{"id":"https://openalex.org/W7204931363","doi":"https://doi.org/10.48550/arxiv.2608.29886","title":"Structural Hierarchy and Geometry in Molecular Representation Learning","display_name":"Structural Hierarchy and Geometry in Molecular Representation Learning","publication_year":2026,"publication_date":"2026-08-30","ids":{"openalex":"https://openalex.org/W7204931363","doi":"https://doi.org/10.48550/arxiv.2608.29886"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.29886","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.29886","pdf_url":"https://arxiv.org/pdf/2608.29886","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.29886","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5148868339","display_name":"David Sulu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Sulu, David","raw_affiliation_strings":["Department of Intelligent Systems , Delft University of Technology , Delft , The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Intelligent Systems , Delft University of Technology , Delft , The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120185735","display_name":"Lorenzo Di Fruscia","orcid":"https://orcid.org/0009-0009-4746-2070","observed_orcids":["https://orcid.org/0009-0009-4746-2070"]},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Di Fruscia, Lorenzo","raw_affiliation_strings":["Department of Intelligent Systems , Delft University of Technology , Delft , The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Intelligent Systems , Delft University of Technology , Delft , The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001961922","display_name":"Jana M. Weber","orcid":"https://orcid.org/0000-0002-2867-0087","observed_orcids":["https://orcid.org/0000-0002-2867-0087"]},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Weber, Jana M.","raw_affiliation_strings":["Department of Intelligent Systems , Delft University of Technology , Delft , The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Intelligent Systems , Delft University of Technology , Delft , The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98358874"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9843999743461609,"subfield":{"id":"https://openalex.org/subfields/3002","display_name":"Drug Discovery"},"field":{"id":"https://openalex.org/fields/30","display_name":"Pharmacology, Toxicology and Pharmaceutics"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9843999743461609,"subfield":{"id":"https://openalex.org/subfields/3002","display_name":"Drug Discovery"},"field":{"id":"https://openalex.org/fields/30","display_name":"Pharmacology, Toxicology and Pharmaceutics"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.004800000227987766,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.002300000051036477,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/bemis-murcko-scaffolds","display_name":"Bemis-Murcko scaffolds","score":0.8790000081062317},{"id":"https://openalex.org/keywords/molecular-embeddings","display_name":"molecular embeddings","score":0.7099999785423279},{"id":"https://openalex.org/keywords/embedding-geometry","display_name":"embedding geometry","score":0.8479999899864197},{"id":"https://openalex.org/keywords/molecular-property-prediction","display_name":"molecular property prediction","score":0.765999972820282},{"id":"https://openalex.org/keywords/hierarchy","display_name":"hierarchy","score":0.45399999618530273},{"id":"https://openalex.org/keywords/data-augmentation","display_name":"data augmentation","score":0.4350000023841858}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7815999984741211},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.6759999990463257},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5906000137329102},{"id":"https://openalex.org/C129782007","wikidata":"https://www.wikidata.org/wiki/Q162886","display_name":"Euclidean geometry","level":2,"score":0.5870000123977661},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.5390999913215637},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5034000277519226},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4717000126838684},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.4578000009059906},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4555000066757202},{"id":"https://openalex.org/C5667645","wikidata":"https://www.wikidata.org/wiki/Q217255","display_name":"Lorentz transformation","level":2,"score":0.421099990606308},{"id":"https://openalex.org/C178910836","wikidata":"https://www.wikidata.org/wiki/Q2196961","display_name":"Molecular model","level":2,"score":0.412200003862381},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.3549000024795532},{"id":"https://openalex.org/C193547582","wikidata":"https://www.wikidata.org/wiki/Q911331","display_name":"Molecular