows the location of the BTO (ontology file), access is fine. However, we were unable to locate the ontology file after some searching through the main BRENDA website; most text would imply there is no free ontology file to be had."
}
],
"license-commentary": [
"The relatively high score is due to knowing where the ontology exists and knowing to look at the header--normal use of the site seems to lead around restricted APIs webpages containing; the free ontology file is hiding in there.",
"Typcial of this is: \\\"Use of this online version of BRENDA is free for academic research only. Commercial use or download access requires a license. See terms of use.\\\" (http://bto.brenda-enzymes.org/copy.php)",
"The \\\"CC-BY\\\" declaration in the ontology file header should be versioned or linked. Due to not knowing what version, we have marked it as a custom; obviously intended to be under very permissive terms."
],
"was-controversial": "false",
"contacts": [
"http://support.brenda-enzymes.org/open.php"
],
"grants": [
{
"label": "This work was supported by the European Union: (FELICS: Free European Life-Science Information and Computational Services: 021902 (RII3); SLING: Serving Life-science Information for the Next Generation: 226073)."
}
],
"license-commentary-embeddable": "The relatively high score is due to knowing where the ontology exists and knowing to look at the header--normal use of the site seems to lead around restricted APIs webpages containing; the free ontology file is hiding in there.
Typcial of this is: \\\"Use of this online version of BRENDA is free for academic research only. Commercial use or download access requires a license. See terms of use.\\\" (http://bto.brenda-enzymes.org/copy.php)
The \\\"CC-BY\\\" declaration in the ontology file header should be versioned or linked. Due to not knowing what version, we have marked it as a custom; obviously intended to be under very permissive terms.",
"data-tags": "biology, ontology, enzyme sources",
"grade-automatic": 4
},
{
"id": "cancer-biomarkers-database",
"description": "The Cancer Biomarkers database is curated and maintained by several clinical and scientific experts in the field of precision oncology.",
"last-curated": "2020-01-17",
"source": "Cancer Biomarkers database",
"source-link": "https://www.cancergenomeinterpreter.org/biomarkers",
"source-type": "source",
"status": "complete",
"data-field": "oncology",
"data-type": "interaction",
"data-categories": [
"cancer",
"drug",
"biomarker",
"oncology"
],
"data-access": [
{
"type": "download",
"location": "https://www.cancergenomeinterpreter.org/data/cgi_biomarkers_latest.zip"
}
],
"license": "CC0-1.0",
"license-type": "permissive",
"license-link": "https://www.cancergenomeinterpreter.org/biomarkers",
"license-hat-used": "false",
"license-issues": [],
"license-commentary": [
"Noting that the footer has a \"Legal advice\" link to more restrictive terms; it seems clear from the context that this is site boilerplate, with the resource hosted within. Similarly for the \"API\" and \"License\" links.",
"License information (as well as data) are all available on the landing page."
],
"was-controversial": "false",
"contacts": [
"http://goo.gl/forms/gV47GKakVvJD3iTz2"
],
"grants": [
{
"label": "European Union's Horizon 2020 funded project."
}
],
"license-commentary-embeddable": "Noting that the footer has a \"Legal advice\" link to more restrictive terms; it seems clear from the context that this is site boilerplate, with the resource hosted within. Similarly for the \"API\" and \"License\" links.
License information (as well as data) are all available on the landing page.",
"data-tags": "oncology, interaction, cancer, drug, biomarker, oncology",
"grade-automatic": 5
},
{
"id": "catalogueoflife",
"description": "The Catalogue of Life is the most comprehensive and authoritative global index of species currently available. It consists of a single integrated species checklist and taxonomic hierarchy. The Catalogue holds essential information on the names, relationships and distributions of over 1.6 million species.",
"last-curated": "2018-02-18",
"source": "Catalogue of Life",
"source-link": "http://catalogueoflife.org/",
"source-type": "source",
"status": "complete",
"data-field": "biology",
"data-type": "custom",
"data-categories": [
"biodiversity",
"distribution",
"biogeography",
"taxonomy",
"ontology"
],
"data-access": [
{
"type": "api",
"location": "http://webservice.catalogueoflife.org/col/webservice"
},
{
"type": "download",
"location": "http://catalogueoflife.org/content/annual-checklist-archive"
}
],
"license": "custom",
"license-type": "restrictive",
"license-link": "http://catalogueoflife.org/content/terms-use",
"license-hat-used": "false",
"license-issues": [
{
"criteria": "A.2.2",
"comment": "The resource uses custom terms."
},
{
"criteria": "B.1",
"comment": "Use seems to hinge on some contact with Sp2000. For example: \\\"If you wish to use the Catalogue of Life content on a public portal or webpage you are required to notify the Species 2000 Secretariat, and to assist with a check that the correct credits are given.\\\" Check check assistance especially seems to violate B.1."
},
{
"criteria": "C.1",
"comment": "The data \\\"download\\\" is quite complicated and should not actually be considered a download (see commentary). The API as given would likely require a custom spider to obtain the data in bulk."
},
{
"criteria": "D.1.2",
"comment": "Distribution seems to be prohibited without negotiation; example on the main ToS: \\\"Commercial use of this compilation or any of the species datasets contained within...or dissemination on the Internet, requires written permission from Species 2000 and ITIS.\\\""
},
{
"criteria": "E.1.1",
"comment": "Non-commercial restrictions exist on the data from the ToS."
}
],
"license-commentary": [
"The offered API, while possibly spiderable given a starting point, does not seem to offer bulk downloads or similarly significant metadata calls. Spiderable, but non-trivial custom code may be required.",
"While not a violation, the credit requirements may be difficult to meet in some cases: \\\"Credit must be given at the following three levels on all occasions that records are shown. The three levels credit the complete work, the contributing database of the record, and the expert who provides taxonomic scrutiny of the individual record.\\\"",
"The custom licensing terms do not seem to make clear rights around derivation and modification.",
"The download is actually a Linux virtual machine in a custom wrapper that tries to drive interaction with a browser on port 8080; this is rather onerous and I do not think this could be considered a \\\"download\\\" so much as an \\\"offline\\\" site clone or application.",
"Embedded in the \\\"download\\\" is further elaboration on the license, which seem to contain terms about internal use as well: \\\"Use of this compilation or any of the databases contained within it by commercial organisations requires a written agreement from Species 2000 and ITIS. This applies when it is used commercially for external services, products or publications and when it is used to provide internal services within an organisation.\\\""
],
"was-controversial": "false",
"contacts": [
"sp2000@sp2000.org"
],
"license-commentary-embeddable": "The offered API, while possibly spiderable given a starting point, does not seem to offer bulk downloads or similarly significant metadata calls. Spiderable, but non-trivial custom code may be required.
While not a violation, the credit requirements may be difficult to meet in some cases: \\\"Credit must be given at the following three levels on all occasions that records are shown. The three levels credit the complete work, the contributing database of the record, and the expert who provides taxonomic scrutiny of the individual record.\\\"
The custom licensing terms do not seem to make clear rights around derivation and modification.
The download is actually a Linux virtual machine in a custom wrapper that tries to drive interaction with a browser on port 8080; this is rather onerous and I do not think this could be considered a \\\"download\\\" so much as an \\\"offline\\\" site clone or application.
Embedded in the \\\"download\\\" is further elaboration on the license, which seem to contain terms about internal use as well: \\\"Use of this compilation or any of the databases contained within it by commercial organisations requires a written agreement from Species 2000 and ITIS. This applies when it is used commercially for external services, products or publications and when it is used to provide internal services within an organisation.\\\"",
"data-tags": "biology, custom, biodiversity, distribution, biogeography, taxonomy, ontology",
"grade-automatic": 2
},
{
"id": "cath",
"last-curated": "2020-10-15",
"source": "CATH Protein Structure Database",
"source-link": "http://cathdb.info",
"source-type": "source",
"status": "complete",
"description": "CATH is a classification of protein structures downloaded from the Protein Data Bank.",
"data-field": "biology",
"data-type": "protein families",
"data-categories": [
"protein family",
"superfamily",
"classification protein structure"
],
"data-access": [
{
"label": "CATH Data Downloads",
"type": "download",
"location": "ftp://orengoftp.biochem.ucl.ac.uk/cath"
}
],
"license": "CC-BY-4.0",
"license-type": "permissive",
"license-link": "http://cathdb.info",
"license-hat-used": "false",
"license-issues": [],
"license-commentary": [
"After browsing the site and checking the usual locations, the footer was the only place the licensing information was found.",
"\"About\" page additionally has: \"The CATH database is a free, publicly available online resource...\"",
"The footer lists as: \"CATH...is licensed under a Creative Commons Attribution 4.0 International License.\"",
"Did not evaluate API.",
"We take their licensing at face value; we note that this is a derivative of the Protein Data Bank (PDB)."
],
"was-controversial": "false",
"provisional": "true",
"contacts": [
"http://cathdb.info/support"
],
"grants": [
{
"label": "\"CATH-GENE3D is part of the ELIXIR infrastructure\""
}
],
"license-commentary-embeddable": "After browsing the site and checking the usual locations, the footer was the only place the licensing information was found.
\"About\" page additionally has: \"The CATH database is a free, publicly available online resource...\"
The footer lists as: \"CATH...is licensed under a Creative Commons Attribution 4.0 International License.\"
Did not evaluate API.
We take their licensing at face value; we note that this is a derivative of the Protein Data Bank (PDB).",
"data-tags": "biology, protein families, protein family, superfamily, classification protein structure",
"grade-automatic": 5
},
{
"id": "chembl",
"description": "ChEMBL is a database of bioactive drug-like small molecules, it contains 2-D structures, calculated properties (e.g. logP, Molecular Weight, Lipinski Parameters, etc.) and abstracted bioactivities (e.g. binding constants, pharmacology and ADMET data).",
"last-curated": "2017-12-03",
"source": "ChEMBL",
"source-link": "https://www.ebi.ac.uk/chembl/",
"source-type": "source",
"status": "complete",
"data-field": "biology",
"data-type": "biochemical",
"data-categories": [
"bioactive drug-like small molecules"
],
"data-access": [
{
"type": "download",
"location": "https://www.ebi.ac.uk/chembl/downloads"
},
{
"type": "api",
"location": "https://www.ebi.ac.uk/chembl/ws"
}
],
"license": "CC-BY-SA-3.0",
"license-type": "copyleft",
"license-link": "ftp://ftp.ebi.ac.uk/pub/databases/chembl/ChEMBLdb/releases/chembl_23/LICENSE",
"license-hat-used": "false",
"license-issues": [
{
"criteria": "D.1.2",
"comment": "CC SA prevents some types of reuse, such and modification and redistribution with data from different license types."
},
{
"criteria": "E.1.2",
"comment": "CC SA prevents all parties from reusing the data as D.1.2."
}
],
"license-commentary": [
"There was no centralized licensing/terms information on the main site, but all download FTP directories we looked at contained terms for the CC SA 3.0; we used as single example as the license link."
],
"was-controversial": "false",
"contacts": [
"https://www.ebi.ac.uk/support/"
],
"grants": [
{
"label": "2014-2019: The ChEMBL Database, Wellcome Trust (Strategic Award WT104104/Z/14/Z)."
},
{
"label": "2009-date: The member states of EMBL."
},
{
"label": "2016-2022: European Commission Horizon 2020 Toxicity Testing and Risk Assessment in the 21 st Century EU-ToxRisk (681002)"
},
{
"label": "2015-2019: Coordinated Research Infrastructures Building Enduring Life-science Services CORBEL (654248)"
},
{
"label": "2014-2017: The Knowledge Management Center (KMC) for the Illuminating the Druggable Genome (IDG) program funded by the National Institutes of Health (NIH) Common Fund. (Grant No. U54CA189205)"
},
{
"label": "2014-2017: The Center for Therapeutic Target Validation (CTTV008)"
},
{
"label": "2013-2018: European Commission FP7 HeCaTos – Safety prediction (602156)"
}
],
"license-commentary-embeddable": "There was no centralized licensing/terms information on the main site, but all download FTP directories we looked at contained terms for the CC SA 3.0; we used as single example as the license link.",
"data-tags": "biology, biochemical, bioactive drug-like small molecules",
"grade-automatic": 3
},
{
"id": "civicdb",
"source": "Clinical Interpretation of Variants in Cancer (CIViC)",
"source-link": "https://civicdb.org",
"status": "complete",
"description": "CIViC is an open access, open source, community-driven web resource for Clinical Interpretation of Variants in Cancer. Our goal is to enable precision medicine by providing an educational forum for dissemination of knowledge and active discussion of the clinical significance of cancer genome alterations.",
"data-field": "biomedical",
"data-type": "human",
"data-categories": [
"cancer",
"precision medicine",
"variants",
"variant disease associations"
],
"data-access": [
{
"type": "download",
"location": "https://civic.genome.wustl.edu/releases"
},
{
"type": "api",
"location": "https://griffithlab.github.io/civic-api-docs/"
}
],
"license": "CC0-1.0",
"license-type": "permissive",
"license-link": "https://civic.genome.wustl.edu/about",
"license-issues": [],
"license-commentary": [],
"contacts": [
"https://civic.genome.wustl.edu/contact"
],
"license-commentary-embeddable": "",
"data-tags": "biomedical, human, cancer, precision medicine, variants, variant disease associations",
"grade-automatic": 5
},
{
"id": "clinvar",
"source": "ClinVar",
"source-link": "https://www.ncbi.nlm.nih.gov/clinvar/",
"source-type": "integrator",
"status": "complete",
"description": "ClinVar archives and aggregates information about relationships among variation and human health. ClinVar collects reports of variants found in patient samples, assertions made regarding their clinical significance, information about the submitter, and other supporting data.",
"last-curated": "2017-12-07",
"data-field": "biomedical",
"data-type": "human",
"data-categories": [
"disease-gene association",
"variant-disease association",
"variant definitions"
],
"data-access": [
{
"type": "download",
"location": "https://www.ncbi.nlm.nih.gov/home/about/policies/"
}
],
"license": "public domain",
"license-type": "permissive",
"license-link": "http://www.ncbi.nlm.nih.gov/clinvar/docs/maintenance_use/",
"license-hat-used": "false",
"license-issues": [
{
"criteria": "A.2.1",
"comment": "Public domain declaration"
},
{
"criteria": "B.2.1",
"comment": "The license page section \\\"Molecular Data Usage\\\" states that all data may not be covered under the public domain (see comments)."
},
{
"criteria": "B.2.2",
"comment": "There does not seem to be any easy way to differentiate the \\\"clean\\\" data."
}
],
"license-commentary": [
"We turned on the \\\"controversial\\\" flag for this resource due to the unclear nature of sumbitted data. While the stated intent seems to have the data available as PD, ClinVar does not require a copyright reassignment and explicitly states that they cannot vouch for submitted data, which rather undermines any PD-style statement. We were intitially intending on adding a B.1 violation as ClinVar would be acting more like a directory than a unified resource, possibly requiring negotiation with upstream resources.",
"While an API is offered through E-Utilities, we will evaluate the more concrete downloads given their ease.",
"Custom PD declaration.",
"The license page section \\\"Molecular Data Usage\\\" states that\\: \\\"NCBI is not in a position to assess the validity of such claims and since there is no transfer of rights from submitters to NCBI, NCBI has no rights to transfer to a third party. Therefore, NCBI cannot provide comment or unrestricted permission concerning the use, copying, or distribution of the information contained in the molecular databases.\\\"",
"We also considered the wording at https://www.ncbi.nlm.nih.gov/clinvar/docs/maintenance_use/ , but decided that the one we chose above was mostly likely indended and correct."
],
"was-controversial": "true",
"contacts": [
"info@ncbi.nlm.nih.gov"
],
"license-commentary-embeddable": "We turned on the \\\"controversial\\\" flag for this resource due to the unclear nature of sumbitted data. While the stated intent seems to have the data available as PD, ClinVar does not require a copyright reassignment and explicitly states that they cannot vouch for submitted data, which rather undermines any PD-style statement. We were intitially intending on adding a B.1 violation as ClinVar would be acting more like a directory than a unified resource, possibly requiring negotiation with upstream resources.
While an API is offered through E-Utilities, we will evaluate the more concrete downloads given their ease.
Custom PD declaration.
The license page section \\\"Molecular Data Usage\\\" states that\\: \\\"NCBI is not in a position to assess the validity of such claims and since there is no transfer of rights from submitters to NCBI, NCBI has no rights to transfer to a third party. Therefore, NCBI cannot provide comment or unrestricted permission concerning the use, copying, or distribution of the information contained in the molecular databases.\\\"
We also considered the wording at https://www.ncbi.nlm.nih.gov/clinvar/docs/maintenance_use/ , but decided that the one we chose above was mostly likely indended and correct.",
"data-tags": "biomedical, human, disease-gene association, variant-disease association, variant definitions",
"grade-automatic": 4
},
{
"id": "cogs",
"description": "Phylogenetic classification of proteins encoded in complete genomes.",
"last-curated": "2019-10-19",
"source": "COGs",
"source-link": "https://www.ncbi.nlm.nih.gov/COG/",
"source-type": "source",
"status": "complete",
"data-field": "biology",
"data-type": "protein function",
"data-categories": [
"protein family",
"function prediction"
],
"data-access": [
{
"label": "2014 update FTP",
"type": "download",
"location": "ftp://ftp.ncbi.nih.gov/pub/COG/COG2014/data"
}
],
"license": "unlicensed",
"license-type": "copyright",
"license-hat-used": "false",
"license-issues": [
{
"criteria": "A.1.2",
"comment": "Could not find any clear terms on any searched pages. See commentary."
}
],
"license-commentary": [
"I could find no licensing information, including in the most recent publication covering the most current FTP downloads."
