{"id":"https://openalex.org/W3029344183","doi":"https://doi.org/10.1186/s13321-020-00434-7","title":"Assessing the information content of structural and protein\u2013ligand interaction representations for the classification of kinase inhibitor binding modes via machine learning and active learning","display_name":"Assessing the information content of structural and protein\u2013ligand interaction representations for the classification of kinase inhibitor binding modes via machine learning and active learning","publication_year":2020,"publication_date":"2020-05-24","ids":{"openalex":"https://openalex.org/W3029344183","doi":"https://doi.org/10.1186/s13321-020-00434-7","mag":"3029344183","pmid":"https://pubmed.ncbi.nlm.nih.gov/33431025"},"language":"en","primary_location":{"id":"doi:10.1186/s13321-020-00434-7","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-020-00434-7","pdf_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/s13321-020-00434-7","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/track/pdf/10.1186/s13321-020-00434-7","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5038390721","display_name":"Raquel Rodr\u00edguez-P\u00e9rez","orcid":"https://orcid.org/0000-0002-2992-3402"},"institutions":[{"id":"https://openalex.org/I135140700","display_name":"University of Bonn","ror":"https://ror.org/041nas322","country_code":"DE","type":"education","lineage":["https://openalex.org/I135140700"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Raquel Rodr\u00edguez-P\u00e9rez","raw_affiliation_strings":["Department of Life Science Informatics, B-IT, LIMES Program Unit Chemical Biology and Medicinal Chemistry, Rheinische Friedrich-Wilhelms-Universit\u00e4t, Endenicher Allee 19c, 53115, Bonn, Germany"],"affiliations":[{"raw_affiliation_string":"Department of Life Science Informatics, B-IT, LIMES Program Unit Chemical Biology and Medicinal Chemistry, Rheinische Friedrich-Wilhelms-Universit\u00e4t, Endenicher Allee 19c, 53115, Bonn, Germany","institution_ids":["https://openalex.org/I135140700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089864495","display_name":"Filip Miljkovi\u0107","orcid":"https://orcid.org/0000-0001-5365-505X"},"institutions":[{"id":"https://openalex.org/I135140700","display_name":"University of Bonn","ror":"https://ror.org/041nas322","country_code":"DE","type":"education","lineage":["https://openalex.org/I135140700"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Filip Miljkovi\u0107","raw_affiliation_strings":["Department of Life Science Informatics, B-IT, LIMES Program Unit Chemical Biology and Medicinal Chemistry, Rheinische Friedrich-Wilhelms-Universit\u00e4t, Endenicher Allee 19c, 53115, Bonn, Germany"],"affiliations":[{"raw_affiliation_string":"Department of Life Science Informatics, B-IT, LIMES Program Unit Chemical Biology and Medicinal Chemistry, Rheinische Friedrich-Wilhelms-Universit\u00e4t, Endenicher Allee 19c, 53115, Bonn, Germany","institution_ids":["https://openalex.org/I135140700"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039926688","display_name":"J\u00fcrgen Bajorath","orcid":"https://orcid.org/0000-0002-0557-5714"},"institutions":[{"id":"https://openalex.org/I135140700","display_name":"University of Bonn","ror":"https://ror.org/041nas322","country_code":"DE","type":"education","lineage":["https://openalex.org/I135140700"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"J\u00fcrgen Bajorath","raw_affiliation_strings":["Department of Life Science Informatics, B-IT, LIMES Program Unit Chemical Biology and Medicinal Chemistry, Rheinische Friedrich-Wilhelms-Universit\u00e4t, Endenicher Allee 19c, 53115, Bonn, Germany. bajorath@bit.uni-bonn.de","Department of Life Science Informatics, B-IT, LIMES Program Unit Chemical Biology and Medicinal Chemistry, Rheinische Friedrich-Wilhelms-Universit\u00e4t, Endenicher Allee 19c, 53115, Bonn, Germany"],"affiliations":[{"raw_affiliation_string":"Department of Life Science Informatics, B-IT, LIMES Program Unit Chemical Biology and Medicinal Chemistry, Rheinische Friedrich-Wilhelms-Universit\u00e4t, Endenicher Allee 19c, 53115, Bonn, Germany. bajorath@bit.uni-bonn.de","institution_ids":[]},{"raw_affiliation_string":"Department of Life Science Informatics, B-IT, LIMES Program Unit Chemical Biology and Medicinal Chemistry, Rheinische Friedrich-Wilhelms-Universit\u00e4t, Endenicher Allee 19c, 