{"id":"https://openalex.org/W2913820882","doi":"https://doi.org/10.1186/s12859-019-2932-0","title":"ProteinNet: a standardized data set for machine learning of protein structure","display_name":"ProteinNet: a standardized data set for machine learning of protein structure","publication_year":2019,"publication_date":"2019-06-11","ids":{"openalex":"https://openalex.org/W2913820882","doi":"https://doi.org/10.1186/s12859-019-2932-0","mag":"2913820882","pmid":"https://pubmed.ncbi.nlm.nih.gov/31185886"},"language":"en","primary_location":{"id":"doi:10.1186/s12859-019-2932-0","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-019-2932-0","pdf_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-019-2932-0","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-019-2932-0","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002987125","display_name":"Mohammed AlQuraishi","orcid":"https://orcid.org/0000-0001-6817-1322"},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]},{"id":"https://openalex.org/I4210155419","display_name":"Center for Systems Biology","ror":"https://ror.org/05r3dyn47","country_code":"US","type":"facility","lineage":["https://openalex.org/I136199984","https://openalex.org/I4210087915","https://openalex.org/I4210155419","https://openalex.org/I48633490"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mohammed AlQuraishi","raw_affiliation_strings":["Laboratory of Systems Pharmacology, Department of Systems Biology, Harvard Medical School, 200 Longwood Avenue, Boston, MA, 02115, USA. alquraishi@hms.harvard.edu","Laboratory of Systems Pharmacology, Department of Systems Biology, Harvard Medical School, 200 Longwood Avenue, Boston, MA, 02115, USA"],"affiliations":[{"raw_affiliation_string":"Laboratory of Systems Pharmacology, Department of Systems Biology, Harvard Medical School, 200 Longwood Avenue, Boston, MA, 02115, USA. alquraishi@hms.harvard.edu","institution_ids":["https://openalex.org/I4210155419"]},{"raw_affiliation_string":"Laboratory of Systems Pharmacology, Department of Systems Biology, Harvard Medical School, 200 Longwood Avenue, Boston, MA, 02115, USA","institution_ids":["https://openalex.org/I4210155419","https://openalex.org/I136199984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5002987125"],"corresponding_institution_ids":["https://openalex.org/I136199984","https://openalex.org/I4210155419"],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":7.5577,"has_fulltext":true,"cited_by_count":159,"citation_normalized_percentile":{"value":0.98124218,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"20","issue":"1","first_page":"311","last_page":"311"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/casp","display_name":"CASP","score":0.9168699383735657},{"id":"https://openalex.org/keywords/protein-structure-prediction","display_name":"Protein structure prediction","score":0.6723037362098694},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.65903639793396},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.617326557636261},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6127275228500366},{"id":"https://openalex.org/keywords/protein-structure-database","display_name":"Protein structure database","score":0.5242792963981628},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4694364070892334},{"id":"https://openalex.org/keywords/sequence-alignment","display_name":"Sequence alignment","score":0.4538908004760742},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.44100192189216614},{"id":"https://openalex.org/keywords/structural-bioinformatics","display_name":"Structural bioinformatics","score":0.43638816475868225},{"id":"https://openalex.org/keywords/protein-function-prediction","display_name":"Protein function prediction","score":0.43618014454841614},{"id":"https://openalex.org/keywords/protein-data-bank","display_name":"Protein Data Bank","score":0.41819214820861816},{"id":"https://openalex.org/keywords/protein-sequencing","display_name":"Protein sequencing","score":0.41594985127449036},{"id":"https://openalex.org/keywords/protein-structure","display_name":"Protein structure","score":0.4014322757720947},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.39936456084251404},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.3486260771751404},{"id":"https://openalex.org/keywords/peptide-sequence","display_name":"Peptide sequence","score":0.21252107620239258},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.19348853826522827},{"id":"https://openalex.org/keywords/sequence-database","display_name":"Sequence database","score":0.1680295765399933},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1266193985939026},{"id":"https://openalex.org/keywords/protein-function","display_name":"Protein function","score":0.09905767440795898},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.08972617983818054}],"concepts":[{"id":"https://openalex.org/C66153294","wikidata":"https://www.wikidata.org/wiki/Q899291","display_name":"CASP","level":4,"score":0.9168699383735657},{"id":"https://openalex.org/C18051474","wikidata":"https://www.wikidata.org/wiki/Q899656","display_name":"Protein structure prediction","level":3,"score":0.6723037362098694},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.65903639793396},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.617326557636261},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6127275228500366},{"id":"https://openalex.org/C136475424","wikidata":"https://www.wikidata.org/wiki/Q7251500","display_name":"Protein structure database","level":4,"score":0.5242792963981628},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4694364070892334},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.4538908004760742},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.44100192189216614},{"id":"https://openalex.org/C69131567","wikidata":"https://www.wikidata.org/wiki/Q2068215","display_name":"Structural