{"id":"https://openalex.org/W4388819251","doi":"https://doi.org/10.1186/s13321-023-00783-z","title":"YoDe-Segmentation: automated noise-free retrieval of molecular structures from scientific publications","display_name":"YoDe-Segmentation: automated noise-free retrieval of molecular structures from scientific publications","publication_year":2023,"publication_date":"2023-11-20","ids":{"openalex":"https://openalex.org/W4388819251","doi":"https://doi.org/10.1186/s13321-023-00783-z","pmid":"https://pubmed.ncbi.nlm.nih.gov/37986007"},"language":"en","primary_location":{"id":"doi:10.1186/s13321-023-00783-z","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-023-00783-z","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-023-00783-z","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/s13321-023-00783-z","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102810853","display_name":"Chong Zhou","orcid":"https://orcid.org/0000-0003-3638-4125"},"institutions":[{"id":"https://openalex.org/I14992734","display_name":"Hunan University of Traditional Chinese Medicine","ror":"https://ror.org/05qfq0x09","country_code":"CN","type":"education","lineage":["https://openalex.org/I14992734"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chong Zhou","raw_affiliation_strings":["School of Informatics, Hunan University of Chinese Medicine, Changsha, 410208, Hunan, People's Republic of China"],"affiliations":[{"raw_affiliation_string":"School of Informatics, Hunan University of Chinese Medicine, Changsha, 410208, Hunan, People's Republic of China","institution_ids":["https://openalex.org/I14992734"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089781672","display_name":"Wei Liu","orcid":"https://orcid.org/0000-0001-7511-3980"},"institutions":[{"id":"https://openalex.org/I14992734","display_name":"Hunan University of Traditional Chinese Medicine","ror":"https://ror.org/05qfq0x09","country_code":"CN","type":"education","lineage":["https://openalex.org/I14992734"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Liu","raw_affiliation_strings":["School of Informatics, Hunan University of Chinese Medicine, Changsha, 410208, Hunan, People's Republic of China. weiliu@hnucm.edu.cn","School of Informatics, Hunan University of Chinese Medicine, Changsha, 410208, Hunan, People's Republic of China"],"affiliations":[{"raw_affiliation_string":"School of Informatics, Hunan University of Chinese Medicine, Changsha, 410208, Hunan, People's Republic of China. weiliu@hnucm.edu.cn","institution_ids":["https://openalex.org/I14992734"]},{"raw_affiliation_string":"School of Informatics, Hunan University of Chinese Medicine, Changsha, 410208, Hunan, People's Republic of China","institution_ids":["https://openalex.org/I14992734"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102581162","display_name":"Xiyue Song","orcid":null},"institutions":[{"id":"https://openalex.org/I14992734","display_name":"Hunan University of Traditional Chinese Medicine","ror":"https://ror.org/05qfq0x09","country_code":"CN","type":"education","lineage":["https://openalex.org/I14992734"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiyue Song","raw_affiliation_strings":["School of Informatics, Hunan University of Chinese Medicine, Changsha, 410208, Hunan, People's Republic of China"],"affiliations":[{"raw_affiliation_string":"School of Informatics, Hunan University of Chinese Medicine, Changsha, 410208, Hunan, People's Republic of China","institution_ids":["https://openalex.org/I14992734"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101268979","display_name":"Mengling Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I14992734","display_name":"Hunan University of Traditional Chinese Medicine","ror":"https://ror.org/05qfq0x09","country_code":"CN","type":"education","lineage":["https://openalex.org/I14992734"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengling Yang","raw_affiliation_strings":["School of Informatics, Hunan University of Chinese Medicine, Changsha, 410208, Hunan, People's Republic of China"],"affiliations":[{"raw_affiliation_string":"School of Informatics, Hunan University of Chinese Medicine, Changsha, 410208, Hunan, People's Republic of China","institution_ids":["https://openalex.org/I14992734"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101268980","display_name":"Xiaowang Peng","orcid":null},"institutions":[{"id":"https://openalex.org/I14992734","display_name":"Hunan University of Traditional Chinese Medicine","ror":"https://ror.org/05qfq0x09","country_code":"CN","type":"education","lineage":["https://openalex.org/I14992734"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaowang Peng","raw_affiliation_strings":["School of Informatics, Hunan University of Chinese Medicine, Changsha, 410208, Hunan, People's Republic of China"],"affiliations":[{"raw_affiliation_string":"School of Informatics, Hunan University of Chinese Medicine, Changsha, 410208, Hunan, People's Republic of China","institution_ids":["https://openalex.org/I14992734"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5102810853"],"corresponding_institution_ids":["https://openalex.org/I14992734"],"apc_list":{"value":1290,"currency":"GBP","value_usd":1582},"apc_paid":{"value":1290,"currency":"GBP","value_usd":1582},"fwci":0.973,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.80049122,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"15","issue":"1","first_page":"111","last_page":"111"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9976000189781189,"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":0.9976000189781189,"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":0.9758999943733215,"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/T10640","display_name":"Spectroscopy and Chemometric Analyses","score":0.9631999731063843,"subfield":{"id":"https://openalex.org/subfields/1602","display_name":"Analytical Chemistry"},"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/computer-science","display_name":"Computer science","score":0.8086279630661011},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.629962682723999},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5795770287513733},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5475576519966125},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5081338882446289},{"id":"https://openalex.org/keywords/data-extraction","display_name":"Data