53115, Bonn, Germany","institution_ids":["https://openalex.org/I135140700"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5038390721"],"corresponding_institution_ids":["https://openalex.org/I135140700"],"apc_list":{"value":1290,"currency":"GBP","value_usd":1582},"apc_paid":{"value":1290,"currency":"GBP","value_usd":1582},"fwci":2.3102,"has_fulltext":true,"cited_by_count":22,"citation_normalized_percentile":{"value":0.90805902,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"12","issue":"1","first_page":"36","last_page":"36"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":1.0,"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":1.0,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.9939000010490417,"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/T10911","display_name":"Chemical Synthesis and Analysis","score":0.9927999973297119,"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/computer-science","display_name":"Computer science","score":0.5863341093063354},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.580424964427948},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5095603466033936},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.49658137559890747},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.467639684677124},{"id":"https://openalex.org/keywords/virtual-screening","display_name":"Virtual screening","score":0.4281827211380005},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.4160923361778259},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.34908339381217957},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32633477449417114},{"id":"https://openalex.org/keywords/drug-discovery","display_name":"Drug discovery","score":0.3062190115451813},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.18726631999015808},{"id":"https://openalex.org/keywords/biochemistry","display_name":"Biochemistry","score":0.18665730953216553},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.14237380027770996}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5863341093063354},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.580424964427948},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5095603466033936},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.49658137559890747},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.467639684677124},{"id":"https://openalex.org/C103697762","wikidata":"https://www.wikidata.org/wiki/Q4112105","display_name":"Virtual screening","level":3,"score":0.4281827211380005},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4160923361778259},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.34908339381217957},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32633477449417114},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.3062190115451813},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.18726631999015808},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.18665730953216553},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.14237380027770996},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1186/s13321-020-00434-7","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-020-00434-7","pdf_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/s13321-020-00434-7","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:33431025","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33431025","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:67125e5d2eec46c6817ddc057c91b2ee","is_oa":true,"landing_page_url":"https://doaj.org/article/67125e5d2eec46c6817ddc057c91b2ee","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":"Journal of Cheminformatics, Vol 12, Iss 1, Pp 1-14 (2020)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:7245824","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/7245824","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":"J Cheminform","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/s13321-020-00434-7","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-020-00434-7","pdf_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/s13321-020-00434-7","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":[{"id":"https://openalex.org/G1865580006","display_name":null,"funder_award_id":"676434","funder_id":"https://openalex.org/F4320338335","funder_display_name":"H2020 European Research Council"},{"id":"https://openalex.org/G2689612763","display_name":null,"funder_award_id":"Marie","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G4956428346","display_name":null,"funder_award_id":"Horizon 2020 research and innovatio","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G5036817778","display_name":null,"funder_award_id":"European Union's Horizon 2020 research and innov","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G5103510783","display_name":null,"funder_award_id":"676434","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8051717526","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8318064016","display_name":null,"funder_award_id":"Horizon","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8633428685","display_name":null,"funder_award_id":"European Union's Horizon 2020 research and innovat","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320324900","display_name":"Rheinische Friedrich-Wilhelms-Universit\u00e4t Bonn","ror":"https://ror.org/041nas322"},{"id":"https://openalex.org/F4320338335","display_name":"H2020 European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3029344183.pdf","grobid_xml":"https://content.openalex.org/works/W3029344183.