{ "access": { "embargo": { "active": false, "reason": null }, "files": "public", "record": "public", "status": "open" }, "created": "2024-03-18T19:16:20.334303+00:00", "custom_fields": {}, "deletion_status": { "is_deleted": false, "status": "P" }, "files": { "count": 1, "enabled": true, "entries": { "GenePT_emebdding_v2.zip": { "access": { "hidden": false }, "checksum": "md5:3f6ce4317e3a0091978ae5cb8fbf05a3", "ext": "zip", "id": "ad3a5b2c-a430-4cf0-9413-d690f8e107c3", "key": "GenePT_emebdding_v2.zip", "links": { "content": "https://zenodo.org/api/records/10833191/files/GenePT_emebdding_v2.zip/content", "self": "https://zenodo.org/api/records/10833191/files/GenePT_emebdding_v2.zip" }, "metadata": null, "mimetype": "application/zip", "size": 574395233, "storage_class": "L" } }, "order": [], "total_bytes": 574395233 }, "id": "10833191", "is_draft": false, "is_published": true, "links": { "access": "https://zenodo.org/api/records/10833191/access", "access_grants": "https://zenodo.org/api/records/10833191/access/grants", "access_links": "https://zenodo.org/api/records/10833191/access/links", "access_request": "https://zenodo.org/api/records/10833191/access/request", "access_users": "https://zenodo.org/api/records/10833191/access/users", "archive": "https://zenodo.org/api/records/10833191/files-archive", "archive_media": "https://zenodo.org/api/records/10833191/media-files-archive", "communities": "https://zenodo.org/api/records/10833191/communities", "communities-suggestions": "https://zenodo.org/api/records/10833191/communities-suggestions", "doi": "https://doi.org/10.5281/zenodo.10833191", "draft": "https://zenodo.org/api/records/10833191/draft", "file_modification": "https://zenodo.org/api/records/10833191/file-modification", "files": "https://zenodo.org/api/records/10833191/files", "latest": "https://zenodo.org/api/records/10833191/versions/latest", "latest_html": "https://zenodo.org/records/10833191/latest", "media_files": "https://zenodo.org/api/records/10833191/media-files", "parent": "https://zenodo.org/api/records/10030425", "parent_doi": "https://doi.org/10.5281/zenodo.10030425", "parent_doi_html": "https://zenodo.org/doi/10.5281/zenodo.10030425", "parent_html": "https://zenodo.org/records/10030425", "preview_html": "https://zenodo.org/records/10833191?preview=1", "quota_increase": "https://zenodo.org/api/records/10833191/quota-increase", "request_deletion": "https://zenodo.org/api/records/10833191/request-deletion", "requests": "https://zenodo.org/api/records/10833191/requests", "reserve_doi": "https://zenodo.org/api/records/10833191/draft/pids/doi", "self": "https://zenodo.org/api/records/10833191", "self_doi": "https://doi.org/10.5281/zenodo.10833191", "self_doi_html": "https://zenodo.org/doi/10.5281/zenodo.10833191", "self_html": "https://zenodo.org/records/10833191", "self_iiif_manifest": "https://zenodo.org/api/iiif/record:10833191/manifest", "self_iiif_sequence": "https://zenodo.org/api/iiif/record:10833191/sequence/default", "versions": "https://zenodo.org/api/records/10833191/versions" }, "media_files": { "count": 0, "enabled": false, "entries": {}, "order": [], "total_bytes": 0 }, "metadata": { "creators": [ { "affiliations": [ { "id": "00f54p054", "identifiers": [ { "identifier": "00f54p054", "scheme": "ror" }, { "identifier": "grid.168010.e", "scheme": "grid" }, { "identifier": "0000 0004 1936 8956", "scheme": "isni" } ], "name": "Stanford University" } ], "person_or_org": { "family_name": "Yiqun", "given_name": "Chen", "identifiers": [ { "identifier": "0000-0002-4100-1507", "scheme": "orcid" } ], "name": "Yiqun, Chen", "type": "personal" }, "role": { "id": "datacollector", "title": { "de": "DatensammlerIn", "en": "Data collector" } } } ], "dates": [ { "date": "2023-10-21", "type": { "id": "submitted", "title": { "de": "Eingereicht", "en": "Submitted" } } }, { "date": "2024-03-18", "type": { "id": "updated", "title": { "de": "Aktualisiert", "en": "Updated" } } } ], "description": "

These are the pulled NCBI (and UniProt, when applicable) summaries of genes, as well as the corresponding OpenAI text embeddings (text-embedding-ada-002 and text-embedding-3-large) computed on the summaries. See methods details in Chen and Zou (2024+).

\n

The unzipped folder contains four different files: 

\n
    \n
  1. NCBI_summary_of_genes.json (NCBI gene card summary of human genes)
    2. \n
  2. NCBI_UniProt_summary_of_genes.json (NCBI gene card and UniProt protein (when applicable) summary of human genes)
    3. \n
  3. GenePT_gene_embedding_ada_text.pickle (a dictionary of numpy array where gene names (upper case) are keys and text-embedding-ada-002 embeddings of the summary in 1. are the values)
    4. \n
  4. GenePT_gene_protein_embedding_model_3_text.pickle (a dictionary of numpy array where gene names (upper case) are keys and text-embedding-3-large embeddings of the summary in 1. are the values)
    5. \n
\n

Reference:

\n

Chen YT, Zou J. (2024+) GenePT: A Simple But Effective Foundation Model for Genes and Cells Built From ChatGPT. bioRxiv preprint: https://www.biorxiv.org/content/10.1101/2023.10.16.562533v1.

", "languages": [ { "id": "eng", "title": { "en": "English" } } ], "publication_date": "2024-03-18", "publisher": "Zenodo", "related_identifiers": [ { "identifier": "10.1101/2023.10.16.562533", "relation_type": { "id": "ispartof", "title": { "de": "Ist Teil von", "en": "Is part of" } }, "resource_type": { "id": "publication-preprint", "title": { "de": "Preprint", "en": "Preprint" } }, "scheme": "doi" } ], "resource_type": { "id": "dataset", "title": { "de": "Datensatz", "en": "Dataset" } }, "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": "Computational Biology" }, { "subject": "Foundation Models" } ], "title": "Gene embeddings used in GenePT: A Simple But Hard-to-Beat Foundation Model for Genes and Cells Built From ChatGPT" }, "parent": { "access": { "owned_by": { "user": "465067" }, "settings": { "accept_conditions_text": null, "allow_guest_requests": false, "allow_user_requests": false, "secret_link_expiration": 0 } }, "communities": {}, "id": "10030425", "pids": { "doi": { "client": "datacite", "identifier": "10.5281/zenodo.10030425", "provider": "datacite" } } }, "pids": { "doi": { "client": "datacite", "identifier": "10.5281/zenodo.10833191", "provider": "datacite" }, "oai": { "identifier": "oai:zenodo.org:10833191", "provider": "oai" } }, "revision_id": 4, "stats": { "all_versions": { "data_volume": 1366307147120.0, "downloads": 2656, "unique_downloads": 1769, "unique_views": 5232, "views": 6041 }, "this_version": { "data_volume": 1265967093532.0, "downloads": 2204, "unique_downloads": 1415, "unique_views": 4290, "views": 4995 } }, "status": "published", "swh": {}, "updated": "2024-03-18T19:16:20.596498+00:00", "versions": { "index": 2, "is_latest": true } }