{"id":"https://openalex.org/W7212972133","doi":"https://doi.org/10.48550/arxiv.2609.12223","title":"Predicting Collision Cross Sections with GRACE: Geometric Residual Adduct Conditioning via Early-fusion","display_name":"Predicting Collision Cross Sections with GRACE: Geometric Residual Adduct Conditioning via Early-fusion","publication_year":2026,"publication_date":"2026-09-10","ids":{"openalex":"https://openalex.org/W7212972133","doi":"https://doi.org/10.48550/arxiv.2609.12223","pmid":"https://pubmed.ncbi.nlm.nih.gov/42856703","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/13648773"},"language":"en","primary_location":{"id":"pmid:42856703","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42856703","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,"listed_in":[],"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":"ArXiv","raw_type":"Journal Article"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.12223","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035539105","display_name":"Parthasarathy Suryanarayanan","orcid":"https://orcid.org/0000-0002-8619-2976","observed_orcids":["https://orcid.org/0000-0002-8619-2976"]},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Suryanarayanan, Parthasarathy","raw_affiliation_strings":["IBM Research , Yorktown Heights , NY 10598 , United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research , Yorktown Heights , NY 10598 , United States","institution_ids":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121097799","display_name":"Susanta Das","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405287411","display_name":"Cleveland Clinic Research","ror":"https://ror.org/053229s83","country_code":"US","type":"facility","lineage":["https://openalex.org/I1316902750","https://openalex.org/I4405287411"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Das, Susanta","raw_affiliation_strings":["Center for Computational Life Sciences , Cleveland Clinic Research ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Computational Life Sciences , Cleveland Clinic Research ,","institution_ids":["https://openalex.org/I4405287411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111583757","display_name":"Shreyans Sethi","orcid":"https://orcid.org/0009-0002-0577-2029","observed_orcids":["https://orcid.org/0009-0002-0577-2029"]},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sethi, Shreyans","raw_affiliation_strings":["IBM Research , Yorktown Heights , NY 10598 , United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research , Yorktown Heights , NY 10598 , United States","institution_ids":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085994852","display_name":"Kenneth M. Merz","orcid":"https://orcid.org/0000-0001-9139-5893","observed_orcids":["https://orcid.org/0000-0001-9139-5893"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Merz,, Kenneth M., Jr.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5072958773","display_name":"Joseph A. Morrone","orcid":"https://orcid.org/0000-0001-8550-4854","observed_orcids":["https://orcid.org/0000-0001-8550-4854"]},"institutions":[{"id":"https://openalex.org/I1316902750","display_name":"Cleveland Clinic","ror":"https://ror.org/03xjacd83","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1316902750"]},{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Morrone, Joseph A.","raw_affiliation_strings":["IBM Research , Yorktown Heights , NY 10598 , United States","The Cleveland Clinic , Cleveland , OH 44195 , United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research , Yorktown Heights , NY 10598 , United States","institution_ids":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]},{"raw_affiliation_string":"The Cleveland Clinic , Cleveland , OH 44195 , United States","institution_ids":["https://openalex.org/I1316902750"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"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/T10683","display_name":"Mass Spectrometry Techniques and Applications","score":0.9448000192642212,"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"}},"topics":[{"id":"https://openalex.org/T10683","display_name":"Mass Spectrometry Techniques and Applications","score":0.9448000192642212,"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/T10211","display_name":"Computational Drug Discovery