{"id":"https://openalex.org/W3113096756","doi":"https://doi.org/10.1186/s13321-021-00500-8","title":"Learning chemistry: exploring the suitability of machine learning for the task of structure-based chemical ontology classification","display_name":"Learning chemistry: exploring the suitability of machine learning for the task of structure-based chemical ontology classification","publication_year":2021,"publication_date":"2021-03-16","ids":{"openalex":"https://openalex.org/W3113096756","doi":"https://doi.org/10.1186/s13321-021-00500-8","mag":"3113096756","pmid":"https://pubmed.ncbi.nlm.nih.gov/33726837"},"language":"en","primary_location":{"id":"doi:10.1186/s13321-021-00500-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-021-00500-8","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-021-00500-8","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"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":"Journal of Cheminformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-021-00500-8","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044072805","display_name":"Janna Hastings","orcid":"https://orcid.org/0000-0002-3469-4923"},"institutions":[{"id":"https://openalex.org/I95793202","display_name":"Otto-von-Guericke-Universit\u00e4t Magdeburg","ror":"https://ror.org/00ggpsq73","country_code":"DE","type":"education","lineage":["https://openalex.org/I95793202"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Janna Hastings","raw_affiliation_strings":["Department of Computer Science, Otto-von-Guericke University of Magdeburg, Magdeburg, Germany. hastings@ovgu.de","Department of Computer Science, Otto-von-Guericke University of Magdeburg, Magdeburg, Germany"],"raw_orcid":"https://orcid.org/0000-0002-3469-4923","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Otto-von-Guericke University of Magdeburg, Magdeburg, Germany. hastings@ovgu.de","institution_ids":["https://openalex.org/I95793202"]},{"raw_affiliation_string":"Department of Computer Science, Otto-von-Guericke University of Magdeburg, Magdeburg, Germany","institution_ids":["https://openalex.org/I95793202"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084910607","display_name":"Martin Glauer","orcid":"https://orcid.org/0000-0001-6772-1943"},"institutions":[{"id":"https://openalex.org/I95793202","display_name":"Otto-von-Guericke-Universit\u00e4t Magdeburg","ror":"https://ror.org/00ggpsq73","country_code":"DE","type":"education","lineage":["https://openalex.org/I95793202"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Martin Glauer","raw_affiliation_strings":["Department of Computer Science, Otto-von-Guericke University of Magdeburg, Magdeburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Otto-von-Guericke University of Magdeburg, Magdeburg, Germany","institution_ids":["https://openalex.org/I95793202"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071777525","display_name":"Adel Memariani","orcid":"https://orcid.org/0000-0002-8368-7658"},"institutions":[{"id":"https://openalex.org/I95793202","display_name":"Otto-von-Guericke-Universit\u00e4t Magdeburg","ror":"https://ror.org/00ggpsq73","country_code":"DE","type":"education","lineage":["https://openalex.org/I95793202"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Adel Memariani","raw_affiliation_strings":["Department of Computer Science, Otto-von-Guericke University of Magdeburg, Magdeburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Otto-von-Guericke University of Magdeburg, Magdeburg, Germany","institution_ids":["https://openalex.org/I95793202"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080272127","display_name":"Fabian Neuhaus","orcid":"https://orcid.org/0000-0002-1058-3102"},"institutions":[{"id":"https://openalex.org/I95793202","display_name":"Otto-von-Guericke-Universit\u00e4t Magdeburg","ror":"https://ror.org/00ggpsq73","country_code":"DE","type":"education","lineage":["https://openalex.org/I95793202"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Fabian Neuhaus","raw_affiliation_strings":["Department of Computer Science, Otto-von-Guericke University of Magdeburg, Magdeburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Otto-von-Guericke University of Magdeburg, Magdeburg, Germany","institution_ids":["https://openalex.org/I95793202"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040001719","display_name":"Till Mossakowski","orcid":"https://orcid.org/0000-0002-8938-5204"},"institutions":[{"id":"https://openalex.org/I95793202","display_name":"Otto-von-Guericke-Universit\u00e4t Magdeburg","ror":"https://ror.org/00ggpsq73","country_code":"DE","type":"education","lineage":["https://openalex.org/I95793202"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Till Mossakowski","raw_affiliation_strings":["Department of Computer Science, Otto-von-Guericke University of Magdeburg, Magdeburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Otto-von-Guericke University