{"id":"https://openalex.org/W4367677280","doi":"https://doi.org/10.1101/2023.05.01.538999","title":"Molecule-Morphology Contrastive Pretraining for Transferable Molecular Representation","display_name":"Molecule-Morphology Contrastive Pretraining for Transferable Molecular Representation","publication_year":2023,"publication_date":"2023-05-02","ids":{"openalex":"https://openalex.org/W4367677280","doi":"https://doi.org/10.1101/2023.05.01.538999"},"language":"en","primary_location":{"id":"doi:10.1101/2023.05.01.538999","doi":"https://doi.org/10.1101/2023.05.01.538999","is_oa":true,"landing_page_url":"https://doi.org/10.1101/2023.05.01.538999","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2023/05/28/2023.05.01.538999.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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2023/05/28/2023.05.01.538999.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051701750","display_name":"Cuong Q. Nguyen","orcid":"https://orcid.org/0000-0002-5151-1893","observed_orcids":["https://orcid.org/0000-0002-5151-1893"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Cuong Q. Nguyen","raw_affiliation_strings":["GSK, Artificial Intelligence and Machine Learning"],"raw_orcid":"https://orcid.org/0000-0002-5151-1893","affiliations":[{"raw_affiliation_string":"GSK, Artificial Intelligence and Machine Learning","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064285155","display_name":"Dante A. Pertusi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dante Pertusi","raw_affiliation_strings":["GSK, Medicine Design"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GSK, Medicine Design","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108519143","display_name":"Kim Branson","orcid":"https://orcid.org/0009-0004-5699-6369","observed_orcids":["https://orcid.org/0009-0004-5699-6369"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kim M. Branson","raw_affiliation_strings":["GSK, Artificial Intelligence and Machine Learning"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GSK, Artificial Intelligence and Machine Learning","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5051701750"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":6,"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":0.9984999895095825,"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":0.9984999895095825,"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":0.00019999999494757503,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.00019999999494757503,"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/cell-morphology","display_name":"cell morphology","score":0.7020000219345093},{"id":"https://openalex.org/keywords/image-based-profiling","display_name":"image-based profiling","score":0.8069999814033508},{"id":"https://openalex.org/keywords/molecular-graphs","display_name":"molecular graphs","score":0.48399999737739563},{"id":"https://openalex.org/keywords/graph-neural-networks","display_name":"graph neural networks","score":0.9020000100135803},{"id":"https://openalex.org/keywords/qsar","display_name":"QSAR","score":0.6880000233650208},{"id":"https://openalex.org/keywords/molecular-property-prediction","display_name":"molecular property prediction","score":0.8389999866485596},{"id":"https://openalex.org/keywords/transfer-learning","display_name":"transfer learning","score":0.5400000214576721},{"id":"https://openalex.org/keywords/pharmacokinetic-prediction","display_name":"pharmacokinetic prediction","score":0.6890000104904175}],"concepts":[{"id":"https://openalex.org/C164126121","wikidata":"https://www.wikidata.org/wiki/Q766383","display_name":"Quantitative structure\u2013activity relationship","level":2,"score":0.6532917022705078},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6161196231842041},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5854370594024658},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5349814891815186},{"id":"https://openalex.org/C2777655017","wikidata":"https://www.wikidata.org/wiki/Q1501161","display_name":"Toolbox","level":2,"score":0.4737478196620941},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4226458966732025},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4123087525367737},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35231539607048035},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1101/2023.05.01.538999","doi":"https://doi.org/10.1101/2023.05.01.538999","is_oa":true,"landing_page_url":"https://doi.org/10.1101/2023.05.01.538999","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2023/05/28/2023.05.01.538999.