{"id":"https://openalex.org/W2807704635","doi":"https://doi.org/10.1038/s41598-018-25440-6","title":"Linguistic measures of chemical diversity and the \u201ckeywords\u201d of molecular collections","display_name":"Linguistic measures of chemical diversity and the \u201ckeywords\u201d of molecular collections","publication_year":2018,"publication_date":"2018-05-09","ids":{"openalex":"https://openalex.org/W2807704635","doi":"https://doi.org/10.1038/s41598-018-25440-6","mag":"2807704635","pmid":"https://pubmed.ncbi.nlm.nih.gov/29765058"},"language":"en","primary_location":{"id":"doi:10.1038/s41598-018-25440-6","doi":"https://doi.org/10.1038/s41598-018-25440-6","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s41598-018-25440-6","pdf_url":"https://www.nature.com/articles/s41598-018-25440-6.pdf","source":{"id":"https://openalex.org/S196734849","display_name":"Scientific Reports","issn_l":"2045-2322","issn":["2045-2322"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","doyens","jufo-1","ki-jl-1","medline","norway-1"],"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","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":"Scientific Reports","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.nature.com/articles/s41598-018-25440-6.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083335301","display_name":"Micha\u0142 Wo\u017aniak","orcid":"https://orcid.org/0000-0001-9018-2204","observed_orcids":["https://orcid.org/0000-0001-9018-2204"]},"institutions":[{"id":"https://openalex.org/I4210107179","display_name":"The Institute of the Polish Language of the Polish Academy of Sciences","ror":"https://ror.org/01h9sha04","country_code":"PL","type":"facility","lineage":["https://openalex.org/I4210107179","https://openalex.org/I99542240"]},{"id":"https://openalex.org/I99542240","display_name":"Polish Academy of Sciences","ror":"https://ror.org/01dr6c206","country_code":"PL","type":"government","lineage":["https://openalex.org/I99542240"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Micha\u0142 Wo\u017aniak","raw_affiliation_strings":["Institute of Polish Language, Polish Academy of Sciences, Cracow, Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Polish Language, Polish Academy of Sciences, Cracow, Poland","institution_ids":["https://openalex.org/I4210107179","https://openalex.org/I99542240"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005462544","display_name":"Agnieszka Wo\u0142os","orcid":"https://orcid.org/0000-0001-9881-1634","observed_orcids":["https://orcid.org/0000-0001-9881-1634"]},"institutions":[{"id":"https://openalex.org/I4210109745","display_name":"Institute of Organic Chemistry","ror":"https://ror.org/01e17d143","country_code":"PL","type":"facility","lineage":["https://openalex.org/I4210109745","https://openalex.org/I99542240"]},{"id":"https://openalex.org/I99542240","display_name":"Polish Academy of Sciences","ror":"https://ror.org/01dr6c206","country_code":"PL","type":"government","lineage":["https://openalex.org/I99542240"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Agnieszka Wo\u0142os","raw_affiliation_strings":["Institute of Organic Chemistry, Polish Academy of Sciences, Warsaw, Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Organic Chemistry, Polish Academy of Sciences, Warsaw, Poland","institution_ids":["https://openalex.org/I4210109745","https://openalex.org/I99542240"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056558403","display_name":"Urszula Modrzyk","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210107179","display_name":"The Institute of the Polish Language of the Polish Academy of Sciences","ror":"https://ror.org/01h9sha04","country_code":"PL","type":"facility","lineage":["https://openalex.org/I4210107179","https://openalex.org/I99542240"]},{"id":"https://openalex.org/I99542240","display_name":"Polish Academy of Sciences","ror":"https://ror.org/01dr6c206","country_code":"PL","type":"government","lineage":["https://openalex.org/I99542240"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Urszula Modrzyk","raw_affiliation_strings":["Institute of Polish Language, Polish Academy of Sciences, Cracow, Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Polish Language, Polish Academy of Sciences, Cracow, Poland","institution_ids":["https://openalex.org/I4210107179","https://openalex.org/I99542240"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076318483","display_name":"Rafa\u0142 