],
"was-controversial": "false",
"provisional": "true",
"contacts": [
"cogs@ncbi.nlm.nih.gov",
"koonin@ncbi.nlm.nih.gov"
],
"grants": [],
"license-commentary-embeddable": "I could find no licensing information, including in the most recent publication covering the most current FTP downloads.",
"data-tags": "biology, protein function, protein family, function prediction",
"grade-automatic": 1
},
{
"id": "coriell-institute",
"source": "Coriell Institute for Medical Research",
"source-link": "https://coriell.org/",
"status": "nonpublic",
"description": "The Coriell Cell Repositories provide essential research reagents to the scientific community by establishing, verifying, maintaining, and distributing cell cultures and DNA derived from cell cultures. These collections, supported by funds from the National Institutes of Health (NIH) and several foundations, are extensively utilized by research scientists around the world. NINDS and NIGMS cell line catalog. NIGMS samples represent a variety of disease states, chromosomal abnormalities, apparently healthy individuals and many distinct human populations. NINDS samples are drawn from subjects with cerebrovascular disease, epilepsy, motor neuron disease, Parkinsonism and Tourette Syndrome, as well as controls.",
"data-field": "biology",
"data-type": "human",
"data-categories": [
"disease-model association"
],
"data-access": [],
"license": "unlicensed",
"license-type": "copyright",
"license-link": "https://www.coriell.org/legal-notice",
"license-issues": [
{
"criteria": "A.1.2",
"comment": "See license commentary."
},
{
"criteria": "C.1",
"comment": "No on-site data."
},
{
"criteria": "C.2",
"comment": "No on-site data."
}
],
"license-commentary": [
"After searching, https://coriell.org, https://catalog.coriell.org, and (for example) https://catalog.coriell.org/1/NHGRI, we could find no information on a publicly available data resource beyond Excel spreadsheets.",
"For example, from https://catalog.coriell.org/1/NHGRI/FAQs : The NHGRI Repository at Coriell is the sample repository for the International HapMap Project and the 1000 Genomes Project. We provide cell lines and DNA, but do not house the data for these projects. Data associated with these samples can be found at the following project websites...",
"This resource has no stars due to no data, possibly due to Coriell not actually being a proper upstream data resource; this doesn not reflect the main work or Coriell."
],
"contacts": [
"communications@coriell.org"
]
},
{
"id": "ctd",
"source": "Comparative Toxicogenomics Database (CTD)",
"source-link": "http://ctdbase.org",
"status": "complete",
"description": "CTD promotes understanding about the effects of environmental chemicals on human health by integrating data from curated scientific literature to describe chemical interactions with genes and proteins, and associations between diseases and chemicals, and diseases and genes/proteins.",
"data-field": "biology",
"data-type": "x-species",
"data-categories": [
"disease-gene association"
],
"data-access": [
{
"type": "api",
"location": "http://ctdbase.org/tools/batchQuery.go"
},
{
"type": "download",
"location": "http://ctdbase.org/downloads/"
}
],
"license": "custom",
"license-type": "restrictive",
"license-link": "http://ctdbase.org/about/legal.jsp",
"license-issues": [
{
"criteria": "A.2.2",
"comment": "Custom license with interesting use restrictions."
},
{
"criteria": "B.1",
"comment": "For quality control purposes, you must provide CTD with periodic access to your publication of our data."
},
{
"criteria": "D.1.2",
"comment": "Given the four statements in the Additional Terms of Data Use, notably number 4, it looks like any downstream user would have to renegotiate with CTD."
},
{
"criteria": "E.1.1",
"comment": "Without negotiation: \"It is to be used only for research and educational purposes.\""
}
],
"license-commentary": [
"There are statements made in the Additional Terms of Data Use that would make it very difficult to re-use the data provided without a air amount o coordination with the resource and changes to information handling."
],
"contacts": [
"http://ctdbase.org/help/contact.go"
],
"license-commentary-embeddable": "There are statements made in the Additional Terms of Data Use that would make it very difficult to re-use the data provided without a air amount o coordination with the resource and changes to information handling.",
"data-tags": "biology, x-species, disease-gene association",
"grade-automatic": 2.5
},
{
"id": "dbgap",
"source": "dbGaP (public)",
"source-link": "https://www.ncbi.nlm.nih.gov/gap",
"status": "complete",
"description": "The database of Genotypes and Phenotypes (dbGaP) was developed to archive and distribute the data and results from studies that have investigated the interaction of genotype and phenotype in Humans. Provides authorized access to protected and raw data (e.g., Genotype-Tissue Expression (GTEx) project).",
"data-field": "biology",
"data-type": "human",
"data-categories": [
"genotype-phenotype"
],
"data-access": [
{
"type": "download",
"location": "ftp://ftp.ncbi.nlm.nih.gov/dbgap/"
}
],
"license": "inconsistent",
"license-type": "unknown",
"license-link": "https://grants.nih.gov/grants/guide/notice-files/NOT-OD-14-124.html",
"license-issues": [
{
"criteria": "A.1.1",
"comment": "Per the dgGaP data use certification, 'The terms and conditions of using dbGaP data vary by study'. All terms and conditions are to align with NIH GDS."
},
{
"criteria": "C.1",
"comment": "Cannot access all the data."
},
{
"criteria": "C.2",
"comment": "Access methods are not transparent."
}
],
"license-commentary": [
"The data seems to include a large amount of identifiable and is controlled as such.",
"There also exists unrestricted data and the thus the NIG GDS data use policy is two-tiered.",
"Controlled-access policy 'https://www.ncbi.nlm.nih.gov/books/NBK99227/'",
"General data sharing information (see data sharing policy section) 'https://www.ncbi.nlm.nih.gov/books/NBK5296/'",
"NIH GDS policy tone and language seems non-uniform and more like case-by-case.",
"Example GTex project submitted policy 'https://dbgap.ncbi.nlm.nih.gov/aa/wga.cgi?view_pdf&stacc=phs000424.v1.p1'",
"NIH GDS states 'NIH expects investigators and their institutions to provide basic plans for following this Policy' however we assume the burden stays with data re-reuser to contact source with questions and issues should they arise effecting criteria B.",
"Regarding institutional affiliation 'https://www.ncbi.nlm.nih.gov/books/NBK45308/'",
"A.2: unknown license type due to 'The terms and conditions of using dbGaP data vary by study'.",
"B.1: Negotation needed for controlled- access data and license type or terms and conditions unknown.",
"B.2.2: Scoping is incomplete as license type or terms and conditions unknown.",
"D.1.2: Because the terms and conditions vary by study, cannot comment on downstream reuse/remix.",
"E.1.1: Language in the NIH GDS policy may be interpreted by non-legal professional that the contents may be reused by researchers (at NIH or with Institutional affiliation)."
],
"contacts": [
"https://www.ncbi.nlm.nih.gov/books/NBK5296/"
],
"license-commentary-embeddable": "The data seems to include a large amount of identifiable and is controlled as such.
There also exists unrestricted data and the thus the NIG GDS data use policy is two-tiered.
Controlled-access policy 'https://www.ncbi.nlm.nih.gov/books/NBK99227/'
General data sharing information (see data sharing policy section) 'https://www.ncbi.nlm.nih.gov/books/NBK5296/'
NIH GDS policy tone and language seems non-uniform and more like case-by-case.
Example GTex project submitted policy 'https://dbgap.ncbi.nlm.nih.gov/aa/wga.cgi?view_pdf&stacc=phs000424.v1.p1'
NIH GDS states 'NIH expects investigators and their institutions to provide basic plans for following this Policy' however we assume the burden stays with data re-reuser to contact source with questions and issues should they arise effecting criteria B.
Regarding institutional affiliation 'https://www.ncbi.nlm.nih.gov/books/NBK45308/'
A.2: unknown license type due to 'The terms and conditions of using dbGaP data vary by study'.
B.1: Negotation needed for controlled- access data and license type or terms and conditions unknown.
B.2.2: Scoping is incomplete as license type or terms and conditions unknown.
D.1.2: Because the terms and conditions vary by study, cannot comment on downstream reuse/remix.
E.1.1: Language in the NIH GDS policy may be interpreted by non-legal professional that the contents may be reused by researchers (at NIH or with Institutional affiliation).",
"data-tags": "biology, human, genotype-phenotype",
"grade-automatic": 0
},
{
"id": "decipher",
"last-curated": "2017-10-12",
"source": "DECIPHER",
"source-link": "https://decipher.sanger.ac.uk",
"status": "complete",
"description": "DECIPHER is used by the clinical community to share and compare phenotypic and genotypic data. The DECIPHER database contains data from 24848 patients who have given consent for broad data-sharing; DECIPHER also supports more limited sharing via consortia.",
"data-field": "biology",
"data-type": "human",
"data-categories": [
"gene",
"genotype",
"rare disease",
"phenotype",
"variant",
"submicroscopic chromosomal imbalance",
"rare sequence variants"
],
"data-access": [],
"license": "custom",
"license-type": "private pool",
"license-link": "https://decipher.sanger.ac.uk/datasharing",
"license-issues": [
{
"criteria": "A.2.2",
"comment": "The resource uses an extensive custom license."
},
{
"criteria": "B.1",
"comment": "There are terms that require possible audits in the future, making future free use something that needs to be negotiated."
},
{
"criteria": "C.1",
"comment": "This could not be evaluated as no description of access was found."
},
{
"criteria": "C.2",
"comment": "This could not be evaluated as no description of access was found."
},
{
"criteria": "D.1.2",
"comment": "Given the numerous restrictions and requirements (e.g. purging, forced QA), it seems that downstream reuse would be problematic, even though there is a carve-out for \"research\"."
},
{
"criteria": "E.1.2",
"comment": "Given the numerous restrictions and requirements (e.g. only \"registered\" users can have access to the data, etc.), it seems that downstream reuse would be problematic, even though there is a carve-out for \"research\"."
}
],
"license-commentary": [
"We are evaluating the bulk data access agreement, rather than the data display agreement, which specifically prevents any type of bulk (re)use.",
"While there are a few data files available at https://decipher.sanger.ac.uk/downloads/data , given the workding and context of the agreement, we believe that this is some other miscellaneous data.",
"Data access is mediated through the Data Access Agreement: https://decipher.sanger.ac.uk/files/pdfs/daa.pdf and becoming a registered user.",
"A written request is required to be submitted and approved before accessing the data.",
"The DAA requires that accepted users: can only use data for research, cannot attempt to uncloak PII, must have proactive data security, must adhere to Data Protection Act 1998, may only share data with others who have agreed to these terms, allow GRL to do audits, accept required reporting of errors, destroy earlier data versions on update, as well as other (somewhat more \"standard\") terms.",
"This seems like a \"closed pool\" type, even though is may just have one member, due to the use of \"registered users\" in the license.",
"Additional terms of use in citation policy: \"Authors who use data from the project must acknowledge DECIPHER using the following wording...\""
],
"grants": [
{
"label": "Funding for the project was provided by the Wellcome Trust."
}
],
"contacts": [
"decipher@sanger.ac.uk"
],
"license-commentary-embeddable": "We are evaluating the bulk data access agreement, rather than the data display agreement, which specifically prevents any type of bulk (re)use.
While there are a few data files available at https://decipher.sanger.ac.uk/downloads/data , given the workding and context of the agreement, we believe that this is some other miscellaneous data.
Data access is mediated through the Data Access Agreement: https://decipher.sanger.ac.uk/files/pdfs/daa.pdf and becoming a registered user.
A written request is required to be submitted and approved before accessing the data.
The DAA requires that accepted users: can only use data for research, cannot attempt to uncloak PII, must have proactive data security, must adhere to Data Protection Act 1998, may only share data with others who have agreed to these terms, allow GRL to do audits, accept required reporting of errors, destroy earlier data versions on update, as well as other (somewhat more \"standard\") terms.
This seems like a \"closed pool\" type, even though is may just have one member, due to the use of \"registered users\" in the license.
Additional terms of use in citation policy: \"Authors who use data from the project must acknowledge DECIPHER using the following wording...\"",
"data-tags": "biology, human, gene, genotype, rare disease, phenotype, variant, submicroscopic chromosomal imbalance, rare sequence variants",
"grade-automatic": 1
},
{
"id": "dictybase",
"source": "dictyBase",
"source-link": "http://dictybase.org",
"status": "complete",
"description": "dictyBase is a database that provides a centralized source of Dictyostelium information for Dictyostelium researchers and Non-Dictyostelium researchers. This includes tutorials, dictyNews, techniques, the Stock Center, genomic and molecular information, colleague infromation, Dictyostelium literature, and much more.",
"data-field": "biology",
"data-type": "MOD",
"data-categories": [
"genotype-phenotype association",
"disease-model association",
"gene expression"
],
"data-access": [
{
"type": "download",
"location": "http://dictybase.org/Downloads/"
}
],
"license": "unlicensed",
"license-type": "copyright",
"license-link": "TODO",
"license-issues": [
{
"criteria": "A.1.2",
"comment": "Could not find any clear terms on any searched pages. See commentary."
}
],
"license-commentary": [
"While there does not seem to be any clear licensing information currently on the site, from a separate conversation (https://github.com/geneontology/noctua/issues/510#issuecomment-334864073), it would seem that this will soon be updated."
],
"last-curated": "2017-10-17",
"contacts": [
"dictybase@northwestern.edu",
"http://dictybase.org/db/cgi-bin/dictyBase/suggestion"
],
"license-commentary-embeddable": "While there does not seem to be any clear licensing information currently on the site, from a separate conversation (https://github.com/geneontology/noctua/issues/510#issuecomment-334864073), it would seem that this will soon be updated.",
"data-tags": "biology, MOD, genotype-phenotype association, disease-model association, gene expression",
"grade-automatic": 1
},
{
"id": "drugbank",
"description": "The DrugBank database is a unique bioinformatics and cheminformatics resource that combines detailed drug data with comprehensive drug target information.",
"last-curated": "2023-09-24",
"source": "DrugBank",
"source-link": "https://go.drugbank.com",
"source-type": "source",
"status": "complete",
"data-field": "pharmacology",
"data-type": "drug",
"data-categories": [
"bioinformatics",
"cheminformatics",
"drugs",
"drug-protein interactions",
"targets",
"pathways"
],
"data-access": [
{
"type": "download",
"location": "https://www.drugbank.ca/releases/latest"
}
],
"license": "CC-BY-NC-4.0",
"license-type": "restrictive",
"license-link": "https://www.drugbank.ca/releases/latest",
"license-hat-used": "false",
"license-issues": [
{
"criteria": "D.1.1",
"comment": "The NC license allows for liberal non-commercial reuse."
},
{
"criteria": "E.1.1",
"comment": "The NC license allows for non-commercial reuse with other non-commercial interests."
}
],
"license-commentary": [
"There is also an open (CC0) data subset for vocabulary and structures that could be evaluated separately; it is ~5mb vs ~150mb for the complete \"academic\" set(about 3%).",
"This seems to be mostly a standard NC/commercial licensing split, with DrugBank+ supporting commerical licensing for fees.",
"To download the full academic set, one must create an account (https://go.drugbank.com/public_users/sign_up), which is a multi-step and human mediated process, with varying turnaround times and follow-up questions."
],
"was-controversial": "false",
"contacts": [
"https://go.drugbank.com/contact",
"info@drugbank.com"
],
"grants": [],
"license-commentary-embeddable": "There is also an open (CC0) data subset for vocabulary and structures that could be evaluated separately; it is ~5mb vs ~150mb for the complete \"academic\" set(about 3%).
This seems to be mostly a standard NC/commercial licensing split, with DrugBank+ supporting commerical licensing for fees.
To download the full academic set, one must create an account (https://go.drugbank.com/public_users/sign_up), which is a multi-step and human mediated process, with varying turnaround times and follow-up questions.",
"data-tags": "pharmacology, drug, bioinformatics, cheminformatics, drugs, drug-protein interactions, targets, pathways",
"grade-automatic": 4
},
{
"id": "drugcentral",
"description": "DrugCentral provides information on active ingredients chemical entities, pharmaceutical products, drug mode of action, indications, pharmacologic action. We monitor FDA, EMA, and PMDA for new drug approval on regular basis to ensure currency of the resource.",
"last-curated": "2017-12-03",
"source": "DrugCentral",
"source-link": "http://drugcentral.org",
"source-type": "integrator",
"status": "complete",
"data-field": "pharmacology",
"data-type": "drug-target interaction",
"data-categories": [
"chemical structure of drugs",
"drug",
"disease"
],
"data-access": [
{
"type": "download",
"location": "http://drugcentral.org/download"
}
],
"license": "CC-BY-SA-4.0",
"license-type": "copyleft",
"license-link": "http://drugcentral.org/privacy",
"license-hat-used": "false",
"license-issues": [
{
"criteria": "D.1.2",
"comment": "By using a copyleft-style license, there may be issues in mixing and redistributing this data with licenses that have incompatible terms."
},
{
"criteria": "E.1.2",
"comment": "By using a copyleft-style license, there may be some parties with issues in mixing and redistributing this data with licenses that have incompatible terms."
}
],
"license-commentary": [
"While there is upstream data integtration, there seems to be no mention of upstream licenses or terms. Not necessarily our issue here."
],
"was-controversial": "false",
"contacts": [
"For questions and comments please contact Oleg Ursu or Jayme Holmes."