of Magdeburg, Magdeburg, Germany","institution_ids":["https://openalex.org/I95793202"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5044072805"],"corresponding_institution_ids":["https://openalex.org/I95793202"],"apc_list":{"value":1290,"currency":"GBP","value_usd":1582},"apc_paid":{"value":1497,"currency":"EUR","value_usd":1614},"fwci":3.1848,"has_fulltext":true,"cited_by_count":29,"citation_normalized_percentile":{"value":0.92518167,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"13","issue":"1","first_page":"23","last_page":"23"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9998000264167786,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9854000210762024,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.9851999878883362,"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/cheminformatics","display_name":"Cheminformatics","score":0.813637375831604},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7750521302223206},{"id":"https://openalex.org/keywords/pubchem","display_name":"PubChem","score":0.6855778694152832},{"id":"https://openalex.org/keywords/chemical-space","display_name":"Chemical space","score":0.6534100770950317},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6486154794692993},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6146341562271118},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5436649918556213},{"id":"https://openalex.org/keywords/ontology","display_name":"Ontology","score":0.5236375331878662},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4243845045566559},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.18464314937591553},{"id":"https://openalex.org/keywords/drug-discovery","display_name":"Drug discovery","score":0.12369006872177124},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.10257917642593384}],"concepts":[{"id":"https://openalex.org/C68762167","wikidata":"https://www.wikidata.org/wiki/Q910164","display_name":"Cheminformatics","level":2,"score":0.813637375831604},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7750521302223206},{"id":"https://openalex.org/C158180186","wikidata":"https://www.wikidata.org/wiki/Q278487","display_name":"PubChem","level":2,"score":0.6855778694152832},{"id":"https://openalex.org/C99726746","wikidata":"https://www.wikidata.org/wiki/Q906396","display_name":"Chemical space","level":3,"score":0.6534100770950317},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6486154794692993},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6146341562271118},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5436649918556213},{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.5236375331878662},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4243845045566559},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.18464314937591553},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.12369006872177124},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.10257917642593384},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1186/s13321-021-00500-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-021-00500-8","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-021-00500-8","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"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":"Journal of Cheminformatics","raw_type":"journal-article"},{"id":"pmid:33726837","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33726837","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":"Journal of cheminformatics","raw_type":null},{"id":"pmh:oai:doaj.org/article:409ce7845df04a41a7f2ef94ba45e76a","is_oa":true,"landing_page_url":"https://doaj.org/article/409ce7845df04a41a7f2ef94ba45e76a","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Cheminformatics, Vol 13, Iss 1, Pp 1-20 (2021)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:7962259","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/7962259","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"J Cheminform","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/s13321-021-00500-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-021-00500-8","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-021-00500-8","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"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":"Journal of Cheminformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320335829","display_name":"Otto von Guericke University