{"id":"https://openalex.org/W7137368690","doi":"https://doi.org/10.1021/acs.jcim.5c02994","title":"Multiscale Hypergraph Masked Autoencoder with \u0394-Property Alignment for Novel Molecular Representation Learning","display_name":"Multiscale Hypergraph Masked Autoencoder with \u0394-Property Alignment for Novel Molecular Representation Learning","publication_year":2026,"publication_date":"2026-03-16","ids":{"openalex":"https://openalex.org/W7137368690","doi":"https://doi.org/10.1021/acs.jcim.5c02994","pmid":"https://pubmed.ncbi.nlm.nih.gov/41837761"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.5c02994","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.5c02994","pdf_url":null,"source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102342189","display_name":"Ziyan Zhu","orcid":"https://orcid.org/0009-0006-1223-5845"},"institutions":[{"id":"https://openalex.org/I161716053","display_name":"China Pharmaceutical University","ror":"https://ror.org/01sfm2718","country_code":"CN","type":"education","lineage":["https://openalex.org/I161716053"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyan Zhu","raw_affiliation_strings":["Laboratory of Molecular Design and Drug Discovery, School of Science, China Pharmaceutical University, 639 Longmian Avenue, Nanjing 211198, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratory of Molecular Design and Drug Discovery, School of Science, China Pharmaceutical University, 639 Longmian Avenue, Nanjing 211198, China","institution_ids":["https://openalex.org/I161716053"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yijie Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I161716053","display_name":"China Pharmaceutical University","ror":"https://ror.org/01sfm2718","country_code":"CN","type":"education","lineage":["https://openalex.org/I161716053"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yijie Wang","raw_affiliation_strings":["Laboratory of Molecular Design and Drug Discovery, School of Science, China Pharmaceutical University, 639 Longmian Avenue, Nanjing 211198, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratory of Molecular Design and Drug Discovery, School of Science, China Pharmaceutical University, 639 Longmian Avenue, Nanjing 211198, China","institution_ids":["https://openalex.org/I161716053"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129604320","display_name":"Xian Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I4210130692","display_name":"Affiliated Hospital of Youjiang Medical University for Nationalities","ror":"https://ror.org/0358v9d31","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xian Wei","raw_affiliation_strings":["Department of Pharmacy, Youjiang Medical University for Nationalities, No. 98 ChengXiang Road, Baise, Youjiang\rDistrict, Guangxi Zhuang Autonomous Region 533000, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Pharmacy, Youjiang Medical University for Nationalities, No. 98 ChengXiang Road, Baise, Youjiang\rDistrict, Guangxi Zhuang Autonomous Region 533000, China","institution_ids":["https://openalex.org/I4210130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129438143","display_name":"Yanmin Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I161716053","display_name":"China Pharmaceutical University","ror":"https://ror.org/01sfm2718","country_code":"CN","type":"education","lineage":["https://openalex.org/I161716053"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yanmin Zhang","raw_affiliation_strings":["Laboratory of Molecular Design and Drug Discovery, School of Science, China Pharmaceutical University, 639 Longmian Avenue, Nanjing 211198, China"],"raw_orcid":"https://orcid.org/0000-0002-4075-7556","affiliations":[{"raw_affiliation_string":"Laboratory of Molecular Design and Drug Discovery, School of Science, China Pharmaceutical University, 639 Longmian Avenue, Nanjing 211198, China","institution_ids":["https://openalex.org/I161716053"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5129438143","https://openalex.org/A5129604320"],"corresponding_institution_ids":["https://openalex.org/I161716053","https://openalex.org/I4210130692"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19471074,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"66","issue":"7","first_page":"3858","last_page":"3877"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.47859999537467957,"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"}},"topics":[{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.47859999537467957,"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/T10211","display_name":"Computational Drug Discovery Methods","score":0.43050000071525574,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.05640000104904175,"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/autoencoder","display_name":"Autoencoder","score":0.7150999903678894},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.7074999809265137},{"id":"https://openalex.org/keywords/hypergraph","display_name":"Hypergraph","score":0.6819000244140625},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.526199996471405},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5022000074386597},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.44830000400543213},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.42329999804496765},{"id":"https://openalex.org/keywords/property","display_name":"Property (philosophy)","score":0.4203000068664551},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.38850000500679016}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.7150999903678894},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7074999809265137},{"id":"https://openalex.org/C2781221856","wikidata":"https://www.wikidata.org/wiki/Q840247","display_name":"Hypergraph","level":2,"score":0.6819000244140625},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6590999960899353},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.526199996471405},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5022000074386597},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.44830000400543213},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4278999865055084},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.42329999804496765},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.4203000068664551},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.38850000500679016},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3765999972820282},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.37229999899864197},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.35179999470710754},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.3497999906539917},{"id":"https://openalex.org/C2780022179","wikidata":"https://www.wikidata.org/wiki/Q1986794","display_name":"Molecular graph","level":3,"score":0.3497999906539917},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33469998836517334},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.3296999931335449},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.32690000534057617},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3237999975681305},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.29670000076293945},{"id":"https://openalex.org/C201399114","wikidata":"https://www.wikidata.org/wiki/Q898401","display_name":"Lipophilicity","level":2,"score":0.28049999475479126},{"id":"https://openalex.org/C124066611","wikidata":"https://www.wikidata.org/wiki/Q28684319","display_name":"Sparse approximation","level":2,"score":0.2718999981880188},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2680000066757202},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.2676999866962433},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.2596000134944916},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.2567000091075897},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.2549000084400177}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000098409","descriptor_name":"Representation Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098409","descriptor_name":"Representation Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098446","descriptor_name":"Autoencoder","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098446","descriptor_name":"Autoencoder","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000098446","descriptor_name":"Autoencoder","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008958","descriptor_name":"Models, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008958","descriptor_name":"Models, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008958","descriptor_name":"Models, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1021/acs.jcim.5c02994","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.5c02994","pdf_url":null,"source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},{"id":"pmid:41837761","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41837761","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 chemical information and modeling","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3543638385","display_name":null,"funder_award_id":"2023SJZD130","funder_id":"https://openalex.org/F4320336600","funder_display_name":"Major Project of Philosophy and Social Science Research in Colleges and Universities of Jiangsu Province"},{"id":"https://openalex.org/G4300687662","display_name":null,"funder_award_id":"2024SJYB0082","funder_id":"https://openalex.org/F4320336600","funder_display_name":"Major Project of Philosophy and Social Science Research in Colleges and Universities of Jiangsu Province"},{"id":"https://openalex.org/G4321429232","display_name":null,"funder_award_id":"2632025ZD04","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G6171854157","display_name":null,"funder_award_id":"2025GXNSFAA069993","funder_id":"https://openalex.org/F4320313613","funder_display_name":"Natural Science Foundation of Guangxi Zhuang Autonomous Region"},{"id":"https://openalex.org/G6756507509","display_name":null,"funder_award_id":"BK20242073","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"}],"funders":[{"id":"https://openalex.org/F4320313613","display_name":"Natural Science Foundation of Guangxi Zhuang Autonomous Region","ror":null},{"id":"https://openalex.org/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null},{"id":"https://openalex.org/F4320336600","display_name":"Major Project of Philosophy and Social Science Research in Colleges and Universities of