{"id":"https://openalex.org/W7214605702","doi":"https://doi.org/10.64898/2026.09.22.753673","title":"Tri-Modality Representation Learning for Molecular Property Prediction","display_name":"Tri-Modality Representation Learning for Molecular Property Prediction","publication_year":2026,"publication_date":"2026-09-28","ids":{"openalex":"https://openalex.org/W7214605702","doi":"https://doi.org/10.64898/2026.09.22.753673","pmid":"https://pubmed.ncbi.nlm.nih.gov/42856112","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/13648364"},"language":"en","primary_location":{"id":"doi:10.64898/2026.09.22.753673","doi":"https://doi.org/10.64898/2026.09.22.753673","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.22.753673","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/28/2026.09.22.753673.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/28/2026.09.22.753673.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057537629","display_name":"Anyin Zhao","orcid":"https://orcid.org/0009-0008-3785-8568","observed_orcids":["https://orcid.org/0009-0008-3785-8568"]},"institutions":[{"id":"https://openalex.org/I58956616","display_name":"Case Western Reserve University","ror":"https://ror.org/051fd9666","country_code":"US","type":"education","lineage":["https://openalex.org/I58956616"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anyin Zhao","raw_affiliation_strings":["Case Western Reserve University, Cleveland OH 44106, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Case Western Reserve University, Cleveland OH 44106, USA","institution_ids":["https://openalex.org/I58956616"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5153251052","display_name":"Jing Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I58956616","display_name":"Case Western Reserve University","ror":"https://ror.org/051fd9666","country_code":"US","type":"education","lineage":["https://openalex.org/I58956616"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jing Li","raw_affiliation_strings":["Case Western Reserve University, Cleveland OH 44106, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Case Western Reserve University, Cleveland OH 44106, USA","institution_ids":["https://openalex.org/I58956616"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5153251052"],"corresponding_institution_ids":["https://openalex.org/I58956616"],"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":0.9980000257492065,"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":0.9980000257492065,"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":0.00039999998989515007,"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/T10002","display_name":"Advanced Chemical Physics Studies","score":0.00019999999494757503,"subfield":{"id":"https://openalex.org/subfields/3107","display_name":"Atomic and Molecular Physics, and Optics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/molecular-property-prediction","display_name":"molecular property prediction","score":0.902999997138977},{"id":"https://openalex.org/keywords/multimodal-representation-learning","display_name":"multimodal representation learning","score":0.8479999899864197},{"id":"https://openalex.org/keywords/smiles","display_name":"SMILES","score":0.6079999804496765},{"id":"https://openalex.org/keywords/molecular-graphs","display_name":"molecular graphs","score":0.9480000138282776},{"id":"https://openalex.org/keywords/cross-attention-fusion","display_name":"cross-attention fusion","score":0.921999990940094},{"id":"https://openalex.org/keywords/pre-trained-encoders","display_name":"pre-trained encoders","score":0.621999979019165},{"id":"https://openalex.org/keywords/drug-property-prediction","display_name":"drug property prediction","score":0.6240000128746033},{"id":"https://openalex.org/keywords/molecular-classification","display_name":"molecular classification","score":0.3109999895095825}],"concepts":[{"id":"https://openalex.org/C2780022179","wikidata":"https://www.wikidata.org/wiki/Q1986794","display_name":"Molecular graph","level":3,"score":0.6805999875068665},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.6062999963760376},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5432000160217285},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5396999716758728},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.5180000066757202},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4699999988079071},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4596000015735626},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42969998717308044},{"id":"https://openalex.org/C164923092","wikidata":"https://www.wikidata.org/wiki/Q3705921","display_name":"Molecular descriptor","level":3,"score":0.428600013256073},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4066999852657318},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.40070000290870667},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.39160001277923584},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.36419999599456787},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.350600004196167},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3352999985218048},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.32679998874664307},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.32679998874664307},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.32359999418258667},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.31279999017715454},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3111000061035156},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.30480000376701355},{"id":"https://openalex.org/C178910836","wikidata":"https://www.wikidata.org/wiki/Q2196961","display_name":"Molecular model","level":2,"score":0.2903999984264374},{"id":"https://openalex.org/C103697762","wikidata":"https://www.wikidata.org/wiki/Q4112105","display_name":"Virtual screening","level":3,"score":0.2734000086784363},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.26739999651908875}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.64898/2026.09.22.753673","doi":"https://doi.org/10.64898/2026.09.22.753673","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.22.753673","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/28/2026.09.22.753673.