],
"license-commentary-embeddable": "While there is upstream data integtration, there seems to be no mention of upstream licenses or terms. Not necessarily our issue here.",
"data-tags": "pharmacology, drug-target interaction, chemical structure of drugs, drug, disease",
"grade-automatic": 3
},
{
"id": "dryad",
"description": "DataDryad.org is a curated general-purpose repository that makes the data underlying scientific publications discoverable, freely reusable, and citable. Dryad has integrated data submission for a growing list of journals; submission of data from other publications is also welcome.",
"last-curated": "2017-12-05",
"source": "Dryad Digital Repository",
"source-link": "https://datadryad.org",
"source-type": "repository",
"status": "complete",
"data-field": "general",
"data-type": "any",
"data-categories": [
"data",
"literature"
],
"data-access": [
{
"type": "api",
"location": "http://wiki.datadryad.org/Data_Access"
}
],
"license": "CC0-1.0",
"license-type": "permissive",
"license-link": "https://datadryad.org/pages/policies#publication",
"license-hat-used": "false",
"license-issues": [],
"license-commentary": [
"Main API information found from the landing page under \\\"About\\\" -> \\\"Repository features and technology\\\": https://datadryad.org/pages/repository",
"Also note more detailed API information in the wiki: http://wiki.datadryad.org/Data_Access",
"\\\"Dryad will make Accepted Content available to the public under a CC0 Waiver\\\""
],
"was-controversial": "false",
"contacts": [
"help@datadryad.org"
],
"license-commentary-embeddable": "Main API information found from the landing page under \\\"About\\\" -> \\\"Repository features and technology\\\": https://datadryad.org/pages/repository
Also note more detailed API information in the wiki: http://wiki.datadryad.org/Data_Access
\\\"Dryad will make Accepted Content available to the public under a CC0 Waiver\\\"",
"data-tags": "general, any, data, literature",
"grade-automatic": 5
},
{
"id": "encode",
"source": "ENCODE",
"source-link": "https://www.genome.gov/10005107/",
"status": "complete",
"description": "The Encyclopedia of DNA Elements (ENCODE) Consortium is an international collaboration of research groups funded by the National Human Genome Research Institute (NHGRI). The goal of ENCODE is to build a comprehensive parts list of functional elements in the human genome, including elements that act at the protein and RNA levels, and regulatory elements that control cells and circumstances in which a gene is active.",
"data-field": "biology",
"data-type": "genomic resource",
"data-categories": [
"genomic elements"
],
"data-access": [
{
"type": "api",
"location": "https://www.encodeproject.org/help/rest-api/"
},
{
"type": "download",
"location": "https://www.ncbi.nlm.nih.gov/geo/info/download.html"
},
{
"type": "download",
"location": "ftp://ftp.ebi.ac.uk/pub/databases/arrayexpress/data/"
}
],
"license": "custom",
"license-type": "permissive",
"license-link": "https://www.genome.gov/27528022/encode-consortium-data-release-policy/",
"license-issues": [
{
"criteria": "A.2.2",
"comment": "Easy and perfectly (re)usable, yet custom."
}
],
"license-commentary": [
"External data users may freely download, analyze and publish results based on any ENCODE data without restrictions as soon as they are released."
],
"contacts": [
"https://www.genome.gov/10005049/questions-and-feedback/"
],
"license-commentary-embeddable": "External data users may freely download, analyze and publish results based on any ENCODE data without restrictions as soon as they are released.",
"data-tags": "biology, genomic resource, genomic elements",
"grade-automatic": 4.5
},
{
"id": "fantom5",
"source": "Fantom5",
"source-link": "http://fantom.gsc.riken.jp/5/",
"status": "complete",
"description": "We are complex multicellular organisms composed of ~400 distinct cell types. This diversity of cell types allow us to see, think, hear, fight infections etc. yet all of this is encoded in the same genome. The difference between all these cells is what parts of the genome they use – for instance, neurons use different genes than muscle cells, and therefore they work very differently. In FANTOM5, we have systematically investigated exactly what are the sets of genes used in virtually all cell types across the human body, and the genomic regions which determine where the genes are read from. We aim to use this information to build transcriptional regulatory models for every primary cell type that makes up a human.",
"data-field": "biology",
"data-type": "human",
"data-categories": [
"gene expression"
],
"data-access": [],
"license": "CC-BY-4.0",
"license-type": "permissive",
"license-link": "http://fantom.gsc.riken.jp/5/",
"license-commentary": [],
"contacts": [
"fantom-help.gsc@riken.jp"
],
"license-commentary-embeddable": "",
"data-tags": "biology, human, gene expression",
"grade-automatic": 5
},
{
"id": "flybase",
"source": "FlyBase",
"source-link": "http://flybase.org",
"status": "complete",
"description": "FlyBase is the model organism database providing integrated genetic, genomic, phenomic, and biological data for Drosophila melanogaster.",
"data-field": "biology",
"data-type": "MOD",
"data-categories": [
"genotype-phenotype association"
],
"data-access": [
{
"type": "download",
"location": "http://flybase.org/static_pages/downloads/ID.html"
}
],
"license": "custom",
"license-type": "restrictive",
"license-link": "http://flybase.org/wiki/FlyBase:About#FlyBase_Copyright",
"license-issues": [
{
"criteria": "A.2.2",
"comment": "Copyright statement includes 'This publication may be copied for non-commercial, scientific uses by individuals or organizations (including for-profit organizations). FlyBase is freely distributed to the scientific community on the understanding that it will not be used for commercial gain by any organization. Any commercial use of this publication, or any parts thereof, is expressly prohibited without permission in writing from the FlyBase consortium.'"
},
{
"criteria": "B.1",
"comment": "Copyright statement includes 'Certain portions of FlyBase are copyrighted separately.'"
},
{
"criteria": "B.2.1",
"comment": "Copyright statement includes 'Certain portions of FlyBase are copyrighted separately.'"
},
{
"criteria": "D.1.1",
"comment": "As stated copyright may be interpreted by non-legal professional that the contents may be reused/remixed in a non-commercial context."
},
{
"criteria": "E.1.1",
"comment": "As stated copyright may be interpreted by non-legal professional that the contents may be reused/remixed in a non-commercial context."
}
],
"license-commentary": [
"Copyright statement is not co-located with the data source."
],
"contacts": [
"http://flybase.org/cgi-bin/mailto-fbhelp.html"
],
"license-commentary-embeddable": "Copyright statement is not co-located with the data source.",
"data-tags": "biology, MOD, genotype-phenotype association",
"grade-automatic": 2.5
},
{
"id": "gdc",
"description": "The NCI\\'s Genomic Data Commons (GDC) provides the cancer research community with a unified data repository that enables data sharing across cancer genomic studies in support of precision medicine.",
"last-curated": "2017-12-03",
"source": "Genomic Data Commons (GDC)",
"source-link": "https://gdc.cancer.gov/",
"source-type": "repository",
"status": "complete",
"data-field": "biology",
"data-type": "human",
"data-categories": [
"cancer genome",
"variants",
"mRNA and miRNA sequence data"
],
"data-access": [
{
"type": "download",
"location": "https://gdc.cancer.gov/access-data/gdc-data-transfer-tool"
},
{
"type": "api",
"location": "https://gdc.cancer.gov/developers/gdc-application-programming-interface-api"
}
],
"license": "unlicensed",
"license-type": "copyright",
"license-hat-used": "false",
"license-issues": [
{
"criteria": "A.1.2",
"comment": "After searching around GDC and cancer.gov, no centralized licensing or terms could be found."
}
],
"license-commentary": [
"After much searching, no centralized or clear terms could be found.",
"When accessing individual files, there was metadata such as \\\"Access\\\": \\\"open\\\", so it would seem that any terms, if they did exist, would unlikely be complete.",
"The initial click-through contains some worrying verbiage: \\\"You are accessing a U.S. Government web site which may contain information that...is intended for Government authorized use only. Unauthorized attempts to...use of this web site may result in disciplinary action, civil, and/or criminal penalties...\\\"",
"Some data would seem to require additional controls: \\\"GDC data is stored in a secure FISMA-compliant facility. Access to controlled data requires authorization via dbGaP. See Data Access Processes and Tools for more information.\\\"",
"While some terms information was found at https://www.cancer.gov/policies/copyright-reuse, it seemed to be about site content rather than data.",
"While licensing information could not be found, access was not problematic."
],
"was-controversial": "false",
"contacts": [
"support@nci-gdc.datacommons.io"
],
"license-commentary-embeddable": "After much searching, no centralized or clear terms could be found.
When accessing individual files, there was metadata such as \\\"Access\\\": \\\"open\\\", so it would seem that any terms, if they did exist, would unlikely be complete.
The initial click-through contains some worrying verbiage: \\\"You are accessing a U.S. Government web site which may contain information that...is intended for Government authorized use only. Unauthorized attempts to...use of this web site may result in disciplinary action, civil, and/or criminal penalties...\\\"
Some data would seem to require additional controls: \\\"GDC data is stored in a secure FISMA-compliant facility. Access to controlled data requires authorization via dbGaP. See Data Access Processes and Tools for more information.\\\"
While some terms information was found at https://www.cancer.gov/policies/copyright-reuse, it seemed to be about site content rather than data.
While licensing information could not be found, access was not problematic.",
"data-tags": "biology, human, cancer genome, variants, mRNA and miRNA sequence data",
"grade-automatic": 1
},
{
"id": "gisaid",
"last-curated": "2020-03-09",
"source": "GISAID",
"source-link": "https://www.gisaid.org",
"source-type": "unknown",
"status": "complete",
"description": "The GISAID Initiative promotes the international sharing of all influenza virus sequences, related clinical and epidemiological data associated with human viruses, and geographical as well as species-specific data associated with avian and other animal viruses, to help researchers understand how the viruses evolve, spread and potentially become pandemics.",
"data-field": "biology",
"data-type": "viral",
"data-categories": [
"gene",
"clinical",
"epidemiology",
"influenza virus sequence",
"aves",
"evolution",
"demographic",
"geo-spatial",
"gis"
],
"data-access": [],
"license": "custom",
"license-type": "private pool",
"license-link": "https://www.gisaid.org/registration/terms-of-use/",
"license-hat-used": "false",
"license-issues": [
{
"criteria": "A.2.2",
"comment": "The resource uses an extensive custom license."
},
{
"criteria": "B.1",
"comment": "There are terms (e.g. 2b) that would make it seem that GISAID would need to be negotiated with for any further reuse beyond."
},
{
"criteria": "C.1",
"comment": "The webapp-style interface is not suitable for scripting or batch operations; bulk access options were not apparent."
},
{
"criteria": "C.2",
"comment": "I believe it would take a bit of knowledge to probe out the correct calls and get through the authorization, assuming scripting was feasible."
},
{
"criteria": "D.1.2",
"comment": "No pass-through of data seems possible except through the license agreement; no academic exception seems to exist."
},
{
"criteria": "E.1.2",
"comment": "No pass-through of data seems possible except through the license agreement; no academic exception seems to exist."
}
],
"license-commentary": [
"The terms found at https://www.gisaid.org/registration/terms-of-use/ appear to be the same as the final version agreed to during registration.",
"Additional terms for registry at https://www.gisaid.org/registration/register/ .",
"Additional terms for registry at https://platform.gisaid.org/epi3/frontend#360c7c .",
"The fact that the license agreement itself has terms makes conversation possibly difficult.",
"While the license is quite readable, it has many interesting terms trying to control the behavior (e.g. 2b) of those under the agreement that may be best understood by law professionals.",
"While not a current criteria violation, I feel it is worth noting that there was a 26 day waiting period between request and account creation."
],
"was-controversial": "false",
"provisional": "true",
"contacts": [
"https://www.gisaid.org/help/contact/"
],
"grants": [
{
"label": "https://www.gisaid.org/about-us/grants/ , no current listing"
}
],
"license-commentary-embeddable": "The terms found at https://www.gisaid.org/registration/terms-of-use/ appear to be the same as the final version agreed to during registration.
Additional terms for registry at https://www.gisaid.org/registration/register/ .
Additional terms for registry at https://platform.gisaid.org/epi3/frontend#360c7c .
The fact that the license agreement itself has terms makes conversation possibly difficult.
While the license is quite readable, it has many interesting terms trying to control the behavior (e.g. 2b) of those under the agreement that may be best understood by law professionals.
While not a current criteria violation, I feel it is worth noting that there was a 26 day waiting period between request and account creation.",
"data-tags": "biology, viral, gene, clinical, epidemiology, influenza virus sequence, aves, evolution, demographic, geo-spatial, gis",
"grade-automatic": 1
},
{
"id": "gnomad",
"description": " The Genome Aggregation Database (gnomAD), is a coalition of investigators seeking to aggregate and harmonize exome and genome sequencing data from a variety of large-scale sequencing projects, and to make summary data available for the wider scientific community. In its first release, which contained exclusively exome data, it was known as the Exome Aggregation Consortium (ExAC).",
"last-curated": "2017-12-03",
"source": "Genome Aggregation Database (gnomAD)",
"source-link": "http://gnomad.broadinstitute.org/",
"source-type": "integrator",
"status": "complete",
"data-field": "biology",
"data-type": "human",
"data-categories": [
"exome sequencing data",
"genome sequencing data",
"disease-specific genetic studies",
"population genetic studies"
],
"data-access": [
{
"type": "download",
"location": "http://gnomad.broadinstitute.org/downloads"
}
],
"license": "ODbL-1.0",
"license-type": "copyleft",
"license-link": "http://gnomad.broadinstitute.org/terms",
"license-hat-used": "false",
"license-issues": [
{
"criteria": "D.1.2",
"comment": "While extremely open, the ODbL does restrict the ability to mix and redistribute with data without similar terms."
},
{
"criteria": "E.1.2",
"comment": "By using the ODbL, there may be some parties with issues in mixing and redistributing this data with licenses that have incompatible terms."
}
],
"license-commentary": [
"All data available under: https://opendatacommons.org/licenses/odbl/1.0/"
],
"was-controversial": "false",
"contacts": [
"http://gnomad.broadinstitute.org/contact"
],
"grants": [
{
"label": "NIGMS R01 GM104371 (PI: MacArthur)"
},
{
"label": "NIDDK U54 DK105566 (PIs: MacArthur and Neale)"
},
{
"label": "The vast majority of the data storage, computing resources, and human effort used to generate this call set were donated by the Broad Institute."
}
],
"license-commentary-embeddable": "All data available under: https://opendatacommons.org/licenses/odbl/1.0/",
"data-tags": "biology, human, exome sequencing data, genome sequencing data, disease-specific genetic studies, population genetic studies",
"grade-automatic": 3
},
{
"id": "go-ann",
"source": "Gene Ontology (annotations)",
"source-link": "http://geneontology.org",
"status": "complete",
"description": "The mission of the GO Consortium is to develop an up-to-date, comprehensive, computational model of biological systems, from the molecular level to larger pathways, cellular and organism-level systems.",
"data-field": "biology",
"data-type": "x-species",
"data-categories": [
"gene annotation",
"gene association",
"biological process",
"molecular function",
"cellular component"
],
"data-access": [
{
"type": "api",
"location": "http://rdf.geneontology.org"
},
{
"type": "download",
"location": "http://geneontology.org/page/download-annotations"
}
],
"license": "CC-BY-4.0",
"license-type": "permissive",
"license-link": "http://geneontology.org/page/use-and-license",
"license-commentary": [],
"contacts": [
"http://help.geneontology.org/"
],
"license-commentary-embeddable": "",
"data-tags": "biology, x-species, gene annotation, gene association, biological process, molecular function, cellular component",
"grade-automatic": 5
},
{
"id": "go-ont",
"source": "Gene Ontology (ontology)",
"source-link": "http://geneontology.org",
"status": "complete",
"description": "The mission of the GO Consortium is to develop an up-to-date, comprehensive, computational model of biological systems, from the molecular level to larger pathways, cellular and organism-level systems.",
"data-field": "biology",
"data-type": "x-species",
"data-categories": [
"ontology",
"biological process",
"molecular function",
"cellular component"
],
"data-access": [
{
"type": "api",
"location": "http://rdf.geneontology.org"
},
{
"type": "download",
"location": "http://geneontology.org/page/download-ontology"
}
],
"license": "CC-BY-4.0",
"license-type": "permissive",
"license-link": "http://geneontology.org/page/use-and-license",
"license-commentary": [],
"contacts": [
"http://help.geneontology.org/"
],
"license-commentary-embeddable": "",
"data-tags": "biology, x-species, ontology, biological process, molecular function, cellular component",
"grade-automatic": 5
},
{
"id": "gtex",
"source": "GTEx",
"source-link": "http://www.gtexportal.org",
"status": "complete",
"description": "The Genotype-Tissue Expression (GTEx) project aims to provide to the scientific community a resource with which to study human gene expression and regulation and its relationship to genetic variation. This project will collect and analyze multiple human tissues from donors who are also densely genotyped, to assess genetic variation within their genomes. By analyzing global RNA expression within individual tissues and treating the expression levels of genes as quantitative traits, variations in gene expression that are highly correlated with genetic variation can be identified as expression quantitative trait loci, or eQTLs.",
"data-field": "biology",
"data-type": "human",
"data-categories": [
"gene expression"
],
"data-access": [
{
"type": "download",
"location": "https://www.gtexportal.org/home/datasets"
}
],
"license": "custom",
"license-type": "permissive",
"license-link": "https://www.gtexportal.org/home/documentationPage",
"license-issues": [
{
"criteria": "A.2.2",
"comment": "Custom license based on the various datasets and NIH Genomic Data Sharing Policy."
},
{
"criteria": "C.1",
"comment": "No API or URL to access all data groupings with single action."
},
{
"criteria": "C.2",
"comment": "No API or URL and therefore no reasonable and transparent access."
},
{
"criteria": "D.1.1",
"comment": "As stated copyright may be interpreted by non-legal professional that the contents may be reused/remixed for research/scientific purposes."
},
{
"criteria": "E.1.1",
"comment": "As stated copyright may be interpreted by non-legal professional that the contents may be reused/remixed research/scientific purposes."