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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.1101/2023.05.01.538999","doi":"https://doi.org/10.1101/2023.05.01.538999","is_oa":true,"landing_page_url":"https://doi.org/10.1101/2023.05.01.538999","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2023/05/28/2023.05.01.538999.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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"score":0.4399999976158142,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4367677280.pdf","grobid_xml":"https://content.openalex.org/works/W4367677280.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W1988037271","https://openalex.org/W1991238353","https://openalex.org/W2016979469","https://openalex.org/W2021748110","https://openalex.org/W2026909852","https://openalex.org/W2096541451","https://openalex.org/W2290847742","https://openalex.org/W2331343529","https://openalex.org/W2498090354","https://openalex.org/W2509141893","https://openalex.org/W2565684601","https://openalex.org/W2594183968","https://openalex.org/W2606209624","https://openalex.org/W2627654851","https://openalex.org/W2728842897","https://openalex.org/W2751756351","https://openalex.org/W2785813126","https://openalex.org/W2806547269","https://openalex.org/W2810144292","https://openalex.org/W2922305141","https://openalex.org/W2966357564","https://openalex.org/W3006781192","https://openalex.org/W3046863270","https://openalex.org/W3100157108","https://openalex.org/W3102400420","https://openalex.org/W3113917069","https://openalex.org/W3127773563","https://openalex.org/W3196897371","https://openalex.org/W3216996162","https://openalex.org/W4281854682","https://openalex.org/W4319592282","https://openalex.org/W4360951525","https://openalex.org/W4394320243","https://openalex.org/W4399907796","https://openalex.org/W6920742332"],"related_works":["https://openalex.org/W2324336873","https://openalex.org/W4293148923","https://openalex.org/W4315490975","https://openalex.org/W4367597904","https://openalex.org/W2532035159","https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4224009465","https://openalex.org/W4286629047","https://openalex.org/W3117501106"],"abstract_inverted_index":{"Abstract":[0],"Image-based":[1],"profiling":[2],"techniques":[3,24],"have":[4,25],"become":[5],"increasingly":[6],"popular":[7],"over":[8],"the":[9,38,49,93,163,170],"past":[10],"decade":[11],"for":[12,69,141,175],"their":[13],"applications":[14],"in":[15,113,139],"target":[16],"identification,":[17],"mechanism-of-action":[18],"inference,":[19],"and":[20,76,86,96,130,137,143],"assay":[21],"development.":[22],"These":[23],"generated":[26],"large":[27],"datasets":[28],"of":[29,40,51,73,103,135,165],"cellular":[30,77,153],"morphologies,":[31],"which":[32],"are":[33,122],"typically":[34],"used":[35],"to":[36,54,82],"investigate":[37],"effects":[39],"small":[41],"molecule":[42],"perturbagens.":[43],"In":[44],"this":[45],"work,":[46],"we":[47],"extend":[48],"impact":[50],"such":[52],"dataset":[53,117],"improving":[55],"quantitative":[56],"structure-activity":[57],"relationship":[58],"(QSAR)":[59],"models":[60],"by":[61],"introducing":[62],"Molecule-Morphology":[63],"Contrastive":[64],"Pretraining":[65],"(MoCoP),":[66],"a":[67],"framework":[68],"learning":[70,172],"multi-modal":[71],"representation":[72],"molecular":[74,109,156],"graphs":[75,157],"morphologies.":[78],"We":[79],"scale":[80],"MoCoP":[81,99,159],"approximately":[83],"100K":[84],"molecules":[85],"600K":[87],"morphological":[88],"profiles":[89],"using":[90,158],"data":[91,129,145],"from":[92],"JUMP-CP":[94],"Consortium":[95],"show":[97,131],"that":[98,151],"consistently":[100],"improves":[101],"performances":[102],"graph":[104],"neural":[105],"networks":[106],"(GNNs)":[107],"on":[108,125],"property":[110],"prediction":[111],"tasks":[112],"ChEMBL20":[114],"across":[115],"all":[116],"sizes.":[118],"The":[119],"pretrained":[120],"GNNs":[121],"also":[123],"evaluated":[124],"internal":[126],"GSK":[127],"pharmacokinetic":[128],"an":[132],"average":[133],"improvement":[134],"2.6%":[136],"6.3%":[138],"AUPRC":[140],"full":[142],"low":[144],"regimes,":[146],"respectively.":[147],"Our":[148],"findings":[149],"suggest":[150],"integrating":[152],"morphologies":[154],"with":[155],"can":[160],"significantly":[161],"improve":[162],"performance":[164],"QSAR":[166,176],"models,":[167],"ultimately":[168],"expanding":[169],"deep":[171],"toolbox":[173],"available":[174],"applications.":[177]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-10-08T09:06:37.294493","created_date":"2025-10-10T00:00:00"}