Methods","score":0.03220000118017197,"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":0.0044999998062849045,"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/collision-cross-section-prediction","display_name":"collision cross section prediction","score":0.9940000176429749},{"id":"https://openalex.org/keywords/ion-mobility-mass-spectrometry","display_name":"ion mobility mass spectrometry","score":0.9660000205039978},{"id":"https://openalex.org/keywords/molecular-adducts","display_name":"molecular adducts","score":0.7580000162124634},{"id":"https://openalex.org/keywords/3d-molecular-geometry","display_name":"3D molecular geometry","score":0.7590000033378601},{"id":"https://openalex.org/keywords/early-fusion","display_name":"feature-level fusion","score":0.5929999947547913},{"id":"https://openalex.org/keywords/residual-learning","display_name":"residual learning","score":0.7749999761581421},{"id":"https://openalex.org/keywords/molecular-annotation","display_name":"molecular annotation","score":0.7009999752044678},{"id":"https://openalex.org/keywords/inductive-bias","display_name":"inductive bias","score":0.5559999942779541}],"concepts":[{"id":"https://openalex.org/C108204754","wikidata":"https://www.wikidata.org/wiki/Q353392","display_name":"Adduct","level":2,"score":0.8073999881744385},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.757099986076355},{"id":"https://openalex.org/C45262634","wikidata":"https://www.wikidata.org/wiki/Q5159291","display_name":"Conditioning","level":2,"score":0.5306000113487244},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.49140000343322754},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.44839999079704285},{"id":"https://openalex.org/C198291218","wikidata":"https://www.wikidata.org/wiki/Q190382","display_name":"Ionization","level":3,"score":0.4235999882221222},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3776000142097473},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.37220001220703125},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3418000042438507},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32829999923706055},{"id":"https://openalex.org/C29554801","wikidata":"https://www.wikidata.org/wiki/Q147027","display_name":"Thought experiment","level":2,"score":0.3215999901294708},{"id":"https://openalex.org/C186060115","wikidata":"https://www.wikidata.org/wiki/Q30336093","display_name":"Biological system","level":1,"score":0.31700000166893005},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.3165999948978424},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.313400000333786},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3133000135421753},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.28999999165534973},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.27889999747276306},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.2775000035762787},{"id":"https://openalex.org/C24872484","wikidata":"https://www.wikidata.org/wiki/Q126818","display_name":"Dimensionless quantity","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C121704057","wikidata":"https://www.wikidata.org/wiki/Q352070","display_name":"Collision","level":2,"score":0.2612000107765198}],"mesh":[],"locations_count":4,"locations":[{"id":"pmid:42856703","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42856703","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,"listed_in":[],"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":"ArXiv","raw_type":"Journal Article"},{"id":"pmh:oai:arXiv.org:2609.12223","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.12223","pdf_url":"https://arxiv.org/pdf/2609.12223","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:pubmedcentral.nih.gov:13648773","doi":null,"is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13648773/","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ArXiv","raw_type":"Text"},{"id":"doi:10.48550/arxiv.2609.12223","doi":"https://doi.org/10.48550/arxiv.2609.12223","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.12223","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.12223","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.12223","pdf_url":"https://arxiv.org/pdf/2609.12223","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G6335681527","display_name":"Collaborative Research: Frameworks: Interoperable High-Performance Classical, Machine Learning and