{"id":"https://openalex.org/W4311219784","doi":"https://doi.org/10.1186/s13321-022-00663-y","title":"An algorithm to classify homologous series within compound datasets","display_name":"An algorithm to classify homologous series within compound datasets","publication_year":2022,"publication_date":"2022-12-13","ids":{"openalex":"https://openalex.org/W4311219784","doi":"https://doi.org/10.1186/s13321-022-00663-y","pmid":"https://pubmed.ncbi.nlm.nih.gov/36510332"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-022-00663-y","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-022-00663-y","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_indexed_in_scopus":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310319965","https://openalex.org/P4310320256"],"host_organization_lineage_names":["Springer Nature","BioMed Central"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},"type":"article","type_crossref":"journal-article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-022-00663-y","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039069854","display_name":"Adelene Lai","orcid":"https://orcid.org/0000-0002-2985-6473"},"institutions":[{"id":"https://openalex.org/I186903577","display_name":"University of Luxembourg","ror":"https://ror.org/036x5ad56","country_code":"LU","type":"funder","lineage":["https://openalex.org/I186903577"]}],"countries":["LU"],"is_corresponding":false,"raw_author_name":"Adelene Lai","raw_affiliation_strings":["Luxembourg Centre for Systems Biomedicine (LCSB), University of Luxembourg, 6 Avenue du Swing, 4367, Belvaux, Luxembourg"],"affiliations":[{"raw_affiliation_string":"Luxembourg Centre for Systems Biomedicine (LCSB), University of Luxembourg, 6 Avenue du Swing, 4367, Belvaux, Luxembourg","institution_ids":["https://openalex.org/I186903577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001536528","display_name":"Jonas Schaub","orcid":"https://orcid.org/0000-0003-1554-6666"},"institutions":[{"id":"https://openalex.org/I76198965","display_name":"Friedrich Schiller University Jena","ror":"https://ror.org/05qpz1x62","country_code":"DE","type":"funder","lineage":["https://openalex.org/I76198965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jonas Schaub","raw_affiliation_strings":["Institute for Inorganic and Analytical Chemistry, Friedrich Schiller University Jena, Lessing Strasse 8, 07743, Jena, Germany"],"affiliations":[{"raw_affiliation_string":"Institute for Inorganic and Analytical Chemistry, Friedrich Schiller University Jena, Lessing Strasse 8, 07743, Jena, Germany","institution_ids":["https://openalex.org/I76198965"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040194803","display_name":"Christoph Steinbeck","orcid":"https://orcid.org/0000-0001-6966-0814"},"institutions":[{"id":"https://openalex.org/I76198965","display_name":"Friedrich Schiller University Jena","ror":"https://ror.org/05qpz1x62","country_code":"DE","type":"funder","lineage":["https://openalex.org/I76198965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christoph Steinbeck","raw_affiliation_strings":["Institute for Inorganic and Analytical Chemistry, Friedrich Schiller University Jena, Lessing Strasse 8, 07743, Jena, Germany"],"affiliations":[{"raw_affiliation_string":"Institute for Inorganic and Analytical Chemistry, Friedrich Schiller University Jena, Lessing Strasse 8, 07743, Jena, Germany","institution_ids":["https://openalex.org/I76198965"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016319274","display_name":"Emma Schymanski","orcid":"https://orcid.org/0000-0001-6868-8145"},"institutions":[{"id":"https://openalex.org/I186903577","display_name":"University of Luxembourg","ror":"https://ror.org/036x5ad56","country_code":"LU","type":"funder","lineage":["https://openalex.org/I186903577"]}],"countries":["LU"],"is_corresponding":false,"raw_author_name":"Emma L. Schymanski","raw_affiliation_strings":["Luxembourg Centre for Systems Biomedicine (LCSB), University of Luxembourg, 6 Avenue du Swing, 4367, Belvaux, Luxembourg"],"affiliations":[{"raw_affiliation_string":"Luxembourg Centre for Systems Biomedicine (LCSB), University of Luxembourg, 6 Avenue du Swing, 4367, Belvaux, Luxembourg","institution_ids":["https://openalex.org/I186903577"]}]}],"institution_assertions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1290,"currency":"GBP","value_usd":1582},"apc_paid":{"value":1662,"currency":"EUR","value_usd":1792},"fwci":0.44,"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":4,"citation_normalized_percentile":{"value":0.695248,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":78,"max":81},"biblio":{"volume":"14","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10836","display_name":"Metabolomics and Mass Spectrometry Studies","score":0.9999,"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"}},"topics":[{"id":"https://openalex.org/T10836","display_name":"Metabolomics and Mass Spectrometry