{"id":"https://openalex.org/W7121055444","doi":"https://doi.org/10.1186/s13321-025-01140-y","title":"Multimodal graph fusion with statistically guided parsimonious descriptor selection for molecular property prediction","display_name":"Multimodal graph fusion with statistically guided parsimonious descriptor selection for molecular property prediction","publication_year":2026,"publication_date":"2026-01-11","ids":{"openalex":"https://openalex.org/W7121055444","doi":"https://doi.org/10.1186/s13321-025-01140-y","pmid":"https://pubmed.ncbi.nlm.nih.gov/41521286"},"language":"en","primary_location":{"id":"doi:10.1186/s13321-025-01140-y","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-025-01140-y","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/s13321-025-01140-y","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058007285","display_name":"Yoonsuk Jang","orcid":"https://orcid.org/0000-0003-0527-8071"},"institutions":[{"id":"https://openalex.org/I191879574","display_name":"Inha University","ror":"https://ror.org/01easw929","country_code":"KR","type":"education","lineage":["https://openalex.org/I191879574"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yoonsuk Jang","raw_affiliation_strings":["Department of Statistics and Data Science, Inha University, 100, Inha-ro, Michuhol-gu, Incheon, 22212, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics and Data Science, Inha University, 100, Inha-ro, Michuhol-gu, Incheon, 22212, Republic of Korea","institution_ids":["https://openalex.org/I191879574"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122740531","display_name":"Juyeon Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]},{"id":"https://openalex.org/I4210161052","display_name":"Korea University","ror":"https://ror.org/05m1gnk07","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210161052"]}],"countries":["JP","KR"],"is_corresponding":false,"raw_author_name":"Juyeon Lee","raw_affiliation_strings":["Department of Biomedical Engineering, Korea University, 145, Anam-ro, Seongbuk-gu, Seoul, 0284, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biomedical Engineering, Korea University, 145, Anam-ro, Seongbuk-gu, Seoul, 0284, Republic of Korea","institution_ids":["https://openalex.org/I4210161052","https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122719236","display_name":"Keunhong Jeong","orcid":null},"institutions":[{"id":"https://openalex.org/I184908088","display_name":"Korea Military Academy","ror":"https://ror.org/024ctqw02","country_code":"KR","type":"education","lineage":["https://openalex.org/I184908088"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Keunhong Jeong","raw_affiliation_strings":["Department of Physics and Chemistry, Korea Military Academy, 574, Hwarang-ro, Nowon-gu, Seoul, 01805, Republic of Korea. doas1mind@gmail.com"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Physics and Chemistry, Korea Military Academy, 574, Hwarang-ro, Nowon-gu, Seoul, 01805, Republic of Korea. doas1mind@gmail.com","institution_ids":["https://openalex.org/I184908088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068657400","display_name":"Jaeoh Kim","orcid":"https://orcid.org/0000-0001-7831-6353"},"institutions":[{"id":"https://openalex.org/I191879574","display_name":"Inha University","ror":"https://ror.org/01easw929","country_code":"KR","type":"education","lineage":["https://openalex.org/I191879574"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Jaeoh Kim","raw_affiliation_strings":["Department of Statistics and Data Science, Inha University, 100, Inha-ro, Michuhol-gu, Incheon, 22212, Republic of Korea. jaeoh.k@inha.ac.kr"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics and Data Science, Inha University, 100, Inha-ro, Michuhol-gu, Incheon, 22212, Republic of Korea. jaeoh.k@inha.ac.kr","institution_ids":["https://openalex.org/I191879574"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5068657400"],"corresponding_institution_ids":["https://openalex.org/I191879574"],"apc_list":{"value":1290,"currency":"GBP","value_usd":1582},"apc_paid":{"value":1290,"currency":"GBP","value_usd":1582},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.08234984,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"18","issue":"1","first_page":"18","last_page":"18"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.4016000032424927,"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":0.4016000032424927,"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":0.2451999932527542,"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":0.20160000026226044,"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/concatenation","display_name":"Concatenation (mathematics)","score":0.7789000272750854},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.6244000196456909},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5803999900817871},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5105000138282776},{"id":"https://openalex.org/keywords/molecular-graph","display_name":"Molecular graph","score":0.4982999861240387},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.4537000060081482},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4287000000476837},{"id":"https://openalex.org/keywords/property","display_name":"Property (philosophy)","score":0.3968999981880188},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.37770000100135803}],"concepts":[{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.7789000272750854},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7523999810218811},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.6244000196456909},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5803999900817871},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5511000156402588},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5105000138282776},{"id":"https://openalex.org/C2780022179","wikidata":"https://www.wikidata.org/wiki/Q1986794","display_name":"Molecular graph","level":3,"score":0.4982999861240387},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.4537000060081482},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45260000228881836},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4287000000476837},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.40209999680519104},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.3968999981880188},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.37770000100135803},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.3504999876022339},{"id":"https://openalex.org/C164923092","wikidata":"https://www.wikidata.org/wiki/Q3705921","display_name":"Molecular