{"id":"https://openalex.org/W7214913348","doi":"https://doi.org/10.48550/arxiv.2609.37384","title":"MoTIF-X: A Multimodal Tokenized Framework for Interpretable and Extensible Molecular Representation Learning","display_name":"MoTIF-X: A Multimodal Tokenized Framework for Interpretable and Extensible Molecular Representation Learning","publication_year":2026,"publication_date":"2026-09-29","ids":{"openalex":"https://openalex.org/W7214913348","doi":"https://doi.org/10.48550/arxiv.2609.37384"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.37384","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.37384","pdf_url":"https://arxiv.org/pdf/2609.37384","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.37384","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050666253","display_name":"Linqing Mo","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mo, Linqing","raw_affiliation_strings":["Department of Computer Science and Engineering , Michigan State University , East Lansing , 48824 , MI , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering , Michigan State University , East Lansing , 48824 , MI , USA","institution_ids":["https://openalex.org/I87216513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153680303","display_name":"Jiayu Zhou","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Jiayu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100427287","display_name":"Bin Chen","orcid":"https://orcid.org/0000-0001-8858-874X","observed_orcids":["https://orcid.org/0000-0001-8858-874X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Bin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/3002","display_name":"Drug Discovery"},"field":{"id":"https://openalex.org/fields/30","display_name":"Pharmacology, Toxicology and Pharmaceutics"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/3002","display_name":"Drug Discovery"},"field":{"id":"https://openalex.org/fields/30","display_name":"Pharmacology, Toxicology and Pharmaceutics"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":9.999999747378752e-05,"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/T13702","display_name":"Machine Learning in Healthcare","score":9.999999747378752e-05,"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/molecular-representation-learning","display_name":"molecular representation learning","score":0.9940000176429749},{"id":"https://openalex.org/keywords/hierarchical-contrastive-learning","display_name":"hierarchical contrastive learning","score":0.8169999718666077},{"id":"https://openalex.org/keywords/smiles","display_name":"SMILES","score":0.6830000281333923},{"id":"https://openalex.org/keywords/dihedral-angle","display_name":"dihedral angle","score":0.7799999713897705},{"id":"https://openalex.org/keywords/molecular-conformers","display_name":"molecular conformers","score":0.6660000085830688},{"id":"https://openalex.org/keywords/drug-likeness","display_name":"drug-likeness","score":0.5759999752044678},{"id":"https://openalex.org/keywords/drug-target-interaction-prediction","display_name":"drug-target interaction prediction","score":0.6779999732971191},{"id":"https://openalex.org/keywords/interpretability","display_name":"interpretability","score":0.8090000152587891},{"id":"https://openalex.org/keywords/computer-aided-drug-discovery","display_name":"computational drug discovery","score":0.890999972820282}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6888999938964844},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5698999762535095},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.550000011920929},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45249998569488525},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.4296000003814697},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.3993000090122223},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.39239999651908875},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3903999924659729},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.362199991941452},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3359000086784363},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.32010000944137573},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.310699999332428},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.29600000381469727},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.2897999882698059},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2678000032901764},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2624000012874603},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.25609999895095825},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.2549999952316284}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.37384","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.37384","pdf_url":"https://arxiv.org/pdf/2609.37384","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.37384","doi":"https://doi.org/10.48550/arxiv.2609.37384","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.37384","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.37384","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.37384","pdf_url":"https://arxiv.org/pdf/2609.37384","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214913348.pdf","grobid_xml":"https://content.openalex.org/works/W7214913348.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W7170147507"],"related_works":["https://openalex.org/W7139065237","https://openalex.org/W7131308666","https://openalex.org/W4413473479","https://openalex.org/W4401024452","https://openalex.org/W6992873280","https://openalex.org/W4387928939","https://openalex.org/W3201168459","https://openalex.org/W4403365201","https://openalex.org/W4413679442","https://openalex.org/W7214605702"],"abstract_inverted_index":{"Molecular":[0,9],"representation":[1],"learning":[2,76],"is":[3],"central":[4],"to":[5,164,180],"computer-aided":[6],"drug":[7],"discovery.":[8],"graphs,":[10],"SMILES":[11,90],"strings,":[12],"and":[13,28,40,64,80,91,120,155,178,215],"3D":[14],"conformations":[15],"provide":[16],"complementary":[17,148],"structural":[18],"information,":[19],"yet":[20],"many":[21],"multimodal":[22,62,95,153],"approaches":[23],"encode":[24],"these":[25,45,87,208],"views":[26],"independently":[27],"align":[29],"them":[30],"only":[31],"at":[32],"a":[33,50,213],"later":[34],"stage,":[35],"limiting":[36],"fine-grained":[37],"cross-modal":[38],"interaction":[39,166],"substructure-level":[41,193],"interpretability.":[42],"To":[43],"address":[44],"limitations,":[46],"we":[47],"introduce":[48],"MoTIF-X,":[49],"motif-centered":[51,189],"framework":[52,162,217],"that":[53],"uses":[54],"graph-grounded":[55],"chemical":[56],"motifs":[57],"as":[58,212],"shared":[59],"anchors":[60],"for":[61,218],"integration":[63],"interpretation.":[65],"Its":[66,188],"first":[67],"pretraining":[68,100],"stage":[69,85],"learns":[70],"motif":[71,196],"representations":[72,88],"through":[73,94],"hierarchical":[74],"contrastive":[75],"across":[77,174],"atomic,":[78],"motif,":[79],"molecular":[81,159,219],"scales.":[82],"The":[83],"second":[84],"contextualizes":[86],"with":[89,104,201],"torsion-angle":[92],"tokens":[93],"masked":[96],"token":[97],"modeling.":[98,220],"After":[99],"on":[101,114],"drug-like":[102],"molecules":[103],"multiple":[105],"conformers,":[106],"MoTIF-X":[107,211],"achieved":[108],"the":[109,121,126,135,147,161,169,175],"lowest":[110],"mean":[111],"absolute":[112],"error":[113],"all":[115],"nine":[116],"OpenADMET":[117],"ExpansionRx":[118],"endpoints":[119],"best":[122,170],"overall":[123],"performance":[124,173],"among":[125],"evaluated":[127,176],"methods.":[128],"Significance":[129],"analyses":[130],"supported":[131,146],"its":[132],"advantage":[133],"in":[134],"vast":[136],"majority":[137],"of":[138,150],"endpoint-baseline":[139],"comparisons":[140],"after":[141],"multiple-testing":[142],"correction.":[143],"Ablation":[144],"studies":[145],"contributions":[149],"motif-token":[151],"contextualization,":[152],"integration,":[154],"two-stage":[156],"pretraining.":[157],"Beyond":[158],"properties,":[160],"extended":[163],"drug-target":[165],"prediction,":[167],"achieving":[168],"average":[171],"classification":[172],"benchmarks":[177],"generalizing":[179],"an":[181],"external":[182],"drug-cold-start":[183],"dataset":[184],"without":[185],"additional":[186],"fine-tuning.":[187],"design":[190],"also":[191],"enabled":[192],"interpretation:":[194],"higher":[195],"attribution":[197],"scores":[198],"were":[199],"associated":[200],"larger":[202],"experimentally":[203],"measured":[204],"activity":[205],"shifts.":[206],"Together,":[207],"findings":[209],"support":[210],"transferable":[214],"interpretable":[216]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-01T00:00:00"}