}
],
"license-commentary": [
"Protected Data and Raw Data in the portal has not included in evaluation of this resource. See the dbGaP file for score.",
"The data not under the exceptions listed are under the NIH GDS (https://grants.nih.gov/grants/guide/notice-files/NOT-OD-14-124.html).",
"Pilot data set (phs000424.v3.p1) - acceptance of the \"Ft. Lauderdale\" principles of rapid, pre-publication data release (see Sharing Data from Large-Scale Biological Research Projects: A System of Tripartite Responsibility, 2003). The continued success of rapid pre-publication data release relies on the scientific community to respect the data producer’s interest to publish a full analysis of their data first. Secondary users are asked to refrain from submitting manuscripts describing comprehensive analyses until the Consortium has published their analysis.",
"May 8, 2015 - No restrictions - main manuscript published.",
"phs000424.v4.p1 - the dataset is subject to 9 months publication restriction starting from the date of the release; no restrictions after Jan 4, 2015.",
"All datasets from phs00424.v5.p1 forward will follow the NIH GDS policy. This means that once released through dbGaP, there are no restrictions on use or publication. This document and an accompanying table of dataset releases can be found at http://www.gtexportal.org/home/documentationPage.",
"https://grants.nih.gov/grants/guide/notice-files/NOT-OD-14-124.html"
],
"contacts": [
"http://www.gtexportal.org/home/contact"
],
"license-commentary-embeddable": "Protected Data and Raw Data in the portal has not included in evaluation of this resource. See the dbGaP file for score.
The data not under the exceptions listed are under the NIH GDS (https://grants.nih.gov/grants/guide/notice-files/NOT-OD-14-124.html).
Pilot data set (phs000424.v3.p1) - acceptance of the \"Ft. Lauderdale\" principles of rapid, pre-publication data release (see Sharing Data from Large-Scale Biological Research Projects: A System of Tripartite Responsibility, 2003). The continued success of rapid pre-publication data release relies on the scientific community to respect the data producer’s interest to publish a full analysis of their data first. Secondary users are asked to refrain from submitting manuscripts describing comprehensive analyses until the Consortium has published their analysis.
May 8, 2015 - No restrictions - main manuscript published.
phs000424.v4.p1 - the dataset is subject to 9 months publication restriction starting from the date of the release; no restrictions after Jan 4, 2015.
All datasets from phs00424.v5.p1 forward will follow the NIH GDS policy. This means that once released through dbGaP, there are no restrictions on use or publication. This document and an accompanying table of dataset releases can be found at http://www.gtexportal.org/home/documentationPage.
https://grants.nih.gov/grants/guide/notice-files/NOT-OD-14-124.html",
"data-tags": "biology, human, gene expression",
"grade-automatic": 2.5
},
{
"id": "hmdb",
"description": "The Human Metabolome Database (HMDB) is a freely available electronic database containing detailed information about small molecule metabolites found in the human body.",
"last-curated": "2017-12-07",
"source": "Human Metabolome Database (HMDB)",
"source-link": "http://www.hmdb.ca",
"source-type": "source",
"status": "complete",
"data-field": "biology",
"data-type": "human",
"data-categories": [
"metabolomics",
"clinical chemistry",
"biomarkers"
],
"data-access": [
{
"type": "download",
"location": "http://www.hmdb.ca/downloads"
}
],
"license": "custom",
"license-type": "restrictive",
"license-link": "http://www.hmdb.ca/about#cite",
"license-hat-used": "false",
"license-issues": [
{
"criteria": "A.2.2",
"comment": "Custom terms at linked license and on downloads page."
},
{
"criteria": "D.1.1",
"comment": "The custom license would appear to allow for liberal non-commercial reuse."
},
{
"criteria": "E.1.1",
"comment": "The custom license would appear to explicitly allow for non-commercial reuse with other non-commercial interests."
}
],
"license-commentary": [
"While the terms are minimal, they seem intended to act a bit the CC-BY-NC; it was evaluated similarly.",
"Given their upstream resources mentioned in http://www.hmdb.ca/sources , it would be interesting to know their pass-through negotiations and differences with Canadian law.."
],
"was-controversial": "false",
"contacts": [
"https://twitter.com/WishartLab"
],
"grants": [
{
"label": "This project is supported by the Canadian Institutes of Health Research (award #111062), Alberta Innovates - Health Solutions, and by The Metabolomics Innovation Centre (TMIC), a nationally-funded research and core facility that supports a wide range of cutting-edge metabolomic studies."
}
],
"license-commentary-embeddable": "While the terms are minimal, they seem intended to act a bit the CC-BY-NC; it was evaluated similarly.
Given their upstream resources mentioned in http://www.hmdb.ca/sources , it would be interesting to know their pass-through negotiations and differences with Canadian law..",
"data-tags": "biology, human, metabolomics, clinical chemistry, biomarkers",
"grade-automatic": 3.5
},
{
"id": "hpo",
"source": "Human Phenotype Ontology (HPO)",
"source-link": "http://human-phenotype-ontology.github.io",
"status": "complete",
"description": "A curated database of human hereditary syndromes from OMIM, Orphanet, and DECIPHER mapped to classes of the human phenotype ontology. Various meta-attributes such as frequency, references and negations are associated with each annotation. These are presently limited to rare mendelian diseases.",
"data-field": "biology",
"data-type": "human",
"data-categories": [
"disease-phenotype association"
],
"data-access": [
{
"type": "download",
"location": "http://human-phenotype-ontology.github.io/downloads.html"
}
],
"license": "custom",
"license-type": "restrictive",
"license-link": "http://human-phenotype-ontology.github.io/license.html",
"license-issues": [
{
"criteria": "A.2.2",
"comment": "HPO is copyrighted to protect ontologies and all changes must be made by hpo developers."
},
{
"criteria": "D.1.2",
"comment": "Restricted downstream use. May not be edited."
},
{
"criteria": "E.1.2",
"comment": "Restricted downstream use translates to agents as well."
}
],
"license-commentary": [
"immutability",
"unclear derivatives",
"That the Human Phenotype Ontology Consortium is acknowledged and cited properly.",
"That neither the content of the HPO file(s) nor the logical relationships embedded within the HPO file(s) be altered in any way."
],
"contacts": [
"http://human-phenotype-ontology.github.io/contact.html"
],
"license-commentary-embeddable": "immutability
unclear derivatives
That the Human Phenotype Ontology Consortium is acknowledged and cited properly.
That neither the content of the HPO file(s) nor the logical relationships embedded within the HPO file(s) be altered in any way.",
"data-tags": "biology, human, disease-phenotype association",
"grade-automatic": 2.5
},
{
"id": "impc",
"source": "International Mouse Phenotyping Consortium (IMPC)",
"source-link": "http://www.mousephenotype.org",
"status": "complete",
"description": "The International Mouse Phenotyping Consortium (IMPC) is generating a knockout mouse strain for every protein coding gene by using the embryonic stem cell resource generated by the International Knockout Mouse Consortium (IKMC). Systematic broad-based phenotyping is performed by each IMPC center using standardized procedures found within the International Mouse Phenotyping Resource of Standardised Screens (IMPReSS) resource. Gene-to-phenotype associations are made by a versioned statistical analysis.",
"data-field": "biology",
"data-type": "mouse",
"data-categories": [
"genotype-phenotype association"
],
"data-access": [
{
"type": "download",
"location": "ftp://ftp.ebi.ac.uk/pub/databases/impc/latest/"
},
{
"type": "api",
"location": "http://www.mousephenotype.org/data/documentation/data-access"
}
],
"license": "all rights reserved",
"license-type": "copyright",
"license-link": null,
"license-issues": [
{
"criteria": "A.1.2",
"comment": "Could not find licensing information in a reasonable location. Determined ARR by default."
},
{
"criteria": "D.1.2",
"comment": "Restricted downstream use per ARR."
},
{
"criteria": "E.1.2",
"comment": "All downstream agents restricted per ARR."
}
],
"license-commentary": [
"Had to google to find the data use agreement page. Could not locate from browsing the website. 'http://www.mousephenotype.org/about-impc/additional-information/data-use-agreement'",
"When the first major Project paper on these analyses is published, then researchers inside and outside the Project are free to present and publish using the Project data for these and other analyses.",
"Perhaps the license page was removed because of publications and lifting of embargo as described above. Which defaults to ARR since no other license was found."
],
"contacts": [
"http://www.mousephenotype.org/contact-us"
],
"license-commentary-embeddable": "Had to google to find the data use agreement page. Could not locate from browsing the website. 'http://www.mousephenotype.org/about-impc/additional-information/data-use-agreement'
When the first major Project paper on these analyses is published, then researchers inside and outside the Project are free to present and publish using the Project data for these and other analyses.
Perhaps the license page was removed because of publications and lifting of embargo as described above. Which defaults to ARR since no other license was found.",
"data-tags": "biology, mouse, genotype-phenotype association",
"grade-automatic": 1
},
{
"id": "kegg-ftp",
"source": "Kyoto Encyclopedia of Genes and Genomes (KEGG), FTP",
"source-link": "http://kegg.jp",
"status": "complete",
"description": "KEGG is an integrated database resource consisting of the seventeen main databases including systems, genomic, chemical, and health information.",
"data-field": "biology",
"data-type": "genomic resource",
"data-categories": [
"gene-pathway association",
"disease-gene association",
"orthology"
],
"data-access": [
{
"type": "download",
"location": "http://www.kegg.jp/kegg/download/"
}
],
"license": "custom",
"license-type": "restrictive",
"license-link": "http://www.kegg.jp/kegg/legal.html",
"license-issues": [
{
"criteria": "A.2.2",
"comment": "For our use case (see commentary), KEGG (FTP) uses custom licensing through NPO Bioinformatics Japan (https://www.bioinformatics.jp/en/keggftp.html)."
},
{
"criteria": "B.1",
"comment": "According to the organizational use agreement: \"Your Product or Service must not allow Your users to obtain KEGG FTP Data, except in small quantities\"; many uses would require negotiation here as continuing reuse is unclear."
},
{
"criteria": "D.1.2",
"comment": "The licensing terms are too restrictive for reasonable reuse (e.g. B.1 violation above)."
},
{
"criteria": "E.1.2",
"comment": "Given our interpretation of the licensing terms, there is unlikely to be much ability to freely reuse the KEGG FTP data within any class."
}
],
"license-commentary": [
"KEGG (FTP) presents special problems as their licensing depends on variables like academic/non-academic, group/individual, commercial/non-commercial, and location. While the end terms do have some variation, for the sake of convenience, we will act as a non-commercial academic group based in the US wanting to access the entire database. Much curation was then based off of the organizational use agreement: https://www.bioinformatics.jp/docs/subscription_organizational.pdf .",
"Given all of the possible use cases, license verbiage, and special conditions, KEGG (FTP) was exceptionally difficult to curate.",
"Academic users license through NPO Bioinformatics Japan (https://www.bioinformatics.jp/en/keggftp.html).",
"Non-academic users license through Pathway Solutions (http://www.pathway.jp/).",
"While there are many possible combinations, any individual or use case should have a single license that they will need to get, giving us a pass on A.1.",
"While we did not go through the registration process, C.1 seems like it would be cleared by the directory layout description on http://www.kegg.jp/kegg/download/ .",
"While we did not go through the registration process, C.2 seems like it would be cleared by the implied straighforward FTP access post licensing.",
"Also see KEGG API and KEGG REST resources."
],
"was-controversial": "true",
"last-curated": "2017-10-17",
"contacts": [
"http://www.genome.jp/feedback/"
],
"license-commentary-embeddable": "KEGG (FTP) presents special problems as their licensing depends on variables like academic/non-academic, group/individual, commercial/non-commercial, and location. While the end terms do have some variation, for the sake of convenience, we will act as a non-commercial academic group based in the US wanting to access the entire database. Much curation was then based off of the organizational use agreement: https://www.bioinformatics.jp/docs/subscription_organizational.pdf .
Given all of the possible use cases, license verbiage, and special conditions, KEGG (FTP) was exceptionally difficult to curate.
Academic users license through NPO Bioinformatics Japan (https://www.bioinformatics.jp/en/keggftp.html).
Non-academic users license through Pathway Solutions (http://www.pathway.jp/).
While there are many possible combinations, any individual or use case should have a single license that they will need to get, giving us a pass on A.1.
While we did not go through the registration process, C.1 seems like it would be cleared by the directory layout description on http://www.kegg.jp/kegg/download/ .
While we did not go through the registration process, C.2 seems like it would be cleared by the implied straighforward FTP access post licensing.
Also see KEGG API and KEGG REST resources.",
"data-tags": "biology, genomic resource, gene-pathway association, disease-gene association, orthology",
"grade-automatic": 2
},
{
"id": "knoweng",
"description": "KnowEnG enables knowledge-guided machine learning and graph mining analysis on genomic datasets using scalable cloud computation and exploration of results with interactive visualizations.",
"last-curated": "2018-03-04",
"source": "KnowEnG",
"source-link": "https://hub.knoweng.org/",
"source-type": "integrator",
"status": "complete",
"data-field": "biology",
"data-type": "x-species",
"data-categories": [
"graph",
"cancer",
"gene",
"ontology",
"platform",
"protein families",
"molecular interaction",
"protein interaction"
],
"data-access": [
{
"type": "api",
"location": "https://platform.knoweng.org"
}
],
"license": "CC-BY-NC-SA-4.0",
"license-type": "restrictive",
"license-link": "https://knoweng.org/kn-overview/",
"license-hat-used": "false",
"license-issues": [
{
"criteria": "B.2.1",
"comment": "Explicit statement that license only applies to new work."
},
{
"criteria": "B.2.2",
"comment": "I found no method of obtaining just the new work data."
},
{
"criteria": "C.1",
"comment": "The resource seems to be a self-contained platform; after some search, I found no bulk methods of download."
},
{
"criteria": "C.2",
"comment": "As C.1."
},
{
"criteria": "D.1.2",
"comment": "While the NC part allows for non-commercial reuse, SA has license requirements."
},
{
"criteria": "E.1.2",
"comment": "While the NC part allows for non-commercial reuse, SA has license requirements."
}
],
"license-commentary": [
"Platform site requires registration/login.",
"In footer of platform: \"Portions licensed under CC BY ND NC 4.0 license\"",
"Nothing of interest under https://platform.knoweng.org/static/#/support/about",
"For knowledge graph, found more explicit info here: https://knoweng.org/kn-overview/",
"Licensing: \"This work is licensed under a Commons Attribution-Non-Commercial-ShareAlike license for academic uses only (https://creativecommons.org/license/by-nc-sa/4.0/, CC BY-NC-SA 4). Where work is the Derivative Works created by KN team from the various databases. We recommend that the researchers contact owners of the data sources directly to obtain necessary permissions and licenses to download data and/or use it in ways not envisioned in our license. The intent is for the KnowEnG system including KN and Tools to be available for free for academic use only.\"",
"Evaluation by taking the latter at face value, assuming that it is an encompassing license for all new work, and the remaining requires negotiation with upstream.",
"The major question is whether this is an A.1.1 violation or not; also, whether NC-SA is \"restrictive\" or \"copyleft\" for our purposes."
],
"was-controversial": "false",
"provisional": "true",
"contacts": [
"knoweng@illinois.edu"
],
"grants": [
{
"label": "The KnowEnG BD2K center is supported by grant 1U54GM114838 awarded by NIGMS through funds provided by the trans-NIH Big Data to Knowledge (BD2K) initiative"
}
],
"license-commentary-embeddable": "Platform site requires registration/login.
In footer of platform: \"Portions licensed under CC BY ND NC 4.0 license\"
Nothing of interest under https://platform.knoweng.org/static/#/support/about
For knowledge graph, found more explicit info here: https://knoweng.org/kn-overview/
Licensing: \"This work is licensed under a Commons Attribution-Non-Commercial-ShareAlike license for academic uses only (https://creativecommons.org/license/by-nc-sa/4.0/, CC BY-NC-SA 4). Where work is the Derivative Works created by KN team from the various databases. We recommend that the researchers contact owners of the data sources directly to obtain necessary permissions and licenses to download data and/or use it in ways not envisioned in our license. The intent is for the KnowEnG system including KN and Tools to be available for free for academic use only.\"
Evaluation by taking the latter at face value, assuming that it is an encompassing license for all new work, and the remaining requires negotiation with upstream.
The major question is whether this is an A.1.1 violation or not; also, whether NC-SA is \"restrictive\" or \"copyleft\" for our purposes.",
"data-tags": "biology, x-species, graph, cancer, gene, ontology, platform, protein families, molecular interaction, protein interaction",
"grade-automatic": 1.5
},
{
"id": "mgi",
"source": "Mouse Genome Informatics (MGI)",
"source-link": "http://www.informatics.jax.org/",
"status": "complete",
"description": "MGI is the international database resource for the laboratory mouse, providing integrated genetic, genomic, and biological data to facilitate the study of human health and disease.",
"data-field": "biology",
"data-type": "MOD",
"data-categories": [
"genotype-phenotype association",
"disease-model association",
"gene expression"
],
"data-access": [
{
"type": "download",
"location": "http://www.informatics.jax.org/downloads/reports/index.html"
}
],
"license": "custom",
"license-type": "permissive",
"license-link": "http://www.informatics.jax.org/mgihome/other/copyright.shtml",
"license-issues": [
{
"criteria": "A.2.2",
"comment": "Custom license."
},
{
"criteria": "E.1.1",
"comment": "distinguishes groups, allowing for research/academic. Commercial groups can negotiate."
}
],
"license-commentary": [
"-This software and data are provided to enhance knowledge and encourage progress in the scientific community and are to be used only for research and educational purposes.",
"-Any reproduction or use for commercial purpose is prohibited without the prior express written permission of the Jackson Laboratory."
],
"contacts": [
"http://www.informatics.jax.org/mgihome/support/mgi_inbox.shtml"
],
"license-commentary-embeddable": "-This software and data are provided to enhance knowledge and encourage progress in the scientific community and are to be used only for research and educational purposes.
