{"id":"https://openalex.org/W4401979467","doi":"https://doi.org/10.1186/s13321-024-00899-w","title":"Evaluating the generalizability of graph neural networks for predicting collision cross section","display_name":"Evaluating the generalizability of graph neural networks for predicting collision cross section","publication_year":2024,"publication_date":"2024-08-29","ids":{"openalex":"https://openalex.org/W4401979467","doi":"https://doi.org/10.1186/s13321-024-00899-w","pmid":"https://pubmed.ncbi.nlm.nih.gov/39210378"},"language":"en","primary_location":{"id":"doi:10.1186/s13321-024-00899-w","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-024-00899-w","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-024-00899-w","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://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-024-00899-w","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037754469","display_name":"Chloe Engler Hart","orcid":"https://orcid.org/0000-0002-9577-0715"},"institutions":[{"id":"https://openalex.org/I4210137457","display_name":"Enveda Therapeutics (United States)","ror":"https://ror.org/04p6vt455","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137457"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Chloe Engler Hart","raw_affiliation_strings":["Enveda Biosciences, Inc., 5700 Flatiron Pkwy, Boulder, CO, 80301, USA"],"affiliations":[{"raw_affiliation_string":"Enveda Biosciences, Inc., 5700 Flatiron Pkwy, Boulder, CO, 80301, USA","institution_ids":["https://openalex.org/I4210137457"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044744702","display_name":"Ant\u00f3nio J. Preto","orcid":"https://orcid.org/0000-0003-4203-2230"},"institutions":[{"id":"https://openalex.org/I4210137457","display_name":"Enveda Therapeutics (United States)","ror":"https://ror.org/04p6vt455","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137457"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ant\u00f3nio Jos\u00e9 Preto","raw_affiliation_strings":["Enveda Biosciences, Inc., 5700 Flatiron Pkwy, Boulder, CO, 80301, USA"],"affiliations":[{"raw_affiliation_string":"Enveda Biosciences, Inc., 5700 Flatiron Pkwy, Boulder, CO, 80301, USA","institution_ids":["https://openalex.org/I4210137457"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054641817","display_name":"Shaurya Chanana","orcid":"https://orcid.org/0000-0002-3021-2210"},"institutions":[{"id":"https://openalex.org/I4210137457","display_name":"Enveda Therapeutics (United States)","ror":"https://ror.org/04p6vt455","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137457"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shaurya Chanana","raw_affiliation_strings":["Enveda Biosciences, Inc., 5700 Flatiron Pkwy, Boulder, CO, 80301, USA"],"affiliations":[{"raw_affiliation_string":"Enveda Biosciences, Inc., 5700 Flatiron Pkwy, Boulder, CO, 80301, USA","institution_ids":["https://openalex.org/I4210137457"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089107006","display_name":"David Healey","orcid":"https://orcid.org/0000-0002-9584-9757"},"institutions":[{"id":"https://openalex.org/I4210137457","display_name":"Enveda Therapeutics (United States)","ror":"https://ror.org/04p6vt455","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137457"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Healey","raw_affiliation_strings":["Enveda Biosciences, Inc., 5700 Flatiron Pkwy, Boulder, CO, 80301, USA"],"affiliations":[{"raw_affiliation_string":"Enveda Biosciences, Inc., 5700 Flatiron Pkwy, Boulder, CO, 80301, USA","institution_ids":["https://openalex.org/I4210137457"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030581253","display_name":"Tobias Kind","orcid":"https://orcid.org/0000-0002-1908-4916"},"institutions":[{"id":"https://openalex.org/I4210137457","display_name":"Enveda Therapeutics (United States)","ror":"https://ror.org/04p6vt455","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137457"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tobias Kind","raw_affiliation_strings":["Enveda Biosciences, Inc., 5700 Flatiron Pkwy, Boulder, CO, 80301, USA"],"affiliations":[{"raw_affiliation_string":"Enveda Biosciences, Inc., 5700 Flatiron Pkwy, Boulder, CO, 80301, USA","institution_ids":["https://openalex.org/I4210137457"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043459521","display_name":"Daniel Domingo\u2010Fern\u00e1nd\u00e9z","orcid":"https://orcid.org/0000-0002-2046-6145"},"institutions":[{"id":"https://openalex.org/I4210137457","display_name":"Enveda Therapeutics (United States)","ror":"https://ror.org/04p6vt455","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137457"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Domingo-Fern\u00e1ndez","raw_affiliation_strings":["Enveda