{"id":"https://openalex.org/W7204997157","doi":"https://doi.org/10.51847/jujwjdusfg","title":"Natural-Product Models Learn What Databases Choose to Record: A Data-Governance Architecture for Structures, Spectra, Bioassays, Taxonomy, Provenance, and Negative Results","display_name":"Natural-Product Models Learn What Databases Choose to Record: A Data-Governance Architecture for Structures, Spectra, Bioassays, Taxonomy, Provenance, and Negative Results","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7204997157","doi":"https://doi.org/10.51847/jujwjdusfg"},"language":null,"primary_location":{"id":"doi:10.51847/jujwjdusfg","doi":"https://doi.org/10.51847/jujwjdusfg","is_oa":true,"landing_page_url":"https://doi.org/10.51847/jujwjdusfg","pdf_url":"https://galaxypub.co/storage/files/article/25520d46-8499-4b1d-baaa-cfb69e7076e9-k02PIZkgYDQCWTyx/ZBCeuAcAoKCw5H5.pdf","source":{"id":"https://openalex.org/S5407047900","display_name":"Specialty journal of Pharmacognosy Phytochemistry and Biotechnology","issn_l":"3062-441X","issn":["3062-441X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Specialty Journal of Pharmacognosy, Phytochemistry, and Biotechnology","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://galaxypub.co/storage/files/article/25520d46-8499-4b1d-baaa-cfb69e7076e9-k02PIZkgYDQCWTyx/ZBCeuAcAoKCw5H5.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5141166550","display_name":"Gabriel Costa","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I110200422","display_name":"Universidade Federal de Minas Gerais","ror":"https://ror.org/0176yjw32","country_code":"BR","type":"education","lineage":["https://openalex.org/I110200422"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"Gabriel Costa","raw_affiliation_strings":["Department of Natural-Product Data Governance and Provenance , Faculty of Pharmacy , Federal University of Minas Gerais , Belo Horizonte , Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Natural-Product Data Governance and Provenance , Faculty of Pharmacy , Federal University of Minas Gerais , Belo Horizonte , Brazil","institution_ids":["https://openalex.org/I110200422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129620687","display_name":"Lucas F. Ribeiro","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I110200422","display_name":"Universidade Federal de Minas Gerais","ror":"https://ror.org/0176yjw32","country_code":"BR","type":"education","lineage":["https://openalex.org/I110200422"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Lucas Ribeiro","raw_affiliation_strings":["Department of Natural-Product Data Governance and Provenance , Faculty of Pharmacy , Federal University of Minas Gerais , Belo Horizonte , Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Natural-Product Data Governance and Provenance , Faculty of Pharmacy , Federal University of Minas Gerais , Belo Horizonte , Brazil","institution_ids":["https://openalex.org/I110200422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141161636","display_name":"Ricardo Alves","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I76903346","display_name":"University of Coimbra","ror":"https://ror.org/04z8k9a98","country_code":"PT","type":"education","lineage":["https://openalex.org/I76903346"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Ricardo Alves","raw_affiliation_strings":["Department of Spectral and Bioassay Database Architecture , Faculty of Pharmacy , University of Coimbra , Coimbra , Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Spectral and Bioassay Database Architecture , Faculty of Pharmacy , University of Coimbra , Coimbra , Portugal","institution_ids":["https://openalex.org/I76903346"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5125342806","display_name":"Mariana Lopes","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Mariana Lopes","raw_affiliation_strings":["Department of Taxonomy and Negative-Result Reporting , Faculty of Pharmacy , University of S\u00e3o Paulo , S\u00e3o Paulo , Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Taxonomy and Negative-Result Reporting , Faculty of Pharmacy , University of S\u00e3o Paulo , S\u00e3o Paulo , Brazil","institution_ids":["https://openalex.org/I17974374"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5141166550"],"corresponding_institution_ids":["https://openalex.org/I110200422"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.67278107,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"6","issue":"1","first_page":"12","last_page":"21"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11937","display_name":"Research Data Management Practices","score":0.7929999828338623,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11937","display_name":"Research Data Management Practices","score":0.7929999828338623,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.06650000065565109,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.020800000056624413,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/natural-products","display_name":"natural products","score":0.8610000014305115},{"id":"https://openalex.org/keywords/data-governance","display_name":"data governance","score":0.906000018119812},{"id":"https://openalex.org/keywords/natural-product-database","display_name":"natural product database","score":0.6230000257492065},{"id":"https://openalex.org/keywords/machine-learning-models","display_name":"machine learning