-Any reproduction or use for commercial purpose is prohibited without the prior express written permission of the Jackson Laboratory.",
"data-tags": "biology, MOD, genotype-phenotype association, disease-model association, gene expression",
"grade-automatic": 4
},
{
"id": "monarch",
"source": "Monarch Initiative",
"source-type": "integrator",
"source-link": "https://monarchinitiative.org",
"status": "complete",
"description": "Integrate, align, and re-distribute cross-species gene, genotype, variant, disease, and phenotype data. Provide a portal for exploration of phenotype-based similarity. Facilitate identification of animal models of human disease through phenotypic similarity. Enable quantitative comparison of cross-species phenotypes. Develop embeddable widgets for data exploration. Influence genotype and phenotype reporting standards. Improve ontologies to better curate genotype-phenotype data.",
"data-field": "biology",
"data-type": "x-species",
"data-categories": [
"gene",
"genotype",
"disease",
"phenotype",
"variant",
"disease-phenotype associations",
"genotype-phenotype associations"
],
"data-access": [
{
"type": "api",
"location": "https://api.monarchinitiative.org/api/"
},
{
"type": "download",
"location": "https://archive.monarchinitiative.org/latest/"
}
],
"license": "inconsistent",
"license-type": "unknown",
"license-link": "https://monarchinitiative.org",
"license-issues": [
{
"criteria": "A.1.1",
"comment": "Text in footer: \"Except where forbidden by the original sources...\"; how these interact is not clear. There is no indication of which data has what sources, so reusability cannot be determined."
},
{
"criteria": "C.1",
"comment": "The scope of the API is not clear and the data downloads locations are apparently not public."
}
],
"license-commentary": [
"I could not find a direct reference to whether the data found at the API and downloads were complete in scope.",
"Apparent license found in footer of all pages.",
"Except where forbidden by the original sources, this work is licensed under a Creative Commons Attribution 3.0 License."
],
"contacts": [
"info@monarchinitiative.org"
],
"license-commentary-embeddable": "I could not find a direct reference to whether the data found at the API and downloads were complete in scope.
Apparent license found in footer of all pages.
Except where forbidden by the original sources, this work is licensed under a Creative Commons Attribution 3.0 License.",
"data-tags": "biology, x-species, gene, genotype, disease, phenotype, variant, disease-phenotype associations, genotype-phenotype associations",
"grade-automatic": 0.5
},
{
"id": "mpd",
"source": "Mouse Phenome Database (MPD)",
"source-link": "https://phenome.jax.org/",
"status": "complete",
"description": "The Mouse Phenome Database is a collaborative standardized collection of measured data on laboratory mouse strains, and includes: baseline phenotype data sets; studies of drug, diet, disease and aging effect; protocols, projects, and publications; and SNP, variation and gene expression studies. MPD collects data for classical inbred strains, other fixed-genotype strains, derived lines and populations that are openly acquirable (strain panel examples). Strains can be from JAX-Mice or from any other vendor that\\'s a recognized breeding source.",
"data-field": "biology",
"data-type": "MOD",
"data-categories": [
"genotype (strain)-phenotype association"
],
"data-access": [
{
"type": "download",
"location": "http://phenome.jax.org/downloads"
}
],
"license": "custom",
"license-type": "permissive",
"license-link": "http://phenome.jax.org/about/termsofuse",
"license-issues": [
{
"criteria": "A.2.2",
"comment": "Custom license, yet consistent."
}
],
"license-commentary": [
"-MPD data contributors waive copyright and related rights, making their data freely available whereby MPD users may freely build upon, enhance and reuse those data for any purpose without restriction. Scholarly citation norms must be followed for content reuse.",
"-The Jackson Laboratory\\'s web site privacy policy applies to all use of this resource.",
"-The Mouse Phenome Database (MPD) is an NIH-funded data sharing repository and adheres to the NIH Genomic Data Sharing Policy.",
"-Any reproduction of JAX(R) Mice mouse images is prohibited without prior express written permission (see the JAX(R) Mice Terms of Use for details).",
"-Data contributors and data users may not use MPD in any unlawful manner, or in any manner that would impair MPD\\'s services, security or functionality. Automated usage (webcrawlers and similar) must observe each page\\'s \"meta robots\" html tags and space requests by ≥ 2 seconds. We reserve the right to block violators and to take any other action as we deem necessary."
],
"contacts": [
"phenome@jax.org"
],
"license-commentary-embeddable": "-MPD data contributors waive copyright and related rights, making their data freely available whereby MPD users may freely build upon, enhance and reuse those data for any purpose without restriction. Scholarly citation norms must be followed for content reuse.
-The Jackson Laboratory\\'s web site privacy policy applies to all use of this resource.
-The Mouse Phenome Database (MPD) is an NIH-funded data sharing repository and adheres to the NIH Genomic Data Sharing Policy.
-Any reproduction of JAX(R) Mice mouse images is prohibited without prior express written permission (see the JAX(R) Mice Terms of Use for details).
-Data contributors and data users may not use MPD in any unlawful manner, or in any manner that would impair MPD\\'s services, security or functionality. Automated usage (webcrawlers and similar) must observe each page\\'s \"meta robots\" html tags and space requests by ≥ 2 seconds. We reserve the right to block violators and to take any other action as we deem necessary.",
"data-tags": "biology, MOD, genotype (strain)-phenotype association",
"grade-automatic": 4.5
},
{
"id": "msigdb",
"source": "MSigDB",
"source-link": "http://software.broadinstitute.org/gsea/msigdb/index.jsp",
"status": "complete",
"description": "The Molecular Signatures Database (MSigDB) is a collection of annotated gene sets for use with GSEA software.",
"data-field": "biology",
"data-type": "gene sets",
"data-access": [
{
"type": "download",
"location": "http://software.broadinstitute.org/gsea/downloads.jsp"
}
],
"license": "CC-BY-4.0",
"license-type": "permissive",
"license-link": "http://software.broadinstitute.org/gsea/msigdb_license_terms.jsp",
"license-issues": [
{
"criteria": "B.2.1",
"comment": "The main body of work is under CC-BY 4.0, with filterable additional works under their own terms from KEGG, BioCarta, and AAAS/STKE. While the filtering step is an annoyance, is can likely easily be done given their instructions and would be a one-time process per release."
}
],
"license-commentary": [
"MSigDB v6.0 is available under a Creative Commons style license, plus additional terms for some gene sets",
"A user must register before being able to view the downloads for tracking purposes. Easy access after that set is done."
],
"contacts": [
"http://software.broadinstitute.org/gsea/contact.jsp"
],
"license-commentary-embeddable": "MSigDB v6.0 is available under a Creative Commons style license, plus additional terms for some gene sets
A user must register before being able to view the downloads for tracking purposes. Easy access after that set is done.",
"data-tags": "biology, gene sets",
"grade-automatic": 4.5
},
{
"id": "mygene-info",
"source": "MyGene.info",
"source-link": "http://mygene.info",
"status": "complete",
"description": "MyGene.info provides simple-to-use REST web services to query/retrieve gene annotation data.",
"data-field": "biology",
"data-type": "genomic resource",
"data-categories": [
"gene definition"
],
"data-access": [
{
"type": "api",
"location": "http://mygene.info/v3/api"
}
],
"license": "custom",
"license-type": "restrictive",
"license-link": "http://mygene.info/terms/",
"license-commentary": [
"MyGene.info may contain information from third party websites, which may or may not be marked with the name of the source. Such information does not necessarily represent the views or opinions of TSRI, and TSRI shall have no responsibility whatsoever for such information.",
"You also agree that you will ensure that any copies of documents you generate by using MyGene.info shall retain and display all copyright and other proprietary notices contained therein.",
"TSRI shall have no responsibility whatsoever for such information [from 3rd party websites].",
"Nothing contained herein shall be construed as conferring by implication, estoppel or otherwise any license or right under any patent, trademark or other intellectual property of TSRI or any third party. Except as expressly provided above, nothing contained herein shall be construed as conferring any right or license under any TSRI copyrights."
],
"license-issues": [
{
"criteria": "A.2.2",
"comment": "Custom license, but consistent."
},
{
"criteria": "B.2.1",
"comment": "Scope is incomplete - they claim no responsibility for data from other sources on their site."
},
{
"criteria": "D.1.2",
"comment": "No re-use allowed, just use."
},
{
"criteria": "E.1.2",
"comment": "No re-use allowed, just use."
}
],
"contacts": [
"help@mygene.info"
],
"license-commentary-embeddable": "MyGene.info may contain information from third party websites, which may or may not be marked with the name of the source. Such information does not necessarily represent the views or opinions of TSRI, and TSRI shall have no responsibility whatsoever for such information.
You also agree that you will ensure that any copies of documents you generate by using MyGene.info shall retain and display all copyright and other proprietary notices contained therein.
TSRI shall have no responsibility whatsoever for such information [from 3rd party websites].
Nothing contained herein shall be construed as conferring by implication, estoppel or otherwise any license or right under any patent, trademark or other intellectual property of TSRI or any third party. Except as expressly provided above, nothing contained herein shall be construed as conferring any right or license under any TSRI copyrights.",
"data-tags": "biology, genomic resource, gene definition",
"grade-automatic": 2
},
{
"id": "myvariant-info",
"description": "MyVariant.info provides simple-to-use REST web services to query/retrieve variant annotation data, aggregated from many popular data resources.",
"last-curated": "2017-12-03",
"source": "MyVariant.info",
"source-link": "http://myvariant.info/",
"source-type": "integrator",
"status": "complete",
"data-field": "biology",
"data-type": "genomic resource",
"data-categories": [
"variants",
"variant annotation"
],
"data-access": [
{
"type": "api",
"location": "http://myvariant.info/docs/"
}
],
"license": "custom",
"license-type": "restrictive",
"license-link": "http://myvariant.info/terms/",
"license-hat-used": "false",
"license-commentary": [
"MyVariant.info may contain information from third party websites, which may or may not be marked with the name of the source. Such information does not necessarily represent the views or opinions of TSRI, and TSRI shall have no responsibility whatsoever for such information.",
"You also agree that you will ensure that any copies of documents you generate by using MyVariant.info shall retain and display all copyright and other proprietary notices contained therein.",
"TSRI shall have no responsibility whatsoever for such information [from 3rd party websites].",
"Nothing contained herein shall be construed as conferring by implication, estoppel or otherwise any license or right under any patent, trademark or other intellectual property of TSRI or any third party. Except as expressly provided above, nothing contained herein shall be construed as conferring any right or license under any TSRI copyrights."
],
"license-issues": [
{
"criteria": "A.2.2",
"comment": "Custom license, but consistent."
},
{
"criteria": "B.2.1",
"comment": "Scope is incomplete - they claim no responsibility for data from other sources on their site."
},
{
"criteria": "D.1.2",
"comment": "No re-use allowed, just use."
},
{
"criteria": "E.1.2",
"comment": "No re-use allowed, just use."
}
],
"was-controversial": "false",
"contacts": [
"help@myvariant.info"
],
"license-commentary-embeddable": "MyVariant.info may contain information from third party websites, which may or may not be marked with the name of the source. Such information does not necessarily represent the views or opinions of TSRI, and TSRI shall have no responsibility whatsoever for such information.
You also agree that you will ensure that any copies of documents you generate by using MyVariant.info shall retain and display all copyright and other proprietary notices contained therein.
TSRI shall have no responsibility whatsoever for such information [from 3rd party websites].
Nothing contained herein shall be construed as conferring by implication, estoppel or otherwise any license or right under any patent, trademark or other intellectual property of TSRI or any third party. Except as expressly provided above, nothing contained herein shall be construed as conferring any right or license under any TSRI copyrights.",
"data-tags": "biology, genomic resource, variants, variant annotation",
"grade-automatic": 2
},
{
"id": "ncbi-gene",
"source": "National Center for Biotechnology Information (Gene)",
"source-link": "https://www.ncbi.nlm.nih.gov/gene/",
"status": "complete",
"description": "Gene integrates information from a wide range of species. A record may include nomenclature, Reference Sequences (RefSeqs), maps, pathways, variations, phenotypes, and links to genome-, phenotype-, and locus-specific resources worldwide.",
"data-field": "biology",
"data-type": "genomic resource",
"data-categories": [
"gene definition",
"taxon definition",
"gene-publication association"
],
"data-access": [
{
"type": "download",
"location": "ftp://ftp.ncbi.nih.gov/gene/"
}
],
"license": "inconsistent",
"license-type": "unknown",
"license-link": "http://www.ncbi.nlm.nih.gov/home/about/policies.shtml",
"license-issues": [
{
"criteria": "A.1.1",
"comment": "The license apparently uses language to declare something similar to \"public domain\", but with the caveat that it may contain data that is otherwise. This is judged to be a violation as any (re)use would depend on negotiating with all upstream copyright holders, which are not presented. It is implied that their license does not cover all data and could not find an explicit \"clean\" version of the data in the downloads."
}
],
"license-commentary": [
"We specifically avoided the more general operation of the EUtils suite, focusing on the provided downloads.",
"The following statements from the license page seem to support a custom \"hands off\" approach. To was difficult to decide if this was \"restrictive\" or \"unknown\" (although inconsistent in practice).",
"...NCBI itself places no restrictions on the use or distribution of the data contained therein. Nor do we accept data when the submitter has requested restrictions on reuse or redistribution...",
"...some submitters of the original data...may claim patent, copyright, or other intellectual property rights in all or a portion of the data (that has been submitted)...",
"...NCBI cannot provide comment or unrestricted permission concerning the use, copying, or distribution of the information contained in the molecular databases..."
],
"contacts": [
"info@ncbi.nlm.nih.gov"
],
"license-commentary-embeddable": "We specifically avoided the more general operation of the EUtils suite, focusing on the provided downloads.
The following statements from the license page seem to support a custom \"hands off\" approach. To was difficult to decide if this was \"restrictive\" or \"unknown\" (although inconsistent in practice).
...NCBI itself places no restrictions on the use or distribution of the data contained therein. Nor do we accept data when the submitter has requested restrictions on reuse or redistribution...
...some submitters of the original data...may claim patent, copyright, or other intellectual property rights in all or a portion of the data (that has been submitted)...
...NCBI cannot provide comment or unrestricted permission concerning the use, copying, or distribution of the information contained in the molecular databases...",
"data-tags": "biology, genomic resource, gene definition, taxon definition, gene-publication association",
"grade-automatic": 1
},
{
"id": "ncit",
"description": "NCI Thesaurus (NCIt) provides reference terminology for many NCI and other systems. It covers vocabulary for clinical care, translational and basic research, and public information and administrative activities.\n",
"last-curated": "2019-05-22",
"source": "NCI Thesaurus",
"source-link": "https://ncithesaurus-stage.nci.nih.gov",
"source-type": "source",
"status": "complete",
"data-field": "biomedical",
"data-type": "ontology",
"data-categories": [
"cancer",
"ontology",
"disease",
"phenotypes",
"pharmacology",
"drugs",
"biomedical coding and reference"
],
"data-access": [
{
"type": "download",
"location": "https://evs.nci.nih.gov/ftp1/NCI_Thesaurus/"
}
],
"license": "CC-BY-4.0",
"license-type": "permissive",
"license-link": "https://evs.nci.nih.gov/ftp1/NCI_Thesaurus/ThesaurusTermsofUse.htm",
"license-hat-used": "false",
"license-issues": [],
"license-commentary": [
"The Terms of Use puts a trademark restriction on re-releasing the data using the name \"NCI Thesaurus\". This was evaluated as be outside the scope of data (re)use.\n"
],
"was-controversial": "false",
"contacts": [
"https://ncithesaurus-stage.nci.nih.gov/ncitbrowser/pages/contact_us.jsf",
"NCIAppSupport@nih.gov",
"http://ncicb.nci.nih.gov/support"
],
"grants": [],
"license-commentary-embeddable": "The Terms of Use puts a trademark restriction on re-releasing the data using the name \"NCI Thesaurus\". This was evaluated as be outside the scope of data (re)use.\n",
"data-tags": "biomedical, ontology, cancer, ontology, disease, phenotypes, pharmacology, drugs, biomedical coding and reference",
"grade-automatic": 5
},
{
"id": "nextprot",
"description": "Developed by the SIB Swiss Institute of Bioinformatics neXtProt is a comprehensive human-centric discovery platform, offering its users a seamless integration of and navigation through protein-related data.",
"last-curated": "2020-03-09",
"source": "neXtProt",
"source-link": "https://www.nextprot.org",
"source-type": "integrator",
"status": "complete",
"data-field": "biology",
"data-type": "human",
"data-categories": [
"protein-related data",
"protein functional data",
"protein-protein interaction",
"subcellular location"
],
"data-access": [
{
"type": "download",
"location": "ftp://ftp.nextprot.org/pub/"
},
{
"type": "api",
"location": "http://api.nextprot.org"
},
{
"type": "api",
"location": "http://sparql.nextprot.org"
},
{
"type": "api",
"location": "http://snorql.nextprot.org"
}
],
"license": "CC-BY-4.0",
"license-type": "permissive",
"license-link": "ftp://ftp.nextprot.org/pub/README",
"license-hat-used": "false",
"license-issues": [],
"license-commentary": [
"Using the license most proximate to the download--in the downloads directory itself. There is a somewhat ambiguous ARR statement at https://www.nextprot.org/copyright."