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},{"id":"pmid:42856112","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42856112","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,"listed_in":[],"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":"bioRxiv : the preprint server for biology","raw_type":"Journal Article"},{"id":"pmh:oai:pubmedcentral.nih.gov:13648364","doi":null,"is_oa":true,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42856112/","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.64898/2026.09.22.753673","doi":"https://doi.org/10.64898/2026.09.22.753673","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.22.753673","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/28/2026.09.22.753673.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G3662945519","display_name":"FET: CCF: Small: Computational Drug Prediction through Joint Learning","funder_award_id":"2006780","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7199570490","display_name":"RAPID:Genomic Variation Analysis of Coronavirus to Better Understand the Spread of COVID-19","funder_award_id":"2027667","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8626495762","display_name":"PIPP Phase I: Comprehensive, Integrated, Intelligent System for Early and Accurate Pandemic Prediction, Prevention, and Preparation at Personal and Population Levels","funder_award_id":"2200255","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G9000881257","display_name":"Robust mapping of chromatin loops from sparse or single cell Hi-C data with DeepLoop","funder_award_id":"R01HG009658","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"},{"id":"https://openalex.org/G9000920411","display_name":"Alzheimer's MultiOme Data Repurposing: Artificial Intelligence, Network Medicine, and Therapeutics Discovery","funder_award_id":"U01AG073323","funder_id":"https://openalex.org/F4320337337","funder_display_name":"National Institute on Aging"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337337","display_name":"National Institute on Aging","ror":"https://ror.org/049v75w11"},{"id":"https://openalex.org/F4320337348","display_name":"National Human Genome Research Institute","ror":"https://ror.org/00baak391"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214605702.pdf","grobid_xml":"https://content.openalex.org/works/W7214605702.grobid-xml"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W1521626043","https://openalex.org/W2766453196","https://openalex.org/W2986232138","https://openalex.org/W2996604169","https://openalex.org/W3093934881","https://openalex.org/W4390783840","https://openalex.org/W4412778849","https://openalex.org/W7132676662"],"related_works":["https://openalex.org/W7131308666","https://openalex.org/W4394770110","https://openalex.org/W4412778849","https://openalex.org/W4414382370","https://openalex.org/W7131839959","https://openalex.org/W4416119658","https://openalex.org/W7154845626","https://openalex.org/W7214885819","https://openalex.org/W4410279898","https://openalex.org/W4408650090"],"abstract_inverted_index":{"Accurate":[0],"molecular":[1,6,26,39,46,102,106,109],"property":[2,110,215],"prediction":[3,216],"requires":[4],"effective":[5,71],"representations":[7,34],"that":[8,97,200],"can":[9],"describe":[10,48],"a":[11,43,94,123,131,144],"molecule":[12],"from":[13,57,158,182],"multiple":[14],"complementary":[15],"perspectives.":[16],"Existing":[17],"deep":[18],"learning":[19],"approaches":[20],"typically":[21],"use":[22],"SMILES":[23,41],"strings,":[24],"two-dimensional":[25],"graphs,":[27,103],"or":[28,67],"three-dimensional":[29],"conformations":[30,53,107],"as":[31],"inputs.":[32],"These":[33],"capture":[35,78],"different":[36],"aspects":[37],"of":[38,210,220,228],"information:":[40],"encodes":[42],"sequential":[44],"description,":[45],"graphs":[47],"atom-bond":[49],"connectivity,":[50],"and":[51,83,104,119,130,180,189,217],"3D":[52,105,120,138],"provide":[54],"spatial":[55],"information":[56],"atomic":[58],"coordinates.":[59],"However,":[60],"these":[61],"modalities":[62],"are":[63,162],"often":[64],"learned":[65],"separately":[66],"merged":[68],"with":[69,122,193],"low":[70],"fusion":[72,223],"operations,":[73],"which":[74],"may":[75],"not":[76],"sufficiently":[77],"interactions":[79],"among":[80],"sequential,":[81],"topological,":[82],"geometric":[84],"features.":[85],"In":[86],"this":[87],"work,":[88],"we":[89],"propose":[90],"Tri-Modality":[91],"Cross-Attention":[92],"(TMCA),":[93],"multimodal":[95],"framework":[96],"integrates":[98],"1D":[99,118,128],"SMILES,":[100],"2D":[101,146],"for":[108,116,126,136,186,213],"prediction.":[111],"TMCA":[112,172,201,229],"uses":[113],"pretrained":[114,134,160],"encoders":[115],"the":[117,127,137,141,156,159,183,203,208,218],"branches,":[121],"SMILES-based":[124],"Transformer":[125],"branch":[129],"recent":[132],"conformation-aware":[133],"model":[135],"branch.":[139],"At":[140],"same":[142],"time,":[143],"trainable":[145],"graph":[147],"encoder":[148],"is":[149,230],"designed":[150],"to":[151,164],"support":[152],"modality":[153],"fusion.":[154],"All":[155],"parameters":[157],"models":[161],"frozen":[163],"make":[165],"overall":[166,205],"training":[167],"more":[168],"efficient.":[169],"We":[170],"evaluate":[171],"on":[173],"four":[174],"datasets":[175],"(i.e.,":[176],"BBBP,":[177],"BACE,":[178],"ClinTox,":[179],"HIV)":[181],"MoleculeNet":[184],"database":[185],"classification":[187],"tasks":[188],"compare":[190],"its":[191],"performance":[192],"state-of-the-art":[194],"competing":[195],"approaches.":[196],"Experimental":[197],"results":[198],"show":[199],"achieves":[202],"best":[204],"performance,":[206],"demonstrating":[207],"value":[209],"multi-modality":[211],"integration":[212],"drug":[214],"effectiveness":[219],"our":[221],"cross-attention-based":[222],"strategy.":[224],"The":[225],"source":[226],"code":[227],"available":[231],"at:":[232],"https://github.com/Ay-Zhao/TMCA.":[233]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-09-29T00:00:00"}