{ "access": { "embargo": { "active": false, "reason": null }, "files": "public", "record": "public", "status": "open" }, "created": "2017-06-29T10:23:44.346770+00:00", "custom_fields": { "imprint:imprint": { "isbn": "978-1-4673-9005-7", "pages": "319-328", "title": "2016 IEEE International Conference on Big Data (Big Data)" }, "meeting:meeting": { "acronym": "Big Data", "dates": "2016-12-05 / 2016-12-08", "place": "Washington, DC, USA", "session": "8", "session_part": "BigD491", "title": "2016 IEEE International Conference on Big Data", "url": "http://cci.drexel.edu/bigdata/bigdata2016/" } }, "deletion_status": { "is_deleted": false, "status": "P" }, "files": { "count": 1, "enabled": true, "entries": { "bagminid.pdf": { "checksum": "md5:91195ab648922564b86d629e83ea88d8", "ext": "pdf", "id": "40d423d3-3375-400e-b524-bb43e28a6bba", "key": "bagminid.pdf", "metadata": null, "mimetype": "application/pdf", "size": 713184 } }, "order": [], "total_bytes": 713184 }, "id": "820878", "is_draft": false, "is_published": true, "links": { "access": "https://zenodo.org/api/records/820878/access", "access_links": "https://zenodo.org/api/records/820878/access/links", "access_request": "https://zenodo.org/api/records/820878/access/request", "access_users": "https://zenodo.org/api/records/820878/access/users", "archive": "https://zenodo.org/api/records/820878/files-archive", "archive_media": "https://zenodo.org/api/records/820878/media-files-archive", "communities": "https://zenodo.org/api/records/820878/communities", "communities-suggestions": "https://zenodo.org/api/records/820878/communities-suggestions", "doi": "https://doi.org/10.1109/BigData.2016.7840618", "draft": "https://zenodo.org/api/records/820878/draft", "files": "https://zenodo.org/api/records/820878/files", "latest": "https://zenodo.org/api/records/820878/versions/latest", "latest_html": "https://zenodo.org/records/820878/latest", "media_files": "https://zenodo.org/api/records/820878/media-files", "parent": "https://zenodo.org/api/records/820877", "parent_doi": "https://zenodo.org/doi/", "parent_html": "https://zenodo.org/records/820877", "requests": "https://zenodo.org/api/records/820878/requests", "reserve_doi": "https://zenodo.org/api/records/820878/draft/pids/doi", "self": "https://zenodo.org/api/records/820878", "self_doi": "https://zenodo.org/doi/10.1109/BigData.2016.7840618", "self_html": "https://zenodo.org/records/820878", "self_iiif_manifest": "https://zenodo.org/api/iiif/record:820878/manifest", "self_iiif_sequence": "https://zenodo.org/api/iiif/record:820878/sequence/default", "versions": "https://zenodo.org/api/records/820878/versions" }, "media_files": { "count": 0, "enabled": false, "entries": {}, "order": [], "total_bytes": 0 }, "metadata": { "contributors": [ { "affiliations": [ { "name": "The University of Chicago" } ], "person_or_org": { "family_name": "Jung", "given_name": "Segun", "name": "Jung, Segun", "type": "personal" }, "role": { "id": "other", "title": { "de": "Andere", "en": "Other" } } } ], "creators": [ { "affiliations": [ { "name": "The University of Chicago and Argonne National Laboratory, Chicago IL, USA" } ], "person_or_org": { "family_name": "Chard", "given_name": "Kyle", "name": "Chard, Kyle", "type": "personal" } }, { "affiliations": [ { "name": "University of Southern California, Los Angeles, CA, USA" } ], "person_or_org": { "family_name": "D'Arcy", "given_name": "Mike", "name": "D'Arcy, Mike", "type": "personal" } }, { "affiliations": [ { "name": "Institute for Systems Biology, Seattle, WA, USA" } ], "person_or_org": { "family_name": "Heavner", "given_name": "Ben", "name": "Heavner, Ben", "type": "personal" } }, { "affiliations": [ { "name": "The University of Chicago and Argonne National Laboratory, Chicago IL, USA" } ], "person_or_org": { "family_name": "Foster", "given_name": "Ian", "name": "Foster, Ian", "type": "personal" } }, { "affiliations": [ { "name": "University of Southern California, Los Angeles, CA, USA" } ], "person_or_org": { "family_name": "Kesselman", "given_name": "Carl", "name": "Kesselman, Carl", "type": "personal" } }, { "affiliations": [ { "name": "The University of Chicago and Argonne National Laboratory, Chicago IL, USA" } ], "person_or_org": { "family_name": "Madduri", "given_name": "Ravi", "name": "Madduri, Ravi", "type": "personal" } }, { "affiliations": [ { "name": "The University of Chicago and Argonne National Laboratory, Chicago IL, USA" } ], "person_or_org": { "family_name": "Rodriguez", "given_name": "Alexis", "name": "Rodriguez, Alexis", "type": "personal" } }, { "affiliations": [ { "name": "The University of Manchester, Manchester, UK" } ], "person_or_org": { "family_name": "Soiland-Reyes", "given_name": "Stian", "name": "Soiland-Reyes, Stian", "type": "personal" } }, { "affiliations": [ { "name": "The University of Manchester, Manchester, UK" } ], "person_or_org": { "family_name": "Goble", "given_name": "Carole", "name": "Goble, Carole", "type": "personal" } }, { "affiliations": [ { "name": "University of Southern California, Los Angeles, CA, USA" } ], "person_or_org": { "family_name": "Clark", "given_name": "Kristi", "name": "Clark, Kristi", "type": "personal" } }, { "affiliations": [ { "name": "Institute for Systems Biology, Seattle, WA, USA" } ], "person_or_org": { "family_name": "Deutsch", "given_name": "Eric W.", "name": "Deutsch, Eric W.", "type": "personal" } }, { "affiliations": [ { "name": "The University of Michigan, Ann Arbor, MI, USA" } ], "person_or_org": { "family_name": "Dinov", "given_name": "Ivo", "name": "Dinov, Ivo", "type": "personal" } }, { "affiliations": [ { "name": "Institute for Systems Biology, Seattle, WA, USA" } ], "person_or_org": { "family_name": "Price", "given_name": "Nathan", "name": "Price, Nathan", "type": "personal" } }, { "affiliations": [ { "name": "University of Southern California, Los Angeles, CA, USA" } ], "person_or_org": { "family_name": "Toga", "given_name": "Arthur", "name": "Toga, Arthur", "type": "personal" } } ], "description": "
Big data workflows often require the assembly and exchange of complex, multi-element datasets. For example, in biomedical applications, the input to an analytic pipeline can be a dataset consisting thousands of images and genome sequences assembled from diverse repositories, requiring a description of the contents of the dataset in a concise and unambiguous form. Typical approaches to creating datasets for big data workflows assume that all data reside in a single location, requiring costly data marshaling and permitting errors of omission and commission because dataset members are not explicitly specified.
\n\nWe address these issues by proposing simple methods and tools for assembling, sharing, and analyzing large and complex datasets that scientists can easily integrate into their daily workflows. These tools combine a simple and robust method for describing data collections (BDBags), data descriptions (Research Objects), and simple persistent identifiers (Minids) to create a powerful ecosystem of tools and services for big data analysis and sharing.
\n\nWe present these tools and use biomedical case studies to illustrate their use for the rapid assembly, sharing, and analysis of large datasets.