Magdeburg","ror":"https://ror.org/00ggpsq73"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3113096756.pdf","grobid_xml":"https://content.openalex.org/works/W3113096756.grobid-xml"},"referenced_works_count":57,"referenced_works":["https://openalex.org/W74015016","https://openalex.org/W1484151351","https://openalex.org/W1503729935","https://openalex.org/W1508604947","https://openalex.org/W1852306145","https://openalex.org/W1910839236","https://openalex.org/W1935434993","https://openalex.org/W1965091013","https://openalex.org/W1975147762","https://openalex.org/W1980352552","https://openalex.org/W1990442426","https://openalex.org/W2001869885","https://openalex.org/W2033377040","https://openalex.org/W2064675550","https://openalex.org/W2098173334","https://openalex.org/W2114940395","https://openalex.org/W2116341502","https://openalex.org/W2130468043","https://openalex.org/W2139315672","https://openalex.org/W2143916531","https://openalex.org/W2147489358","https://openalex.org/W2150766729","https://openalex.org/W2155459813","https://openalex.org/W2157058953","https://openalex.org/W2157331557","https://openalex.org/W2161919540","https://openalex.org/W2294320291","https://openalex.org/W2396132865","https://openalex.org/W2507974895","https://openalex.org/W2510317721","https://openalex.org/W2548357532","https://openalex.org/W2578240541","https://openalex.org/W2582187633","https://openalex.org/W2769423117","https://openalex.org/W2792163150","https://openalex.org/W2801991413","https://openalex.org/W2809634777","https://openalex.org/W2891967723","https://openalex.org/W2895677720","https://openalex.org/W2896457183","https://openalex.org/W2899070097","https://openalex.org/W2901212243","https://openalex.org/W2946752867","https://openalex.org/W2950128007","https://openalex.org/W2970862234","https://openalex.org/W2990351990","https://openalex.org/W3039185146","https://openalex.org/W3041064262","https://openalex.org/W3099732023","https://openalex.org/W3108604517","https://openalex.org/W3202344023","https://openalex.org/W3206742358","https://openalex.org/W3208790722","https://openalex.org/W4233659707","https://openalex.org/W4255318870","https://openalex.org/W6683413043","https://openalex.org/W6702248584"],"related_works":["https://openalex.org/W2460225311","https://openalex.org/W1964976889","https://openalex.org/W4382246684","https://openalex.org/W1990683923","https://openalex.org/W4387845407","https://openalex.org/W2151971404","https://openalex.org/W2770765812","https://openalex.org/W2902857455","https://openalex.org/W4207004502","https://openalex.org/W164221359"],"abstract_inverted_index":{"Chemical":[0,39],"data":[1,26,107],"is":[2,61,77,95,191,210],"increasingly":[3],"openly":[4],"available":[5],"in":[6,71],"databases":[7],"such":[8,28,82,173],"as":[9,18,81,115,174,229,231],"PubChem,":[10],"which":[11,111],"contains":[12],"approximately":[13],"110":[14],"million":[15],"compound":[16],"entries":[17],"of":[19,25,44,55,65,90,181,197],"February":[20],"2021.":[21],"With":[22],"the":[23,30,56,87,153,188],"availability":[24],"at":[27],"scale,":[29],"burden":[31],"has":[32],"shifted":[33],"to":[34,86,103,193,206,213],"organisation,":[35],"analysis":[36],"and":[37,53,80,141,148,159,209,226],"interpretation.":[38],"ontologies":[40],"provide":[41],"structured":[42],"classifications":[43],"chemical":[45,58,67,92,106,109,154,163,185],"entities":[46],"that":[47,100,169],"can":[48,112],"be":[49,113],"used":[50,70],"for":[51,98,129,152,218],"navigation":[52],"filtering":[54],"large":[57],"space.":[59],"ChEBI":[60,76],"a":[62,66,96,116,215],"prominent":[63],"example":[64],"ontology,":[68],"widely":[69],"life":[72],"science":[73],"contexts.":[74],"However,":[75],"manually":[78],"maintained":[79],"cannot":[83],"easily":[84],"scale":[85],"full":[88],"scope":[89],"public":[91],"data.":[93],"There":[94],"need":[97],"tools":[99],"are":[101],"able":[102,192,212],"automatically":[104],"classify":[105],"into":[108],"ontologies,":[110],"framed":[114],"hierarchical":[117],"multi-class":[118],"classification":[119],"problem.":[120],"In":[121],"this":[122,130],"paper":[123],"we":[124],"evaluate":[125],"machine":[126],"learning":[127,134,171],"approaches":[128,151,172],"task,":[131],"comparing":[132],"different":[133,149],"frameworks":[135],"including":[136,156,235],"logistic":[137,175],"regression,":[138],"decision":[139],"trees":[140],"long":[142],"short-term":[143],"memory":[144],"artificial":[145],"neural":[146,189],"networks,":[147],"encoding":[150,161],"structures,":[155],"cheminformatics":[157],"fingerprints":[158],"character-based":[160],"from":[162],"line":[164],"notation":[165],"representations.":[166],"We":[167],"find":[168],"classical":[170],"regression":[176],"perform":[177],"well":[178,230],"with":[179],"sets":[180,196],"relatively":[182],"specific,":[183],"disjoint":[184],"classes,":[186],"while":[187],"network":[190,233],"handle":[194],"larger":[195],"overlapping":[198],"classes":[199],"but":[200],"needs":[201],"more":[202],"examples":[203],"per":[204],"class":[205,216],"learn":[207],"from,":[208],"not":[211],"make":[214],"prediction":[217],"every":[219],"molecule.":[220],"Future":[221],"work":[222],"will":[223],"explore":[224],"hybrid":[225],"ensemble":[227],"approaches,":[228],"alternative":[232],"architectures":[234],"neuro-symbolic":[236],"approaches.":[237]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":5}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}