L. G\u00f3rski","orcid":"https://orcid.org/0000-0003-4727-2639","observed_orcids":["https://orcid.org/0000-0003-4727-2639"]},"institutions":[{"id":"https://openalex.org/I4210107179","display_name":"The Institute of the Polish Language of the Polish Academy of Sciences","ror":"https://ror.org/01h9sha04","country_code":"PL","type":"facility","lineage":["https://openalex.org/I4210107179","https://openalex.org/I99542240"]},{"id":"https://openalex.org/I99542240","display_name":"Polish Academy of Sciences","ror":"https://ror.org/01dr6c206","country_code":"PL","type":"government","lineage":["https://openalex.org/I99542240"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Rafa\u0142 L. G\u00f3rski","raw_affiliation_strings":["Institute of Polish Language, Polish Academy of Sciences, Cracow, Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Polish Language, Polish Academy of Sciences, Cracow, Poland","institution_ids":["https://openalex.org/I4210107179","https://openalex.org/I99542240"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070231167","display_name":"Jan Winkowski","orcid":"https://orcid.org/0000-0002-0301-8471","observed_orcids":["https://orcid.org/0000-0002-0301-8471"]},"institutions":[{"id":"https://openalex.org/I4210107179","display_name":"The Institute of the Polish Language of the Polish Academy of Sciences","ror":"https://ror.org/01h9sha04","country_code":"PL","type":"facility","lineage":["https://openalex.org/I4210107179","https://openalex.org/I99542240"]},{"id":"https://openalex.org/I99542240","display_name":"Polish Academy of Sciences","ror":"https://ror.org/01dr6c206","country_code":"PL","type":"government","lineage":["https://openalex.org/I99542240"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Jan Winkowski","raw_affiliation_strings":["Institute of Polish Language, Polish Academy of Sciences, Cracow, Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Polish Language, Polish Academy of Sciences, Cracow, Poland","institution_ids":["https://openalex.org/I4210107179","https://openalex.org/I99542240"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049940396","display_name":"Micha\u0142 Dariusz Bajczyk","orcid":"https://orcid.org/0000-0002-5016-2134","observed_orcids":["https://orcid.org/0000-0002-5016-2134"]},"institutions":[{"id":"https://openalex.org/I4210109745","display_name":"Institute of Organic Chemistry","ror":"https://ror.org/01e17d143","country_code":"PL","type":"facility","lineage":["https://openalex.org/I4210109745","https://openalex.org/I99542240"]},{"id":"https://openalex.org/I99542240","display_name":"Polish Academy of Sciences","ror":"https://ror.org/01dr6c206","country_code":"PL","type":"government","lineage":["https://openalex.org/I99542240"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Micha\u0142 Bajczyk","raw_affiliation_strings":["Institute of Organic Chemistry, Polish Academy of Sciences, Warsaw, Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Organic Chemistry, Polish Academy of Sciences, Warsaw, Poland","institution_ids":["https://openalex.org/I4210109745","https://openalex.org/I99542240"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073461173","display_name":"Sara Szymku\u0107","orcid":"https://orcid.org/0000-0002-3475-3663","observed_orcids":["https://orcid.org/0000-0002-3475-3663"]},"institutions":[{"id":"https://openalex.org/I4210109745","display_name":"Institute of Organic Chemistry","ror":"https://ror.org/01e17d143","country_code":"PL","type":"facility","lineage":["https://openalex.org/I4210109745","https://openalex.org/I99542240"]},{"id":"https://openalex.org/I99542240","display_name":"Polish Academy of Sciences","ror":"https://ror.org/01dr6c206","country_code":"PL","type":"government","lineage":["https://openalex.org/I99542240"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Sara Szymku\u0107","raw_affiliation_strings":["Institute of Organic Chemistry, Polish Academy of Sciences, Warsaw, Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Organic Chemistry, Polish Academy of Sciences, Warsaw, Poland","institution_ids":["https://openalex.org/I4210109745","https://openalex.org/I99542240"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087895403","display_name":"Bartosz A. Grzybowski","orcid":"https://orcid.org/0000-0001-6613-4261","observed_orcids":["https://orcid.org/0000-0001-6613-4261"]},"institutions":[{"id":"https://openalex.org/I4210104335","display_name":"Institute for Basic