bioinformatics","level":3,"score":0.43638816475868225},{"id":"https://openalex.org/C207060522","wikidata":"https://www.wikidata.org/wiki/Q7251473","display_name":"Protein function prediction","level":4,"score":0.43618014454841614},{"id":"https://openalex.org/C119145174","wikidata":"https://www.wikidata.org/wiki/Q7251429","display_name":"Protein Data Bank","level":3,"score":0.41819214820861816},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.41594985127449036},{"id":"https://openalex.org/C47701112","wikidata":"https://www.wikidata.org/wiki/Q735188","display_name":"Protein structure","level":2,"score":0.4014322757720947},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39936456084251404},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.3486260771751404},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.21252107620239258},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.19348853826522827},{"id":"https://openalex.org/C41584329","wikidata":"https://www.wikidata.org/wiki/Q175902","display_name":"Sequence database","level":3,"score":0.1680295765399933},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1266193985939026},{"id":"https://openalex.org/C2986374874","wikidata":"https://www.wikidata.org/wiki/Q8054","display_name":"Protein function","level":3,"score":0.09905767440795898},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.08972617983818054},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D012015","descriptor_name":"Reference Standards","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012015","descriptor_name":"Reference Standards","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012015","descriptor_name":"Reference Standards","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1186/s12859-019-2932-0","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-019-2932-0","pdf_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-019-2932-0","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},{"id":"pmid:31185886","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/31185886","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC bioinformatics","raw_type":null},{"id":"pmh:oai:doaj.org/article:9eba93e027e14eed9782f7c28be49cb9","is_oa":true,"landing_page_url":"https://doaj.org/article/9eba93e027e14eed9782f7c28be49cb9","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, Vol 20, Iss 1, Pp 1-10 (2019)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:6560865","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/6560865","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/s12859-019-2932-0","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-019-2932-0","pdf_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-019-2932-0","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3268359520","display_name":null,"funder_award_id":"P50-GM107618","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"},{"id":"https://openalex.org/G3447611","display_name":null,"funder_award_id":"U54-CA225088","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G5612980095","display_name":null,"funder_award_id":"U54-CA225088","funder_id":"https://openalex.org/F4320337351","funder_display_name":"National Cancer Institute"},{"id":"https://openalex.org/G92043430","display_name":null,"funder_award_id":"P50GM107618","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337351","display_name":"National Cancer Institute","ror":"https://ror.org/040gcmg81"},{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2913820882.pdf","grobid_xml":"https://content.openalex.org/works/W2913820882.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W1019830208","https://openalex.org/W1537929670","https://openalex.org/W1966041739","https://openalex.org/W2051210555","https://openalex.org/W2101220662","https://openalex.org/W2109476464","https://openalex.org/W2109801072","https://openalex.org/W2116435022","https://openalex.org/W2117539524","https://openalex.org/W2126103104","https://openalex.org/W2136856901","https://openalex.org/W2138122982","https://openalex.org/W2145268834","https://openalex.org/W2149769193","https://openalex.org/W2153153865","https://openalex.org/W2154139219","https://openalex.org/W2161072217","https://openalex.org/W2402144811","https://openalex.org/W2521372695","https://openalex.org/W2550969987","https://openalex.org/W2557283755","https://openalex.org/W2574496196","https://openalex.org/W2737584047","https://openalex.org/W2770647690","https://openalex.org/W2799619538","https://openalex.org/W2799723178","https://openalex.org/W2899771611","https://openalex.org/W2918063357","https://openalex.org/W2919115771","https://openalex.org/W2950954328","https://openalex.org/W2951934944","https://openalex.org/W2952317511","https://openalex.org/W3198971594","https://openalex.org/W4233120011","https://openalex.org/W6713134421","https://openalex.org/W6756040250"],"related_works":["https://openalex.org/W2146442590","https://openalex.org/W4388749535","https://openalex.org/W3171039768","https://openalex.org/W4206949911","https://openalex.org/W3013234621","https://openalex.org/W2607853144","https://openalex.org/W4285340733","https://openalex.org/W4389309199","https://openalex.org/W2593264178","https://openalex.org/W2181530468"],"abstract_inverted_index":{"ProteinNet":[0],"represents":[1],"a":[2],"comprehensive":[3],"and":[4,9],"accessible":[5],"resource":[6],"for":[7],"training":[8],"assessing":[10],"machine-learned":[11],"models":[12],"of":[13],"protein":[14],"structure.":[15]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":21},{"year":2024,"cited_by_count":24},{"year":2023,"cited_by_count":22},{"year":2022,"cited_by_count":22},{"year":2021,"cited_by_count":37},{"year":2020,"cited_by_count":20},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}