Jiangsu Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W1483072991","https://openalex.org/W1966878439","https://openalex.org/W1971251199","https://openalex.org/W1975147762","https://openalex.org/W1978813754","https://openalex.org/W1987971958","https://openalex.org/W1988037271","https://openalex.org/W1991615245","https://openalex.org/W2051224630","https://openalex.org/W2051628563","https://openalex.org/W2052611179","https://openalex.org/W2085487226","https://openalex.org/W2087563523","https://openalex.org/W2097308346","https://openalex.org/W2101491865","https://openalex.org/W2110065044","https://openalex.org/W2119885577","https://openalex.org/W2128021408","https://openalex.org/W2147421370","https://openalex.org/W2399767476","https://openalex.org/W2594183968","https://openalex.org/W2908510526","https://openalex.org/W2911964244","https://openalex.org/W2963430933","https://openalex.org/W2966357564","https://openalex.org/W2968734407","https://openalex.org/W3009999522","https://openalex.org/W3023204497","https://openalex.org/W3033513666","https://openalex.org/W3087318293","https://openalex.org/W3093934881","https://openalex.org/W3094640617","https://openalex.org/W3116202926","https://openalex.org/W3174191946","https://openalex.org/W3206711231","https://openalex.org/W3213042299","https://openalex.org/W4214868967","https://openalex.org/W4290876361","https://openalex.org/W4297179162","https://openalex.org/W4297632148","https://openalex.org/W4309218736","https://openalex.org/W4310787484","https://openalex.org/W4313156423","https://openalex.org/W4367047461","https://openalex.org/W4381679608","https://openalex.org/W4390221451","https://openalex.org/W4392543831","https://openalex.org/W4394686508","https://openalex.org/W4396616941","https://openalex.org/W4400140641","https://openalex.org/W4408815288","https://openalex.org/W4410792183","https://openalex.org/W4413055614","https://openalex.org/W4414070064","https://openalex.org/W4414645235","https://openalex.org/W4414715259"],"related_works":[],"abstract_inverted_index":{"Molecular":[0],"representation":[1,41],"learning":[2],"often":[3],"focuses":[4],"on":[5,140,155,162,198,209,255],"recognizing":[6],"local":[7],"structural":[8,221,241],"patterns":[9],"but":[10],"struggles":[11],"to":[12,74,95,110,135,189],"capture":[13,76],"functional":[14,61],"groups":[15],"and":[16,55,65,69,82,97,99,104,158,175,185,192,200,202,236,258,271],"cross-scale":[17],"interactions":[18],"in":[19,245,263],"a":[20,34,48,87],"chemically":[21],"meaningful":[22],"way.":[23],"Here,":[24],"we":[25,115],"propose":[26],"the":[27,79,108,130,231,246,259],"Multiscale":[28],"Hypergraph":[29],"Convolutional":[30],"Masked":[31],"Autoencoder":[32],"(MSHG-MAE),":[33],"hypergraph-based":[35],"self-supervised":[36],"framework":[37],"for":[38],"drug-like":[39],"molecular":[40,50,83,143],"learning.":[42],"We":[43],"model":[44,109],"each":[45],"molecule":[46],"as":[47],"unified":[49],"hypergraph":[51,72],"with":[52,124,178],"atom":[53],"nodes":[54],"multitype":[56],"hyperedges,":[57,68],"including":[58],"bond,":[59],"ring,":[60],"group,":[62],"conjugated":[63],"system,":[64],"hydrogen":[66],"bond":[67],"use":[70],"multiscale":[71],"convolutions":[73],"jointly":[75],"dependencies":[77],"at":[78],"atomic,":[80],"substructural,":[81],"levels.":[84],"In":[85],"pretraining,":[86],"semantics-aware":[88],"masked":[89,101],"autoencoding":[90],"objective":[91],"applies":[92],"biased":[93],"masking":[94],"atoms":[96],"hyperedges":[98],"reconstructs":[100],"node":[102],"features":[103],"hyperedge":[105],"attributes,":[106],"encouraging":[107],"internalize":[111],"functional-group":[112,223,243],"semantics.":[113],"Furthermore,":[114],"introduce":[116],"\u0394-Property":[117],"Alignment":[118],"(\u0394-PropAlign),":[119],"which":[120],"aligns":[121],"embedding":[122,234],"differences":[123,127,235,238],"proxy":[125],"property":[126,144,237],"so":[128],"that":[129,150,228],"learned":[131,247],"representations":[132],"remain":[133],"sensitive":[134],"interpretable":[136],"structure-property":[137],"changes.":[138],"Experiments":[139],"multiple":[141],"public":[142],"benchmarks":[145,169],"under":[146,170],"scaffold":[147,171,213],"splits":[148,172],"show":[149],"MSHG-MAE":[151,177],"consistently":[152],"outperforms":[153],"baselines":[154],"regression":[156,168],"tasks":[157],"achieves":[159,180],"competitive":[160],"results":[161,226],"classification":[163],"benchmarks.":[164],"On":[165],"three":[166],"physicochemical":[167],"(ESOL,":[173],"FreeSolv,":[174],"Lipophilicity),":[176],"\u0394-PropAlign":[179,229],"RMSEs":[181],"of":[182],"0.465,":[183],"0.780,":[184],"0.501,":[186],"respectively,":[187],"corresponding":[188],"approximately":[190,203],"40%":[191],"47%":[193],"lower":[194,205],"RMSE":[195,206],"than":[196,207],"Uni-Mol":[197],"ESOL":[199],"FreeSolv":[201],"27%":[204],"D-MPNN":[208],"Lipophilicity":[210],"(Table":[211],"5,":[212],"split":[214],"80/10/10,":[215],"3":[216],"seeds),":[217],"while":[218],"not":[219],"degrading":[220],"or":[222,242],"geometry.":[224],"These":[225],"indicate":[227],"improves":[230],"consistency":[232],"between":[233],"without":[239],"sacrificing":[240],"organization":[244],"representations.":[248],"The":[249],"core":[250],"code":[251],"is":[252],"publicly":[253,267],"available":[254,268],"GitHub":[256],"(https://github.com/Irzos/MSHG-MAE),":[257],"data":[260],"sets":[261],"used":[262],"this":[264],"study":[265],"are":[266],"from":[269],"ZINC20":[270],"MoleculeNet.":[272]},"counts_by_year":[],"updated_date":"2026-08-09T07:27:16.801131","created_date":"2026-03-17T00:00:00"}