Science","ror":"https://ror.org/00y0zf565","country_code":"KR","type":"facility","lineage":["https://openalex.org/I4210104335"]},{"id":"https://openalex.org/I4210109745","display_name":"Institute of Organic Chemistry","ror":"https://ror.org/01e17d143","country_code":"PL","type":"facility","lineage":["https://openalex.org/I4210109745","https://openalex.org/I99542240"]},{"id":"https://openalex.org/I48566637","display_name":"Ulsan National Institute of Science and Technology","ror":"https://ror.org/017cjz748","country_code":"KR","type":"education","lineage":["https://openalex.org/I48566637"]},{"id":"https://openalex.org/I99542240","display_name":"Polish Academy of Sciences","ror":"https://ror.org/01dr6c206","country_code":"PL","type":"government","lineage":["https://openalex.org/I99542240"]}],"countries":["KR","PL"],"is_corresponding":true,"raw_author_name":"Bartosz A. Grzybowski","raw_affiliation_strings":["Center for Soft and Living Matter of Korea's Institute for Basic Science (IBS), Ulsan, South Korea. nanogrzybowski@gmail.com","Department of Chemistry, Ulsan National Institute of Science and Technology, Ulsan, South Korea. nanogrzybowski@gmail.com","Institute of Organic Chemistry, Polish Academy of Sciences, Warsaw, Poland. nanogrzybowski@gmail.com","Institute of Organic Chemistry, Polish Academy of Sciences, Warsaw, Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Soft and Living Matter of Korea's Institute for Basic Science (IBS), Ulsan, South Korea. nanogrzybowski@gmail.com","institution_ids":["https://openalex.org/I4210104335"]},{"raw_affiliation_string":"Department of Chemistry, Ulsan National Institute of Science and Technology, Ulsan, South Korea. nanogrzybowski@gmail.com","institution_ids":["https://openalex.org/I48566637"]},{"raw_affiliation_string":"Institute of Organic Chemistry, Polish Academy of Sciences, Warsaw, Poland. nanogrzybowski@gmail.com","institution_ids":["https://openalex.org/I4210109745","https://openalex.org/I99542240"]},{"raw_affiliation_string":"Institute of Organic Chemistry, Polish Academy of Sciences, Warsaw, Poland","institution_ids":["https://openalex.org/I4210109745","https://openalex.org/I99542240"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052407843","display_name":"Maciej Eder","orcid":"https://orcid.org/0000-0002-1429-5036","observed_orcids":["https://orcid.org/0000-0002-1429-5036"]},"institutions":[{"id":"https://openalex.org/I4210107179","display_name":"The Institute of the Polish Language of the Polish Academy of Sciences","ror":"https://ror.org/01h9sha04","country_code":"PL","type":"facility","lineage":["https://openalex.org/I4210107179","https://openalex.org/I99542240"]},{"id":"https://openalex.org/I99542240","display_name":"Polish Academy of Sciences","ror":"https://ror.org/01dr6c206","country_code":"PL","type":"government","lineage":["https://openalex.org/I99542240"]}],"countries":["PL"],"is_corresponding":true,"raw_author_name":"Maciej Eder","raw_affiliation_strings":["Institute of Polish Language, Polish Academy of Sciences, Cracow, Poland. maciejeder@gmail.com","Institute of Polish Language, Polish Academy of Sciences, Cracow, Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Polish Language, Polish Academy of Sciences, Cracow, Poland. maciejeder@gmail.com","institution_ids":["https://openalex.org/I4210107179","https://openalex.org/I99542240"]},{"raw_affiliation_string":"Institute of Polish Language, Polish Academy of Sciences, Cracow, Poland","institution_ids":["https://openalex.org/I4210107179","https://openalex.org/I99542240"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5052407843","https://openalex.org/A5087895403"],"corresponding_institution_ids":["https://openalex.org/I4210104335","https://openalex.org/I4210107179","https://openalex.org/I4210109745","https://openalex.org/I48566637","https://openalex.org/I99542240"],"apc_list":{"value":2690,"currency":"USD","value_usd":2690},"apc_paid":{"value":2690,"currency":"USD","value_usd":2690},"fwci":1.9559,"has_fulltext":true,"cited_by_count":53,"citation_normalized_percentile":{"value":0.87442697,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"8","issue":"1","first_page":"7598","last_page":"7598"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.7997999787330627,"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":0.7997999787330627,"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/T11476","display_name":"Graph theory and applications","score":0.030500000342726707,"subfield":{"id":"https://openalex.org/subfields/2608","display_name":"Geometry