Quantum Free Energy Methods in AMBER","funder_award_id":"2209717","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320309680","display_name":"Cleveland Clinic","ror":"https://ror.org/03xjacd83"},{"id":"https://openalex.org/F4320309681","display_name":"Cleveland Clinic Foundation","ror":"https://ror.org/03xjacd83"},{"id":"https://openalex.org/F4320310016","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320332431","display_name":"College of Engineering, Michigan State University","ror":"https://ror.org/05hs6h993"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7212972133.pdf","grobid_xml":"https://content.openalex.org/works/W7212972133.grobid-xml"},"referenced_works_count":2,"referenced_works":["https://openalex.org/W2788775653","https://openalex.org/W4287828570"],"related_works":["https://openalex.org/W4383186611","https://openalex.org/W4413868375","https://openalex.org/W4393281497","https://openalex.org/W7211878962","https://openalex.org/W7129626555","https://openalex.org/W3212565553","https://openalex.org/W4385194797","https://openalex.org/W4413093622","https://openalex.org/W4400454031","https://openalex.org/W4401979467"],"abstract_inverted_index":{"Collision":[0],"cross":[1],"section":[2],"(CCS),":[3],"derived":[4],"from":[5],"ion":[6],"mobility":[7],"mass":[8],"spectrometry,":[9],"is":[10,18],"a":[11,34,50,72,78,96,113,126,224],"common":[12],"descriptor":[13,104],"for":[14,20,256],"molecular":[15,36,80],"annotation.":[16],"Prediction":[17],"challenging":[19],"machine":[21],"learning":[22,188,247],"models":[23,162],"because":[24],"it":[25],"reflects":[26],"the":[27,110,123,153,159,169,174,180,193,219,230],"size,":[28],"shape,":[29],"and":[30,106,117,139,148,177,248],"ionization":[31],"state":[32],"of":[33,129],"gas-phase":[35],"ion.":[37],"Most":[38],"predictors":[39],"either":[40],"ignore":[41],"explicit":[42],"3D":[43,73],"structure":[44],"or":[45],"treat":[46],"adduct":[47,86,107,115,250],"identity":[48],"as":[49,252],"late":[51,205],"categorical":[52],"feature,":[53],"which":[54],"limits":[55],"their":[56],"ability":[57],"to":[58,100,143,204],"capture":[59],"adduct-dependent":[60],"geometric":[61,84],"effects.":[62],"We":[63,121],"present":[64],"GRACE":[65,91,151,213,227],"(Geometric":[66],"Residual":[67],"Adduct":[68],"Conditioning":[69],"via":[70,88,112],"Early-fusion),":[71],"CCS":[74,134,259],"predictor":[75],"that":[76,186],"adapts":[77],"pretrained":[79],"geometry":[81],"encoder":[82,111],"using":[83],"residual":[85,97,187,246],"conditioning":[87,108,251],"early":[89,198],"fusion.":[90,206],"combines":[92],"two":[93],"inductive":[94,254],"biases:":[95],"objective":[98],"relative":[99,203],"an":[101],"adduct-aware":[102],"physical":[103],"baseline":[105],"within":[109],"learned":[114,161],"token":[116],"low-rank":[118],"attention":[119],"adapters.":[120],"evaluate":[122],"model":[124],"on":[125,163,168,173,179],"curated":[127],"set":[128],"over":[130],"9,000":[131],"experimental":[132],"molecule-adduct":[133],"records":[135],"with":[136,237],"random,":[137],"scaffold,":[138],"adduct-sensitive":[140,181,201],"splits":[141],"designed":[142],"separate":[144],"interpolation,":[145],"scaffold":[146,175],"generalization,":[147],"adduct-driven":[149],"generalization.":[150],"achieves":[152],"best":[154],"mean":[155,232],"percentage":[156],"difference":[157,234],"among":[158],"evaluated":[160,221],"all":[164],"three":[165],"splits:":[166],"1.67%":[167],"random":[170],"split,":[171,176],"2.11%":[172],"2.36%":[178],"split.":[182],"Diagnostic":[183],"analyses":[184],"suggest":[185],"stabilizes":[189],"training":[190],"by":[191],"removing":[192],"dominant":[194],"mass-CCS":[195],"trend,":[196],"while":[197],"fusion":[199],"improves":[200],"prediction":[202],"Across":[207],"four":[208,238],"independent":[209],"external":[210],"test":[211],"sets,":[212],"shows":[214],"consistently":[215],"lower":[216],"error":[217],"than":[218],"other":[220],"models.":[222],"On":[223],"held-out":[225],"set,":[226],"also":[228],"attains":[229],"lowest":[231],"percent":[233],"when":[235],"compared":[236],"previously":[239],"reported":[240],"physics-based":[241],"workflows.":[242],"These":[243],"results":[244],"support":[245],"encoder-level":[249],"practical":[253],"biases":[255],"fast,":[257],"accurate":[258],"prediction.":[260]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-15T00:00:00"}