{"id":"https://openalex.org/W4416246306","doi":"https://doi.org/10.48550/arxiv.2511.09774","title":"Solvaformer: an SE(3)-equivariant graph transformer for small molecule solubility prediction","display_name":"Solvaformer: an SE(3)-equivariant graph transformer for small molecule solubility prediction","publication_year":2025,"publication_date":"2025-11-12","ids":{"openalex":"https://openalex.org/W4416246306","doi":"https://doi.org/10.48550/arxiv.2511.09774"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2511.09774","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.09774","pdf_url":"https://arxiv.org/pdf/2511.09774","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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","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/2511.09774","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111214584","display_name":"Jonathan Broadbent","orcid":"https://orcid.org/0009-0000-7255-553X","observed_orcids":["https://orcid.org/0009-0000-7255-553X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Broadbent, Jonathan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Bailey, Michael","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bailey, Michael","raw_affiliation_strings":["Louis De Lescure Sanofi , CMC Synthetics Cambridge , MA 02141","Sanofi , Digital R&D Toronto , ON M5V 0E9"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Louis De Lescure Sanofi , CMC Synthetics Cambridge , MA 02141","institution_ids":[]},{"raw_affiliation_string":"Sanofi , Digital R&D Toronto , ON M5V 0E9","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032774792","display_name":"Mingxuan Li","orcid":"https://orcid.org/0009-0006-7883-3303","observed_orcids":["https://orcid.org/0009-0006-7883-3303"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Mingxuan","raw_affiliation_strings":["Sanofi , Digital R&D Cambridge , MA 02141"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sanofi , Digital R&D Cambridge , MA 02141","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041404124","display_name":"Abhishek Paul","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Paul, Abhishek","raw_affiliation_strings":["Sanofi , CMC Synthetics Cambridge , MA 02141"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sanofi , CMC Synthetics Cambridge , MA 02141","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048595702","display_name":"Louis de Lescure","orcid":"https://orcid.org/0000-0002-5777-3771","observed_orcids":["https://orcid.org/0000-0002-5777-3771"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"De Lescure, Louis","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128217768","display_name":"Paul Chauvin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210093939","display_name":"Sanofi (Spain)","ror":"https://ror.org/00g51ew42","country_code":"ES","type":"company","lineage":["https://openalex.org/I3018075036","https://openalex.org/I4210093939"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Chauvin, Paul","raw_affiliation_strings":["Sanofi , Digital R&D Barcelona , 08016 , Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sanofi , Digital R&D Barcelona , 08016 , Spain","institution_ids":["https://openalex.org/I4210093939"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092566344","display_name":"Lorenzo Kogler-Anele","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kogler-Anele, Lorenzo","raw_affiliation_strings":["Jangjou Sanofi , CMC Synthetics Cambridge , MA 02141","Sanofi , Digital R&D Toronto , ON M5V 0E9 Yasser"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jangjou Sanofi , CMC Synthetics Cambridge , MA 02141","institution_ids":[]},{"raw_affiliation_string":"Sanofi , Digital R&D Toronto , ON M5V 0E9 Yasser","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106018469","display_name":"Yasser Jangjou","orcid":"https://orcid.org/0009-0005-9839-5948","observed_orcids":["https://orcid.org/0009-0005-9839-5948"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jangjou, Yasser","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5010048143","display_name":"Sven J\u00e4ger","orcid":"https://orcid.org/0000-0003-1410-9114","observed_orcids":["https://orcid.org/0000-0003-1410-9114"]},"institutions":[{"id":"https://openalex.org/I4210138838","display_name":"Sanofi (Germany)","ror":"https://ror.org/03ytdtb31","country_code":"DE","type":"company","lineage":["https://openalex.org/I3018075036","https://openalex.org/I4210138838"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jager, Sven","raw_affiliation_strings":["Sanofi , Digital R&D Frankfurt , 65929 , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sanofi , Digital R&D Frankfurt , 65929 , Germany","institution_ids":["https://openalex.org/I4210138838"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"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":0.6234999895095825,"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":0.6234999895095825,"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":0.27469998598098755,"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":0.06459999829530716,"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/solvation-free-energy","display_name":"solvation free energy","score":0.8560000061988831},{"id":"https://openalex.org/keywords/se-3-equivariance","display_name":"SE(3) equivariance","score":0.8960000276565552},{"id":"https://openalex.org/keywords/graph-transformer","display_name":"graph transformer","score":0.8870000243186951},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"multi-task learning","score":0.6800000071525574},{"id":"https://openalex.org/keywords/hydrogen-bonding","display_name":"hydrogen bonding","score":0.6240000128746033},{"id":"https://openalex.org/keywords/regioisomers","display_name":"regioisomers","score":0.8370000123977661},{"id":"https://openalex.org/keywords/interpretability","display_name":"interpretability","score":0.6800000071525574}],"concepts":[{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.6383000016212463},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5338000059127808},{"id":"https://openalex.org/C75079739","wikidata":"https://www.wikidata.org/wiki/Q1571801","display_name":"Intramolecular force","level":2,"score":0.5094000101089478},{"id":"https://openalex.org/C166950319","wikidata":"https://www.wikidata.org/wiki/Q245031","display_name":"Intermolecular force","level":3,"score":0.4819999933242798},{"id":"https://openalex.org/C155574463","wikidata":"https://www.wikidata.org/wiki/Q170731","display_name":"Solubility","level":2,"score":0.4788999855518341},{"id":"https://openalex.org/C79772020","wikidata":"https://www.wikidata.org/wiki/Q5159264","display_name":"Conditional independence","level":2,"score":0.45559999346733093},{"id":"https://openalex.org/C161624437","wikidata":"https://www.wikidata.org/wiki/Q1988322","display_name":"Small molecule","level":2,"score":0.4449000060558319},{"id":"https://openalex.org/C148093993","wikidata":"https://www.wikidata.org/wiki/Q739398","display_name":"Solvation","level":3,"score":0.4124000072479248},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.39430001378059387},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.36820000410079956},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3580999970436096},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.3562999963760376},{"id":"https://openalex.org/C57691317","wikidata":"https://www.wikidata.org/wiki/Q1289248","display_name":"Scalar (mathematics)","level":2,"score":0.34790000319480896},{"id":"https://openalex.org/C186060115","wikidata":"https://www.wikidata.org/wiki/Q30336093","display_name":"Biological system","level":1,"score":0.3337000012397766},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.3285999894142151},{"id":"https://openalex.org/C2780022179","wikidata":"https://www.wikidata.org/wiki/Q1986794","display_name":"Molecular graph","level":3,"score":0.32749998569488525},{"id":"https://openalex.org/C132459708","wikidata":"https://www.wikidata.org/wiki/Q744069","display_name":"Extrapolation","level":2,"score":0.32710000872612},{"id":"https://openalex.org/C79518650","wikidata":"https://www.wikidata.org/wiki/Q2081431","display_name":"Integrator","level":3,"score":0.32109999656677246},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3199000060558319},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31929999589920044},{"id":"https://openalex.org/C88230418","wikidata":"https://www.wikidata.org/wiki/Q131476","display_name":"Graph theory","level":2,"score":0.29989999532699585},{"id":"https://openalex.org/C164126121","wikidata":"https://www.wikidata.org/wiki/Q766383","display_name":"Quantitative structure\u2013activity relationship","level":2,"score":0.2957000136375427},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.28949999809265137},{"id":"https://openalex.org/C32909587","wikidata":"https://www.wikidata.org/wiki/Q11369","display_name":"Molecule","level":2,"score":0.27709999680519104},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26899999380111694},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.26739999651908875},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.26660001277923584},{"id":"https://openalex.org/C50942859","wikidata":"https://www.wikidata.org/wiki/Q4967193","display_name":"Rectification","level":3,"score":0.2597000002861023},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C187593909","wikidata":"https://www.wikidata.org/wiki/Q838024","display_name":"Bond