{"id":"https://openalex.org/W4410595594","doi":"https://doi.org/10.1186/s13321-025-01004-5","title":"Benchmarking molecular conformer augmentation with context-enriched training: graph-based transformer versus GNN models","display_name":"Benchmarking molecular conformer augmentation with context-enriched training: graph-based transformer versus GNN models","publication_year":2025,"publication_date":"2025-05-22","ids":{"openalex":"https://openalex.org/W4410595594","doi":"https://doi.org/10.1186/s13321-025-01004-5","pmid":"https://pubmed.ncbi.nlm.nih.gov/40405272"},"language":"en","primary_location":{"id":"doi:10.1186/s13321-025-01004-5","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-025-01004-5","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-025-01004-5","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","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://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-025-01004-5","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028658142","display_name":"Cecile Valsecchi","orcid":"https://orcid.org/0000-0002-5535-053X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Cecile Valsecchi","raw_affiliation_strings":["Discovery, Product Development and Supply, Janssen Cilag S.p.a., Viale Fulvio Testi 280/6, 20126, Milano, Italy. cvalsecc@its.jnj.com"],"affiliations":[{"raw_affiliation_string":"Discovery, Product Development and Supply, Janssen Cilag S.p.a., Viale Fulvio Testi 280/6, 20126, Milano, Italy. cvalsecc@its.jnj.com","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039286688","display_name":"Jose A. Arjona-Medina","orcid":"https://orcid.org/0000-0002-5033-4725"},"institutions":[{"id":"https://openalex.org/I4210163156","display_name":"Complejo Hospitalario Universitario de Toledo","ror":"https://ror.org/04q4ppz72","country_code":"ES","type":"healthcare","lineage":["https://openalex.org/I4210141158","https://openalex.org/I4210163156"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Jose A. Arjona-Medina","raw_affiliation_strings":["Discovery, Product Development and Supply, Janssen Cilag S.p.a., C. R\u00edo Jarama 75, 45007, Toledo, Spain"],"affiliations":[{"raw_affiliation_string":"Discovery, Product Development and Supply, Janssen Cilag S.p.a., C. R\u00edo Jarama 75, 45007, Toledo, Spain","institution_ids":["https://openalex.org/I4210163156"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030110742","display_name":"Natalia Dyubankova","orcid":"https://orcid.org/0000-0002-5892-3778"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Natalia Dyubankova","raw_affiliation_strings":["Discovery, Product Development and Supply, Janssen Pharmaceutica N.V., Turnhoutseweg 30, 2340, Beerse, Belgium. ndyubank@its.jnj.com"],"affiliations":[{"raw_affiliation_string":"Discovery, Product Development and Supply, Janssen Pharmaceutica N.V., Turnhoutseweg 30, 2340, Beerse, Belgium. ndyubank@its.jnj.com","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091636547","display_name":"Ramil Nugmanov","orcid":"https://orcid.org/0000-0002-8541-9681"},"institutions":[{"id":"https://openalex.org/I137982388","display_name":"Janssen (Belgium)","ror":"https://ror.org/04yzcpd71","country_code":"BE","type":"company","lineage":["https://openalex.org/I1330063522","https://openalex.org/I137982388"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Ramil Nugmanov","raw_affiliation_strings":["Discovery, Product Development and Supply, Janssen Pharmaceutica N.V., Turnhoutseweg 30, 2340, Beerse, Belgium"],"affiliations":[{"raw_affiliation_string":"Discovery, Product Development and Supply, Janssen Pharmaceutica N.V., Turnhoutseweg 30, 2340, Beerse, Belgium","institution_ids":["https://openalex.org/I137982388"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5028658142"],"corresponding_institution_ids":[],"apc_list":{"value":1290,"currency":"GBP","value_usd":1582},"apc_paid":{"value":1290,"currency":"GBP","value_usd":1582},"fwci":0.4667,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.59236412,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"17","issue":"1","first_page":"80","last_page":"80"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9980000257492065,"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/T10683","display_name":"Mass Spectrometry Techniques and Applications","score":0.9817000031471252,"subfield":{"id":"https://openalex.org/subfields/1607","display_name":"Spectroscopy"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.8251906633377075},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6733722686767578},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6043304800987244},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.47162652015686035},{"id":"https://openalex.org/keywords/conformational-isomerism","display_name":"Conformational isomerism","score":0.4547601640224457},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.43131494522094727},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4250502288341522},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3376137614250183},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.21986722946166992},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.1945887804031372},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12967973947525024},{"id":"https://openalex.org/keywords/molecule","display_name":"Molecule","score":0.11072742938995361},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.08543425798416138},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.08348506689071655}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.8251906633377075},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6733722686767578},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6043304800987244},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.47162652015686035},{"id":"https://openalex.org/C18705241","wikidata":"https://www.wikidata.org/wiki/Q1128023","display_name":"Conformational