],
"was-controversial": "false",
"contacts": [
"support@nextprot.org"
],
"license-commentary-embeddable": "Using the license most proximate to the download--in the downloads directory itself. There is a somewhat ambiguous ARR statement at https://www.nextprot.org/copyright.",
"data-tags": "biology, human, protein-related data, protein functional data, protein-protein interaction, subcellular location",
"grade-automatic": 5
},
{
"id": "nextstrain",
"source": "Nextstrain",
"source-link": "http://www.nextstrain.org",
"status": "nonpublic",
"description": "Nextstrain is an open-source project to harness the scientific and public health potential of pathogen genome data. We provide a continually-updated view of publicly available data with powerful analytics and visualizations showing pathogen evolution and epidemic spread. Our goal is to aid epidemiological understanding and improve outbreak response.",
"data-field": "biology",
"data-type": "genomic resource",
"data-categories": [
"viral phylogeny",
"virus evolution"
],
"data-access": [],
"license": "unlicensed",
"license-type": "copyright",
"license-link": "TODO",
"license-issues": [
{
"criteria": "A.1.2",
"comment": "Could not find any clear terms on any searched pages. See commentary."
}
],
"license-commentary": [
"This is apparently not a public data resource: it is consuming open science, but producing nothing for downstream. I have checked the three non-application pages and there is no data, downloads, or copyright beyond software: /, /about, and /methods.",
"From the site: This work is made possible by the open sharing of genetic data by research groups from all over the world. We gratefully acknowledge their contributions."
],
"contacts": []
},
{
"id": "omia",
"source": "Online Mendelian Inheritance in Animals (OMIA)",
"source-link": "http://omia.angis.org.au",
"status": "complete",
"description": "Online Mendelian Inheritance in Animals (OMIA) is a catalogue/compendium of inherited disorders, other (single-locus) traits, and genes in 215 (non-model) animal species.",
"data-field": "biology",
"data-type": "veterinary x-species",
"data-categories": [
"gene-disease association"
],
"data-access": [
{
"type": "download",
"location": "http://omia.angis.org.au/download/"
}
],
"license": "all rights reserved",
"license-type": "copyright",
"license-link": "http://sydney.edu.au/disclaimer.html",
"license-issues": [
{
"criteria": "D.1.2",
"comment": "The license seems to be a standard ARR, with no exception for any kind of bulk (re)use."
},
{
"criteria": "E.1.2",
"comment": "The license seems to be a standard ARR, with no exception for any kind of bulk (re)use."
}
],
"license-commentary": [
"Appears to be the equivalent of Australian ARR with one exception, which looks fairly standard as well. The exception, however, adds little for our use case over ARR.",
"The order of the copyright statments is: this is under copyright, a couple of groups may use a portion, but besides those no \\\"material from this site may not be reproduced for commercial purposes without prior written permission of the University of Sydney.\\\" We are reading this to mean that those specified limited categories may the data for commercial purposes, but all others must contact OMIA."
],
"contacts": [
"http://omia.angis.org.au/contact/"
],
"license-commentary-embeddable": "Appears to be the equivalent of Australian ARR with one exception, which looks fairly standard as well. The exception, however, adds little for our use case over ARR.
The order of the copyright statments is: this is under copyright, a couple of groups may use a portion, but besides those no \\\"material from this site may not be reproduced for commercial purposes without prior written permission of the University of Sydney.\\\" We are reading this to mean that those specified limited categories may the data for commercial purposes, but all others must contact OMIA.",
"data-tags": "biology, veterinary x-species, gene-disease association",
"grade-automatic": 3
},
{
"id": "omim",
"last-curated": "2017-12-07",
"source": "Mendelian Inheritance in Man (OMIM)",
"source-link": "https://www.omim.org",
"source-type": "source",
"status": "complete",
"description": "OMIM is a comprehensive, authoritative compendium of human genes and genetic phenotypes with full-text, referenced overviews that contains information on all known mendelian disorders and over 12,000 genes. OMIM focuses on the relationship between phenotype and genotype.",
"data-field": "biomedical",
"data-type": "human",
"data-categories": [
"disease-phenotype association",
"gene-disease association",
"variant-disease association"
],
"data-access": [
{
"type": "api",
"location": "https://omim.org/api"
},
{
"type": "download",
"location": "https://omim.org/downloads"
}
],
"license": "custom",
"license-type": "restrictive",
"license-link": "http://www.omim.org/help/agreement",
"license-hat-used": "false",
"license-issues": [
{
"criteria": "A.2.2",
"comment": "The license at link is custom."
},
{
"criteria": "B.1",
"comment": "Agreement section 13 requires downloads to be updated by downstream; section 14 discussion arbitrary API key revocation."
},
{
"criteria": "C.2",
"comment": "Downloads and access are provided post-registration; as the API key is used for access control, it violates the C.2 example."
},
{
"criteria": "D.1.2",
"comment": "Sections 8, 9, and 10 of the agreement make it seems that while a non-profit reasearcher may access the data, there is no reuse (pass-through) possible."
},
{
"criteria": "E.1.2",
"comment": "Sections 8, 9, and 10 of the agreement make it seems that while a non-profit reasearcher may access the data, there is no reuse (pass-through) possible."
}
],
"license-commentary": [
"Assuming that one registered, it seems that data access would be relatively pain-free; so no C.1 violation.",
"See also: https://omim.org/downloads and https://omim.org/api for additional access information.",
"It is worth reading through the linked agreement; there are many sections that are restrictive or would be best interpreted with legal advice."
],
"was-controversial": "false",
"contacts": [
"JHTT-Communications@jhmi.edu"
],
"grants": [
{
"label": "\\\"OMIM curation and updating is funded by a grant from the National Human Genome Research Institute (NHGRI) [1U41HG006627]. Initial development of the OMIM.org website was supported by Johns Hopkins Medicine and a grant from the Maryland Department of Health and Mental Hygiene. OMIM is hosted at University of California Santa Cruz (UCSC) Genome Bioinformatics.\\\""
}
],
"license-commentary-embeddable": "Assuming that one registered, it seems that data access would be relatively pain-free; so no C.1 violation.
See also: https://omim.org/downloads and https://omim.org/api for additional access information.
It is worth reading through the linked agreement; there are many sections that are restrictive or would be best interpreted with legal advice.",
"data-tags": "biomedical, human, disease-phenotype association, gene-disease association, variant-disease association",
"grade-automatic": 1.5
},
{
"id": "oncokb",
"source": "OncoKB",
"source-link": "http://oncokb.org",
"status": "complete",
"description": "OncoKB is a precision oncology knowledge base and contains information about the effects and treatment implications of specific cancer gene alterations. It is developed and maintained by the Knowledge Systems group in the Marie Josée and Henry R. Kravis Center for Molecular Oncology at Memorial Sloan Kettering Cancer Center (MSK), in partnership with Quest Diagnostics.",
"data-field": "biology",
"data-type": "human",
"data-categories": [
"variants",
"cancer genes",
"gene expression"
],
"data-access": [
{
"type": "download",
"location": "http://oncokb.org/#/dataAccess"
}
],
"license": "custom",
"license-type": "restrictive",
"license-link": "http://oncokb.org/#/terms",
"license-issues": [
{
"criteria": "A.2.2",
"comment": "While custom, the terms are quite clear."
},
{
"criteria": "D.1.1",
"comment": "Restrictions on type of use appear in the license, even or research:\"You may copy, reproduce, or create derivative works of the Content only if:...you are using the Content only to replicate OncoKB locally, whether in whole or in part; or you are aggregating the Content with other data of similar nature for the purposes of advancing cancer research.\""
},
{
"criteria": "E.1.1",
"comment": "Restrictions exist on who may use the data: \"You may copy, reproduce, or create derivative works of the Content only if: you are a researcher or a non-profit entity; and...\""
}
],
"license-commentary": [
"While there does not seem to be any clear licensing information currently on the site, from a separate conversation (https://github.com/geneontology/noctua/issues/510#issuecomment-334864073), it would seem that this will soon be updated."
],
"last-curated": "2017-12-03",
"contacts": [
"team@oncokb.org"
],
"license-commentary-embeddable": "While there does not seem to be any clear licensing information currently on the site, from a separate conversation (https://github.com/geneontology/noctua/issues/510#issuecomment-334864073), it would seem that this will soon be updated.",
"data-tags": "biology, human, variants, cancer genes, gene expression",
"grade-automatic": 3.5
},
{
"id": "orphanet-academic",
"source": "Orphanet portal for rare diseases and orphan drugs (academic access subset)",
"source-link": "http://www.orpha.net",
"source-type": "source",
"status": "complete",
"description": "Orphanet provides reference information on rare diseases and orphan drugs to help improve the diagnosis, care and treatment of patients with rare diseases.",
"last-curated": "2018-01-25",
"data-field": "biomedical",
"data-type": "human",
"data-categories": [
"disease-gene association",
"disease-phenotype association",
"disease classification",
"clinical metadata",
"disease epidemiology",
"orphan drugs",
"ontology"
],
"data-access": [],
"license": "custom",
"license-type": "restrictive",
"license-link": "http://www.orphadata.org/cgi-bin/contact.php",
"license-hat-used": "true",
"license-commentary": [
"The was based on the Academic DTA from Orphanet; there is also a commercial version of the Data Transfer Agreement (DTA), but we will not evaluate that for the time being.",
"Note that the license link above is to the contact request form as one must actively pursue the DTA--it was not apparently available directly from the site. Whether this is a A.1.2 violation is under consideration.",
"Data access details are not known as we did not pursue the agreement; given the descriptions (http://www.orphadata.org/cgi-bin/docs/CataloguePdt-Academia.pdf) and evaluation for the free dataset, we have erred on the side that there are no C violations.",
"Interestingly, the agreement is: \\\"...governed by French laws...French courts shall have sole jurisdiction for any litigation...\\\"."
],
"license-issues": [
{
"criteria": "A.2.2",
"comment": "Non-standard/custom license."
},
{
"criteria": "B.1",
"comment": "Section 11.1 of the DTA we looked at discusses the term of the agreement, which would have to be renewed approximately every year."
},
{
"criteria": "D.1.2",
"comment": "The user \\\"...may freely use the Data only for data analysis...any other use of the Data must receive the authorization of Orphanet management board...\\\""
},
{
"criteria": "E.1.2",
"comment": "The license is \\\"personal, non-transferable and non-communicable\\\", so cannot be freely reused."
}
],
"was-controversial": "false",
"contacts": [
"http://www.orphadata.org/cgi-bin/contact.php"
],
"grants": [
{
"label": "The European Commission funds the inventory of rare diseases, the encyclopaedia, and the collection of data on expert resources in European countries (since 2000, DG Health and Consumers Protection grant N°s S12.305098; S12.324970; SPC.2002269-2003220, 2006119, 20091215 and since 2004, DG Research and Innovation grant N°s LSSM-CT-2004-503246; LSHB-CT-2004-512148; LSHB-CT-2006-018933; Health-F2-2008-201230, HEALTH-F2-2009-223355, DG Santé grant 20133305-Operating Grant Orphanet). In 2014, the DG Santé grant 20102206 (Orphanet Europe Joint Action) was extended for one year without additional funding. In 2015, Orphanet participated in the ECRIN Integrating Activity (ECRIN-IA, 284395), funded by the European Union Framework Program 7.In 2016 Orphanet participated in the HIPBI-RD project (Erare Joint calls). Orphanet consortium is funded by the DG Santé grant RD-ACTION Joint Action 677024 (2015-2018)."
}
],
"license-commentary-embeddable": "The was based on the Academic DTA from Orphanet; there is also a commercial version of the Data Transfer Agreement (DTA), but we will not evaluate that for the time being.
Note that the license link above is to the contact request form as one must actively pursue the DTA--it was not apparently available directly from the site. Whether this is a A.1.2 violation is under consideration.
Data access details are not known as we did not pursue the agreement; given the descriptions (http://www.orphadata.org/cgi-bin/docs/CataloguePdt-Academia.pdf) and evaluation for the free dataset, we have erred on the side that there are no C violations.
Interestingly, the agreement is: \\\"...governed by French laws...French courts shall have sole jurisdiction for any litigation...\\\".",
"data-tags": "biomedical, human, disease-gene association, disease-phenotype association, disease classification, clinical metadata, disease epidemiology, orphan drugs, ontology",
"grade-automatic": 2
},
{
"id": "orphanet-open",
"source": "Orphanet portal for rare diseases and orphan drugs (open access subset)",
"source-link": "http://www.orpha.net",
"status": "complete",
"description": "Orphanet provides reference information on rare diseases and orphan drugs to help improve the diagnosis, care and treatment of patients with rare diseases.",
"data-field": "biomedical",
"data-type": "human",
"data-categories": [
"disease-gene association",
"disease-phenotype association",
"disease classification",
"ontology"
],
"data-access": [
{
"type": "download",
"location": "http://www.orphadata.org/cgi-bin/index.php/"
},
{
"type": "api",
"location": "http://www.orpha.net/sparql"
}
],
"license": "CC-BY-ND-3.0",
"license-type": "restrictive",
"license-link": "http://www.orphadata.org/cgi-bin/inc/legal.inc.php",
"license-commentary": [
"...you are free to copy, distribute, display and make commercial use of these databases in all legislations, provided you give us credit.",
"However, if you intend to distribute a modified version of one of our databases, you must ask us for permission first.",
"Users from Academia can obtain access for free via signature of a data transfer agreement",
"Freely-accesssible dataset"
],
"license-issues": [
{
"criteria": "D.1.2",
"comment": "The CC-BY-ND license prevents derivation."
},
{
"criteria": "E.1.2",
"comment": "The CC-BY-ND license prevents derivation."
}
],
"contacts": [
"http://www.orphadata.org/cgi-bin/contact.php"
],
"license-commentary-embeddable": "...you are free to copy, distribute, display and make commercial use of these databases in all legislations, provided you give us credit.
However, if you intend to distribute a modified version of one of our databases, you must ask us for permission first.
Users from Academia can obtain access for free via signature of a data transfer agreement
Freely-accesssible dataset",
"data-tags": "biomedical, human, disease-gene association, disease-phenotype association, disease classification, ontology",
"grade-automatic": 3
},
{
"id": "panther",
"source": "Protein ANalysis THrough Evolutionary Relationships Classification System (PANTHER)",
"source-link": "http://pantherdb.org/",
"status": "complete",
"description": "The PANTHER (Protein ANalysis THrough Evolutionary Relationships) Classification System was designed to classify proteins (and their genes) according to evolutionary family/subfamily, molecular function, biological process, and pathway. The PANTHER Classifications are the result of human curation as well as sophisticated bioinformatics algorithms.",
"data-field": "biology",
"data-type": "genomic resource",
"data-categories": [
"orthology"
],
"data-access": [
{
"type": "download",
"location": "http://pantherdb.org/downloads/index.jsp"
}
],
"license": "all rights reserved",
"license-type": "copyright",
"license-issues": [
{
"criteria": "D.1.2",
"comment": "Given the all rights reserved copyright statement, any downstream reuse would require negotiation."
},
{
"criteria": "E.1.2",
"comment": "Given the all rights reserved copyright statement, all user/agent types would need to negotiate downstream reuse."
}
],
"license-commentary": [
"There is an alternate curation for this resource that bases itself off of 'http://www.pantherdb.org/tou.jsp', which was found using a narrow Google search and not given consideration due to the difficulties in finding it--we have found no access to this document yet except for the Google search.",
"Considering the alternate license, downloads are under a permissive minimal license that states '...as long as the following copyright statement is placed at the top of each file: Copyright © 2005 SRI International', which besides being likely out of data, is custom and does not cover APIs, remixing, and the like. It is hard to interpret the consequences of this license."
],
"contacts": [
"feedback@pantherdb.org",
"pdthomas@usc.edu"
],
"license-commentary-embeddable": "There is an alternate curation for this resource that bases itself off of 'http://www.pantherdb.org/tou.jsp', which was found using a narrow Google search and not given consideration due to the difficulties in finding it--we have found no access to this document yet except for the Google search.
Considering the alternate license, downloads are under a permissive minimal license that states '...as long as the following copyright statement is placed at the top of each file: Copyright © 2005 SRI International', which besides being likely out of data, is custom and does not cover APIs, remixing, and the like. It is hard to interpret the consequences of this license.",
"data-tags": "biology, genomic resource, orthology",
"grade-automatic": 3
},
{
"id": "pfam",
"description": "The Pfam database is a large collection of protein families, each represented by multiple sequence alignments and hidden Markov models (HMMs).",
"last-curated": "2019-10-18",
"source": "Pfam",
"source-link": "http://pfam.xfam.org",
"source-type": "repository",
"status": "complete",
"data-field": "biology",
"data-type": "protein families",
"data-categories": [
"protein family alignments",
"HMMs"
],
"data-access": [
{
"type": "download",
"location": "ftp://ftp.ebi.ac.uk/pub/databases/Pfam/"
}
],
"license": "CC0-1.0",
"license-type": "permissive",
"license-link": "http://pfam.xfam.org/about",
"license-hat-used": "false",
"license-issues": [],
"license-commentary": [
"Pfam is freely available under the Creative Commons Zero (\"CC0\") licence."
],
"was-controversial": "false",
"contacts": [
"pfam-help@ebi.ac.uk"
],
"grants": [
{
"label": "EMBL is EMBL-EBI\\'s parent organisation. It provides core funding (staff, space, equipment) for Pfam."
},
{
"label": "The Wellcome Trust has supported Pfam since the database inception, via core funding when based at the Wellcome Trust Sanger Institute. As well as providing and maintaining the campus on which the EMBL-EBI is located, the Wellcome Trust also now provides significant funding for Pfam (grant 108433/Z/15/Z). The current grant runs from October 2015 to September 2020."
},
{
"label": "BBSRC currently supports Pfam activities via the grants (BB/L024136/1 and BB/N00521X/1)."
},
{
"label": "The Howard Hughes Medical Institute supports the Eddy group."
