{"id":"https://openalex.org/W4400362104","doi":"https://doi.org/10.1038/s42256-024-00856-0","title":"Molecular set representation learning","display_name":"Molecular set representation learning","publication_year":2024,"publication_date":"2024-07-05","ids":{"openalex":"https://openalex.org/W4400362104","doi":"https://doi.org/10.1038/s42256-024-00856-0"},"language":"en","primary_location":{"id":"doi:10.1038/s42256-024-00856-0","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s42256-024-00856-0","pdf_url":"https://www.nature.com/articles/s42256-024-00856-0.pdf","source":{"id":"https://openalex.org/S2912241403","display_name":"Nature Machine Intelligence","issn_l":"2522-5839","issn":["2522-5839"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","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":"Nature Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://www.nature.com/articles/s42256-024-00856-0.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076132010","display_name":"Maria Boulougouri","orcid":"https://orcid.org/0000-0001-5969-3292"},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Maria Boulougouri","raw_affiliation_strings":["Signal Processing Laboratory 2, Institute of Electrical and Micro Engineering, School of Engineering, EPFL, Lausanne, Switzerland"],"affiliations":[{"raw_affiliation_string":"Signal Processing Laboratory 2, Institute of Electrical and Micro Engineering, School of Engineering, EPFL, Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028520858","display_name":"Pierre Vandergheynst","orcid":"https://orcid.org/0000-0002-9070-900X"},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Pierre Vandergheynst","raw_affiliation_strings":["Signal Processing Laboratory 2, Institute of Electrical and Micro Engineering, School of Engineering, EPFL, Lausanne, Switzerland"],"affiliations":[{"raw_affiliation_string":"Signal Processing Laboratory 2, Institute of Electrical and Micro Engineering, School of Engineering, EPFL, Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046410250","display_name":"Daniel Probst","orcid":"https://orcid.org/0000-0003-1737-4407"},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Daniel Probst","raw_affiliation_strings":["Signal Processing Laboratory 2, Institute of Electrical and Micro Engineering, School of Engineering, EPFL, Lausanne, Switzerland"],"affiliations":[{"raw_affiliation_string":"Signal Processing Laboratory 2, Institute of Electrical and Micro Engineering, School of Engineering, EPFL, Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5076132010"],"corresponding_institution_ids":["https://openalex.org/I5124864"],"apc_list":{"value":9750,"currency":"EUR","value_usd":11690},"apc_paid":{"value":9750,"currency":"EUR","value_usd":11690},"fwci":10.2524,"has_fulltext":true,"cited_by_count":28,"citation_normalized_percentile":{"value":0.98696926,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"6","issue":"7","first_page":"754","last_page":"763"},"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":0.9980000257492065,"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":0.9664000272750854,"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/representation","display_name":"Representation (politics)","score":0.623751163482666},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5942426919937134},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5018899440765381},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.0800161063671112},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.05179482698440552}],"concepts":[{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.623751163482666},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5942426919937134},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5018899440765381},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0800161063671112},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.05179482698440552},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1038/s42256-024-00856-0","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s42256-024-00856-0","pdf_url":"https://www.nature.com/articles/s42256-024-00856-0.pdf","source":{"id":"https://openalex.org/S2912241403","display_name":"Nature Machine Intelligence","issn_l":"2522-5839","issn":["2522-5839"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","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":"Nature