{"id":"https://openalex.org/W4412531925","doi":"https://doi.org/10.1186/s13321-025-01045-w","title":"The topology of molecular representations and its influence on machine learning performance","display_name":"The topology of molecular representations and its influence on machine learning performance","publication_year":2025,"publication_date":"2025-07-21","ids":{"openalex":"https://openalex.org/W4412531925","doi":"https://doi.org/10.1186/s13321-025-01045-w","pmid":"https://pubmed.ncbi.nlm.nih.gov/40691856"},"language":"en","primary_location":{"id":"doi:10.1186/s13321-025-01045-w","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-025-01045-w","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-025-01045-w","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","datacite","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-025-01045-w","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5094178932","display_name":"Florian Rottach","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Florian Rottach","raw_affiliation_strings":["Central Data Science, Boehringer Ingelheim GmbH, Biberach/Riss, Germany. florian.rottach@boehringer-ingelheim.com","School of Medicine, University of T\u00fcbingen, T\u00fcbingen, Germany. florian.rottach@boehringer-ingelheim.com"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Central Data Science, Boehringer Ingelheim GmbH, Biberach/Riss, Germany. florian.rottach@boehringer-ingelheim.com","institution_ids":[]},{"raw_affiliation_string":"School of Medicine, University of T\u00fcbingen, T\u00fcbingen, Germany. florian.rottach@boehringer-ingelheim.com","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067734121","display_name":"Sebastian Schieferdecker","orcid":"https://orcid.org/0000-0002-4016-7409"},"institutions":[{"id":"https://openalex.org/I1330995197","display_name":"Boehringer Ingelheim (Germany)","ror":"https://ror.org/00q32j219","country_code":"DE","type":"company","lineage":["https://openalex.org/I1330995197"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sebastian Schieferdecker","raw_affiliation_strings":["Computational Toxicology, Boehringer Ingelheim Pharma GmbH & Co. KG, Biberach/Riss, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Toxicology, Boehringer Ingelheim Pharma GmbH & Co. KG, Biberach/Riss, Germany","institution_ids":["https://openalex.org/I1330995197"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014921416","display_name":"Carsten Eickhoff","orcid":"https://orcid.org/0000-0001-9895-4061"},"institutions":[{"id":"https://openalex.org/I8087733","display_name":"University of T\u00fcbingen","ror":"https://ror.org/03a1kwz48","country_code":"DE","type":"education","lineage":["https://openalex.org/I8087733"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Carsten Eickhoff","raw_affiliation_strings":["School of Medicine, University of T\u00fcbingen, T\u00fcbingen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Medicine, University of T\u00fcbingen, T\u00fcbingen, Germany","institution_ids":["https://openalex.org/I8087733"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5094178932"],"corresponding_institution_ids":[],"apc_list":{"value":1290,"currency":"GBP","value_usd":1582},"apc_paid":{"value":1290,"currency":"GBP","value_usd":1582},"fwci":3.9525,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.9407162,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"17","issue":"1","first_page":"109","last_page":"109"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9998999834060669,"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":0.9998999834060669,"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":0.993399977684021,"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"}},{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.9815999865531921,"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":0.7132092714309692},{"id":"https://openalex.org/keywords/topology","display_name":"Topology (electrical circuits)","score":0.570431113243103},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4087987244129181},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4065989553928375},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37333351373672485},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09724023938179016},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.06717678904533386}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7132092714309692},{"id":"https://openalex.org/C184720557","wikidata":"https://www.wikidata.org/wiki/Q7825049","display_name":"Topology (electrical circuits)","level":2,"score":0.570431113243103},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4087987244129181},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4065989553928375},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37333351373672485},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09724023938179016},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.06717678904533386}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1186/s13321-025-01045-w","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-025-01045-w","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-025-01045-w","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:40691856","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40691856","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:a988feb44e12476c98b46f2ba0c2fad3","is_oa":true,"landing_page_url":"https://doaj.org/article/a988feb44e12476c98b46f2ba0c2fad3","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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Cheminformatics, Vol 17, Iss 1, Pp 1-25 (2025)","raw_type":"article"},{"id":"pmh:oai:europepmc.org:11093445","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12281805","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"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":null,"raw_type":"Text"},{"id":"doi:10.15496/publikation-119762","is_oa":true,"landing_page_url":"https://doi.org/10.15496/publikation-119762","pdf_url":null,"source":{"id":"https://openalex.org/S7407053000","display_name":"Universit\u00e4tsbibliothek