{"id":"https://openalex.org/W7159951782","doi":"https://doi.org/10.1186/s13321-026-01209-2","title":"AdaptMol: domain adaptation for molecular image recognition with limited supervision","display_name":"AdaptMol: domain adaptation for molecular image recognition with limited supervision","publication_year":2026,"publication_date":"2026-05-02","ids":{"openalex":"https://openalex.org/W7159951782","doi":"https://doi.org/10.1186/s13321-026-01209-2","pmid":"https://pubmed.ncbi.nlm.nih.gov/42070053"},"language":"en","primary_location":{"id":"doi:10.1186/s13321-026-01209-2","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-026-01209-2","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","license_id":"https://openalex.org/licenses/cc-by","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/s13321-026-01209-2","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126419140","display_name":"Feng Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Feng Hu","raw_affiliation_strings":["School of Computing Technologies, RMIT University, Melbourne, VIC, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing Technologies, RMIT University, Melbourne, VIC, Australia","institution_ids":["https://openalex.org/I82951845"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126373964","display_name":"Estrid He","orcid":null},"institutions":[{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Estrid He","raw_affiliation_strings":["School of Computing Technologies, RMIT University, Melbourne, VIC, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing Technologies, RMIT University, Melbourne, VIC, Australia","institution_ids":["https://openalex.org/I82951845"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067214173","display_name":"Karin Verspoor","orcid":"https://orcid.org/0000-0002-8661-1544"},"institutions":[{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Karin Verspoor","raw_affiliation_strings":["School of Computing Technologies, RMIT University, Melbourne, VIC, Australia. karin.verspoor@rmit.edu.au"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing Technologies, RMIT University, Melbourne, VIC, Australia. karin.verspoor@rmit.edu.au","institution_ids":["https://openalex.org/I82951845"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5067214173"],"corresponding_institution_ids":["https://openalex.org/I82951845"],"apc_list":{"value":2190,"currency":"USD","value_usd":2190},"apc_paid":{"value":2190,"currency":"USD","value_usd":2190},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.35295685,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"18","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.8525999784469604,"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"}},"topics":[{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.8525999784469604,"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/T10211","display_name":"Computational Drug Discovery Methods","score":0.034299999475479126,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.03280000016093254,"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/robustness","display_name":"Robustness (evolution)","score":0.6326000094413757},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.5670999884605408},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5590999722480774},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.5544999837875366},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.46160000562667847},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4546000063419342},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.45019999146461487},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.42890000343322754},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4244999885559082}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7541999816894531},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.635699987411499},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6326000094413757},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.5670999884605408},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5590999722480774},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.5544999837875366},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.46160000562667847},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4546000063419342},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.45019999146461487},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4345000088214874},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.42890000343322754},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4244999885559082},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.41029998660087585},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.37720000743865967},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.3675999939441681},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.3614000082015991},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.34779998660087585},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.30730000138282776},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.29820001125335693},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.296099990606308},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2881999909877777},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.2858999967575073},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2833000123500824},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2806999981403351},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.25609999895095825}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1186/s13321-026-01209-2","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-026-01209-2","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","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},{"id":"pmid:42070053","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42070053","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":"Journal