{"id":"https://openalex.org/W7213699809","doi":null,"title":"Structure-to-Shift Prediction for 19F NMR: Comparison of Graph Neural Networks, HOSE Code, and Large Language Models","display_name":"Structure-to-Shift Prediction for 19F NMR: Comparison of Graph Neural Networks, HOSE Code, and Large Language Models","alternate_titles":[],"publication_year":2026,"publication_date":"2026-09-14","ids":{"openalex":"https://openalex.org/W7213699809"},"language":"en","primary_location":{"id":"pmh:oai:ueaeprints.uea.ac.uk:104577","doi":null,"is_oa":true,"landing_page_url":"https://ueaeprints.uea.ac.uk/id/eprint/104577/1/SMASH_Poster_2026.pdf","pdf_url":"https://ueaeprints.uea.ac.uk/id/eprint/104577/1/SMASH_Poster_2026.pdf","source":{"id":"https://openalex.org/S4306400384","display_name":"UEA Digital Repository (University of East Anglia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1118541","host_organization_name":"University of East Anglia","host_organization_lineage":["https://openalex.org/I1118541"],"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":"Conference or Workshop Item"},"parent_works":[],"lineage":["https://openalex.org/W7213699809"],"child_works_count":0,"type":"conference-paper","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://ueaeprints.uea.ac.uk/id/eprint/104577/1/SMASH_Poster_2026.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5147240267","display_name":"Nathan O'Neill","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"O'Neill, Nathan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5152188481","display_name":"Adam P. Jones","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jones, Adam P.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122445627","display_name":"Katharina T. Huber","orcid":"https://orcid.org/0000-0002-6368-7511","observed_orcids":["https://orcid.org/0000-0002-6368-7511"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huber, Katharina T.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057519519","display_name":"E. Kate Kemsley","orcid":"https://orcid.org/0000-0003-0669-3883","observed_orcids":["https://orcid.org/0000-0003-0669-3883"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kemsley, E. Kate","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046778406","display_name":"Carlos Cobas","orcid":"https://orcid.org/0000-0002-7494-7876","observed_orcids":["https://orcid.org/0000-0002-7494-7876"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cobas, Carlos","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102159009","display_name":"David C. Williamson","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Williamson, David","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049157976","display_name":"Gary J. Sharman","orcid":"https://orcid.org/0000-0002-6164-0736","observed_orcids":["https://orcid.org/0000-0002-6164-0736"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sharman, Gary","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5081955363","display_name":"John Hollerton","orcid":"https://orcid.org/0000-0003-1453-9931","observed_orcids":["https://orcid.org/0000-0003-1453-9931"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hollerton, John","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_pulled":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.4350999891757965,"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":0.4350999891757965,"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/T11809","display_name":"Advanced NMR Techniques and Applications","score":0.24379999935626984,"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"}},{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.09700000286102295,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/graph-convolutional-networks","display_name":"graph convolutional networks","score":0.9390000104904175},{"id":"https://openalex.org/keywords/message-passing-neural-networks","display_name":"message passing neural networks","score":0.8529999852180481},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9169999957084656},{"id":"https://openalex.org/keywords/claude","display_name":"Claude","score":0.6100000143051147},{"id":"https://openalex.org/keywords/fluorine-containing-compounds","display_name":"fluorine-containing compounds","score":0.7570000290870667},{"id":"https://openalex.org/keywords/structure-confirmation","display_name":"structure confirmation","score":0.7429999709129333},{"id":"https://openalex.org/keywords/forecasting-model-comparison","display_name":"forecasting model