Studies","score":0.9999,"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/T10211","display_name":"Computational Drug Discovery Methods","score":0.9987,"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/T10908","display_name":"Analytical Chemistry and Chromatography","score":0.9964,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/homologous-series","display_name":"Homologous series","score":0.87922925}],"concepts":[{"id":"https://openalex.org/C2776482079","wikidata":"https://www.wikidata.org/wiki/Q741844","display_name":"Homologous series","level":2,"score":0.87922925},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.648059},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5671593},{"id":"https://openalex.org/C143724316","wikidata":"https://www.wikidata.org/wiki/Q312468","display_name":"Series (stratigraphy)","level":2,"score":0.51464164},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4297818},{"id":"https://openalex.org/C64894306","wikidata":"https://www.wikidata.org/wiki/Q849622","display_name":"Homologous chromosome","level":3,"score":0.42827636},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.40752244},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3481539},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.33026972},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32814562},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.26350814},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22266018},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.19089693},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.14206931},{"id":"https://openalex.org/C8010536","wikidata":"https://www.wikidata.org/wiki/Q160398","display_name":"Crystallography","level":1,"score":0.12062311},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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}],"mesh":[],"locations_count":6,"locations":[{"is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-022-00663-y","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-022-00663-y","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_indexed_in_scopus":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310319965","https://openalex.org/P4310320256"],"host_organization_lineage_names":["Springer Nature","BioMed Central"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":false,"landing_page_url":"https://doaj.org/article/d1af9bc2dedf49a8ac9151a8fd29fdeb","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"http://orbilu.uni.lu/handle/10993/53097","pdf_url":"https://orbilu.uni.lu/bitstream/10993/53097/1/s13321-022-00663-y.pdf","source":{"id":"https://openalex.org/S4306401815","display_name":"Open Repository and Bibliography (University of Luxembourg)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":"https://openalex.org/I186903577","host_organization_name":"University of Luxembourg","host_organization_lineage":["https://openalex.org/I186903577"],"host_organization_lineage_names":["University of Luxembourg"],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9746203","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_indexed_in_scopus":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":["National Institutes of Health"],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-2019306/v1","pdf_url":"https://www.researchsquare.com/article/rs-2019306/latest.pdf","source":{"id":"https://openalex.org/S4306402450","display_name":"Research Square (Research Square)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":"https://openalex.org/I4210096694","host_organization_name":"Research Square (United States)","host_organization_lineage":["https://openalex.org/I4210096694"],"host_organization_lineage_names":["Research Square (United States)"],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false},{"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36510332","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_indexed_in_scopus":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":["National Institutes of Health"],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-022-00663-y","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-022-00663-y","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_indexed_in_scopus":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310319965","https://openalex.org/P4310320256"],"host_organization_lineage_names":["Springer Nature","BioMed Central"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},"sustainable_development_goals":[{"score":0.4,"id":"https://metadata.un.org/sdg/12","display_name":"Responsible consumption and production"}],"grants":[{"funder":"https://openalex.org/F4320309895","funder_display_name":"Carl-Zeiss-Stiftung","award_id":null},{"funder":"https://openalex.org/F4320313941","funder_display_name":"Friedrich-Schiller-Universit\u00e4t Jena","award_id":null},{"funder":"https://openalex.org/F4320321038","funder_display_name":"Fonds National de la Recherche