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W307744830","https://openalex.org/W1480376833","https://openalex.org/W1891334654","https://openalex.org/W1965555277","https://openalex.org/W1971606559","https://openalex.org/W1975436091","https://openalex.org/W1985748743","https://openalex.org/W1988037271","https://openalex.org/W1995875735","https://openalex.org/W2004652899","https://openalex.org/W2021552823","https://openalex.org/W2026501736","https://openalex.org/W2079398727","https://openalex.org/W2096729078","https://openalex.org/W2101234009","https://openalex.org/W2101807845","https://openalex.org/W2109553965","https://openalex.org/W2117897510","https://openalex.org/W2143482176","https://openalex.org/W2156373035","https://openalex.org/W2168045053","https://openalex.org/W2187089797","https://openalex.org/W2189824412","https://openalex.org/W2211136176","https://openalex.org/W2225513621","https://openalex.org/W2563678022","https://openalex.org/W2570764145","https://openalex.org/W2593984551","https://openalex.org/W2773242491","https://openalex.org/W2784662425","https://openalex.org/W2787894218","https://openalex.org/W2895061638","https://openalex.org/W2903778222","https://openalex.org/W2911964244","https://openalex.org/W2915792373","https://openalex.org/W2949071206","https://openalex.org/W2970198780"],"related_works":["https://openalex.org/W3180887190","https://openalex.org/W2320211095","https://openalex.org/W3193043704","https://openalex.org/W4386259002","https://openalex.org/W2059230675","https://openalex.org/W2376003823","https://openalex.org/W4394984040","https://openalex.org/W4402273478","https://openalex.org/W2594726310","https://openalex.org/W2355193834"],"abstract_inverted_index":{"For":[0,220],"kinase":[1,16,91,229],"inhibitors,":[2],"X-ray":[3],"crystallography":[4],"has":[5],"revealed":[6],"different":[7,41,85],"types":[8],"of":[9,38,57,90,105,128,143,179,189,197,224,227,234],"binding":[10,20,42,80,93,152,225],"modes.":[11,43],"Currently,":[12],"more":[13,151],"than":[14,118,155],"2000":[15],"inhibitors":[17,39,230],"with":[18,40,97],"known":[19],"modes":[21,94,226],"are":[22],"available,":[23],"which":[24],"makes":[25],"it":[26],"possible":[27],"to":[28,50,78,110,137,149,160,213],"derive":[29],"and":[30,52,66],"test":[31],"machine":[32],"learning":[33,122,184,202],"models":[34,163,181,214],"for":[35,173],"the":[36,54,139,177,232],"prediction":[37,48,210,223],"We":[44],"have":[45],"addressed":[46],"this":[47],"task":[49],"evaluate":[51],"compare":[53],"information":[55,125,141,154,195],"content":[56,142,196],"distinct":[58,144],"molecular":[59],"representations":[60],"including":[61],"protein-ligand":[62],"interaction":[63,82],"fingerprints":[64,70],"(IFPs)":[65],"compound":[67],"structure-based":[68],"structural":[69],"(i.e.,":[71],"atom":[72,111,156,174,217],"environment/fragment":[73],"fingerprints).":[74],"IFPs":[75,106,146,198],"were":[76,95,147,168],"designed":[77],"capture":[79,150],"mode-specific":[81],"patterns":[83],"at":[84],"resolution":[86],"levels.":[87],"Accurate":[88],"predictions":[89],"inhibitor":[92],"achieved":[96],"random":[98],"forests":[99],"using":[100,216],"both":[101],"representations.":[102,145],"The":[103],"performance":[104],"was":[107,131],"consistently":[108],"superior":[109],"environment":[112,157,175,218],"fingerprints,":[113,158,176],"albeit":[114],"only":[115,203],"by":[116,200],"less":[117],"10%.":[119],"An":[120],"active":[121,183,201],"strategy":[123],"applying":[124],"entropy-based":[126,187],"selection":[127,188],"training":[129,166,191],"instances":[130,167],"applied":[132],"as":[133],"a":[134],"diagnostic":[135],"approach":[136],"assess":[138],"relative":[140],"found":[148],"mode-relevant":[153],"leading":[159],"highly":[161,238],"predictive":[162],"even":[164],"when":[165],"randomly":[169],"selected.":[170],"By":[171],"contrast,":[172],"derivation":[178],"accurate":[180],"via":[182],"depended":[185],"on":[186,231],"informative":[190],"compounds.":[192],"Notably,":[193],"higher":[194],"confirmed":[199],"resulted":[204],"in":[205,208],"small":[206],"improvements":[207],"global":[209],"accuracy":[211],"compared":[212],"derived":[215],"fingerprints.":[219],"practical":[221],"applications,":[222],"new":[228],"basis":[233],"chemical":[235],"structure":[236],"is":[237],"attractive.":[239]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}