descriptor","level":3,"score":0.34369999170303345},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.328900009393692},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.31929999589920044},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.30649998784065247},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2922999858856201},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.29010000824928284},{"id":"https://openalex.org/C79772020","wikidata":"https://www.wikidata.org/wiki/Q5159264","display_name":"Conditional independence","level":2,"score":0.2761000096797943},{"id":"https://openalex.org/C35651441","wikidata":"https://www.wikidata.org/wiki/Q625303","display_name":"Independence (probability theory)","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2718999981880188},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.26930001378059387},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.26600000262260437},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.263700008392334},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2615000009536743}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1186/s13321-025-01140-y","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-025-01140-y","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:41521286","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41521286","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:440bc9fdbcc34c31b96fa0e01f77d0aa","is_oa":true,"landing_page_url":"https://doaj.org/article/440bc9fdbcc34c31b96fa0e01f77d0aa","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 1-52 (2026)","raw_type":"article"},{"id":"pmh:oai:europepmc.org:11689998","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12882498","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:12882498","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12882498/","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/s13321-025-01140-y","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-025-01140-y","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":[{"display_name":"Responsible consumption and production","id":"https://metadata.un.org/sdg/12","score":0.44219672679901123},{"display_name":"Life in Land","id":"https://metadata.un.org/sdg/15","score":0.44025883078575134}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321370","display_name":"Inha University","ror":"https://ror.org/01easw929"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W2008505552","https://openalex.org/W2020925091","https://openalex.org/W2076498053","https://openalex.org/W2122825543","https://openalex.org/W2135046866","https://openalex.org/W2141696759","https://openalex.org/W2154560360","https://openalex.org/W2594183968","https://openalex.org/W2788036298","https://openalex.org/W2805399276","https://openalex.org/W2898646011","https://openalex.org/W2907492528","https://openalex.org/W2913099012","https://openalex.org/W2942422815","https://openalex.org/W2955415481","https://openalex.org/W2957050889","https://openalex.org/W2962712142","https://openalex.org/W2963066927","https://openalex.org/W2963383024","https://openalex.org/W2963717374","https://openalex.org/W2964051675","https://openalex.org/W2966357564","https://openalex.org/W2969457089","https://openalex.org/W2996092187","https://openalex.org/W2999177618","https://openalex.org/W3015494591","https://openalex.org/W3026620303","https://openalex.org/W3043016077","https://openalex.org/W3137551757","https://openalex.org/W3169801598","https://openalex.org/W3176232375","https://openalex.org/W4307493889","https://openalex.org/W4376226279","https://openalex.org/W4390242499","https://openalex.org/W4396678548","https://openalex.org/W4405805197","https://openalex.org/W4409563056","https://openalex.org/W4410199780","https://openalex.org/W4410743402","https://openalex.org/W4411759572"],"related_works":[],"abstract_inverted_index":{"Graph":[0],"convolutional":[1],"networks":[2],"(GCN)":[3],"are":[4,63],"effective":[5],"for":[6,38,164,169,230],"learning":[7,42],"molecular":[8,40,51,231],"representations,":[9],"but":[10,114],"their":[11,22],"reliance":[12],"on":[13,84,156],"local":[14],"message":[15],"passing":[16],"and":[17,89,100,122,128,150,172,193,224],"simple":[18,201],"feature":[19],"concatenation":[20,202],"limits":[21],"ability":[23],"to":[24,56],"capture":[25],"global":[26],"physicochemical":[27],"properties.":[28],"We":[29],"present":[30],"KROnecker-product":[31],"based":[32],"multimodal":[33,218],"fusion":[34,134,196,220],"with":[35,50,75,97,217],"Variable":[36],"sElection":[37],"eXpressive":[39],"representation":[41],"(KROVEX),":[43],"a":[44,54,66,161,227],"method":[45,109],"that":[46,69,180,212],"integrates":[47],"graph":[48,219],"embeddings":[49],"descriptors":[52,62,207],"through":[53],"Kronecker-product":[55,195],"explicitly":[57],"model":[58],"second-order":[59],"interactions.":[60],"Informative":[61],"identified":[64],"using":[65],"two-stage":[67],"procedure":[68],"combines":[70],"iterative":[71],"sure":[72],"independence":[73],"screening":[74],"Elastic":[76],"Net":[77],"regularization.":[78],"The":[79],"proposed":[80],"approach":[81],"was":[82],"evaluated":[83],"two":[85,94],"benchmark":[86,163],"datasets":[87,96],"(FreeSolv":[88],"ESOL)":[90],"as":[91,93,103,119,203],"well":[92],"self-curated":[95],"vapor":[98,157],"pressure":[99,158],"aqueous":[101],"solubility":[102],"the":[104,126,133,137,204],"target":[105],"property.":[106],"Overall,":[107],"our":[108],"outperformed":[110],"not":[111],"only":[112],"GCN":[113],"also":[115],"fusion-based":[116],"baselines":[117],"such":[118],"EGCN,":[120],"D-MPNN,":[121],"BAN":[123],"under":[124],"both":[125],"random":[127],"scaffold":[129],"split.":[130],"More":[131],"importantly,":[132],"operates":[135],"at":[136],"final":[138],"embedding":[139],"level,":[140],"enabling":[141],"consistent":[142],"performance":[143,155,223],"across":[144],"different":[145],"GNN":[146],"backbones":[147],"(e.g.,":[148],"GAT":[149],"GIN).":[151],"KROVEX":[152],"achieves":[153],"state-of-the-art":[154],"prediction,":[159],"establishing":[160],"new":[162],"this":[165],"safety-critical":[166],"property":[167,232],"essential":[168],"environmental":[170],"monitoring":[171],"industrial":[173],"process":[174],"design.":[175],"Ablation":[176],"studies":[177],"further":[178],"demonstrated":[179],"(1)":[181],"statistically":[182],"guided":[183],"descriptor":[184,214],"selection":[185,215],"yields":[186],"more":[187],"informative":[188],"features":[189],"than":[190,200],"predefined":[191],"descriptors,":[192],"(2)":[194],"provides":[197],"greater":[198],"improvements":[199],"number":[205],"of":[206],"increases.":[208],"These":[209],"results":[210],"demonstrate":[211],"parsimonious":[213],"combined":[216],"enhances":[221],"predictive":[222],"interpretability,":[225],"providing":[226],"generalizable":[228],"framework":[229],"prediction.":[233]},"counts_by_year":[],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2026-01-11T00:00:00"}