Luxembourg","award_id":"A18/BM/12341006"}],"datasets":[],"versions":[],"referenced_works_count":62,"referenced_works":["https://openalex.org/W1937338252","https://openalex.org/W1976892175","https://openalex.org/W1982870104","https://openalex.org/W1988037271","https://openalex.org/W1999440281","https://openalex.org/W2018622518","https://openalex.org/W2033542580","https://openalex.org/W2044525777","https://openalex.org/W2044834685","https://openalex.org/W2051760084","https://openalex.org/W2055102854","https://openalex.org/W2060531713","https://openalex.org/W2071234745","https://openalex.org/W2071653911","https://openalex.org/W2078432427","https://openalex.org/W2103626206","https://openalex.org/W2118086604","https://openalex.org/W2145885671","https://openalex.org/W2179066627","https://openalex.org/W2179324695","https://openalex.org/W2213735563","https://openalex.org/W2315565293","https://openalex.org/W2318794083","https://openalex.org/W2591002382","https://openalex.org/W2783024199","https://openalex.org/W2804460419","https://openalex.org/W2900920506","https://openalex.org/W2903331367","https://openalex.org/W2963613589","https://openalex.org/W2964237212","https://openalex.org/W2968362538","https://openalex.org/W2969475047","https://openalex.org/W2977052496","https://openalex.org/W3023313568","https://openalex.org/W3043559002","https://openalex.org/W3096321011","https://openalex.org/W3097145107","https://openalex.org/W3097605476","https://openalex.org/W3111515949","https://openalex.org/W3118695441","https://openalex.org/W3120715532","https://openalex.org/W3121899439","https://openalex.org/W3133965623","https://openalex.org/W3159789740","https://openalex.org/W3163850647","https://openalex.org/W3196865634","https://openalex.org/W3211416309","https://openalex.org/W3216996724","https://openalex.org/W4200417966","https://openalex.org/W4205683904","https://openalex.org/W4210869613","https://openalex.org/W4213287388","https://openalex.org/W4280641045","https://openalex.org/W4286497146","https://openalex.org/W4294534758","https://openalex.org/W4297256900","https://openalex.org/W4306986298","https://openalex.org/W4308683713","https://openalex.org/W4311219784","https://openalex.org/W4393490671","https://openalex.org/W4393538258","https://openalex.org/W4393845646"],"related_works":["https://openalex.org/W4230782844","https://openalex.org/W2388568305","https://openalex.org/W2188171182","https://openalex.org/W2086637863","https://openalex.org/W2049291217","https://openalex.org/W2043682602","https://openalex.org/W2030960607","https://openalex.org/W2021648688","https://openalex.org/W2012891529","https://openalex.org/W1977667614"],"abstract_inverted_index":{"Homologous":[0],"series":[1,25,74,125,162,172],"are":[2,26],"groups":[3],"of":[4,27,90,114,129,153],"related":[5],"compounds":[6,43],"that":[7,17],"share":[8],"the":[9,83,165],"same":[10],"core":[11,120],"structure":[12],"attached":[13],"to":[14,19,54,71,123,160],"a":[15,88,96],"motif":[16],"repeats":[18],"different":[20],"degrees.":[21],"Compounds":[22],"forming":[23],"homologous":[24,42,73,124,161],"interest":[28],"in":[29,48],"multiple":[30],"domains,":[31],"including":[32],"natural":[33,149],"products,":[34],"environmental":[35,137],"chemistry,":[36],"and":[37,58,80,95,119,148,170],"drug":[38],"design.":[39],"However,":[40],"many":[41],"remain":[44],"unannotated":[45],"as":[46,92,102,104],"such":[47],"compound":[49,76,134],"datasets,":[50],"which":[51],"poses":[52],"obstacles":[53],"understanding":[55],"chemical":[56],"diversity":[57],"their":[59],"analytical":[60],"identification":[61],"via":[62],"database":[63],"matching.":[64],"To":[65],"overcome":[66],"these":[67],"challenges,":[68],"an":[69,109],"algorithm":[70,86],"detect":[72],"within":[75],"datasets":[77,135],"was":[78],"developed":[79],"implemented":[81],"using":[82,164],"RDKit.":[84],"The":[85],"takes":[87],"list":[89],"molecules":[91],"SMILES":[93],"strings":[94],"monomer":[97],"(i.e.,":[98],"repeating":[99,115],"unit)":[100],"encoded":[101],"SMARTS":[103],"its":[105],"main":[106],"inputs.":[107],"In":[108],"iterative":[110],"process,":[111],"substructure":[112],"matching":[113],"units,":[116],"molecule":[117],"fragmentation,":[118],"detection":[121],"lead":[122],"classification":[126,163],"through":[127],"grouping":[128],"identical":[130],"cores.":[131],"Three":[132],"open":[133],"from":[136],"chemistry":[138],"(NORMAN":[139],"Suspect":[140],"List":[141],"Exchange,":[142],"NORMAN-SLE),":[143],"exposomics":[144],"(PubChemLite":[145],"for":[146],"Exposomics),":[147],"products":[150],"(the":[151],"COlleCtion":[152],"Open":[154],"NatUral":[155],"producTs,":[156],"COCONUT)":[157],"were":[158],"subject":[159],"algorithm.":[166],"Over":[167],"2000,":[168],"12,000,":[169],"5000":[171],"with":[173],"CH":[174]},"abstract_inverted_index_v3":null,"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4311219784","counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-04-27T09:03:15.321195","created_date":"2022-12-24"}