{"id":"https://openalex.org/W4394818987","doi":"https://doi.org/10.1186/s13321-024-00831-2","title":"Zombie cheminformatics: extraction and conversion of Wiswesser Line Notation (WLN) from chemical documents","display_name":"Zombie cheminformatics: extraction and conversion of Wiswesser Line Notation (WLN) from chemical documents","publication_year":2024,"publication_date":"2024-04-15","ids":{"openalex":"https://openalex.org/W4394818987","doi":"https://doi.org/10.1186/s13321-024-00831-2","pmid":"https://pubmed.ncbi.nlm.nih.gov/38622746"},"language":"en","primary_location":{"id":"doi:10.1186/s13321-024-00831-2","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-024-00831-2","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-024-00831-2","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/s13321-024-00831-2","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020232942","display_name":"Michael L. Blakey","orcid":"https://orcid.org/0000-0002-2906-1777"},"institutions":[{"id":"https://openalex.org/I43439940","display_name":"University of Southampton","ror":"https://ror.org/01ryk1543","country_code":"GB","type":"education","lineage":["https://openalex.org/I43439940"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Michael Blakey","raw_affiliation_strings":["Department of Chemistry, University of Southampton, University Road, Southampton, Hampshire, SO17 1BJ, UK. M.Blakey@soton.ac.uk","Department of Chemistry, University of Southampton, University Road, Southampton, Hampshire, SO17 1BJ, UK"],"affiliations":[{"raw_affiliation_string":"Department of Chemistry, University of Southampton, University Road, Southampton, Hampshire, SO17 1BJ, UK. M.Blakey@soton.ac.uk","institution_ids":["https://openalex.org/I43439940"]},{"raw_affiliation_string":"Department of Chemistry, University of Southampton, University Road, Southampton, Hampshire, SO17 1BJ, UK","institution_ids":["https://openalex.org/I43439940"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009212856","display_name":"Samantha Kanza","orcid":"https://orcid.org/0000-0002-4831-9489"},"institutions":[{"id":"https://openalex.org/I43439940","display_name":"University of Southampton","ror":"https://ror.org/01ryk1543","country_code":"GB","type":"education","lineage":["https://openalex.org/I43439940"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Samantha Pearman-Kanza","raw_affiliation_strings":["Department of Chemistry, University of Southampton, University Road, Southampton, Hampshire, SO17 1BJ, UK"],"affiliations":[{"raw_affiliation_string":"Department of Chemistry, University of Southampton, University Road, Southampton, Hampshire, SO17 1BJ, UK","institution_ids":["https://openalex.org/I43439940"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025830443","display_name":"Jeremy G. Frey","orcid":"https://orcid.org/0000-0003-0842-4302"},"institutions":[{"id":"https://openalex.org/I43439940","display_name":"University of Southampton","ror":"https://ror.org/01ryk1543","country_code":"GB","type":"education","lineage":["https://openalex.org/I43439940"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jeremy G. Frey","raw_affiliation_strings":["Department of Chemistry, University of Southampton, University Road, Southampton, Hampshire, SO17 1BJ, UK"],"affiliations":[{"raw_affiliation_string":"Department of Chemistry, University of Southampton, University Road, Southampton, Hampshire, SO17 1BJ, UK","institution_ids":["https://openalex.org/I43439940"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5020232942"],"corresponding_institution_ids":["https://openalex.org/I43439940"],"apc_list":{"value":1290,"currency":"GBP","value_usd":1582},"apc_paid":{"value":1290,"currency":"GBP","value_usd":1582},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05351635,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"16","issue":"1","first_page":"42","last_page":"42"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9921000003814697,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9921000003814697,"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":0.9485999941825867,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9244999885559082,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/cheminformatics","display_name":"Cheminformatics","score":0.9666102528572083},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.620177149772644},{"id":"https://openalex.org/keywords/zombie","display_name":"Zombie","score":0.5909906029701233},{"id":"https://openalex.org/keywords/line","display_name":"Line (geometry)","score":0.5090927481651306},{"id":"https://openalex.org/keywords/notation","display_name":"Notation","score":0.47848623991012573},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3650255501270294},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3341562747955322},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.22579652070999146},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07161936163902283}],"concepts":[{"id":"https://openalex.org/C68762167","wikidata":"https://www.wikidata.org/wiki/Q910164","display_name":"Cheminformatics","level":2,"score":0.9666102528572083},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.620177149772644},{"id":"https://openalex.org/C144446859","wikidata":"https://www.wikidata.org/wiki/Q219164","display_name":"Zombie","level":2,"score":0.5909906029701233},{"id":"https://openalex.org/C198352243","wikidata":"https://www.wikidata.org/wiki/Q37105","display_name":"Line (geometry)","level":2,"score":0.5090927481651306},{"id":"https://openalex.org/C45357846","wikidata":"https://www.wikidata.org/wiki/Q2001982","display_name":"Notation","level":2,"score":0.47848623991012573},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3650255501270294},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3341562747955322},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.22579652070999146},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07161936163902283},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0},{"id":"https://openalex.org/C147597530","wikidata":"https://www.wikidata.org/wiki/Q369472","display_name":"Computational chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1186/s13321-024-00831-2","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-024-00831-2","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-024-00831-2","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:38622746","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38622746","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:eprints.soton.ac.uk:489426","is_oa":true,"landing_page_url":"http://doi.org/10.1186/s13321-024-00831-2>).","pdf_url":"https://eprints.soton.ac.uk/489426/1/Zombie_Cheminformatics_Extraction_and_Conversion_of_Wiswesser_Line_Notation_WLN_from_Chemical_Documents_Version_2.pdf","source":{"id":"https://openalex.org/S4306401019","display_name":"ePrints Soton (University of Southampton)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I43439940","host_organization_name":"University of Southampton","host_organization_lineage":["https://openalex.org/I43439940"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"},{"id":"pmh:oai:pubmedcentral.nih.gov:11017645","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11017645","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11017645/pdf/13321_2024_Article_831.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:e15f3c3ac6e3491c93e2cfe07b80dd4f","is_oa":true,"landing_page_url":"https://doaj.org/article/e15f3c3ac6e3491c93e2cfe07b80dd4f","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 1-15 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13321-024-00831-2","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-024-00831-2","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-024-00831-2","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":[{"id":"https://openalex.org/G3069159407","display_name":null,"funder_award_id":"EP/S000356/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G4222052364","display_name":"Physical Sciences Data Infrastructure Phase 1b","funder_award_id":"EP/X032701/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G6867062684","display_name":null,"funder_award_id":"EP/N014189/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320314731","display_name":"UK Research and Innovation","ror":"https://ror.org/001aqnf71"},{"id":"https://openalex.org/F4320320277","display_name":"University of Southampton","ror":"https://ror.org/01ryk1543"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4394818987.pdf","grobid_xml":"https://content.openalex.org/works/W4394818987.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W1976892175","https://openalex.org/W1980090013","https://openalex.org/W1993440717","https://openalex.org/W2009660063","https://openalex.org/W2024175682","https://openalex.org/W2031019186","https://openalex.org/W2034206500","https://openalex.org/W2034354062","https://openalex.org/W2036638351","https://openalex.org/W2043808377","https://openalex.org/W2064363672","https://openalex.org/W2076488370","https://openalex.org/W2079082724","https://openalex.org/W2087563523","https://openalex.org/W2096541451","https://openalex.org/W2119289922","https://openalex.org/W2124955716","https://openalex.org/W2136794542","https://openalex.org/W2166468803","https://openalex.org/W2169678694","https://openalex.org/W2170973067","https://openalex.org/W2172216479","https://openalex.org/W2177317049","https://openalex.org/W2610394652","https://openalex.org/W2903943503","https://openalex.org/W2923162556","https://openalex.org/W2951788263","https://openalex.org/W4231677362","https://openalex.org/W4233756358","https://openalex.org/W4245608944","https://openalex.org/W4248027902"],"related_works":["https://openalex.org/W4408385070","https://openalex.org/W3211952845","https://openalex.org/W3187978971","https://openalex.org/W459167536","https://openalex.org/W4287028859","https://openalex.org/W4380874517","https://openalex.org/W4213192136","https://openalex.org/W3104387239","https://openalex.org/W2898750407","https://openalex.org/W2917626761"],"abstract_inverted_index":{"Tools":[0],"for":[1],"both":[2],"the":[3,17,25,33,39],"extraction":[4],"and":[5,22,47],"conversion":[6],"of":[7,27],"WLN":[8,28,36],"from":[9],"chemical":[10,48],"documents":[11],"have":[12],"been":[13],"successfully":[14],"developed.":[15],"Both":[16],"Deterministic":[18],"Finite":[19],"Automaton":[20],"(DFA)":[21],"parser":[23,40],"handle":[24],"majority":[26],"rules":[29],"officially":[30],"endorsed":[31],"in":[32,45],"three":[34],"major":[35],"manuals,":[37],"with":[38],"showing":[41],"a":[42],"clear":[43],"jump":[44],"accuracy":[46],"coverage":[49],"over":[50],"previous":[51],"submissions.":[52],"The":[53],"GitHub":[54],"repository":[55],"can":[56],"be":[57],"found":[58],"here:":[59],"https://github.com/Mblakey/wiswesser":[60],".":[61]},"counts_by_year":[],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}