Article"},{"id":"pmh:oai:doaj.org/article:d6a46b77b2b04dfd834451ebf5390ce3","is_oa":false,"landing_page_url":"https://doaj.org/article/d6a46b77b2b04dfd834451ebf5390ce3","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Cheminformatics, Vol 18, Iss 1 (2026)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:13330488","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13330488/","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J Cheminform","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/s13321-026-01209-2","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-026-01209-2","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","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1966456689","https://openalex.org/W1975147762","https://openalex.org/W1990451437","https://openalex.org/W2031489346","https://openalex.org/W2101926813","https://openalex.org/W2119002393","https://openalex.org/W2177317049","https://openalex.org/W2621742623","https://openalex.org/W2740407088","https://openalex.org/W2766736793","https://openalex.org/W2895677720","https://openalex.org/W2909063104","https://openalex.org/W2947423323","https://openalex.org/W2963734039","https://openalex.org/W3007750971","https://openalex.org/W3092396754","https://openalex.org/W3097598035","https://openalex.org/W3138074128","https://openalex.org/W3138516171","https://openalex.org/W3159789740","https://openalex.org/W3203895579","https://openalex.org/W3208328927","https://openalex.org/W4206029367","https://openalex.org/W4224926211","https://openalex.org/W4282936206","https://openalex.org/W4283761122","https://openalex.org/W4289936378","https://openalex.org/W4306179830","https://openalex.org/W4309218736","https://openalex.org/W4353112191","https://openalex.org/W4382199684","https://openalex.org/W4390872067","https://openalex.org/W4400358811","https://openalex.org/W4402778052","https://openalex.org/W4409369201"],"related_works":[],"abstract_inverted_index":{"Optical":[0],"Chemical":[1],"Structure":[2],"Recognition":[3],"(OCSR)":[4],"aims":[5],"to":[6,35,37,69,147,159,229,245,255,302],"convert":[7],"two-dimensional":[8],"molecular":[9,176,200,216,231],"images":[10,201,232],"into":[11],"machine-readable":[12],"formats":[13],"such":[14],"as":[15,218],"SMILES":[16],"strings.":[17],"Deep":[18],"learning":[19],"has":[20],"substantially":[21],"improved":[22],"OCSR":[23],"performance,":[24],"yet":[25],"most":[26],"methods":[27],"rely":[28],"on":[29,93,170],"synthetic":[30,68,94,228],"training":[31,89,257],"data":[32,71,156,253,258],"and":[33,47,96,105,183,205,222,268,298],"struggle":[34],"generalize":[36],"real-world":[38,70],"inputs,":[39],"especially":[40],"hand-drawn":[41,175,230],"diagrams,":[42],"where":[43],"stroke":[44],"width,":[45],"geometry,":[46],"drawing":[48],"conventions":[49],"vary":[50],"widely":[51],"across":[52,130,196,249],"individuals.":[53],"In":[54],"this":[55],"work,":[56],"we":[57,136],"propose":[58,209],"an":[59,83,211],"image-to-graph":[60,212],"model":[61,92,99,179,213,263],"AdaptMol":[62,81],"that":[63,86,111,124,214,277,289],"enables":[64],"effective":[65,225],"transfer":[66,226],"from":[67,202,227],"without":[72,233],"requiring":[73,234],"manual":[74],"graph":[75,237],"annotations":[76],"in":[77,116,306],"the":[78,161,164,185,270],"target":[79,172,235],"domains.":[80,131],"is":[82,110],"integrated":[84],"pipeline":[85],"starts":[87],"with":[88,251,279],"a":[90,154,285],"base":[91,165,262],"data,":[95],"then":[97],"refines":[98],"representations":[100],"through":[101,293],"unsupervised":[102],"domain":[103,134,236],"adaptation":[104],"self-training.":[106],"Our":[107],"key":[108],"insight":[109],"bond":[112,247],"features":[113,248],"are":[114,125],"domain-invariant":[115],"nature;":[117],"they":[118],"encode":[119],"structural":[120],"relationships":[121],"between":[122],"atoms":[123,221],"independent":[126],"of":[127,163,220,274],"visual":[128],"variations":[129],"Thus,":[132],"during":[133],"adaptation,":[135],"align":[137,246],"bond-level":[138],"feature":[139],"distributions":[140],"via":[141],"class-conditional":[142,241],"Maximum":[143,242],"Mean":[144,243],"Discrepancy":[145,244],"(MMD)":[146],"enforce":[148],"cross-domain":[149],"consistency.":[150],"We":[151,239,282],"also":[152],"design":[153],"comprehensive":[155,252],"augmentation":[157,254],"strategy":[158],"enhance":[160],"robustness":[162],"model,":[166],"facilitating":[167],"stable":[168],"self-training":[169,267],"unlabeled":[171],"samples.":[173],"On":[174],"images,":[177],"our":[178],"achieves":[180],"82.6%":[181],"accuracy":[182,264],"outperforms":[184],"best":[186],"prior":[187,275],"method":[188],"by":[189],"10.7":[190],"points,":[191],"while":[192],"maintaining":[193],"competitive":[194],"performance":[195],"four":[197],"benchmarks":[198],"comprising":[199],"scientific":[203],"literature":[204],"patent":[206],"documents.Scientific":[207],"contributionWe":[208],"AdaptMol,":[210],"predicts":[215],"structures":[217],"graphs":[219],"bonds,":[223],"achieving":[224],"annotations.":[238],"combine":[240],"domains":[250],"increase":[256],"variation,":[259],"jointly":[260],"improving":[261],"sufficiently":[265],"for":[266],"addressing":[269],"critical":[271],"failure":[272],"mode":[273],"approaches":[276],"begin":[278],"insufficient":[280],"accuracy.":[281],"further":[283],"introduce":[284],"dual":[286],"position":[287],"representation":[288],"supervises":[290],"atom":[291,307],"positions":[292],"both":[294],"discrete":[295],"coordinate":[296],"tokens":[297],"continuous":[299],"spatial":[300],"heatmaps":[301],"reduce":[303],"false":[304],"positives":[305],"localization.":[308]},"counts_by_year":[],"updated_date":"2026-08-06T08:24:18.245995","created_date":"2026-05-04T00:00:00"}