", "funding": [ { "award": { "acronym": "BioExcel", "id": "00k4n6c32::675728", "identifiers": [ { "identifier": "https://cordis.europa.eu/projects/675728", "scheme": "url" } ], "number": "675728", "program": "H2020", "title": { "en": "Centre of Excellence for Biomolecular Research" } }, "funder": { "id": "00k4n6c32", "name": "European Commission" } } ], "publication_date": "2016-12-05", "publisher": "IEEE", "related_identifiers": [ { "identifier": "https://static.aminer.org/pdf/fa/bigdata2016/BigD418.pdf", "relation_type": { "id": "isidenticalto", "title": { "de": "Ist identisch mit", "en": "Is identical to" } }, "scheme": "url" }, { "identifier": "https://www.research.manchester.ac.uk/portal/files/45989205/bagminid.pdf", "relation_type": { "id": "isidenticalto", "title": { "de": "Ist identisch mit", "en": "Is identical to" } }, "scheme": "url" }, { "identifier": "http://bd2k.ini.usc.edu/tools/", "relation_type": { "id": "issupplementedby", "title": { "de": "Wird erg\u00e4nzt durch", "en": "Is supplemented by" } }, "scheme": "url" }, { "identifier": "https://github.com/ini-bdds/bdbag", "relation_type": { "id": "issupplementedby", "title": { "de": "Wird erg\u00e4nzt durch", "en": "Is supplemented by" } }, "scheme": "url" }, { "identifier": "https://www.research.manchester.ac.uk/portal/en/publications/ill-take-that-to-go(8335e672-1d85-4649-a245-56fbdb1bd423).html", "relation_type": { "id": "ispartof", "title": { "de": "Ist Teil von", "en": "Is part of" } }, "scheme": "url" }, { "identifier": "https://w3id.org/ro/bagit", "relation_type": { "id": "cites", "title": { "de": "Zitiert", "en": "Cites" } }, "scheme": "url" } ], "resource_type": { "id": "publication-conferencepaper", "title": { "de": "Konferenzbeitrag", "en": "Conference paper" } }, "rights": [ { "description": { "en": "The Creative Commons Attribution license allows re-distribution and re-use of a licensed work on the condition that the creator is appropriately credited." }, "icon": "cc-by-icon", "id": "cc-by-4.0", "props": { "scheme": "spdx", "url": "https://creativecommons.org/licenses/by/4.0/legalcode" }, "title": { "en": "Creative Commons Attribution 4.0 International" } } ], "subjects": [ { "subject": "Big Data" }, { "subject": "data analysis" }, { "subject": "BDBags" }, { "subject": "Big Data analysis" }, { "subject": "Big Data bags" }, { "subject": "Big Data sharing" }, { "subject": "Minid" }, { "subject": "data assembling" }, { "subject": "data collections" }, { "subject": "data descriptions" }, { "subject": "datasets" }, { "subject": "identifiers" }, { "subject": "research objects" }, { "subject": "Encoding" }, { "subject": "Metadata" }, { "subject": "Payloads" }, { "subject": "Robustness" }, { "subject": "Software" }, { "subject": "Uniform resource locators" }, { "subject": "bdbag" } ], "title": "I'll take that to go: Big data bags and minimal identifiers for exchange of large, complex datasets" }, "parent": { "access": { "owned_by": { "user": 4363 } }, "communities": { "entries": [ { "access": { "member_policy": "open", "record_policy": "open", "review_policy": "open", "visibility": "public" }, "children": { "allow": false }, "created": "2014-06-06T03:54:06+00:00", "custom_fields": {}, "deletion_status": { "is_deleted": false, "status": "P" }, "id": "b638e3e5-64a3-451b-a2cd-1e27ffa319a3", "links": {}, "metadata": { "curation_policy": "Accepting published peer-reviewed publications; recommendations and standards; open source software; vocabularies and ontologies; linked data datasets; theses and student reports.
\r\n", "page": "Linked Data is a way to publish structured information on the Web, using well-defined properties with links related resources, all identified with accessible URIs.