geometry","level":3,"score":0.3547999858856201},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33629998564720154},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3325999975204468},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.328900009393692},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.3212999999523163},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3140000104904175},{"id":"https://openalex.org/C2780841128","wikidata":"https://www.wikidata.org/wiki/Q5073781","display_name":"Characterization (materials science)","level":2,"score":0.30570000410079956},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.27459999918937683},{"id":"https://openalex.org/C32909587","wikidata":"https://www.wikidata.org/wiki/Q11369","display_name":"Molecule","level":2,"score":0.2732999920845032},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.2653999924659729},{"id":"https://openalex.org/C59593255","wikidata":"https://www.wikidata.org/wiki/Q901663","display_name":"Molecular dynamics","level":2,"score":0.25209999084472656},{"id":"https://openalex.org/C164923092","wikidata":"https://www.wikidata.org/wiki/Q3705921","display_name":"Molecular descriptor","level":3,"score":0.2517000138759613}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.29886","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.29886","pdf_url":"https://arxiv.org/pdf/2608.29886","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.29886","doi":"https://doi.org/10.48550/arxiv.2608.29886","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.29886","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.29886","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.29886","pdf_url":"https://arxiv.org/pdf/2608.29886","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321012","display_name":"Technische Universiteit Delft","ror":"https://ror.org/02e2c7k09"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204931363.pdf","grobid_xml":"https://content.openalex.org/works/W7204931363.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W2060531713","https://openalex.org/W2199357291","https://openalex.org/W2594183968","https://openalex.org/W2618798060","https://openalex.org/W2804622816","https://openalex.org/W2894175828","https://openalex.org/W2899070097","https://openalex.org/W2996604169","https://openalex.org/W3005680577","https://openalex.org/W4214868967","https://openalex.org/W4221151574","https://openalex.org/W4297808394","https://openalex.org/W4366460749","https://openalex.org/W4406086741"],"related_works":["https://openalex.org/W3133549463","https://openalex.org/W7128080919","https://openalex.org/W7211903526","https://openalex.org/W4385152156","https://openalex.org/W7167506092","https://openalex.org/W7137368690","https://openalex.org/W4403391227","https://openalex.org/W3136379721","https://openalex.org/W7196955819","https://openalex.org/W4321175689"],"abstract_inverted_index":{"Molecular":[0],"self-supervised":[1],"learning":[2],"uses":[3],"chemical":[4],"structures":[5],"to":[6,26,64],"guide":[7],"which":[8],"molecular":[9,29,76,97,133],"embeddings":[10,73],"should":[11],"be":[12],"similar.":[13],"We":[14,36],"study":[15],"whether":[16,39],"explicitly":[17,116],"encoding":[18],"a":[19,108,121],"molecule's":[20],"Bemis-Murcko":[21],"scaffold":[22,94],"and":[23,50,67,123],"using":[24],"it":[25],"supervise":[27],"the":[28,33,44,83,88,118,130,137],"embedding":[30,45,134],"changes":[31],"what":[32],"model":[34],"learns.":[35],"further":[37],"test":[38],"this":[40,142],"effect":[41,92],"depends":[42],"on":[43,79,87,96],"geometry":[46,106],"by":[47],"comparing":[48],"Euclidean":[49],"Lorentz":[51,102],"contrastive":[52],"objectives.":[53],"Across":[54],"two":[55],"augmentation":[56],"strengths,":[57],"scaffold-supervised":[58],"models":[59],"consistently":[60],"organize":[61],"molecules":[62],"according":[63],"both":[65],"identical":[66],"structurally":[68],"related":[69],"scaffolds.":[70],"The":[71,91],"resulting":[72],"also":[74],"improve":[75],"property":[77],"prediction":[78],"several":[80],"tasks,":[81],"while":[82,136],"exact":[84],"gains":[85],"depend":[86],"predicted":[89],"property.":[90],"of":[93,132,139,141],"supervision":[95],"organization":[98,131,143],"is":[99],"stronger":[100],"under":[101],"objectives,":[103],"but":[104],"neither":[105],"provides":[107],"consistent":[109],"overall":[110],"advantage.":[111],"These":[112],"results":[113],"show":[114],"that":[115],"teaching":[117],"relation":[119],"between":[120],"molecule":[122],"its":[124],"structural":[125],"core":[126],"can":[127],"reliably":[128],"shape":[129],"space,":[135],"extent":[138],"usefulness":[140],"remains":[144],"task":[145],"dependent.":[146]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-02T00:00:00"}