graph","level":2,"score":0.25609999895095825},{"id":"https://openalex.org/C2780615836","wikidata":"https://www.wikidata.org/wiki/Q2471869","display_name":"USable","level":2,"score":0.2549000084400177},{"id":"https://openalex.org/C107908354","wikidata":"https://www.wikidata.org/wiki/Q4781456","display_name":"Applicability domain","level":3,"score":0.2533999979496002}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2511.09774","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.09774","pdf_url":"https://arxiv.org/pdf/2511.09774","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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2511.09774","doi":"https://doi.org/10.48550/arxiv.2511.09774","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.09774","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:2511.09774","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.09774","pdf_url":"https://arxiv.org/pdf/2511.09774","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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416246306.pdf","grobid_xml":"https://content.openalex.org/works/W4416246306.grobid-xml"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W2041644459","https://openalex.org/W2125285583","https://openalex.org/W3118102630","https://openalex.org/W4206142589","https://openalex.org/W4283641078","https://openalex.org/W4320011602","https://openalex.org/W4362586627","https://openalex.org/W4392918434"],"related_works":["https://openalex.org/W7213306435","https://openalex.org/W7213870219","https://openalex.org/W4417328599","https://openalex.org/W4412984965","https://openalex.org/W4320011602","https://openalex.org/W7128698064","https://openalex.org/W4416297816","https://openalex.org/W7202072739","https://openalex.org/W7138883066","https://openalex.org/W7169859900"],"abstract_inverted_index":{"Accurate":[0],"prediction":[1,164],"of":[2],"small":[3],"molecule":[4],"solubility":[5,80,146],"using":[6,87],"material-sparing":[7],"approaches":[8,25,114],"is":[9,20],"critical":[10],"for":[11],"accelerating":[12],"synthesis":[13],"and":[14,22,83,97,113,124,158,179],"process":[15],"optimization,":[16],"yet":[17],"experimental":[18,99,180],"measurement":[19],"costly":[21],"many":[23],"learning":[24],"either":[26],"depend":[27],"on":[28,93,98,176],"quantumderived":[29],"descriptors":[30],"or":[31],"offer":[32],"limited":[33],"interpretability.":[34],"We":[35,70],"introduce":[36],"Solvaformer,":[37],"a":[38,74,115,171],"geometry-aware":[39],"graph":[40],"transformer":[41],"that":[42,91,144],"models":[43,112],"solutions":[44],"as":[45],"multiple":[46],"molecules":[47],"with":[48,58,170],"independent":[49],"SE(3)":[50],"symmetries.":[51],"The":[52],"architecture":[53],"combines":[54],"intramolecular":[55],"SE(3)-equivariant":[56],"attention":[57,130],"intermolecular":[59],"scalar":[60],"attention,":[61],"enabling":[62],"cross-molecular":[63],"communication":[64],"without":[65],"imposing":[66],"spurious":[67],"relative":[68],"geometry.":[69],"train":[71],"Solvaformer":[72,103,153],"in":[73,148],"multi-task":[75],"setting":[76],"to":[77,161],"predict":[78],"both":[79],"(log":[81],"S)":[82],"solvation":[84],"free":[85],"energy,":[86],"an":[88,121,155],"alternating-batch":[89],"regimen":[90],"trains":[92],"quantum-mechanical":[94],"data":[95],"(CombiSolv-QM)":[96],"measurements":[100],"(BigSolDB":[101],"2.0).":[102],"attains":[104],"the":[105,110],"strongest":[106],"overall":[107],"performance":[108],"among":[109],"learned":[111],"DFT-assisted":[116],"gradient-boosting":[117],"baseline,":[118],"while":[119],"outperforming":[120],"EquiformerV2":[122],"ablation":[123],"sequence-based":[125],"alternatives.":[126],"In":[127],"addition,":[128],"token-level":[129],"produces":[131],"chemically":[132],"coherent":[133],"attributions:":[134],"case":[135],"studies":[136],"recover":[137],"known":[138],"intra-":[139],"vs.":[140],"inter-molecular":[141],"hydrogen-bonding":[142],"patterns":[143],"govern":[145],"differences":[147],"positional":[149],"isomers.":[150],"Taken":[151],"together,":[152],"provides":[154],"accurate,":[156],"scalable,":[157],"interpretable":[159],"approach":[160],"solution-phase":[162],"property":[163],"by":[165],"uniting":[166],"geometric":[167],"inductive":[168],"bias":[169],"mixed":[172],"dataset":[173],"training":[174],"strategy":[175],"complementary":[177],"computational":[178],"data.":[181]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-11-15T00:00:00"}