isomerism","level":3,"score":0.4547601640224457},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.43131494522094727},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4250502288341522},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3376137614250183},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.21986722946166992},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.1945887804031372},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12967973947525024},{"id":"https://openalex.org/C32909587","wikidata":"https://www.wikidata.org/wiki/Q11369","display_name":"Molecule","level":2,"score":0.11072742938995361},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.08543425798416138},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.08348506689071655},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1186/s13321-025-01004-5","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-025-01004-5","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-025-01004-5","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},{"id":"pmid:40405272","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40405272","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":null},{"id":"pmh:oai:doaj.org/article:dbb41081feaf49c8bbed9ab955666e93","is_oa":true,"landing_page_url":"https://doaj.org/article/dbb41081feaf49c8bbed9ab955666e93","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Cheminformatics, Vol 17, Iss 1, Pp 1-15 (2025)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:12100853","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12100853","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J Cheminform","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/s13321-025-01004-5","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-025-01004-5","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-025-01004-5","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","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":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4410595594.pdf","grobid_xml":"https://content.openalex.org/works/W4410595594.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W1988037271","https://openalex.org/W2004226047","https://openalex.org/W2194775991","https://openalex.org/W2805401872","https://openalex.org/W2886791556","https://openalex.org/W2913340405","https://openalex.org/W3023204497","https://openalex.org/W3039711511","https://openalex.org/W3114339437","https://openalex.org/W3199467597","https://openalex.org/W4206367183","https://openalex.org/W4214868967","https://openalex.org/W4226128774","https://openalex.org/W4283836015","https://openalex.org/W4311366447","https://openalex.org/W4318952054","https://openalex.org/W4321769975","https://openalex.org/W4360780118","https://openalex.org/W4386804175","https://openalex.org/W4389068696","https://openalex.org/W4390221451","https://openalex.org/W4392110488","https://openalex.org/W4395481566","https://openalex.org/W6601258443","https://openalex.org/W6602680078","https://openalex.org/W6603109618","https://openalex.org/W6609523394","https://openalex.org/W6609649096","https://openalex.org/W6825770484"],"related_works":["https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2059640416","https://openalex.org/W1490753184","https://openalex.org/W2284465472","https://openalex.org/W2291782699","https://openalex.org/W1993948687","https://openalex.org/W2000169967","https://openalex.org/W2112883198"],"abstract_inverted_index":{"The":[0],"field":[1],"of":[2,72,85,139,148],"molecular":[3,13,156],"representation":[4,157],"has":[5],"witnessed":[6],"a":[7,31,62,152],"shift":[8],"towards":[9],"models":[10,49,59,74,77,123,150],"trained":[11],"on":[12,78,93,105,128],"structures":[14],"represented":[15],"by":[16],"strings":[17],"or":[18],"graphs,":[19],"with":[20,57,124,135],"chemical":[21],"information":[22],"encoded":[23],"in":[24,54],"nodes":[25],"and":[26,35,39,46,98,112,141],"bonds.":[27],"Graph-based":[28,47],"representations":[29],"offer":[30],"more":[32],"realistic":[33],"depiction":[34],"support":[36],"3D":[37],"geometry":[38],"conformer-based":[40],"augmentation.":[41],"Graph":[42],"Neural":[43],"Networks":[44],"(GNNs)":[45],"Transformer":[48],"(GTs)":[50],"represent":[51],"two":[52],"paradigms":[53],"this":[55,66],"field,":[56],"GT":[58,73,122,149],"emerging":[60],"as":[61,151],"flexible":[63],"alternative.":[64],"In":[65],"study,":[67],"we":[68],"compare":[69],"the":[70,83,136,146],"performance":[71,114],"against":[75],"GNN":[76,133],"three":[79],"datasets.":[80],"We":[81,119],"explore":[82],"impact":[84],"training":[86,90,126],"procedures,":[87],"including":[88],"context-enriched":[89,125],"through":[91],"pretraining":[92],"quantum":[94],"mechanical":[95],"atomic-level":[96],"properties":[97],"auxiliary":[99],"task":[100],"training.":[101],"Our":[102,143],"analysis":[103],"focuses":[104],"sterimol":[106],"parameters":[107],"estimation,":[108,111],"binding":[109],"energy":[110],"generalization":[113],"for":[115,155],"transition":[116],"metal":[117],"complexes.":[118],"find":[120],"that":[121],"provide":[127],"par":[129],"results":[130],"compared":[131],"to":[132],"models,":[134],"added":[137],"advantages":[138],"speed":[140],"flexibility.":[142],"findings":[144],"highlight":[145],"potential":[147],"valid":[153],"alternative":[154],"learning":[158],"tasks.":[159]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}