{ "access": { "embargo": { "active": false, "reason": null }, "files": "public", "record": "public", "status": "open" }, "created": "2024-02-21T01:29:10.699242+00:00", "custom_fields": {}, "deletion_status": { "is_deleted": false, "status": "P" }, "files": { "count": 7, "default_preview": "README.txt", "enabled": true, "entries": { "AQM-gas.hdf5": { "access": { "hidden": false }, "checksum": "md5:e4cee28996ee002bcc37157691f7600a", "ext": "hdf5", "id": "68ba7a12-1c54-459f-931a-fb476d6bb488", "key": "AQM-gas.hdf5", "links": { "content": "https://zenodo.org/api/records/10208010/files/AQM-gas.hdf5/content", "self": "https://zenodo.org/api/records/10208010/files/AQM-gas.hdf5" }, "metadata": null, "mimetype": "application/octet-stream", "size": 1574429632, "storage_class": "L" }, "AQM-initial.xz": { "access": { "hidden": false }, "checksum": "md5:c84d69fc6a3bacb2b80d8b9a7dbd0ec7", "ext": "xz", "id": "aab8d925-98cb-4d0b-ad74-8a9f493d0e43", "key": "AQM-initial.xz", "links": { "content": "https://zenodo.org/api/records/10208010/files/AQM-initial.xz/content", "self": "https://zenodo.org/api/records/10208010/files/AQM-initial.xz" }, "metadata": null, "mimetype": "application/x-xz", "size": 2610738960, "storage_class": "L" }, "AQM-sol.hdf5": { "access": { "hidden": false }, "checksum": "md5:71c86586e3e26a1471721555325026ce", "ext": "hdf5", "id": "7d4e4c0d-47f1-4448-b5db-06bbd87e79fc", "key": "AQM-sol.hdf5", "links": { "content": "https://zenodo.org/api/records/10208010/files/AQM-sol.hdf5/content", "self": "https://zenodo.org/api/records/10208010/files/AQM-sol.hdf5" }, "metadata": null, "mimetype": "application/octet-stream", "size": 1668808000, "storage_class": "L" }, "README.txt": { "access": { "hidden": false }, "checksum": "md5:fc615ca71f9c6432bb88a2652802c270", "ext": "txt", "id": "2a590065-500b-4eb7-ba4f-758b7e9e6b62", "key": "README.txt", "links": { "content": "https://zenodo.org/api/records/10208010/files/README.txt/content", "self": "https://zenodo.org/api/records/10208010/files/README.txt" }, "metadata": null, "mimetype": "text/plain", "size": 2821, "storage_class": "L" }, "info-final-AQM.csv": { "access": { "hidden": false }, "checksum": "md5:a722d765bda6e9274925bbf0dc899e85", "ext": "csv", "id": "e49c00a3-8f16-444f-95b1-a5a8298c366f", "key": "info-final-AQM.csv", "links": { "content": "https://zenodo.org/api/records/10208010/files/info-final-AQM.csv/content", "self": "https://zenodo.org/api/records/10208010/files/info-final-AQM.csv" }, "metadata": null, "mimetype": "text/csv", "size": 328948, "storage_class": "L" }, "info-initial-AQM.csv": { "access": { "hidden": false }, "checksum": "md5:2103b824abc6d6000d4ea3a1b0dd7b81", "ext": "csv", "id": "d4ef5f3f-e287-4641-b668-24a8c5bf5361", "key": "info-initial-AQM.csv", "links": { "content": "https://zenodo.org/api/records/10208010/files/info-initial-AQM.csv/content", "self": "https://zenodo.org/api/records/10208010/files/info-initial-AQM.csv" }, "metadata": null, "mimetype": "text/csv", "size": 524368, "storage_class": "L" }, "readAQM.py": { "access": { "hidden": false }, "checksum": "md5:40500597b2501dafc3f29e91a760ebd4", "ext": "py", "id": "fe66580c-631a-4107-a052-011a2c29fcec", "key": "readAQM.py", "links": { "content": "https://zenodo.org/api/records/10208010/files/readAQM.py/content", "self": "https://zenodo.org/api/records/10208010/files/readAQM.py" }, "metadata": null, "mimetype": "text/x-python", "size": 1040, "storage_class": "L" } }, "order": [], "total_bytes": 5854833769 }, "id": "10208010", "is_draft": false, "is_published": true, "links": { "access": "https://zenodo.org/api/records/10208010/access", "access_grants": "https://zenodo.org/api/records/10208010/access/grants", "access_links": "https://zenodo.org/api/records/10208010/access/links", "access_request": "https://zenodo.org/api/records/10208010/access/request", "access_users": "https://zenodo.org/api/records/10208010/access/users", "archive": "https://zenodo.org/api/records/10208010/files-archive", "archive_media": "https://zenodo.org/api/records/10208010/media-files-archive", "communities": "https://zenodo.org/api/records/10208010/communities", "communities-suggestions": "https://zenodo.org/api/records/10208010/communities-suggestions", "doi": "https://doi.org/10.5281/zenodo.10208010", "draft": "https://zenodo.org/api/records/10208010/draft", "file_modification": "https://zenodo.org/api/records/10208010/file-modification", "files": "https://zenodo.org/api/records/10208010/files", "latest": "https://zenodo.org/api/records/10208010/versions/latest", "latest_html": "https://zenodo.org/records/10208010/latest", "media_files": "https://zenodo.org/api/records/10208010/media-files", "parent": "https://zenodo.org/api/records/10208009", "parent_doi": "https://doi.org/10.5281/zenodo.10208009", "parent_doi_html": "https://zenodo.org/doi/10.5281/zenodo.10208009", "parent_html": "https://zenodo.org/records/10208009", "preview_html": "https://zenodo.org/records/10208010?preview=1", "quota_increase": "https://zenodo.org/api/records/10208010/quota-increase", "request_deletion": "https://zenodo.org/api/records/10208010/request-deletion", "requests": "https://zenodo.org/api/records/10208010/requests", "reserve_doi": "https://zenodo.org/api/records/10208010/draft/pids/doi", "self": "https://zenodo.org/api/records/10208010", "self_doi": "https://doi.org/10.5281/zenodo.10208010", "self_doi_html": "https://zenodo.org/doi/10.5281/zenodo.10208010", "self_html": "https://zenodo.org/records/10208010", "self_iiif_manifest": "https://zenodo.org/api/iiif/record:10208010/manifest", "self_iiif_sequence": "https://zenodo.org/api/iiif/record:10208010/sequence/default", "versions": "https://zenodo.org/api/records/10208010/versions" }, "media_files": { "count": 0, "enabled": false, "entries": {}, "order": [], "total_bytes": 0 }, "metadata": { "contributors": [ { "affiliations": [ { "id": "04yzcpd71", "identifiers": [ { "identifier": "04yzcpd71", "scheme": "ror" }, { "identifier": "grid.419619.2", "scheme": "grid" }, { "identifier": "0000 0004 0623 0341", "scheme": "isni" } ], "name": "Janssen (Belgium)" } ], "person_or_org": { "family_name": "Van Rompaey", "given_name": "Dries", "identifiers": [ { "identifier": "0000-0003-0823-8235", "scheme": "orcid" } ], "name": "Van Rompaey, Dries", "type": "personal" }, "role": { "id": "researcher", "title": { "de": "WissenschaftlerIn", "en": "Researcher" } } }, { "affiliations": [ { "id": "04yzcpd71", "identifiers": [ { "identifier": "04yzcpd71", "scheme": "ror" }, { "identifier": "grid.419619.2", "scheme": "grid" }, { "identifier": "0000 0004 0623 0341", "scheme": "isni" } ], "name": "Janssen (Belgium)" }, { "id": "036x5ad56", "identifiers": [ { "identifier": "036x5ad56", "scheme": "ror" }, { "identifier": "grid.16008.3f", "scheme": "grid" }, { "identifier": "0000 0001 2295 9843", "scheme": "isni" } ], "name": "University of Luxembourg" } ], "person_or_org": { "family_name": "Fallani", "given_name": "Alessio", "name": "Fallani, Alessio", "type": "personal" }, "role": { "id": "researcher", "title": { "de": "WissenschaftlerIn", "en": "Researcher" } } }, { "affiliations": [ { "id": "036x5ad56", "identifiers": [ { "identifier": "036x5ad56", "scheme": "ror" }, { "identifier": "grid.16008.3f", "scheme": "grid" }, { "identifier": "0000 0001 2295 9843", "scheme": "isni" } ], "name": "University of