comparison","score":0.6140000224113464}],"concepts":[{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.6554999947547913},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6010000109672546},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5938000082969666},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5419999957084656},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.526199996471405},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4921000003814697},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.44609999656677246},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4124999940395355},{"id":"https://openalex.org/C188154048","wikidata":"https://www.wikidata.org/wiki/Q6803609","display_name":"Mean absolute error","level":3,"score":0.3725999891757965},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.36410000920295715},{"id":"https://openalex.org/C150217764","wikidata":"https://www.wikidata.org/wiki/Q6803607","display_name":"Mean absolute percentage error","level":3,"score":0.3531999886035919},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35019999742507935},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3449999988079071},{"id":"https://openalex.org/C111429119","wikidata":"https://www.wikidata.org/wiki/Q899127","display_name":"Chemical shift","level":2,"score":0.3287000060081482},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.32269999384880066},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.319599986076355},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.3091000020503998},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.30660000443458557},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.30649998784065247},{"id":"https://openalex.org/C122383733","wikidata":"https://www.wikidata.org/wiki/Q865920","display_name":"Approximation error","level":2,"score":0.3012000024318695},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.299699991941452},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.2957000136375427},{"id":"https://openalex.org/C203394866","wikidata":"https://www.wikidata.org/wiki/Q2881060","display_name":"Chemical database","level":2,"score":0.2888000011444092},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.28630000352859497},{"id":"https://openalex.org/C68762167","wikidata":"https://www.wikidata.org/wiki/Q910164","display_name":"Cheminformatics","level":2,"score":0.2799000144004822},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.25690001249313354},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.2524999976158142},{"id":"https://openalex.org/C88230418","wikidata":"https://www.wikidata.org/wiki/Q131476","display_name":"Graph theory","level":2,"score":0.25209999084472656},{"id":"https://openalex.org/C167085575","wikidata":"https://www.wikidata.org/wiki/Q6803654","display_name":"Mean squared prediction error","level":2,"score":0.2515000104904175},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:ueaeprints.uea.ac.uk:104577","doi":null,"is_oa":true,"landing_page_url":"https://ueaeprints.uea.ac.uk/id/eprint/104577/1/SMASH_Poster_2026.pdf","pdf_url":"https://ueaeprints.uea.ac.uk/id/eprint/104577/1/SMASH_Poster_2026.pdf","source":{"id":"https://openalex.org/S4306400384","display_name":"UEA Digital Repository (University of East Anglia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1118541","host_organization_name":"University of East Anglia","host_organization_lineage":["https://openalex.org/I1118541"],"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":"Conference or Workshop Item"}],"best_oa_location":{"id":"pmh:oai:ueaeprints.uea.ac.uk:104577","doi":null,"is_oa":true,"landing_page_url":"https://ueaeprints.uea.ac.uk/id/eprint/104577/1/SMASH_Poster_2026.pdf","pdf_url":"https://ueaeprints.uea.ac.uk/id/eprint/104577/1/SMASH_Poster_2026.pdf","source":{"id":"https://openalex.org/S4306400384","display_name":"UEA Digital Repository (University of East Anglia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1118541","host_organization_name":"University of East Anglia","host_organization_lineage":["https://openalex.org/I1118541"],"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":"Conference or Workshop Item"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7213699809.pdf","grobid_xml":"https://content.openalex.org/works/W7213699809.