extraction","score":0.48546674847602844},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4623381495475769},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4503334164619446},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.43940412998199463},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37308788299560547},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3298930525779724},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.1475161910057068},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.12120586633682251}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8086279630661011},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.629962682723999},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5795770287513733},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5475576519966125},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5081338882446289},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.48546674847602844},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4623381495475769},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4503334164619446},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.43940412998199463},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37308788299560547},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3298930525779724},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.1475161910057068},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.12120586633682251},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.0},{"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/s13321-023-00783-z","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-023-00783-z","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-023-00783-z","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:37986007","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37986007","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:10662772","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10662772","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10662772/pdf/13321_2023_Article_783.pdf","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":"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:b5f32c2a17b94ffc9416803431ca7d5b","is_oa":true,"landing_page_url":"https://doaj.org/article/b5f32c2a17b94ffc9416803431ca7d5b","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 15, Iss 1, Pp 1-11 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13321-023-00783-z","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-023-00783-z","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-023-00783-z","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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5899999737739563}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4388819251.pdf"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W1966456689","https://openalex.org/W1975147762","https://openalex.org/W2051554764","https://openalex.org/W2064985253","https://openalex.org/W2963150697","https://openalex.org/W2963734039","https://openalex.org/W3009321976","https://openalex.org/W3013318641","https://openalex.org/W3045928028","https://openalex.org/W3092396754","https://openalex.org/W3097598035","https://openalex.org/W3130247384","https://openalex.org/W3134776119","https://openalex.org/W3159789740","https://openalex.org/W4281484410","https://openalex.org/W4283761122","https://openalex.org/W4289936378","https://openalex.org/W4353112191","https://openalex.org/W4365150514","https://openalex.org/W4386001223","https://openalex.org/W6600007113"],"related_works":["https://openalex.org/W2770593030","https://openalex.org/W4281727072","https://openalex.org/W4312219546","https://openalex.org/W3154990682","https://openalex.org/W2171975302","https://openalex.org/W1589637664","https://openalex.org/W2560201613","https://openalex.org/W2142809053","https://openalex.org/W1532073221","https://openalex.org/W2377538627"],"abstract_inverted_index":{"In":[0,163],"chemistry-related":[1],"disciplines,":[2],"a":[3,43,104,128,244],"vast":[4],"repository":[5],"of":[6,38,74,118,185,213,224,235],"molecular":[7,40,75,119,142,178,187],"structural":[8],"data":[9],"has":[10],"been":[11],"documented":[12],"in":[13,67,110,158,182],"scientific":[14,122],"publications":[15],"but":[16,238],"remains":[17],"inaccessible":[18],"to":[19,23,46,94,204,216],"computational":[20],"analyses":[21,57],"owing":[22],"its":[24,241],"non-machine-readable":[25],"format.":[26],"Optical":[27],"chemical":[28,39,61],"structure":[29,179],"recognition":[30],"(OCSR)":[31],"addresses":[32],"this":[33,100,111],"gap":[34],"by":[35],"converting":[36],"images":[37],"structures":[41,120,143,157],"into":[42],"format":[44],"accessible":[45],"computers":[47],"and":[48,58,83,135,140,169,233],"convenient":[49],"for":[50,55,87,114],"storage,":[51],"paving":[52],"the":[53,71,88,91,115,145,159,164,176,183,201,210,231,236],"way":[54],"further":[56],"studies":[59],"on":[60,154,243],"information.":[62],"A":[63],"pivotal":[64],"initial":[65],"step":[66],"OCSR":[68],"is":[69,96],"automating":[70],"noise-free":[72],"extraction":[73,89,222],"descriptions":[76],"from":[77,121,196],"literature.":[78],"Despite":[79],"efforts":[80],"utilising":[81],"rule-based":[82],"deep":[84,105],"learning":[85,106],"approaches":[86],"process,":[90],"accuracy":[92],"achieved":[93],"date":[95],"unsatisfactory.":[97],"To":[98],"address":[99],"issue,":[101],"we":[102],"introduce":[103],"model":[107,125,190,237],"named":[108],"YoDe-Segmentation":[109,214],"study,":[112],"engineered":[113],"automated":[116],"retrieval":[117],"documents.":[123],"This":[124,226],"operates":[126],"via":[127],"three-stage":[129],"process":[130],"encompassing":[131],"detection,":[132],"mask":[133,149,160,171],"generation,":[134],"calculation.":[136],"Initially,":[137],"it":[138],"identifies":[139],"isolates":[141],"during":[144],"detection":[146],"phase.":[147],"Subsequently,":[148],"maps":[150,172],"are":[151,173],"created":[152],"based":[153],"these":[155],"isolated":[156,177],"generation":[161],"stage.":[162],"final":[165],"calculation":[166],"stage,":[167],"refined":[168],"separated":[170],"combined":[174],"with":[175,200],"images,":[180],"resulting":[181],"acquisition":[184],"pure":[186],"structures.":[188],"Our":[189],"underwent":[191],"rigorous":[192],"testing":[193],"using":[194],"texts":[195],"multiple":[197],"chemistry-centric":[198],"journals,":[199],"outcomes":[202],"subjected":[203],"manual":[205],"validation.":[206],"The":[207],"results":[208],"revealed":[209],"superior":[211],"performance":[212],"compared":[215],"alternative":[217],"algorithms,":[218],"documenting":[219],"an":[220],"average":[221],"efficiency":[223],"97.62%.":[225],"outcome":[227],"not":[228],"only":[229],"highlights":[230],"robustness":[232],"reliability":[234],"also":[239],"suggests":[240],"applicability":[242],"broad":[245],"scale.":[246]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}