}
],
"license-commentary-embeddable": "Pfam is freely available under the Creative Commons Zero (\"CC0\") licence.",
"data-tags": "biology, protein families, protein family alignments, HMMs",
"grade-automatic": 5
},
{
"id": "pharos",
"description": "Pharos is the user interface to the Knowledge Management Center (KMC) for the Illuminating the Druggable Genome (IDG) program...",
"last-curated": "2017-12-03",
"source": "Pharos",
"source-link": "https://pharos.nih.gov/",
"source-type": "integrator",
"status": "complete",
"data-field": "biology",
"data-type": "",
"data-categories": [
"disease",
"targets",
"ligands"
],
"data-access": [
{
"type": "api",
"location": "https://pharos.nih.gov/idg/api"
},
{
"type": "download",
"location": "http://juniper.health.unm.edu/tcrd/download/"
}
],
"license": "inconsistent",
"license-type": "unknown",
"license-link": "http://juniper.health.unm.edu/tcrd/download/README",
"license-hat-used": "false",
"license-issues": [
{
"criteria": "A.1.1",
"comment": "While any novel data is under a CC license (CC-BY-SA-4.0), the integrated resources are under whatever license the upstream is, with the user expected to sort it out."
}
],
"license-commentary": [
"Unfortunately, the API ToS link leads to a bad (404-type) Swagger page.",
"From the license page: \\\"Please note that TCRD incoporates many data sources with a variety of associated licenses...Users of the TCRD downloads are resposible for compliance with these licenses.\\\"",
"Given the variety and terms of the upstream resources, the inconsistency is not unexpected.",
"The license is also found here at https://pharos.nih.gov/idg/about, which has similar wording to the README on the downloads page, but makes no note of the user responsibility to adhere to licenses from original data sources."
],
"was-controversial": "false",
"contacts": [
"pharos@mail.nih.gov"
],
"grants": [
{
"label": "Pharos is the user interface to the Knowledge Management Center (KMC) for the Illuminating the Druggable Genome (IDG) program funded by the National Institutes of Health (NIH) Common Fund. (Grant No. 5U54CA189205-02).",
"url": "https://projectreporter.nih.gov/project_info_details.cfm?aid=8898033&icde=28628127&ddparam=&ddvalue=&ddsub=&cr=3&csb=default&cs=ASC"
}
],
"license-commentary-embeddable": "Unfortunately, the API ToS link leads to a bad (404-type) Swagger page.
From the license page: \\\"Please note that TCRD incoporates many data sources with a variety of associated licenses...Users of the TCRD downloads are resposible for compliance with these licenses.\\\"
Given the variety and terms of the upstream resources, the inconsistency is not unexpected.
The license is also found here at https://pharos.nih.gov/idg/about, which has similar wording to the README on the downloads page, but makes no note of the user responsibility to adhere to licenses from original data sources.",
"data-tags": "biology, disease, targets, ligands",
"grade-automatic": 1
},
{
"id": "pombase",
"source": "PomBase",
"source-link": "http://pombase.org",
"status": "complete",
"description": "PomBase is a comprehensive database for the fission yeast Schizosaccharomyces pombe, providing structural and functional annotation, literature curation and access to large-scale data sets.",
"data-field": "biology",
"data-type": "MOD",
"data-categories": [
"genotype-phenotype association",
"disease-model association",
"gene expression"
],
"data-access": [
{
"type": "download",
"location": "http://www.pombase.org/downloads"
}
],
"license": "CC-BY-4.0",
"license-type": "permissive",
"license-link": "https://www.pombase.org/about/terms-of-use",
"license-commentary": [],
"last-curated": "2019-03-01",
"provisional": "true",
"grants": [
{
"label": "PomBase is funded by the Wellcome Trust [104967/Z/14/Z]."
}
],
"contacts": [
"helpdesk@pombase.org"
],
"license-commentary-embeddable": "",
"data-tags": "biology, MOD, genotype-phenotype association, disease-model association, gene expression",
"grade-automatic": 5
},
{
"id": "reactome",
"source": "Reactome",
"source-link": "http://www.reactome.org",
"status": "complete",
"description": "Reactome is a free, open-source, curated and peer reviewed pathway database. Our goal is to provide intuitive bioinformatics tools for the visualization, interpretation and analysis of pathway knowledge to support basic research, genome analysis, modeling, systems biology and education.",
"data-field": "biology",
"data-type": "pathway",
"data-categories": [
"pathway data"
],
"data-access": [
{
"type": "download",
"location": "http://reactome.org/pages/download-data/"
},
{
"type": "api",
"location": "http://reactome.org/pages/documentation/developer-guide/content-service/"
}
],
"license": "CC-BY-4.0",
"license-type": "permissive",
"license-link": "http://www.reactome.org/pages/about/license-agreement/",
"license-issues": [
{
"criteria": "B.2.2",
"comment": "KEGG gene and pathway annotations used to construct Reactome Functional Interaction (FI) Network are not licenced CC-BY-4.0. There is a comment that \"the recipient may not distribute this data to other users without a license from Pathway Solutions, Inc.\""
}
],
"license-commentary": [
"The issue with criteria B.2.2 could be rectified if Reactome provided a clean copy of the data that can be redistributed without negotiation."
],
"contacts": [
"help@reactome.org"
],
"license-commentary-embeddable": "The issue with criteria B.2.2 could be rectified if Reactome provided a clean copy of the data that can be redistributed without negotiation.",
"data-tags": "biology, pathway, pathway data",
"grade-automatic": 4.5
},
{
"id": "rfam",
"description": "The Rfam database is a collection of RNA families, each represented by multiple sequence alignments, consensus secondary structures and covariance models (CMs).",
"last-curated": "2019-10-18",
"source": "Rfam",
"source-link": "http://rfam.org",
"source-type": "source",
"status": "complete",
"data-field": "biology",
"data-type": "RNA families",
"data-categories": [
"RNA family",
"multiple sequence alignments",
"msa"
],
"data-access": [
{
"type": "download",
"location": "ftp://ftp.ebi.ac.uk/pub/databases/Rfam/CURRENT"
}
],
"license": "CC0-1.0",
"license-type": "permissive",
"license-link": "ftp://ftp.ebi.ac.uk/pub/databases/Rfam/CURRENT/COPYING",
"license-hat-used": "false",
"license-issues": [],
"license-commentary": [
"While one would \"pass\" the license on the way to the data downloads, I could not find mention any other location except a pointer at https://rfam.readthedocs.io/en/latest/ftp-help.html.",
"License only found within COPYING in release FTP.",
"Did not evaluate API."
],
"was-controversial": "false",
"provisional": "true",
"contacts": [
"rfam-help@ebi.ac.uk"
],
"grants": [
{
"label": "\"Rfam is part of the ELIXER infrastructure\""
}
],
"license-commentary-embeddable": "While one would \"pass\" the license on the way to the data downloads, I could not find mention any other location except a pointer at https://rfam.readthedocs.io/en/latest/ftp-help.html.
License only found within COPYING in release FTP.
Did not evaluate API.",
"data-tags": "biology, RNA families, RNA family, multiple sequence alignments, msa",
"grade-automatic": 5
},
{
"id": "rgd",
"source": "Rat Genome Database (RGD)",
"source-link": "http://rgd.mcw.edu",
"status": "complete",
"description": "The Rat Genome Database (RGD) was established in 1999 and is the premier site for genetic, genomic, phenotype, and disease data generated from rat research. In addition, it provides easy access to corresponding human and mouse data for cross-species comparisons.",
"data-field": "biology",
"data-type": "MOD",
"data-categories": [
"genotype-phenotype association",
"disease-model association",
"gene expression"
],
"data-access": [
{
"type": "download",
"location": "ftp://ftp.rgd.mcw.edu/pub/"
},
{
"type": "api",
"location": "http://rest.rgd.mcw.edu/rgdws/swagger-ui.html"
}
],
"license": "CC-BY-4.0",
"license-type": "permissive",
"license-link": "http://rgd.mcw.edu/wg/home/disclaimer",
"license-issues": [],
"license-commentary": [
"Information found in the \"Legal Disclaimer\" footer on all pages, next to CC BY 4.0 link."
],
"last-curated": "2019-06-22",
"grants": [
{
"label": "RGD is funded by grant HL64541 from the National Heart, Lung, and Blood Institute on behalf of the NIH."
}
],
"contacts": [
"http://rgd.mcw.edu/contact/index.shtml"
],
"license-commentary-embeddable": "Information found in the \"Legal Disclaimer\" footer on all pages, next to CC BY 4.0 link.",
"data-tags": "biology, MOD, genotype-phenotype association, disease-model association, gene expression",
"grade-automatic": 5
},
{
"id": "rhea",
"description": "Rhea is an expert curated resource of biochemical reactions designed for the annotation of enzymes and genome-scale metabolic networks and models. Rhea uses the ChEBI (Chemical Entities of Biological Interest) ontology of small molecules to precisely describe reactions participants and their chemical structures. All reactions are balanced for mass and charge and are linked to source literature, metabolic resources and other functional vocabularies such as the enzyme classification of the NC-IUBMB.",
"last-curated": "2017-12-03",
"source": "Rhea",
"source-link": "http://www.rhea-db.org",
"source-type": "source",
"status": "complete",
"data-field": "biology",
"data-type": "biochemical",
"data-categories": [
"enzymes",
"metabolic networks",
"reactions"
],
"data-access": [
{
"type": "download",
"location": "http://www.rhea-db.org/download"
},
{
"type": "api",
"location": "http://www.rhea-db.org/webservice"
}
],
"license": "CC-BY-4.0",
"license-type": "permissive",
"license-link": "http://www.rhea-db.org/licensedisclaimer",
"license-hat-used": "false",
"license-issues": [],
"license-commentary": [],
"was-controversial": "false",
"contacts": [
"http://www.rhea-db.org/feedback"
],
"grants": [
{
"label": "Rhea development and curation activities at the SIB are supported by the Swiss Federal Government through the State Secretariat for Education, Research and Innovation (SERI), and by the SystemsX.ch, The Swiss Initiative in Systems Biology."
},
{
"label": "Rhea curation was partially supported by MICROME (an EU Framework Programme 7 Collaborative Project. Grant Agreement Number 222886-2)."
}
],
"license-commentary-embeddable": "",
"data-tags": "biology, biochemical, enzymes, metabolic networks, reactions",
"grade-automatic": 5
},
{
"id": "sgd",
"source": "Saccharomyces Genome Database (SGD)",
"source-link": "https://yeastgenome.org/",
"status": "complete",
"description": "The Saccharomyces Genome Database (SGD) provides comprehensive integrated biological information for the budding yeast Saccharomyces cerevisiae along with search and analysis tools to explore these data, enabling the discovery of functional relationships between sequence and gene products in fungi and higher organisms.",
"data-field": "biology",
"data-type": "MOD",
"data-categories": [
"genotype-phenotype association",
"disease-model association",
"gene expression"
],
"data-access": [
{
"type": "download",
"location": "https://www.yeastgenome.org/search?category=download"
},
{
"type": "api",
"location": "https://yeastmine.yeastgenome.org/yeastmine/api.do"
}
],
"license": "CC-BY-4.0",
"license-type": "permissive",
"license-link": "https://sites.google.com/view/yeastgenome-help/about",
"license-issues": [
{
"criteria": "B.2.1",
"comment": "While the downloadable data seems quite clearly CC-BY-4.0, the API footer has terms that indicate that all data may not be covered under the same license (see comments)."
},
{
"criteria": "B.2.2",
"comment": "The API does not seem to be any easy way to differentiate the \\\"clean\\\" CC-BY-4.0 data from other licenses."
}
],
"license-commentary": [
"The license information found in the \"About SGD\" paragraph on the SGD Help page at https://sites.google.com/view/yeastgenome-help/about",
"SGD operates under the Creative Commons Attribution 4.0 International license (CC BY 4.0).",
"However, the license information for the API is much less clear, reading: \"Permission to use the information contained in this database was given by the researchers/institutes who contributed or published the information. Users of the database are solely responsible for compliance with any copyright restrictions, including those applying to the author abstracts.\"",
"The API did not seem to offer any way of filter out things with other licenses.",
"Without ascending, noting that various upstream for the SGD API could have other terms: https://yeastmine.yeastgenome.org/yeastmine/dataCategories.do"
],
"was-controversial": "false",
"provisional": "true",
"last-curated": "2019-03-01",
"grants": [
{
"label": "The SGD is funded by the US National Institutes of Health, National Human Genome Research Institute (NHGRI), [U41HG001315]. Our efforts are also supported via the Gene Ontology Consortium (GOC) funded by the NHGRI [U41HG002273] and the Alliance of Genome Resources supplement via WormBase [U41HG02223-17S1]."
}
],
"contacts": [
"https://www.yeastgenome.org/suggestion",
"sgd-helpdesk@lists.stanford.edu"
],
"license-commentary-embeddable": "The license information found in the \"About SGD\" paragraph on the SGD Help page at https://sites.google.com/view/yeastgenome-help/about
SGD operates under the Creative Commons Attribution 4.0 International license (CC BY 4.0).
However, the license information for the API is much less clear, reading: \"Permission to use the information contained in this database was given by the researchers/institutes who contributed or published the information. Users of the database are solely responsible for compliance with any copyright restrictions, including those applying to the author abstracts.\"
The API did not seem to offer any way of filter out things with other licenses.
Without ascending, noting that various upstream for the SGD API could have other terms: https://yeastmine.yeastgenome.org/yeastmine/dataCategories.do",
"data-tags": "biology, MOD, genotype-phenotype association, disease-model association, gene expression",
"grade-automatic": 4.5
},
{
"id": "smart",
"description": "Identification and annotation of genetically mobile domains and the analysis of domain architectures.",
"last-curated": "2019-10-19",
"source": "Simple Modular Architecture Research Tool (SMART)",
"source-link": "http://smart.embl-heidelberg.de",
"source-type": "source",
"status": "complete",
"data-field": "biology",
"data-type": "protein domains",
"data-categories": [
"protein domain identification",
"protein domain annotation"
],
"data-access": [],
"license": "custom",
"license-type": "restrictive",
"license-link": "https://software.embl-em.de/stream/license_pdf/24/56fb8ca3363b8_License_Academic_SMART.pdf",
"license-hat-used": "true",
"license-issues": [
{
"criteria": "A.2.2",
"comment": "custom license used"
},
{
"criteria": "C.1",
"comment": "The main site seems to be a web application, with no bulk access possible."
},
{
"criteria": "C.2",
"comment": "While there is a software download where one may be able to recreate the data and/or website, the evaluator believes that the process and package around it violates access criteria."
},
{
"criteria": "D.1.2",
"comment": "The restrictive licensing terms prevent further reuse."
},
{
"criteria": "E.1.2",
"comment": "The restrictive licensing terms prevent further reuse."
}
],
"license-commentary": [
"From FAQ: \"...[I]f you just want the basic searching functionality...you can sign a license agreement, and get our set of Hidden Markov Models, alignments and thresholds. The license is free to academics, but not commercial users. For further details on the academic license, visit SMART page at EMBLEM.\"",
"\"From \"You need te [sic: read to] be a registered User to download EMBLEM Software.\"",
"From EMBLEM page: \"License...Academic SMART...(none defined)\"",
"On registrations and click-through, found license at: https://software.embl-em.de/license/24",
"From license: non-commercial license only covers \"public funded academic and/or education and/or research institution or an individual working for such institution\"",
"From license: \"non-exclusive, non-transferable\"",
"From license: \"shall not have the right to download...and/or to make copies...for either internal use or for back-up purposes\"",
"From license: \"software code of the Licensed Software shall be treated as trade secrets and confidential information\"",
"From license: \"Except as otherwise expressly permitted in this Agreement, LICENSEE may not (i) modify or create any derivative works of the Licensed Software or documentation to the Licensed Software, including customization, translation or localization...(iii) redistribute, encumber, sell, rent, lease, sublicense, or otherwise transfer rights to the Licensed Software\"",
"From license: \"...agrees to cite the use of the Licensed Software on all related scientific publications, posters, grant applications, institutional reports or brochures\"",
"From FAQ: \"If you are a commerical user, please contact biobyte solutions GmbH. They provide the commercial version of SMART...\""
],
"was-controversial": "false",
"provisional": "true",
"contacts": [
"smart@embl.de"
],
"grants": [
{
"label": "From latest paper: \"German Network for Bioinformatics Infrastructure (de.NBI); EMBL. Funding for open access charge: European Molecular Biology Laboratory.\""
}
],
"license-commentary-embeddable": "From FAQ: \"...[I]f you just want the basic searching functionality...you can sign a license agreement, and get our set of Hidden Markov Models, alignments and thresholds. The license is free to academics, but not commercial users. For further details on the academic license, visit SMART page at EMBLEM.\"
\"From \"You need te [sic: read to] be a registered User to download EMBLEM Software.\"
From EMBLEM page: \"License...Academic SMART...(none defined)\"
On registrations and click-through, found license at: https://software.embl-em.de/license/24
From license: non-commercial license only covers \"public funded academic and/or education and/or research institution or an individual working for such institution\"
From license: \"non-exclusive, non-transferable\"
From license: \"shall not have the right to download...and/or to make copies...for either internal use or for back-up purposes\"
From license: \"software code of the Licensed Software shall be treated as trade secrets and confidential information\"
From license: \"Except as otherwise expressly permitted in this Agreement, LICENSEE may not (i) modify or create any derivative works of the Licensed Software or documentation to the Licensed Software, including customization, translation or localization...(iii) redistribute, encumber, sell, rent, lease, sublicense, or otherwise transfer rights to the Licensed Software\"
From license: \"...agrees to cite the use of the Licensed Software on all related scientific publications, posters, grant applications, institutional reports or brochures\"
From FAQ: \"If you are a commerical user, please contact biobyte solutions GmbH. They provide the commercial version of SMART...\"",
"data-tags": "biology, protein domains, protein domain identification, protein domain annotation",
"grade-automatic": 1.5
},
{
"id": "string",
"source": "STRING",
"source-link": "https://string-db.org",
"status": "complete",
"description": "STRING is a database of known and predicted protein-protein interactions. The interactions include direct (physical) and indirect (functional) associations; they stem from computational prediction, from knowledge transfer between organisms, and from interactions aggregated from other (primary) databases.",
"data-field": "biology",
"data-type": "cross-species",
"data-categories": [
"protein-protein interaction",
"protein families"
],
"data-access": [
{
"type": "download",
"location": "https://string-db.org/cgi/download.pl"
}
],
"license": "CC-BY-4.0",
"license-type": "permissive",
"license-link": "https://string-db.org/cgi/access.pl",
"license-commentary": [
"While there are APIs available, we skipped evaluation as they explicitly state they are now meant for bulk use and downloads are available anyways."