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7218362100","https://openalex.org/W4390586758","https://openalex.org/W3180986738","https://openalex.org/W2009242551","https://openalex.org/W7203628878","https://openalex.org/W3189795580","https://openalex.org/W4389615002","https://openalex.org/W4403500602","https://openalex.org/W4399391515","https://openalex.org/W4389048198"],"abstract_inverted_index":{"Accurate":[0],"prediction":[1,47,115,128,219,292,303,326],"of":[2,10,13,40,80,133,202,255,287,333,340,357],"19F":[3,85,207],"NMR":[4,291,306,329],"chemical":[5,86,137,143,208],"shifts":[6,144],"underpins":[7],"structural":[8,170],"verification":[9],"fluorine-containing":[11,177],"compounds,":[12,157],"importance":[14],"in":[15,179,193,218,305,327],"the":[16,41,106,180,194,227,232,243,256,283],"pharmaceutical":[17],"and":[18,125,136,149,164,205,214,266,320],"agrichemical":[19],"industries.":[20],"Here":[21],"we":[22],"compare":[23],"three":[24,140],"distinct":[25],"approaches":[26],"to":[27,92,123,154,176,188,253],"structure-to-shift":[28],"prediction:":[29],"\u2022":[30,44,57],"Supervised":[31],"machine":[32],"learning":[33],"using":[34,48,88,331],"Graph":[35],"Convolutional":[36],"Neural":[37],"Networks":[38],"(GCNNs)":[39],"message-passing":[42],"type":[43],"Empirical":[45],"database-based":[46],"Mnova\u2019s":[49],"Modgraph":[50,102],"NMRPredict,":[51],"a":[52,76,113,127,158,199,248],"commercially-available":[53],"tool":[54],"from":[55,146],"SciY-Mestrelab":[56],"A":[58],"zero-shot":[59],"reasoning":[60],"workflow":[61],"generated":[62],"by":[63,95],"Anthropic's":[64],"Claude-Fable":[65,120],"large":[66],"language":[67],"model":[68,225],"(LLM)":[69],"The":[70,100,211,223,264],"GCNN":[71,224,265],"models":[72],"were":[73,186],"trained":[74,294],"on":[75,131,295],"proprietary,":[77],"curated":[78,296],"collection":[79,110],"~15,000":[81],"structures":[82,191,204],"assigned":[83],"with":[84],"shifts,":[87],"an":[89],"approach":[90],"analogous":[91],"that":[93,254],"described":[94],"Williamson":[96],"et":[97],"al":[98],"[1].":[99],"Mnova":[101],"predictor":[103,259],"draws":[104],"upon":[105],"same":[107],"underlying":[108],"data":[109,297],"but":[111],"employs":[112],"HOSE-code-based":[114],"strategy":[116],"[2].":[117],"In":[118],"contrast,":[119],"was":[121,174],"prompted":[122],"devise":[124],"implement":[126],"methodology":[129],"based":[130],"analysis":[132],"molecular":[134,147],"environments":[135],"reasoning.":[138],"All":[139],"methods":[141],"predict":[142],"directly":[145],"structure":[148],"can":[150],"therefore":[151],"be":[152],"applied":[153,175],"previously":[155],"unseen":[156],"key":[159],"requirement":[160],"for":[161,301],"discovery":[162],"chemistry":[163],"quantitative":[165,302],"downstream":[166],"applications":[167],"such":[168],"as":[169],"verification.":[171],"Each":[172],"method":[173],"compounds":[178],"publicly":[181],"available":[182],"database,":[183],"nmrshiftdb2.":[184],"These":[185,278],"filtered":[187],"exclude":[189],"any":[190],"present":[192],"GCNN/Modgraph":[195],"training":[196],"set,":[197],"yielding":[198],"test":[200],"set":[201],"795":[203],"4599":[206],"shift":[209,325],"annotations.":[210],"respective":[212],"Mean":[213,234],"Median":[215,249,273],"Absolute":[216,235,250,274],"Errors":[217,275],"are":[220],"summarized":[221],"below:":[222],"delivered":[226],"best":[228],"overall":[229],"performance,":[230],"achieving":[231],"lowest":[233],"Error":[236,251],"(5.98":[237],"ppm,":[238],"approximately":[239],"25%":[240],"lower":[241,272],"than":[242,276],"other":[244],"methods),":[245],"while":[246],"exhibiting":[247],"comparable":[252],"established":[257],"ModGraph":[258,267],"(2.96":[260],"versus":[261],"2.89":[262],"ppm).":[263],"predictors":[268],"both":[269],"achieved":[270],"substantially":[271],"Claude-Fable.":[277],"results":[279],"indicate":[280],"that,":[281],"notwithstanding":[282],"impressive":[284],"general":[285],"capabilities":[286],"modern":[288],"LLMs,":[289],"dedicated":[290],"engines":[293],"collections":[298],"remain":[299],"advantageous":[300],"tasks":[304],"spectroscopy.":[307],"References":[308],"[1]":[309],"D.":[310],"Williamson,":[311],"S.":[312],"Ponte,":[313],"I.":[314],"Iglesias,":[315],"N.":[316],"Tonge,":[317],"C.":[318],"Cobas,":[319],"E.":[321],"K.":[322],"Kemsley,":[323],"\"Chemical":[324],"13C":[328],"spectroscopy":[330],"ensembles":[332],"message":[334],"passing":[335],"neural":[336],"networks":[337],"(MPNNs)\"":[338],"Journal":[339],"Magnetic":[341],"Resonance,":[342],"vol.":[343],"368,":[344],"p.":[345],"107795,":[346],"2024/11/01/2024":[347],"[2]":[348],"Kuhn,":[349],"Stefan":[350],"&":[351],"Johnson,":[352],"Sean.":[353],"(2019).":[354],"Stereo-Aware":[355],"Extension":[356],"HOSE":[358],"Codes.":[359],"ACS":[360],"Omega.":[361],"4.":[362],"10.1021/acsomega.9b00488.":[363]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W7213699809","counts_by_year":[],"updated_date":"2026-11-16T12:05:36.265796","created_date":"2026-09-20T00:00:00"}
