{"id":"https://openalex.org/W4413035203","doi":"https://doi.org/10.1021/acs.jcim.5c01317","title":"AccFG: Accurate Functional Group Extraction and Molecular Structure Comparison","display_name":"AccFG: Accurate Functional Group Extraction and Molecular Structure Comparison","publication_year":2025,"publication_date":"2025-08-07","ids":{"openalex":"https://openalex.org/W4413035203","doi":"https://doi.org/10.1021/acs.jcim.5c01317","pmid":"https://pubmed.ncbi.nlm.nih.gov/40770870"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.5c01317","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.5c01317","pdf_url":null,"source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5115596245","display_name":"Xuan Liu","orcid":"https://orcid.org/0000-0003-1590-8276"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xuan Liu","raw_affiliation_strings":["Department of Chemical and Biomolecular Engineering, University of Illinois at Urbana\u2212Champaign, 600 S Mathews Ave, Urbana, Illinois 61801, United States"],"raw_orcid":"https://orcid.org/0000-0003-1590-8276","affiliations":[{"raw_affiliation_string":"Department of Chemical and Biomolecular Engineering, University of Illinois at Urbana\u2212Champaign, 600 S Mathews Ave, Urbana, Illinois 61801, United States","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108502423","display_name":"S. Swaminathan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sarathkrishna Swaminathan","raw_affiliation_strings":["IBM Research Almaden, 650 Harry Rd, San Jose, California 95120, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research Almaden, 650 Harry Rd, San Jose, California 95120, United States","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090730388","display_name":"Dmitry Yu. Zubarev","orcid":"https://orcid.org/0000-0001-7961-3149"},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dmitry Zubarev","raw_affiliation_strings":["IBM Research Almaden, 650 Harry Rd, San Jose, California 95120, United States"],"raw_orcid":"https://orcid.org/0000-0001-7961-3149","affiliations":[{"raw_affiliation_string":"IBM Research Almaden, 650 Harry Rd, San Jose, California 95120, United States","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007398329","display_name":"Brandi Ransom","orcid":"https://orcid.org/0000-0002-9041-6725"},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brandi Ransom","raw_affiliation_strings":["IBM Research Almaden, 650 Harry Rd, San Jose, California 95120, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research Almaden, 650 Harry Rd, San Jose, California 95120, United States","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030471186","display_name":"Nathaniel H. Park","orcid":"https://orcid.org/0000-0002-6564-3387"},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nathaniel Park","raw_affiliation_strings":["IBM Research Almaden, 650 Harry Rd, San Jose, California 95120, United States"],"raw_orcid":"https://orcid.org/0000-0002-6564-3387","affiliations":[{"raw_affiliation_string":"IBM Research Almaden, 650 Harry Rd, San Jose, California 95120, United States","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085426538","display_name":"Kristin Schmidt","orcid":"https://orcid.org/0000-0003-1339-841X"},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kristin Schmidt","raw_affiliation_strings":["IBM Research Almaden, 650 Harry Rd, San Jose, California 95120, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research Almaden, 650 Harry Rd, San Jose, California 95120, United States","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014465828","display_name":"Huimin Zhao","orcid":"https://orcid.org/0000-0002-9069-6739"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Huimin Zhao","raw_affiliation_strings":["Department of Chemical and Biomolecular Engineering, University of Illinois at Urbana\u2212Champaign, 600 S Mathews Ave, Urbana, Illinois 61801, United States"],"raw_orcid":"https://orcid.org/0000-0002-9069-6739","affiliations":[{"raw_affiliation_string":"Department of Chemical and Biomolecular Engineering, University of Illinois at Urbana\u2212Champaign, 600 S Mathews Ave, Urbana, Illinois 61801, United States","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5014465828"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20540472,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"65","issue":"16","first_page":"8593","last_page":"8602"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9994999766349792,"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/T10836","display_name":"Metabolomics and Mass Spectrometry Studies","score":0.9959999918937683,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10911","display_name":"Chemical Synthesis and Analysis","score":0.9958000183105469,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/group","display_name":"Group (periodic table)","score":0.632537305355072},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.6041713356971741},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.42840084433555603},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.3904774487018585},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.3586329221725464},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.3027688264846802},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.1450386941432953},{"id":"https://openalex.org/keywords/organic-chemistry","display_name":"Organic chemistry","score":0.08344858884811401}],"concepts":[{"id":"https://openalex.org/C2781311116","wikidata":"https://www.wikidata.org/wiki/Q83306","display_name":"Group (periodic