Biosciences, Inc., 5700 Flatiron Pkwy, Boulder, CO, 80301, USA. daniel.domingo-fernandez@envedabio.com","Enveda Biosciences, Inc., 5700 Flatiron Pkwy, Boulder, CO, 80301, USA"],"affiliations":[{"raw_affiliation_string":"Enveda Biosciences, Inc., 5700 Flatiron Pkwy, Boulder, CO, 80301, USA. daniel.domingo-fernandez@envedabio.com","institution_ids":["https://openalex.org/I4210137457"]},{"raw_affiliation_string":"Enveda Biosciences, Inc., 5700 Flatiron Pkwy, Boulder, CO, 80301, USA","institution_ids":["https://openalex.org/I4210137457"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5037754469"],"corresponding_institution_ids":["https://openalex.org/I4210137457"],"apc_list":{"value":1290,"currency":"GBP","value_usd":1582},"apc_paid":{"value":1290,"currency":"GBP","value_usd":1582},"fwci":1.9965,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.88509061,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"16","issue":"1","first_page":"105","last_page":"105"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12423","display_name":"Software Reliability and Analysis Research","score":0.9696999788284302,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12423","display_name":"Software Reliability and Analysis Research","score":0.9696999788284302,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T11357","display_name":"Risk and Safety Analysis","score":0.929099977016449,"subfield":{"id":"https://openalex.org/subfields/1804","display_name":"Statistics, Probability and Uncertainty"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9110999703407288,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/generalizability-theory","display_name":"Generalizability theory","score":0.8767341375350952},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7481536269187927},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5785763263702393},{"id":"https://openalex.org/keywords/collision","display_name":"Collision","score":0.5756786465644836},{"id":"https://openalex.org/keywords/section","display_name":"Section (typography)","score":0.5372357964515686},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5198953151702881},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.48838919401168823},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4387551248073578},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42749476432800293},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.41007184982299805},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.2535915970802307},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.12337890267372131},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.11980608105659485},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10769206285476685}],"concepts":[{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.8767341375350952},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7481536269187927},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5785763263702393},{"id":"https://openalex.org/C121704057","wikidata":"https://www.wikidata.org/wiki/Q352070","display_name":"Collision","level":2,"score":0.5756786465644836},{"id":"https://openalex.org/C2780129039","wikidata":"https://www.wikidata.org/wiki/Q1931107","display_name":"Section (typography)","level":2,"score":0.5372357964515686},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5198953151702881},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.48838919401168823},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4387551248073578},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42749476432800293},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.41007184982299805},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2535915970802307},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.12337890267372131},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.11980608105659485},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10769206285476685},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1186/s13321-024-00899-w","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-024-00899-w","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-024-00899-w","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:39210378","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39210378","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:pubmedcentral.nih.gov:11363525","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11363525","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11363525/pdf/13321_2024_Article_899.