T\u00fcbingen","issn_l":null,"issn":[],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.1186/s13321-025-01045-w","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-025-01045-w","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-025-01045-w","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/F4320321112","display_name":"Eberhard Karls Universit\u00e4t T\u00fcbingen","ror":"https://ror.org/03a1kwz48"},{"id":"https://openalex.org/F4320333403","display_name":"Universit\u00e4tsklinikum T\u00fcbingen","ror":"https://ror.org/00pjgxh97"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412531925.pdf","grobid_xml":"https://content.openalex.org/works/W4412531925.grobid-xml"},"referenced_works_count":81,"referenced_works":["https://openalex.org/W81555090","https://openalex.org/W1975147762","https://openalex.org/W1979273469","https://openalex.org/W1988037271","https://openalex.org/W1991566301","https://openalex.org/W1998255116","https://openalex.org/W2025556769","https://openalex.org/W2028569884","https://openalex.org/W2034541070","https://openalex.org/W2038287971","https://openalex.org/W2060531713","https://openalex.org/W2061937956","https://openalex.org/W2064440950","https://openalex.org/W2096864392","https://openalex.org/W2107081909","https://openalex.org/W2151697120","https://openalex.org/W2159887157","https://openalex.org/W2177317049","https://openalex.org/W2200017991","https://openalex.org/W2547330766","https://openalex.org/W2754478492","https://openalex.org/W2777416523","https://openalex.org/W2892349988","https://openalex.org/W2892377642","https://openalex.org/W2905600194","https://openalex.org/W2936324353","https://openalex.org/W2937307539","https://openalex.org/W2944466104","https://openalex.org/W2950128007","https://openalex.org/W2963192955","https://openalex.org/W2966357564","https://openalex.org/W2970175280","https://openalex.org/W2979826702","https://openalex.org/W2997578645","https://openalex.org/W2998679948","https://openalex.org/W2999001809","https://openalex.org/W3006781192","https://openalex.org/W3009321976","https://openalex.org/W3009999522","https://openalex.org/W3012107310","https://openalex.org/W3012585755","https://openalex.org/W3023042104","https://openalex.org/W3023204497","https://openalex.org/W3035302862","https://openalex.org/W3045928028","https://openalex.org/W3087318293","https://openalex.org/W3104335155","https://openalex.org/W3116202926","https://openalex.org/W3187980261","https://openalex.org/W3194368700","https://openalex.org/W3195831412","https://openalex.org/W3198796775","https://openalex.org/W3202868818","https://openalex.org/W3206571981","https://openalex.org/W3210813272","https://openalex.org/W4206367183","https://openalex.org/W4211238337","https://openalex.org/W4213070269","https://openalex.org/W4293199734","https://openalex.org/W4296035488","https://openalex.org/W4310222678","https://openalex.org/W4310273071","https://openalex.org/W4310603653","https://openalex.org/W4313485929","https://openalex.org/W4318952054","https://openalex.org/W4362503491","https://openalex.org/W4366188919","https://openalex.org/W4367049415","https://openalex.org/W4377232456","https://openalex.org/W4382982253","https://openalex.org/W4385501835","https://openalex.org/W4387617009","https://openalex.org/W4387874094","https://openalex.org/W4393152099","https://openalex.org/W4400831251","https://openalex.org/W6601473709","https://openalex.org/W6602311867","https://openalex.org/W6605656274","https://openalex.org/W6636364444","https://openalex.org/W6851816929","https://openalex.org/W6894079230"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"Advancements":[0],"in":[1],"cheminformatics":[2],"have":[3],"led":[4],"to":[5,26,120,133,163],"numerous":[6],"methods":[7],"for":[8,67],"encoding":[9],"molecules":[10],"numerically.":[11],"The":[12],"choice":[13],"of":[14,22,82,91,111,141,149],"molecular":[15,125,150],"representation":[16,34],"impacts":[17],"the":[18,32,80,88,92,108,131,139,145],"accuracy":[19],"and":[20,30,40,123,144],"generalizability":[21],"learning":[23,52,114,147],"algorithms":[24],"applied":[25],"chemical":[27],"datasets.":[28],"Designing":[29],"selecting":[31],"appropriate":[33],"often":[35],"lacks":[36],"a":[37,76,117],"systematic":[38],"approach":[39],"follows":[41],"computationally":[42],"exhaustive":[43],"empirical":[44,136],"testing.":[45],"Moreover,":[46],"research":[47,129,157],"has":[48],"shown":[49],"that":[50,78,101],"deep":[51],"models":[53],"do":[54],"not":[55],"substantially":[56],"outperform":[57],"traditional":[58],"approaches":[59],"across":[60],"many":[61],"tasks":[62],"with":[63,107],"no":[64],"clear":[65],"explanation":[66],"this":[68,71],"shortfall.":[69],"In":[70,152],"work,":[72],"we":[73,99,154],"present":[74],"TopoLearn,":[75],"model":[77],"predicts":[79],"effectiveness":[81],"representations":[83],"on":[84,87],"datasets":[85],"based":[86],"topological":[89],"characteristics":[90],"corresponding":[93],"feature":[94,142],"space.":[95],"Using":[96],"interpretability":[97],"techniques,":[98],"find":[100],"persistent":[102],"homology":[103],"descriptors":[104],"are":[105],"linked":[106],"error":[109],"metrics":[110],"trained":[112],"machine":[113,146],"models,":[115],"offering":[116],"new":[118],"method":[119],"better":[121],"understand":[122],"select":[124],"representations.Scientific":[126],"contribution":[127],"Our":[128],"is":[130],"first":[132],"establish":[134],"an":[135],"connection":[137],"between":[138],"topology":[140],"spaces":[143],"performance":[148],"representations.":[151],"addition,":[153],"facilitate":[155],"future":[156],"endeavors":[158],"by":[159],"providing":[160],"open":[161],"access":[162],"our":[164],"developed":[165],"model.":[166]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-25T08:17:42.794288","created_date":"2025-10-10T00:00:00"}