Luxembourg" } ], "person_or_org": { "family_name": "Hilfiker", "given_name": "Mathias", "name": "Hilfiker, Mathias", "type": "personal" }, "role": { "id": "researcher", "title": { "de": "WissenschaftlerIn", "en": "Researcher" } } }, { "affiliations": [ { "id": "04yzcpd71", "identifiers": [ { "identifier": "04yzcpd71", "scheme": "ror" }, { "identifier": "grid.419619.2", "scheme": "grid" }, { "identifier": "0000 0004 0623 0341", "scheme": "isni" } ], "name": "Janssen (Belgium)" } ], "person_or_org": { "family_name": "Hahn", "given_name": "David", "name": "Hahn, David", "type": "personal" }, "role": { "id": "researcher", "title": { "de": "WissenschaftlerIn", "en": "Researcher" } } }, { "affiliations": [ { "id": "04yzcpd71", "identifiers": [ { "identifier": "04yzcpd71", "scheme": "ror" }, { "identifier": "grid.419619.2", "scheme": "grid" }, { "identifier": "0000 0004 0623 0341", "scheme": "isni" } ], "name": "Janssen (Belgium)" } ], "person_or_org": { "family_name": "Perez-Benito", "given_name": "Laura", "name": "Perez-Benito, Laura", "type": "personal" }, "role": { "id": "researcher", "title": { "de": "WissenschaftlerIn", "en": "Researcher" } } }, { "affiliations": [ { "id": "04yzcpd71", "identifiers": [ { "identifier": "04yzcpd71", "scheme": "ror" }, { "identifier": "grid.419619.2", "scheme": "grid" }, { "identifier": "0000 0004 0623 0341", "scheme": "isni" } ], "name": "Janssen (Belgium)" } ], "person_or_org": { "family_name": "Verhoeven", "given_name": "Jonas", "name": "Verhoeven, Jonas", "type": "personal" }, "role": { "id": "researcher", "title": { "de": "WissenschaftlerIn", "en": "Researcher" } } }, { "affiliations": [ { "id": "04yzcpd71", "identifiers": [ { "identifier": "04yzcpd71", "scheme": "ror" }, { "identifier": "grid.419619.2", "scheme": "grid" }, { "identifier": "0000 0004 0623 0341", "scheme": "isni" } ], "name": "Janssen (Belgium)" } ], "person_or_org": { "family_name": "Tresadern", "given_name": "Gary", "name": "Tresadern, Gary", "type": "personal" }, "role": { "id": "researcher", "title": { "de": "WissenschaftlerIn", "en": "Researcher" } } }, { "affiliations": [ { "id": "04yzcpd71", "identifiers": [ { "identifier": "04yzcpd71", "scheme": "ror" }, { "identifier": "grid.419619.2", "scheme": "grid" }, { "identifier": "0000 0004 0623 0341", "scheme": "isni" } ], "name": "Janssen (Belgium)" } ], "person_or_org": { "family_name": "Kurt Wegner", "given_name": "Joerg", "name": "Kurt Wegner, Joerg", "type": "personal" }, "role": { "id": "researcher", "title": { "de": "WissenschaftlerIn", "en": "Researcher" } } }, { "affiliations": [ { "id": "04yzcpd71", "identifiers": [ { "identifier": "04yzcpd71", "scheme": "ror" }, { "identifier": "grid.419619.2", "scheme": "grid" }, { "identifier": "0000 0004 0623 0341", "scheme": "isni" } ], "name": "Janssen (Belgium)" } ], "person_or_org": { "family_name": "Ceulemans", "given_name": "Hugo", "name": "Ceulemans, Hugo", "type": "personal" }, "role": { "id": "researcher", "title": { "de": "WissenschaftlerIn", "en": "Researcher" } } }, { "affiliations": [ { "id": "036x5ad56", "identifiers": [ { "identifier": "036x5ad56", "scheme": "ror" }, { "identifier": "grid.16008.3f", "scheme": "grid" }, { "identifier": "0000 0001 2295 9843", "scheme": "isni" } ], "name": "University of Luxembourg" } ], "person_or_org": { "family_name": "Tkatchenko", "given_name": "Alexandre", "name": "Tkatchenko, Alexandre", "type": "personal" }, "role": { "id": "researcher", "title": { "de": "WissenschaftlerIn", "en": "Researcher" } } } ], "creators": [ { "affiliations": [ { "id": "036x5ad56", "identifiers": [ { "identifier": "036x5ad56", "scheme": "ror" }, { "identifier": "grid.16008.3f", "scheme": "grid" }, { "identifier": "0000 0001 2295 9843", "scheme": "isni" } ], "name": "University of Luxembourg" } ], "person_or_org": { "family_name": "Medrano Sandonas", "given_name": "Leonardo", "identifiers": [ { "identifier": "0000-0002-7673-3142", "scheme": "orcid" } ], "name": "Medrano Sandonas, Leonardo", "type": "personal" }, "role": { "id": "contactperson", "title": { "de": "Kontaktperson", "en": "Contact person" } } } ], "dates": [ { "date": "2024-06-30", "type": { "id": "available", "title": { "de": "Verf\u00fcgbar", "en": "Available" } } } ], "description": "

