{"id":"https://openalex.org/W4417078580","doi":"https://doi.org/10.1186/s13321-025-01126-w","title":"Multi-MoleScale: a multi-scale approach for molecular property prediction with graph contrastive and sequence learning","display_name":"Multi-MoleScale: a multi-scale approach for molecular property prediction with graph contrastive and sequence learning","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W4417078580","doi":"https://doi.org/10.1186/s13321-025-01126-w","pmid":"https://pubmed.ncbi.nlm.nih.gov/41353381"},"language":"en","primary_location":{"id":"doi:10.1186/s13321-025-01126-w","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-025-01126-w","pdf_url":null,"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","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://doi.org/10.1186/s13321-025-01126-w","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Xinpo Lou","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113703","display_name":"Henan University of Urban Construction","ror":"https://ror.org/01x1skr92","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210113703"]},{"id":"https://openalex.org/I49835588","display_name":"Macao Polytechnic University","ror":"https://ror.org/02sf5td35","country_code":"MO","type":"education","lineage":["https://openalex.org/I49835588"]}],"countries":["CN","MO"],"is_corresponding":false,"raw_author_name":"Xinpo Lou","raw_affiliation_strings":["Centre for Artificial Intelligence Driven Drug Discovery, Faculty of Applied Sciences, Macao Polytechnic University, Macao, 999078, China","School of Computer and Data Science, Henan University of Urban Construction, Pingdingshan, 467036, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Artificial Intelligence Driven Drug Discovery, Faculty of Applied Sciences, Macao Polytechnic University, Macao, 999078, China","institution_ids":["https://openalex.org/I49835588"]},{"raw_affiliation_string":"School of Computer and Data Science, Henan University of Urban Construction, Pingdingshan, 467036, China","institution_ids":["https://openalex.org/I4210113703"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001119403","display_name":"Jianxiu Cai","orcid":"https://orcid.org/0000-0003-2342-8969"},"institutions":[{"id":"https://openalex.org/I49835588","display_name":"Macao Polytechnic University","ror":"https://ror.org/02sf5td35","country_code":"MO","type":"education","lineage":["https://openalex.org/I49835588"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Jianxiu Cai","raw_affiliation_strings":["Faculty of Applied Sciences, Macao Polytechnic University, Macao, 999078, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Applied Sciences, Macao Polytechnic University, Macao, 999078, China","institution_ids":["https://openalex.org/I49835588"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102848446","display_name":"Shirley W. I. Siu","orcid":"https://orcid.org/0000-0002-3695-7758"},"institutions":[{"id":"https://openalex.org/I49835588","display_name":"Macao Polytechnic University","ror":"https://ror.org/02sf5td35","country_code":"MO","type":"education","lineage":["https://openalex.org/I49835588"]}],"countries":["MO"],"is_corresponding":true,"raw_author_name":"Shirley W. I. Siu","raw_affiliation_strings":["Centre for Artificial Intelligence Driven Drug Discovery, Faculty of Applied Sciences, Macao Polytechnic University, Macao, 999078, China. shirleysiu@mpu.edu.mo","Centre for Artificial Intelligence Driven Drug Discovery, Faculty of Applied Sciences, Macao Polytechnic University, Macao, 999078, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Artificial Intelligence Driven Drug Discovery, Faculty of Applied Sciences, Macao Polytechnic University, Macao, 999078, China. shirleysiu@mpu.edu.mo","institution_ids":["https://openalex.org/I49835588"]},{"raw_affiliation_string":"Centre for Artificial Intelligence Driven Drug Discovery, Faculty of Applied Sciences, Macao Polytechnic University, Macao, 999078, China","institution_ids":["https://openalex.org/I49835588"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5102848446"],"corresponding_institution_ids":["https://openalex.org/I49835588"],"apc_list":{"value":2190,"currency":"USD","value_usd":2190},"apc_paid":{"value":2190,"currency":"USD","value_usd":2190},"fwci":0.7721,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.80424737,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"18","issue":"1","first_page":"5","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.6998999714851379,"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":0.6998999714851379,"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":0.15850000083446503,"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"}},{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.06719999760389328,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.550599992275238},{"id":"https://openalex.org/keywords/property","display_name":"Property (philosophy)","score":0.513700008392334},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.5095000267028809},{"id":"https://openalex.org/keywords/molecular-graph","display_name":"Molecular graph","score":0.4830999970436096},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4113999903202057},{"id":"https://openalex.org/keywords/ensemble-learning","display_name":"Ensemble learning","score":0.35580000281333923},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3447999954223633}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7872999906539917},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.554099977016449},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.550599992275238},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.513700008392334},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.5095000267028809},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.487199991941452},{"id":"https://openalex.org/C2780022179","wikidata":"https://www.wikidata.org/wiki/Q1986794","display_name":"Molecular graph","level":3,"score":0.4830999970436096},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4113999903202057},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.35580000281333923},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3447999954223633},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.32659998536109924},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.32260000705718994},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.30149999260902405},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2700999975204468},{"id":"https://openalex.org/C40506919","wikidata":"https://www.wikidata.org/wiki/Q7452469","display_name":"Sequence