and Topology"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13297","display_name":"History and advancements in chemistry","score":0.013199999928474426,"subfield":{"id":"https://openalex.org/subfields/1606","display_name":"Physical and Theoretical 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/chemical-diversity","display_name":"chemical diversity","score":0.7120000123977661},{"id":"https://openalex.org/keywords/structural-fragments","display_name":"structural fragments","score":0.7699999809265137},{"id":"https://openalex.org/keywords/chemical-databases","display_name":"chemical databases","score":0.5070000290870667},{"id":"https://openalex.org/keywords/corpus-linguistics","display_name":"corpus linguistics","score":0.5879999995231628}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7440921068191528},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.6169272661209106},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.5762711763381958},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5293066501617432},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.4970698654651642},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46319952607154846},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3604881763458252},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.34737926721572876},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.06389155983924866},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.057316362857818604},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1038/s41598-018-25440-6","doi":"https://doi.org/10.1038/s41598-018-25440-6","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s41598-018-25440-6","pdf_url":"https://www.nature.com/articles/s41598-018-25440-6.pdf","source":{"id":"https://openalex.org/S196734849","display_name":"Scientific Reports","issn_l":"2045-2322","issn":["2045-2322"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","doyens","jufo-1","ki-jl-1","medline","norway-1"],"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","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":"Scientific Reports","raw_type":"journal-article"},{"id":"pmid:29765058","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/29765058","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":"Scientific reports","raw_type":"Journal Article"},{"id":"pmh:oai:europepmc.org:4877508","doi":null,"is_oa":true,"landing_page_url":"http://europepmc.org/pmc/articles/PMC5953938","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:5953938","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/5953938","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sci Rep","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:cb3bb3ade27f4b13a2b20861629d946e","doi":null,"is_oa":true,"landing_page_url":"https://doaj.org/article/cb3bb3ade27f4b13a2b20861629d946e","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":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Scientific Reports, Vol 8, Iss 1, Pp 1-10 (2018)","raw_type":"article"},{"id":"pmh:oai:scholarworks.unist.ac.kr:201301/24194","doi":null,"is_oa":true,"landing_page_url":"https://www.nature.com/articles/s41598-018-25440-6","pdf_url":null,"source":{"id":"https://openalex.org/S4306401118","display_name":"Scholarworks@UNIST (Ulsan National Institute of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I48566637","host_organization_name":"Ulsan National Institute of Science and Technology","host_organization_lineage":["https://openalex.org/I48566637"],"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":"","raw_type":"ARTICLE"}],"best_oa_location":{"id":"doi:10.1038/s41598-018-25440-6","doi":"https://doi.org/10.1038/s41598-018-25440-6","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s41598-018-25440-6","pdf_url":"https://www.nature.com/articles/s41598-018-25440-6.pdf","source":{"id":"https://openalex.org/S196734849","display_name":"Scientific Reports","issn_l":"2045-2322","issn":["2045-2322"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","doyens","jufo-1","ki-jl-1","medline","norway-1"],"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","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":"Scientific Reports","raw_type":"journal-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"display_name":"Quality education","id":"https://metadata.un.org/sdg/4","score":0.6000000238418579}],"study_designs":[],"awards":[{"id":"https://openalex.org/G1042849371","display_name":null,"funder_award_id":"IBS-R-020","funder_id":"https://openalex.org/F4320326441","funder_display_name":"Institute