],
"last-curated": "2017-12-03",
"contacts": [
"https://string-db.org/cgi/support.pl"
],
"license-commentary-embeddable": "While there are APIs available, we skipped evaluation as they explicitly state they are now meant for bulk use and downloads are available anyways.",
"data-tags": "biology, cross-species, protein-protein interaction, protein families",
"grade-automatic": 5
},
{
"id": "supfam",
"description": "SUPERFAMILY is a database of structural and functional annotation for all proteins and genomes.",
"last-curated": "2019-10-18",
"source": "SUPERFAMILY",
"source-link": "http://www.supfam.org",
"source-type": "source",
"status": "complete",
"data-field": "biology",
"data-type": "annotation",
"data-categories": [
"structural annotation",
"functional annotation",
"HMM",
"protein superfamily"
],
"data-access": [
{
"label": "SUPERFAMILY Genomes",
"type": "download",
"location": "http://supfam.org/genome/hierarchy"
},
{
"label": "SCOP Hierarchy",
"type": "download",
"location": "http://supfam.org/scop"
}
],
"license": "custom",
"license-type": "permissive",
"license-link": "http://www.supfam.org/about",
"license-hat-used": "false",
"license-issues": [
{
"criteria": "A.2.2",
"comment": "No formal license used, just a declaration that: \"All annotation, models and the database dump are freely available for download to everyone.\""
},
{
"criteria": "C.1",
"comment": "There seems to be no central clearing location of the data, but rather a hierarchy view, navigate, click on individual set, then download. Scriptable."
}
],
"license-commentary": [
"The relatively high score hinges on the positive or negative evaluation of whether the declaration of \"freely available...to everyone\" constitutes a wnough of license; I have decided that it does, but it is a close call.",
"Only other notice was in footer: \"© The SUPERFAMILY authors and Julian Gough 2001-2019.\"; taking this a an elaboration on above.",
"Very minimal website."
],
"was-controversial": "false",
"provisional": "true",
"contacts": [
"http://www.supfam.org/contact"
],
"grants": [],
"license-commentary-embeddable": "The relatively high score hinges on the positive or negative evaluation of whether the declaration of \"freely available...to everyone\" constitutes a wnough of license; I have decided that it does, but it is a close call.
Only other notice was in footer: \"© The SUPERFAMILY authors and Julian Gough 2001-2019.\"; taking this a an elaboration on above.
Very minimal website.",
"data-tags": "biology, annotation, structural annotation, functional annotation, HMM, protein superfamily",
"grade-automatic": 4
},
{
"id": "tair-open",
"description": "The Arabidopsis Information Resource (TAIR) maintains a database of genetic and molecular biology data for the model higher plant Arabidopsis thaliana.",
"last-curated": "2017-12-03",
"source": "The Arabidopsis Information Resource (TAIR, public)",
"source-link": "http://www.arabidopsis.org/",
"source-type": "source",
"status": "complete",
"data-field": "biology",
"data-type": "MOD",
"data-categories": [
"sequence",
"gene structure",
"gene expression",
"functional annotation"
],
"data-access": [
{
"type": "download",
"location": "http://www.arabidopsis.org/download/index.jsp"
}
],
"license": "CC-BY-4.0",
"license-type": "permissive",
"license-link": "http://www.arabidopsis.org/download_files/Public_Data_Releases/README.txt",
"license-hat-used": "false",
"license-issues": [],
"license-commentary": [
"This curation is for the post one-year embargo window data; data within that window is available for a subscription. The data sets are clearly separately available."
],
"was-controversial": "false",
"contacts": [
"curator@arabidopsis.org"
],
"license-commentary-embeddable": "This curation is for the post one-year embargo window data; data within that window is available for a subscription. The data sets are clearly separately available.",
"data-tags": "biology, MOD, sequence, gene structure, gene expression, functional annotation",
"grade-automatic": 5
},
{
"id": "tigrfams",
"description": "TIGRFAMs is a resource consisting of curated multiple sequence alignments, Hidden Markov Models (HMMs) for protein sequence classification, and associated information designed to support automated annotation of (mostly prokaryotic) proteins.\n",
"last-curated": "2022-05-19",
"source": "TIGRFAMs",
"source-link": "https://www.ncbi.nlm.nih.gov/genome/annotation_prok/tigrfams/",
"source-type": "source",
"status": "complete",
"data-field": "biology",
"data-type": "protein",
"data-categories": [
"MSA",
"HMM",
"protein sequence classification"
],
"data-access": [
{
"type": "download",
"location": "https://ftp.ncbi.nlm.nih.gov/hmm/current/"
}
],
"license": "CC-BY-SA-4.0",
"license-type": "copyleft",
"license-link": "ftp://ftp.jcvi.org/pub/data/TIGRFAMs/COPYRIGHT",
"license-hat-used": "false",
"license-issues": [
{
"criteria": "D.1.2",
"comment": "By using a copyleft-style license, there may be issues in mixing and redistributing this data with licenses that have incompatible terms."
},
{
"criteria": "E.1.2",
"comment": "By using a copyleft-style license, there may be some parties with issues in mixing and redistributing this data with licenses that have incompatible terms."
}
],
"license-commentary": [
"\"TIGRFAMs data are made available under a Creative Commons Attribution-ShareAlike 4.0 license.\"\n",
"TIGRFAMs used to be at a different location; ownership was apparently formally transferred to NCBI in April 2018: https://ftp.ncbi.nlm.nih.gov/hmm/TIGRFAMs/license_and_availability.txt\n"
],
"was-controversial": "false",
"provisional": "true",
"contacts": [
"https://support.nlm.nih.gov/"
],
"grants": [],
"license-commentary-embeddable": "\"TIGRFAMs data are made available under a Creative Commons Attribution-ShareAlike 4.0 license.\"\n
TIGRFAMs used to be at a different location; ownership was apparently formally transferred to NCBI in April 2018: https://ftp.ncbi.nlm.nih.gov/hmm/TIGRFAMs/license_and_availability.txt\n",
"data-tags": "biology, protein, MSA, HMM, protein sequence classification",
"grade-automatic": 3
},
{
"id": "umls",
"description": "The UMLS integrates and distributes key terminology, classification and coding standards, and associated resources to promote creation of more effective and interoperable biomedical information systems and services, including electronic health records.",
"last-curated": "2023-08-11",
"source": "Unified Medical Language System (UMLS)",
"source-link": "https://www.nlm.nih.gov/research/umls/",
"source-type": "integrator",
"status": "complete",
"data-field": "biomedial",
"data-type": "terminology",
"data-categories": [
"standards",
"concept",
"ontology"
],
"data-access": [],
"license": "custom",
"license-type": "restrictive",
"license-link": "https://uts.nlm.nih.gov/uts/assets/LicenseAgreement.pdf",
"license-hat-used": "true",
"license-issues": [
{
"criteria": "A.2.2",
"comment": "Non-standard/custom license."
},
{
"criteria": "B.1",
"comment": "One term of the license is that you must \"[...]provide NLM with a brief report on the usefulness of the UMLS Metathesaurus in general[...]\" (term 5); this rises to a barrier to reuse as a manual step invloving people has been added to use."
},
{
"criteria": "B.2.1",
"comment": "Violation occurs in section 11 \"Some of the Material in the UMLS Metathesaurus is from copyrighted sources\"."
},
{
"criteria": "C.1",
"comment": "Was unable to be exavluated due to the terms of the license requiring agreeing to reporting before proceeding, producing a barrier to access."
},
{
"criteria": "C.2",
"comment": "Was unable to be exavluated due to the terms of the license requiring agreeing to reporting before proceeding, producing a barrier to access."
},
{
"criteria": "D.1.2",
"comment": "Various types of restrictions are given for various subsets/sources; for example, section 12.1 forbidding translation and derivative works."
},
{
"criteria": "E.1.1",
"comment": "\"UMLS licenses are issued only to individuals and not to groups or organizations\"; while an individual research may be able to get access and use, companies (for example) would not."
}
],
"license-commentary": [
"Could not access C categories as proceeding to access demanded signing up for giving reports: \"[...]I will provide an annual report[...]\", https://uts.nlm.nih.gov/uts/signUp",
"\"License hat\" was required to be used as \"UMLS licenses are issued only to individuals and not to groups or organizations[...]\", https://www.nlm.nih.gov/databases/umls.html"
],
"was-controversial": "false",
"provisional": "true",
"contacts": [
"https://www.nlm.nih.gov/research/umls/support.html"
],
"grants": [],
"license-commentary-embeddable": "Could not access C categories as proceeding to access demanded signing up for giving reports: \"[...]I will provide an annual report[...]\", https://uts.nlm.nih.gov/uts/signUp
\"License hat\" was required to be used as \"UMLS licenses are issued only to individuals and not to groups or organizations[...]\", https://www.nlm.nih.gov/databases/umls.html",
"data-tags": "biomedial, terminology, standards, concept, ontology",
"grade-automatic": 1
},
{
"id": "uniprotkb",
"description": "The mission of UniProt is to provide the scientific community with a comprehensive, high-quality and freely accessible resource of protein sequence and functional information. Includes: UniProtKB, UniRef, UniParc, and Proteomes.",
"last-curated": "2019-03-01",
"source": "UniProt",
"source-link": "http://www.uniprot.org",
"source-type": "source",
"status": "complete",
"data-field": "biology",
"data-type": "sequence",
"data-categories": [
"protein sequence",
"protein function"
],
"data-access": [
{
"type": "download",
"location": "http://www.uniprot.org/downloads"
}
],
"license": "CC-BY-4.0",
"license-type": "permissive",
"license-link": "https://www.uniprot.org/help/license",
"license-hat-used": "false",
"license-commentary": [
"We have chosen to apply the Creative Commons Attribution (CC BY 4.0) License to all copyrightable parts of our databases."
],
"was-controversial": "false",
"provisional": "true",
"contacts": [
"help@uniprot.org"
],
"grants": [
{
"label": "UniProt is supported by the National Institutes of Health (NIH), National Human Genome Research Institute (NHGRI) and National Institute of General Medical Sciences (NIGMS) grant U41HG007822. Additional support for the EMBL-EBI's involvement in UniProt comes from European Molecular Biology Laboratory (EMBL), the British Heart Foundation (BHF) (RG/13/5/30112), the Parkinson's Disease United Kingdom (PDUK) GO grant G-1307, and the NIH GO grant U41HG02273. UniProt activities at the SIB are additionally supported by the Swiss Federal Government through the State Secretariat for Education, Research and Innovation SERI. PIR's UniProt activities are also supported by the NIH grants R01GM080646, G08LM010720, and P20GM103446, and the National Science Foundation (NSF) grant DBI-1062520."
}
],
"license-commentary-embeddable": "We have chosen to apply the Creative Commons Attribution (CC BY 4.0) License to all copyrightable parts of our databases.",
"data-tags": "biology, sequence, protein sequence, protein function",
"grade-automatic": 5
},
{
"id": "wikipathways",
"description": " WikiPathways is a database of biological pathways maintained by and for the scientific community.",
"last-curated": "2019-05-10",
"source": "WikiPathways",
"source-link": "https://www.wikipathways.org",
"source-type": "source",
"status": "complete",
"data-field": "biology",
"data-type": "pathway",
"data-categories": [
"disease",
"micronutrient",
"nanomaterial",
"ExDNA",
"renal genomics",
"adverse outcomes",
"regenerative medicine",
"clinical proteomic tumor analysis"
],
"data-access": [
{
"type": "download",
"location": "http://data.wikipathways.org/current/"
},
{
"type": "api",
"location": "https://www.wikipathways.org/index.php/Help:WikiPathways_Webservice/API"
}
],
"license": "CC0-1.0",
"license-type": "permissive",
"license-link": "https://www.wikipathways.org/index.php/WikiPathways:License_Terms",
"license-hat-used": "false",
"license-issues": [],
"license-commentary": [
"I would note that the terms page makes an interesting and clear distinction between legal code and social norms, with an interesting list of social expectation that they would like users to adhere to.",
"Not explicitly referenced except by external link, but using CC0 1.0."
],
"was-controversial": "false",
"contacts": [
"https://www.wikipathways.org/index.php/Contact_Us"
],
"grants": [
{
"label": "The BioRange program of the Netherlands Bioinformatics Centre (NBIC) (Netherland Genomics Initiative grant)"
},
{
"label": "The WikiPathways project is funded by the National Institute for General Medical Sciences (NIH grant R01-GM100039)"
},
{
"label": "The WikiPathways project is also funded by the National Resource for Network Biology (National Institute of General Medical Sciences grant P41 GM103504)."
},
{
"label": "Google Summer of Code has supported a number of students working on WikiPathways"
},
{
"label": "Maastricht University: Broad Research Strategy Program Part 2 (BOS2)"
},
{
"label": "Transnational University Limburg (tUL)"
},
{
"label": "IOP Gut Health"
},
{
"label": "EU network of Excellence NuGO (EC FP6 grant 506360)"
},
{
"label": "MicroGennet (EU Marie Curie action program IRSES grant 269210)"
},
{
"label": "Open PHACTS (IMI grant)"
},
{
"label": "eNanoMapper (EC FP7 grant 604134)"
}
],
"license-commentary-embeddable": "I would note that the terms page makes an interesting and clear distinction between legal code and social norms, with an interesting list of social expectation that they would like users to adhere to.
Not explicitly referenced except by external link, but using CC0 1.0.",
"data-tags": "biology, pathway, disease, micronutrient, nanomaterial, ExDNA, renal genomics, adverse outcomes, regenerative medicine, clinical proteomic tumor analysis",
"grade-automatic": 5
},
{
"id": "wormbase",
"source": "WormBase",
"source-link": "http://www.wormbase.org",
"status": "complete",
"description": "WormBase is an international consortium dedicated to providing the research community with accurate, current, accessible information concerning the genetics, genomics and biology of C. elegans and related nematodes.",
"data-field": "biology",
"data-type": "model organism genome sequences",
"data-access": [
{
"type": "download",
"location": "http://www.wormbase.org/about/userguide#3--10"
},
{
"type": "api",
"location": "http://www.wormbase.org/about/userguide/for_developers/api-rest#01--10"
}
],
"license": "inconsistent",
"license-type": "unknown",
"license-link": "http://www.wormbase.org/about/policies#2--10",
"license-issues": [
{
"criteria": "A.1.1",
"comment": "A single license is not provided, rather data users are intructed that they are responsible for identifying and complying with licensing and copyright restrictions for each piece of information in the database."
}
],
"license-commentary": [
"Because this no single license is provided, this source can only be awarded a total of 1 stars. As both components of criteria C were met, 1 star total was awarded."
],
"contacts": [
"help@wormbase.org"
],
"license-commentary-embeddable": "Because this no single license is provided, this source can only be awarded a total of 1 stars. As both components of criteria C were met, 1 star total was awarded.",
"data-tags": "biology, model organism genome sequences",
"grade-automatic": 1
},
{
"id": "zfin",
"source": "Zebrafish Information Network (ZFIN)",
"source-link": "http://zfin.org",
"status": "complete",
"description": "The Zebrafish Information Resource is the community database resource for the laboratory use of zebrafish which develops and supports integrated zebrafish genetic, genomic and developmental information, maintains the definitive reference data sets of zebrafish research information toward facilitation of the use of zebrafish as a model for human biology.",
"data-field": "biology",
"data-type": "model organism database",
"data-access": [
{
"type": "download",
"location": "http://zfin.org/downloads"
}
],
"license": "custom",
"license-type": "restrictive",
"license-link": "http://zfin.org/warranty.html",
"license-issues": [
{
"criteria": "A.2.2",
"comment": "Custom license with non-academic and non-research use restrictions."
},
{
"criteria": "B.1",
"comment": "The license explicity requires intervention for downstream reuse and redistribution."
},
{
"criteria": "D.1.2",
"comment": "The license requires written permission for redistribution."
},
{
"criteria": "E.1.2",
"comment": "The license requires written premission for redistribution even for academic and non commerical parties."
}
],
"license-commentary": [
"-ZFIN Software and Data are provided to enhance knowledge and encourage progress in the scientific community, and are to be used only for research and educational purposes. ZFIN reserves all rights not expressly granted. Further, ZFIN retains all rights, title, and interest in and to the Software and Data. Any reproduction or use for a commercial purpose is prohibited without the prior express written permission of ZFIN. Distribution of the Software or Data to any third party, without a separate written agreement with ZFIN, is prohibited."
],
"contacts": [
"jknight@zfin.org"
],
"license-commentary-embeddable": "-ZFIN Software and Data are provided to enhance knowledge and encourage progress in the scientific community, and are to be used only for research and educational purposes. ZFIN reserves all rights not expressly granted. Further, ZFIN retains all rights, title, and interest in and to the Software and Data. Any reproduction or use for a commercial purpose is prohibited without the prior express written permission of ZFIN. Distribution of the Software or Data to any third party, without a separate written agreement with ZFIN, is prohibited.",
"data-tags": "biology, model organism database",
"grade-automatic": 2
}
]