learning","level":2,"score":0.263700008392334},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.2581999897956848}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1186/s13321-025-01126-w","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-025-01126-w","pdf_url":null,"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},{"id":"pmid:41353381","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41353381","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:b5928d8120904779a54c801f0f1921c7","is_oa":true,"landing_page_url":"https://doaj.org/article/b5928d8120904779a54c801f0f1921c7","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"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":"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 18, Iss 1, Pp 1-18 (2025)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:12797713","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12797713/","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J Cheminform","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/s13321-025-01126-w","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-025-01126-w","pdf_url":null,"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W1964513093","https://openalex.org/W2008505552","https://openalex.org/W2076498053","https://openalex.org/W2096541451","https://openalex.org/W2145578524","https://openalex.org/W2406943157","https://openalex.org/W2461470610","https://openalex.org/W2461620095","https://openalex.org/W2512582262","https://openalex.org/W2594183968","https://openalex.org/W2778051509","https://openalex.org/W2900090807","https://openalex.org/W2907492528","https://openalex.org/W2964015378","https://openalex.org/W2968734407","https://openalex.org/W2973114758","https://openalex.org/W3091107267","https://openalex.org/W3110933132","https://openalex.org/W3112890400","https://openalex.org/W3113291402","https://openalex.org/W3130309548","https://openalex.org/W3130891725","https://openalex.org/W3154258817","https://openalex.org/W3154492312","https://openalex.org/W3163493952","https://openalex.org/W3204651332","https://openalex.org/W3211865849","https://openalex.org/W3216163675","https://openalex.org/W4214868967","https://openalex.org/W4221023051","https://openalex.org/W4224220091","https://openalex.org/W4226068197","https://openalex.org/W4229369522","https://openalex.org/W4283389995","https://openalex.org/W4298009900","https://openalex.org/W4306976400","https://openalex.org/W4309218736","https://openalex.org/W4311584330","https://openalex.org/W4311821010","https://openalex.org/W4312064763","https://openalex.org/W4362503491","https://openalex.org/W4365455552","https://openalex.org/W4379055456","https://openalex.org/W4380715275","https://openalex.org/W4388423838","https://openalex.org/W4388455891","https://openalex.org/W4391345293","https://openalex.org/W4394911012","https://openalex.org/W4400555240"],"related_works":[],"abstract_inverted_index":{"In":[0,28],"recent":[1],"years,":[2],"machine":[3],"learning":[4,99,160,163],"models":[5,51,227],"have":[6],"shown":[7],"substantial":[8],"progress":[9],"in":[10,194],"predicting":[11],"molecular":[12,16,59,95,109,118,138,183,201,237,257,267],"properties.":[13],"However,":[14],"integrating":[15],"graph":[17,238],"structures":[18,239],"with":[19,49,225,240],"sequence":[20,241],"information":[21],"continues":[22],"to":[23,39,75,89,103],"present":[24],"a":[25,34,180,189,215],"significant":[26],"challenge.":[27,42],"this":[29,41],"paper,":[30],"we":[31,127],"introduce":[32,213],"Multi-MoleScale,":[33,214],"novel":[35,216],"multi-scale":[36,217],"framework":[37,218],"designed":[38],"address":[40],"By":[43,247],"combining":[44],"Graph":[45,221],"Contrastive":[46,222],"Learning":[47,223],"(GCL)":[48,224],"sequence-based":[50,226],"like":[52],"BERT,":[53],"Multi-MoleScale":[54,102,155,188,259],"enhances":[55],"the":[56,71,78,91,122,141,166,261],"prediction":[57],"of":[58,68,82,124,182],"properties":[60],"by":[61],"capturing":[62,248],"both":[63,249],"structural":[64],"and":[65,107,144,161,177,199,206,253,265],"contextual":[66,92,254],"representations":[67],"molecules.":[69],"Specifically,":[70],"model":[72,167],"leverages":[73],"GCL":[74],"effectively":[76,235],"capture":[77],"intrinsic":[79,250],"graph-based":[80,251],"features":[81,252],"molecules":[83],"while":[84],"utilizing":[85],"BERT\u2019s":[86],"pretraining":[87],"capabilities":[88],"learn":[90],"relationships":[93,255],"within":[94,256],"sequences.":[96],"The":[97,151],"contrastive":[98],"component":[100],"enables":[101,260],"distinguish":[104],"between":[105,263],"relevant":[106,264],"irrelevant":[108,266],"features,":[110,172],"thereby":[111],"enhancing":[112,244],"its":[113],"predictive":[114,245],"accuracy":[115],"across":[116],"diverse":[117],"types.":[119],"To":[120],"assess":[121],"performance":[123],"our":[125],"method,":[126],"conducted":[128],"experiments":[129],"on":[130],"several":[131],"widely":[132],"used":[133],"public":[134],"datasets,":[135,140],"including":[136],"12":[137],"property":[139],"ADMET":[142],"dataset,":[143],"14":[145],"breast":[146],"cancer":[147],"cell":[148],"line":[149],"datasets.":[150],"results":[152],"show":[153],"that":[154,219],"consistently":[156],"outperforms":[157],"existing":[158],"deep":[159],"self-supervised":[162],"approaches.":[164],"Notably,":[165],"does":[168],"not":[169],"require":[170],"handcrafted":[171],"making":[173],"it":[174],"highly":[175],"adaptable":[176],"versatile":[178],"for":[179,192],"variety":[181],"discovery":[184],"tasks.":[185],"This":[186,231],"makes":[187],"promising":[190],"tool":[191],"applications":[193],"drug":[195],"discovery,":[196],"materials":[197],"science,":[198],"other":[200],"research":[202],"fields.":[203],"Our":[204],"data":[205],"code":[207],"are":[208],"available":[209],"at":[210],"https://github.com/pdssunny/Multi-MoleScale.":[211],"We":[212],"integrates":[220],"such":[228],"as":[229],"BERT.":[230],"innovative":[232],"dual":[233],"approach":[234],"combines":[236],"information,":[242],"significantly":[243],"accuracy.":[246],"sequences,":[258],"differentiation":[262],"features.":[268]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-12-06T00:00:00"}