Open challenges in computational drug design include the understanding and accurate description of solvent effects as well as collective dispersion interactions for realistic drug-like molecules. Both interactions profoundly influence the conformational stability of drug molecules and, consequently, the determination of other important quantum-mechanical (QM) observables. In this context, we here introduce the Aquamarine (AQM) dataset -- an extensive QM dataset that contains the structural and electronic information -- of 59,786 low-and high-energy conformers of 1,653 molecules containing up to 54 non-hydrogen atoms (including  C, N, O, F, P, S and Cl). To gain insights into the solvent effects, we have carried out QM calculations of structures and properties in gas phase and in an aqueous solution modeled with implicit solvent. AQM contains over 40 global (molecular) and local (atom-in-a-molecule) physicochemical properties (including ground-state and response properties) per molecular structure computed at the tightly converged PBE0+MBD level of theory for gas-phase molecules, whereas PBE0+MBD supplemented with the modified Poisson-Boltzmann (MPB) model of water was used for solvated molecules. By treating both molecule-solvent and dispersion interactions, the AQM dataset can help understand the impact of both interactions in structure-property and property-property relationships of realistic drug-like molecules. Therefore, we propose the AQM dataset as a  benchmark for current state-of-the-art machine learning methods for property prediction as well as for the de novo generation of large and flexible (solvated) molecules with pharmaceutical and biological relevance.

", "funding": [ { "funder": { "id": "04yzcpd71", "name": "Janssen (Belgium)" } }, { "funder": { "id": "019w4f821", "name": "European Union" } }, { "funder": { "id": "036x5ad56", "name": "University of Luxembourg" } } ], "languages": [ { "id": "eng", "title": { "en": "English" } } ], "publication_date": "2024-06-30", "publisher": "Zenodo", "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": "Drug design" }, { "subject": "Quantum mechanics" }, { "subject": "Machine learning" }, { "subject": "Solvation" }, { "subject": "property space" } ], "title": "Aquamarine: Quantum-Mechanical Exploration of Conformers and Solvent Effects in Large Drug-like Molecules", "version": "1.0" }, "parent": { "access": { "owned_by": { "user": "89199" }, "settings": { "accept_conditions_text": null, "allow_guest_requests": false, "allow_user_requests": false, "secret_link_expiration": 0 } }, "communities": {}, "id": "10208009", "pids": { "doi": { "client": "datacite", "identifier": "10.5281/zenodo.10208009", "provider": "datacite" } } }, "pids": { "doi": { "client": "datacite", "identifier": "10.5281/zenodo.10208010", "provider": "datacite" }, "oai": { "identifier": "oai:zenodo.org:10208010", "provider": "oai" } }, "revision_id": 10, "stats": { "all_versions": { "data_volume": 4415845335031.0, "downloads": 2917, "unique_downloads": 1296, "unique_views": 783, "views": 872 }, "this_version": { "data_volume": 4415845335031.0, "downloads": 2917, "unique_downloads": 1296, "unique_views": 783, "views": 872 } }, "status": "published", "swh": {}, "updated": "2024-03-16T14:05:56.997763+00:00", "versions": { "index": 1, "is_latest": true } }