for Basic Science"},{"id":"https://openalex.org/G1057460214","display_name":null,"funder_award_id":"69461-CH-DRP #W911NF1610384","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G1209599001","display_name":null,"funder_award_id":"IBS-R-020-D1","funder_id":"https://openalex.org/F4320326441","funder_display_name":"Institute for Basic Science"},{"id":"https://openalex.org/G375635608","display_name":null,"funder_award_id":"69461-CH-DRP","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G5043223076","display_name":null,"funder_award_id":"W911NF1610384","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G7416298312","display_name":null,"funder_award_id":"Project Code IBS-R020-D1","funder_id":"https://openalex.org/F4320326441","funder_display_name":"Institute for Basic Science"},{"id":"https://openalex.org/G8524864788","display_name":null,"funder_award_id":"R020-D1","funder_id":"https://openalex.org/F4320326441","funder_display_name":"Institute for Basic Science"}],"funders":[{"id":"https://openalex.org/F4320326441","display_name":"Institute for Basic Science","ror":"https://ror.org/00y0zf565"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2807704635.pdf","grobid_xml":"https://content.openalex.org/works/W2807704635.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W602425687","https://openalex.org/W1505524995","https://openalex.org/W1606480292","https://openalex.org/W1891860149","https://openalex.org/W1964981516","https://openalex.org/W1977429173","https://openalex.org/W2003722831","https://openalex.org/W2007035566","https://openalex.org/W2014552602","https://openalex.org/W2017945055","https://openalex.org/W2032146015","https://openalex.org/W2038178664","https://openalex.org/W2046564413","https://openalex.org/W2060581674","https://openalex.org/W2061843861","https://openalex.org/W2077706425","https://openalex.org/W2103626206","https://openalex.org/W2107845562","https://openalex.org/W2109294083","https://openalex.org/W2117682071","https://openalex.org/W2140010870","https://openalex.org/W2145546477","https://openalex.org/W2162106505","https://openalex.org/W2254039285","https://openalex.org/W2314727869","https://openalex.org/W2412446857","https://openalex.org/W2610394652","https://openalex.org/W2622322262","https://openalex.org/W2769423117","https://openalex.org/W3103059940","https://openalex.org/W4211148787"],"related_works":["https://openalex.org/W2065457896","https://openalex.org/W3173234801","https://openalex.org/W2167984027","https://openalex.org/W3021302227","https://openalex.org/W10630519","https://openalex.org/W1919377569","https://openalex.org/W3144288563","https://openalex.org/W3123907821","https://openalex.org/W2382319620","https://openalex.org/W1513671779"],"abstract_inverted_index":{"Computerized":[0],"linguistic":[1],"analyses":[2],"have":[3],"proven":[4],"of":[5,89],"immense":[6],"value":[7],"in":[8,92],"comparing":[9],"and":[10,95,107],"searching":[11],"through":[12],"large":[13],"text":[14],"collections":[15,103],"(\"corpora\"),":[16],"including":[17],"those":[18],"deposited":[19],"on":[20,59],"the":[21,33,87],"Internet":[22],"-":[23],"indeed,":[24],"it":[25,82],"would":[26],"nowadays":[27],"be":[28,54],"hard":[29],"to":[30,56,85,96],"imagine":[31],"browsing":[32],"Web":[34],"without,":[35],"for":[36],"instance,":[37],"search":[38],"algorithms":[39],"extracting":[40],"most":[41],"appropriate":[42],"keywords":[43],"from":[44],"documents.":[45],"This":[46],"paper":[47],"describes":[48],"how":[49],"such":[50,102],"corpus-linguistic":[51],"concepts":[52],"can":[53],"extended":[55],"chemistry":[57],"based":[58],"characteristic":[60],"\"chemical":[61],"words\"":[62],"that":[63],"span":[64],"more":[65],"than":[66],"traditional":[67],"functional":[68],"groups":[69],"and,":[70],"instead,":[71],"look":[72],"at":[73],"common":[74],"structural":[75],"fragments":[76],"molecules":[77],"share.":[78],"Using":[79],"these":[80],"words,":[81],"is":[83],"possible":[84],"quantify":[86],"diversity":[88],"chemical":[90],"collections/databases":[91],"new":[93],"ways":[94],"define":[97],"molecular":[98],"\"keywords\"":[99],"by":[100],"which":[101],"are":[104],"best":[105],"characterized":[106],"annotated.":[108]},"counts_by_year":[{"year":2026,"cited_by_count":26},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":1}],"updated_date":"2026-09-22T06:50:58.402377","created_date":"2025-10-10T00:00:00"}