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","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":"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"},{"id":"pmh:oai:doaj.org/article:b355a92d23be450180c06177219466ee","is_oa":true,"landing_page_url":"https://doaj.org/article/b355a92d23be450180c06177219466ee","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 16, Iss 1, Pp 1-11 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13321-024-00899-w","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-024-00899-w","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-024-00899-w","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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4401979467.pdf","grobid_xml":"https://content.openalex.org/works/W4401979467.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W2059903043","https://openalex.org/W2060531713","https://openalex.org/W2076018148","https://openalex.org/W2079699273","https://openalex.org/W2606202972","https://openalex.org/W2746158299","https://openalex.org/W2898312403","https://openalex.org/W2902734986","https://openalex.org/W2909063104","https://openalex.org/W2925495008","https://openalex.org/W3008673945","https://openalex.org/W3095090736","https://openalex.org/W4226016500","https://openalex.org/W4307641507","https://openalex.org/W4311703785","https://openalex.org/W4378515234","https://openalex.org/W4383186611","https://openalex.org/W4386406888","https://openalex.org/W4388409846","https://openalex.org/W4392143551","https://openalex.org/W4399047870"],"related_works":["https://openalex.org/W2118717649","https://openalex.org/W2413243053","https://openalex.org/W410723623","https://openalex.org/W2015341305","https://openalex.org/W2035068594","https://openalex.org/W4225593417","https://openalex.org/W2573498121","https://openalex.org/W3022298670","https://openalex.org/W3160494304","https://openalex.org/W3006162251"],"abstract_inverted_index":{"Ion":[0],"Mobility":[1],"coupled":[2],"with":[3],"Mass":[4],"Spectrometry":[5],"(IM-MS)":[6],"is":[7,41],"a":[8],"promising":[9],"analytical":[10],"technique":[11],"that":[12],"enhances":[13],"molecular":[14,27,162],"characterization":[15],"by":[16,44,152,178,229],"measuring":[17],"collision":[18,195],"cross-section":[19],"(CCS)":[20],"values,":[21],"which":[22,144],"are":[23],"indicative":[24],"of":[25,35,48,54,94,122,182,203],"the":[26,32,45,52,80,91,120,129,166,180,183,201],"size":[28],"and":[29,127,165,208],"shape.":[30],"However,":[31],"effective":[33],"application":[34],"CCS":[36,77,125,136,184],"values":[37,78],"in":[38,61,123,210,222],"structural":[39],"analysis":[40],"still":[42],"constrained":[43],"limited":[46],"availability":[47],"experimental":[49],"data,":[50],"necessitating":[51],"development":[53],"accurate":[55],"machine":[56],"learning":[57],"(ML)":[58],"models":[59,96,154,175,205],"for":[60,131,157,193],"silico":[62,124],"predictions.":[63],"In":[64],"this":[65,235],"study,":[66],"we":[67,141,170,227],"evaluated":[68,221],"state-of-the-art":[69,189],"Graph":[70],"Neural":[71],"Networks":[72],"(GNNs),":[73],"trained":[74,207],"to":[75,85,101,111,155,233],"predict":[76],"using":[79],"largest":[81],"publicly":[82,134],"available":[83,135],"dataset":[84],"date.":[86],"Although":[87],"our":[88],"results":[89],"confirm":[90],"high":[92],"accuracy":[93,202,218],"these":[95,204],"within":[97],"chemical":[98,212],"spaces":[99],"similar":[100,211],"their":[102,105,217],"training":[103],"environments,":[104],"performance":[106],"significantly":[107],"declines":[108],"when":[109,206,220],"applied":[110],"structurally":[112,223],"novel":[113,224],"regions.":[114,225],"This":[115],"discrepancy":[116],"raises":[117],"concerns":[118],"about":[119],"reliability":[121,181],"predictions":[126],"underscores":[128],"need":[130],"releasing":[132],"further":[133],"datasets.":[137],"To":[138],"mitigate":[139,234],"this,":[140],"introduce":[142],"Mol2CCS":[143],"demonstrates":[145],"how":[146,173,216],"generalization":[147],"can":[148,176],"be":[149],"partially":[150],"improved":[151],"extending":[153],"account":[156],"additional":[158],"features":[159],"such":[160],"as":[161],"fingerprints,":[163],"descriptors,":[164],"molecule":[167],"types.":[168],"Lastly,":[169,226],"also":[171,215],"show":[172],"confidence":[174],"support":[177],"enhancing":[179],"estimates.Scientific":[185],"contributionWe":[186],"have":[187],"benchmarked":[188],"graph":[190],"neural":[191],"networks":[192],"predicting":[194],"cross":[196],"section.":[197],"Our":[198],"work":[199],"highlights":[200],"predicted":[209],"spaces,":[213],"but":[214],"drops":[219],"conclude":[228],"presenting":[230],"potential":[231],"approaches":[232],"issue.":[236]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2024-08-29T00:00:00"}