\r\n\r\nLinked Data builds on (and includes) Semantic Web technologies like RDF, HTTP, REST and JSON-LD, and has a strong emphasis on openess and reuse of identifiers. Interoperability and ease of use has higher priority than reaching ideal semantic clarity.
\r\n\r\nLinked Data is also an important part of the Open Data movement, as it standardizes how to structure data and merging multiple disparate data sets is made possible using common identifiers and vocabularies.
\r\n\r\nThis community's logo is adapted from the Linking Open Data cloud diagram 2014, by Max Schmachtenberg, Christian Bizer, Anja Jentzsch and Richard Cyganiak. http://lod-cloud.net/
", "title": "Linked Data" }, "revision_id": 0, "slug": "linkeddata", "updated": "2018-03-07T16:51:40.482257+00:00" }, { "access": { "member_policy": "open", "record_policy": "open", "review_policy": "open", "visibility": "public" }, "children": { "allow": false }, "created": "2022-11-23T15:53:29.436323+00:00", "custom_fields": {}, "deletion_status": { "is_deleted": false, "status": "P" }, "id": "f0a8b890-f97a-4eb2-9eac-8b8a712d3a6c", "links": {}, "metadata": { "curation_policy": "", "description": "", "page": "", "title": "EU" }, "revision_id": 0, "slug": "eu", "updated": "2022-11-23T15:53:29.436331+00:00" }, { "access": { "member_policy": "open", "record_policy": "open", "review_policy": "open", "visibility": "public" }, "children": { "allow": false }, "created": "2016-09-16T09:22:02.863128+00:00", "custom_fields": {}, "deletion_status": { "is_deleted": false, "status": "P" }, "id": "fe037ff6-6dac-4d56-afde-704f1f800893", "links": {}, "metadata": { "description": "The leading European Centre of Excellence for Computational Biomolecular Research. Established in 2015, the centre has grown into a major research and innovation hub for scientific computing.", "funding": [ { "award": { "id": "00k4n6c32::823830" }, "funder": { "id": "00k4n6c32" } }, { "award": { "id": "00k4n6c32::675728" }, "funder": { "id": "00k4n6c32" } }, { "award": { "id": "00k4n6c32::101093290" }, "funder": { "id": "00k4n6c32" } } ], "page": "BioExcel (www.bioexcel.eu) is the leading European Centre of Excellence for computational biomolecular research. We develop world-class applications for modelling and simulations; methods for extreme scaling on modern supercomputing architectures; user-friendly automation workflows and extensive program for training and support of academic and industrial researchers in the use of high-performance computing (HPC) and high-throughput computing (HTC) in biomolecular research.
\n\nBioExcel is funded by the European Union Horizon 2020 program under grant agreements 823830, 675728.
", "title": "BioExcel Centre of Excellence for Computational Biomolecular Research", "type": { "id": "organization" }, "website": "https://bioexcel.eu" }, "revision_id": 1, "slug": "bioexcel", "updated": "2023-11-03T17:08:06.861102+00:00" } ], "ids": [ "b638e3e5-64a3-451b-a2cd-1e27ffa319a3", "f0a8b890-f97a-4eb2-9eac-8b8a712d3a6c", "fe037ff6-6dac-4d56-afde-704f1f800893" ] }, "id": "820877", "pids": {} }, "pids": { "doi": { "identifier": "10.1109/BigData.2016.7840618", "provider": "external" }, "oai": { "identifier": "oai:zenodo.org:820878", "provider": "oai" } }, "revision_id": 10, "stats": { "all_versions": { "data_volume": 390111648.0, "downloads": 547, "unique_downloads": 508, "unique_views": 1073, "views": 1164 }, "this_version": { "data_volume": 389398464.0, "downloads": 546, "unique_downloads": 507, "unique_views": 1069, "views": 1160 } }, "status": "published", "updated": "2020-01-20T17:36:56.085578+00:00", "versions": { "index": 1, "is_latest": true } }