models","score":0.6079999804496765},{"id":"https://openalex.org/keywords/spectroscopic-data","display_name":"spectral data","score":0.5059999823570251},{"id":"https://openalex.org/keywords/bioassay-data","display_name":"bioassay data","score":0.9010000228881836},{"id":"https://openalex.org/keywords/taxonomy","display_name":"taxonomy","score":0.5550000071525574},{"id":"https://openalex.org/keywords/provenance","display_name":"provenance","score":0.9200000166893005},{"id":"https://openalex.org/keywords/negative-results","display_name":"negative results","score":0.996999979019165},{"id":"https://openalex.org/keywords/data-normalization","display_name":"data normalization","score":0.47699999809265137},{"id":"https://openalex.org/keywords/data-linkage","display_name":"data linkage","score":0.40799999237060547},{"id":"https://openalex.org/keywords/data-curation","display_name":"data curation","score":0.367000013589859}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6603000164031982},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.453000009059906},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.398499995470047},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3305000066757202},{"id":"https://openalex.org/C98025372","wikidata":"https://www.wikidata.org/wiki/Q477538","display_name":"Systems architecture","level":3,"score":0.31209999322891235},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2822999954223633},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2777000069618225},{"id":"https://openalex.org/C180198813","wikidata":"https://www.wikidata.org/wiki/Q121182","display_name":"Information system","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2712000012397766},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26669999957084656},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.25360000133514404}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.51847/jujwjdusfg","doi":"https://doi.org/10.51847/jujwjdusfg","is_oa":true,"landing_page_url":"https://doi.org/10.51847/jujwjdusfg","pdf_url":"https://galaxypub.co/storage/files/article/25520d46-8499-4b1d-baaa-cfb69e7076e9-k02PIZkgYDQCWTyx/ZBCeuAcAoKCw5H5.pdf","source":{"id":"https://openalex.org/S5407047900","display_name":"Specialty journal of Pharmacognosy Phytochemistry and Biotechnology","issn_l":"3062-441X","issn":["3062-441X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Specialty Journal of Pharmacognosy, Phytochemistry, and Biotechnology","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.51847/jujwjdusfg","doi":"https://doi.org/10.51847/jujwjdusfg","is_oa":true,"landing_page_url":"https://doi.org/10.51847/jujwjdusfg","pdf_url":"https://galaxypub.co/storage/files/article/25520d46-8499-4b1d-baaa-cfb69e7076e9-k02PIZkgYDQCWTyx/ZBCeuAcAoKCw5H5.pdf","source":{"id":"https://openalex.org/S5407047900","display_name":"Specialty journal of Pharmacognosy Phytochemistry and Biotechnology","issn_l":"3062-441X","issn":["3062-441X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Specialty Journal of Pharmacognosy, Phytochemistry, and Biotechnology","raw_type":"journal-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204997157.pdf","grobid_xml":"https://content.openalex.org/works/W7204997157.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W3049190563","https://openalex.org/W3082081167","https://openalex.org/W3118695441","https://openalex.org/W3176586111","https://openalex.org/W3210489033","https://openalex.org/W4281658583","https://openalex.org/W4313597804","https://openalex.org/W4383187427","https://openalex.org/W4385406507","https://openalex.org/W4388448853","https://openalex.org/W4388455891","https://openalex.org/W4389564374","https://openalex.org/W4392093325","https://openalex.org/W4401648307","https://openalex.org/W4403663385","https://openalex.org/W4404511389","https://openalex.org/W4404642680","https://openalex.org/W4404642710","https://openalex.org/W4404707456","https://openalex.org/W4404707458","https://openalex.org/W4405230358","https://openalex.org/W4406201162","https://openalex.org/W4408969965","https://openalex.org/W4409334630","https://openalex.org/W4410706574","https://openalex.org/W4411259040","https://openalex.org/W4411804077","https://openalex.org/W4415384230","https://openalex.org/W4416298756","https://openalex.org/W4417153701","https://openalex.org/W7128682674","https://openalex.org/W7131788055","https://openalex.org/W7133221954","https://openalex.org/W7162937859","https://openalex.org/W7165652260"],"related_works":[],"abstract_inverted_index":{"Natural-product":[0],"machine-learning":[1],"models":[2],"do":[3],"not":[4],"encounter":[5,14],"molecules,":[6],"spectra,":[7],"organisms,":[8],"or":[9],"biological":[10],"responses":[11],"directly;":[12],"they":[13],"database":[15],"records":[16],"produced":[17],"through":[18],"choices":[19,43],"about":[20],"what":[21],"is":[22],"deposited,":[23],"normalized,":[24],"linked,":[25],"corrected,":[26],"omitted,":[27],"and":[28],"retained.":[29],"This":[30],"article":[31],"develops":[32],"an":[33],"original":[34],"data-governance":[35],"architecture":[36],"for":[37],"natural-product":[38],"modeling":[39],"that":[40],"treats":[41],"these":[42],"as":[44,52],"part":[45],"of":[46],"the":[47],"inferential":[48],"system":[49],"rather":[50],"than":[51],"background":[53],"data-management":[54],"operations.":[55],"The":[56],"analysis":[57],"integrates":[58],"structural":[59],"i":[60]},"counts_by_year":[],"updated_date":"2026-10-17T09:40:24.721904","created_date":"2026-09-02T00:00:00"}