table)","level":2,"score":0.632537305355072},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.6041713356971741},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.42840084433555603},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3904774487018585},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.3586329221725464},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.3027688264846802},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.1450386941432953},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.08344858884811401}],"mesh":[{"descriptor_ui":"D000080911","descriptor_name":"Cheminformatics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D000080911","descriptor_name":"Cheminformatics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D000080911","descriptor_name":"Cheminformatics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D000080911","descriptor_name":"Cheminformatics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013329","descriptor_name":"Structure-Activity Relationship","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013329","descriptor_name":"Structure-Activity Relationship","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013329","descriptor_name":"Structure-Activity Relationship","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013329","descriptor_name":"Structure-Activity Relationship","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015394","descriptor_name":"Molecular Structure","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015394","descriptor_name":"Molecular Structure","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015394","descriptor_name":"Molecular Structure","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015394","descriptor_name":"Molecular Structure","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1021/acs.jcim.5c01317","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.5c01317","pdf_url":null,"source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},{"id":"pmid:40770870","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40770870","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 chemical information and modeling","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2063335192","display_name":null,"funder_award_id":"2019897","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1980352552","https://openalex.org/W2017646651","https://openalex.org/W2022476850","https://openalex.org/W2033377040","https://openalex.org/W2045270356","https://openalex.org/W2059737570","https://openalex.org/W2096725584","https://openalex.org/W2114940395","https://openalex.org/W2137796142","https://openalex.org/W2152968740","https://openalex.org/W2157058953","https://openalex.org/W2169678694","https://openalex.org/W2219397146","https://openalex.org/W2406943157","https://openalex.org/W2407040666","https://openalex.org/W2417535199","https://openalex.org/W2461470610","https://openalex.org/W2500078320","https://openalex.org/W2548357532","https://openalex.org/W2594183968","https://openalex.org/W2602318385","https://openalex.org/W2615600057","https://openalex.org/W2622206241","https://openalex.org/W2933530798","https://openalex.org/W2966357564","https://openalex.org/W3042595256","https://openalex.org/W4225158300","https://openalex.org/W4307468148","https://openalex.org/W4315928585","https://openalex.org/W4323347906","https://openalex.org/W4388423838","https://openalex.org/W4388455891","https://openalex.org/W4396723768","https://openalex.org/W4401710746","https://openalex.org/W4402049868","https://openalex.org/W4403256806","https://openalex.org/W4404228269","https://openalex.org/W4406932684","https://openalex.org/W6606298547"],"related_works":["https://openalex.org/W4387497383","https://openalex.org/W2948807893","https://openalex.org/W2899084033","https://openalex.org/W2778153218","https://openalex.org/W2748952813","https://openalex.org/W1531601525","https://openalex.org/W4391375266","https://openalex.org/W2078814861","https://openalex.org/W2527526854","https://openalex.org/W1976181487"],"abstract_inverted_index":{"Functional":[0],"groups":[1,27,89,137],"are":[2],"specific":[3],"molecular":[4,30,50,100,147,152,180],"patterns":[5],"that":[6,131,159],"influence":[7],"a":[8,33,41,65,164],"molecule's":[9],"chemical":[10],"and":[11,49,56,74,90,123,141,154,171,182],"physical":[12],"properties.":[13,183],"Identifying":[14],"them":[15],"is":[16,186],"crucial":[17],"for":[18,44,61,167],"understanding":[19],"the":[20,70,76,104,151],"structure-activity":[21],"relationships.":[22],"Currently,":[23],"accurately":[24,134],"extracting":[25],"functional":[26,46,58,80,88,105,136,143,169],"from":[28,138],"complex":[29],"structures":[31,181],"remains":[32],"challenge.":[34],"In":[35],"this":[36],"work,":[37],"we":[38],"present":[39],"AccFG,":[40],"tool":[42,166],"designed":[43],"precise":[45],"group":[47,59,81,106],"extraction":[48],"structure":[51,101],"comparison.":[52],"AccFG":[53,132,160],"generates":[54],"refined":[55],"structured":[57,174],"descriptors":[60],"molecules":[62,140],"based":[63],"on":[64,119],"predefined":[66],"library,":[67],"while":[68],"lowering":[69],"barrier":[71],"to":[72],"encoding":[73],"extending":[75],"library":[77],"with":[78,92,108,125],"new":[79],"definitions.":[82],"Additionally,":[83],"AccFG's":[84],"output":[85,175],"includes":[86],"identified":[87],"heterocycles":[91],"their":[93],"corresponding":[94],"mapped":[95],"atom":[96],"numbers,":[97],"which":[98],"enables":[99,176],"comparisons":[102],"at":[103,188],"level":[107],"alkane":[109],"differences":[110,145],"(differences":[111],"in":[112],"carbon":[113],"backbone).":[114],"We":[115,157],"evaluated":[116],"its":[117,172],"performance":[118],"various":[120],"data":[121],"sets":[122],"examples":[124],"manual":[126],"examination.":[127],"The":[128,184],"results":[129],"demonstrate":[130],"can":[133],"extract":[135],"individual":[139],"identify":[142],"group-level":[144],"between":[146,179],"pairs,":[148],"effectively":[149],"bridging":[150],"modality":[153],"textual":[155],"descriptors.":[156],"anticipate":[158],"will":[161],"serve":[162],"as":[163],"useful":[165],"processing":[168],"groups,":[170],"comprehensive,":[173],"fine-grained":[177],"insights":[178],"code":[185],"available":[187],"https://github.com/xuanliugit/AccFG.":[189]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