Machine Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:infoscience.epfl.ch:20.500.14299/247680","is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/247680","pdf_url":"https://infoscience.epfl.ch/bitstreams/a6baeb00-3b4f-484b-82c5-47e0a4b6d686/download","source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"research article"}],"best_oa_location":{"id":"doi:10.1038/s42256-024-00856-0","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s42256-024-00856-0","pdf_url":"https://www.nature.com/articles/s42256-024-00856-0.pdf","source":{"id":"https://openalex.org/S2912241403","display_name":"Nature Machine Intelligence","issn_l":"2522-5839","issn":["2522-5839"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","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":"Nature Machine Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4400362104.pdf","grobid_xml":"https://content.openalex.org/works/W4400362104.grobid-xml"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W1975147762","https://openalex.org/W1986357594","https://openalex.org/W1988037271","https://openalex.org/W1999798000","https://openalex.org/W2016500278","https://openalex.org/W2148512505","https://openalex.org/W2162415170","https://openalex.org/W2583907533","https://openalex.org/W2785942661","https://openalex.org/W2894384847","https://openalex.org/W2935857979","https://openalex.org/W2966357564","https://openalex.org/W2969507301","https://openalex.org/W2984234582","https://openalex.org/W3003906593","https://openalex.org/W3010488723","https://openalex.org/W3021453944","https://openalex.org/W3034806393","https://openalex.org/W3035302862","https://openalex.org/W3085084733","https://openalex.org/W3096561213","https://openalex.org/W3109549311","https://openalex.org/W3153418506","https://openalex.org/W3173107846","https://openalex.org/W3194618792","https://openalex.org/W3199883166","https://openalex.org/W3208687975","https://openalex.org/W4213077304","https://openalex.org/W4214868967","https://openalex.org/W4226145240","https://openalex.org/W4280535719","https://openalex.org/W4286224803","https://openalex.org/W4313367248","https://openalex.org/W4313485929","https://openalex.org/W4321227311","https://openalex.org/W4324122028","https://openalex.org/W4377232456","https://openalex.org/W4387764395","https://openalex.org/W4388412569","https://openalex.org/W6744580074","https://openalex.org/W6929905089"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"Abstract":[0],"Computational":[1],"representation":[2,85,115,161],"of":[3,13,23,41,69,93,100,125,131],"molecules":[4],"can":[5,121],"take":[6],"many":[7],"forms,":[8],"including":[9],"graphs,":[10,14],"string":[11],"encodings":[12],"binary":[15],"vectors":[16],"or":[17],"learned":[18],"embeddings":[19],"in":[20,31,128],"the":[21,53,65,98,105,123,129,155],"form":[22],"real-valued":[24],"vectors.":[25],"These":[26],"representations":[27],"are":[28],"then":[29],"used":[30],"downstream":[32],"classification":[33],"and":[34,110,134,147,167,183],"regression":[35],"tasks":[36,81,178],"using":[37],"a":[38,70,75,113],"wide":[39],"range":[40],"machine":[42,79,176],"learning":[43,80,90,162,177],"models.":[44],"However,":[45],"existing":[46],"models":[47,103],"come":[48],"with":[49],"limitations,":[50],"such":[51],"as":[52],"requirement":[54],"for":[55,77,145,175],"clearly":[56],"defined":[57],"chemical":[58,107,184],"bonds,":[59],"which":[60],"often":[61],"do":[62],"not":[63],"represent":[64],"true":[66],"underlying":[67],"nature":[68],"molecule.":[71],"Here":[72],"we":[73,152,157],"propose":[74],"framework":[76],"molecular":[78,159],"based":[82],"on":[83,91,104,179],"set":[84,114,140,160],"learning.":[86],"We":[87,137],"show":[88,153],"that":[89,111,154],"sets":[92],"atom":[94],"invariants":[95],"alone":[96],"reaches":[97],"performance":[99,124],"state-of-the-art":[101],"graph-based":[102],"most-used":[106],"benchmark":[108],"datasets":[109],"introducing":[112],"layer":[116],"into":[117],"graph":[118,171],"neural":[119,142,172],"networks":[120],"surpass":[122],"established":[126],"methods":[127],"domains":[130],"chemistry,":[132],"biology":[133],"material":[135],"science.":[136],"introduce":[138],"specialized":[139],"representation-based":[141],"network":[143,173],"architectures":[144,174],"reaction-yield":[146],"protein\u2013ligand":[148],"binding-affinity":[149],"prediction.":[150],"Overall,":[151],"technique":[156],"denote":[158],"is":[163],"both":[164],"an":[165,168],"alternative":[166],"extension":[169],"to":[170],"molecules,":[180],"molecule":[181],"complexes":[182],"reactions.":[185]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":26}],"updated_date":"2026-03-24T08:02:53.985720","created_date":"2025-10-10T00:00:00"}