{"id":"https://openalex.org/W7223070576","doi":"https://doi.org/10.64898/2026.10.14.759107","title":"ALLCAPS: a scalable and accurate deep-learning method for in silico pneumococcal serotyping","display_name":"ALLCAPS: a scalable and accurate deep-learning method for in silico pneumococcal serotyping","publication_year":2026,"publication_date":"2026-10-20","ids":{"openalex":"https://openalex.org/W7223070576","doi":"https://doi.org/10.64898/2026.10.14.759107"},"language":"en","primary_location":{"id":"doi:10.64898/2026.10.14.759107","doi":"https://doi.org/10.64898/2026.10.14.759107","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.14.759107","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/20/2026.10.14.759107.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/20/2026.10.14.759107.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5123534811","display_name":"Alireza Tajmirriahi","orcid":"https://orcid.org/0009-0002-4117-0279","observed_orcids":["https://orcid.org/0009-0002-4117-0279"]},"institutions":[{"id":"https://openalex.org/I1303153112","display_name":"European Bioinformatics Institute","ror":"https://ror.org/02catss52","country_code":"GB","type":"facility","lineage":["https://openalex.org/I1303153112","https://openalex.org/I4210138560"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Alireza Tajmirriahi","raw_affiliation_strings":["European Bioinformatics Institute, European Molecular Biology Laboratory, Wellcome Genome Campus, Hinxton, Cambridge CB10 1SD, United Kingdom"],"raw_orcid":"https://orcid.org/0009-0002-4117-0279","affiliations":[{"raw_affiliation_string":"European Bioinformatics Institute, European Molecular Biology Laboratory, Wellcome Genome Campus, Hinxton, Cambridge CB10 1SD, United Kingdom","institution_ids":["https://openalex.org/I1303153112"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031757155","display_name":"Teodora Mateeva","orcid":"https://orcid.org/0000-0003-0368-5124","observed_orcids":["https://orcid.org/0000-0003-0368-5124"]},"institutions":[{"id":"https://openalex.org/I2802476451","display_name":"Wellcome Sanger Institute","ror":"https://ror.org/05cy4wa09","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I2802476451","https://openalex.org/I87048295"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Teodora Mateeva","raw_affiliation_strings":["Parasites and Microbes, Wellcome Sanger Institute, Cambridge CB10 1RQ, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0003-0368-5124","affiliations":[{"raw_affiliation_string":"Parasites and Microbes, Wellcome Sanger Institute, Cambridge CB10 1RQ, United Kingdom","institution_ids":["https://openalex.org/I2802476451"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026815774","display_name":"Matthew Russell","orcid":"https://orcid.org/0000-0001-6140-6723","observed_orcids":["https://orcid.org/0000-0001-6140-6723","https://orcid.org/0000-0002-1976-4153"]},"institutions":[{"id":"https://openalex.org/I1303153112","display_name":"European Bioinformatics Institute","ror":"https://ror.org/02catss52","country_code":"GB","type":"facility","lineage":["https://openalex.org/I1303153112","https://openalex.org/I4210138560"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Matthew J. Russell","raw_affiliation_strings":["European Bioinformatics Institute, European Molecular Biology Laboratory, Wellcome Genome Campus, Hinxton, Cambridge CB10 1SD, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-1976-4153","affiliations":[{"raw_affiliation_string":"European Bioinformatics Institute, European Molecular Biology Laboratory, Wellcome Genome Campus, Hinxton, Cambridge CB10 1SD, United Kingdom","institution_ids":["https://openalex.org/I1303153112"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051684533","display_name":"Oliver Lorenz","orcid":"https://orcid.org/0000-0002-3018-4336","observed_orcids":["https://orcid.org/0000-0002-3018-4336"]},"institutions":[{"id":"https://openalex.org/I126231945","display_name":"Queen's University Belfast","ror":"https://ror.org/00hswnk62","country_code":"GB","type":"education","lineage":["https://openalex.org/I126231945"]},{"id":"https://openalex.org/I2802476451","display_name":"Wellcome Sanger Institute","ror":"https://ror.org/05cy4wa09","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I2802476451","https://openalex.org/I87048295"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Oliver Lorenz","raw_affiliation_strings":["Parasites and Microbes, Wellcome Sanger Institute, Cambridge CB10 1RQ, United Kingdom","School of Biological Sciences, Queen\u2019s University Belfast, 19 Chlorine Gardens, Biological Sciences Building, Belfast, BT9 5DL, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-3018-4336","affiliations":[{"raw_affiliation_string":"Parasites and Microbes, Wellcome Sanger Institute, Cambridge CB10 1RQ, United Kingdom","institution_ids":["https://openalex.org/I2802476451"]},{"raw_affiliation_string":"School of Biological Sciences, Queen\u2019s University Belfast, 19 Chlorine Gardens, Biological Sciences Building, Belfast, BT9 5DL, United Kingdom","institution_ids":["https://openalex.org/I126231945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5159128475","display_name":"Soo Jeong Kim","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1303153112","display_name":"European Bioinformatics Institute","ror":"https://ror.org/02catss52","country_code":"GB","type":"facility","lineage":["https://openalex.org/I1303153112","https://openalex.org/I4210138560"]},{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Soo-Jeong Kim","raw_affiliation_strings":["European Bioinformatics Institute, European Molecular Biology Laboratory, Wellcome Genome Campus, Hinxton, Cambridge CB10 1SD, United Kingdom","University of Cambridge, Trinity Ln, Cambridge CB2 1TN, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"European Bioinformatics Institute, European Molecular Biology Laboratory, Wellcome Genome Campus, Hinxton, Cambridge CB10 1SD, United Kingdom","institution_ids":["https://openalex.org/I1303153112"]},{"raw_affiliation_string":"University of Cambridge, Trinity Ln, Cambridge CB2 1TN, United Kingdom","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022302563","display_name":"Stephanie W. Lo","orcid":"https://orcid.org/0000-0002-2182-0222","observed_orcids":["https://orcid.org/0000-0002-2182-0222","https://orcid.org/0000-0001-5268-7535"]},"institutions":[{"id":"https://openalex.org/I1303153112","display_name":"European Bioinformatics Institute","ror":"https://ror.org/02catss52","country_code":"GB","type":"facility","lineage":["https://openalex.org/I1303153112","https://openalex.org/I4210138560"]},{"id":"https://openalex.org/I2802476451","display_name":"Wellcome Sanger Institute","ror":"https://ror.org/05cy4wa09","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I2802476451","https://openalex.org/I87048295"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Stephanie W. Lo","raw_affiliation_strings":["European Bioinformatics Institute, European Molecular Biology Laboratory, Wellcome Genome Campus, Hinxton, Cambridge CB10 1SD, United Kingdom","Parasites and Microbes, Wellcome Sanger Institute, Cambridge CB10 1RQ, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-2182-0222","affiliations":[{"raw_affiliation_string":"European Bioinformatics Institute, European Molecular Biology Laboratory, Wellcome Genome Campus, Hinxton, Cambridge CB10 1SD, United Kingdom","institution_ids":["https://openalex.org/I1303153112"]},{"raw_affiliation_string":"Parasites and Microbes, Wellcome Sanger Institute, Cambridge CB10 1RQ, United Kingdom","institution_ids":["https://openalex.org/I2802476451"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077742706","display_name":"Stephen D. Bentley","orcid":"https://orcid.org/0000-0001-8094-3751","observed_orcids":["https://orcid.org/0000-0001-8094-3751"]},"institutions":[{"id":"https://openalex.org/I2802476451","display_name":"Wellcome Sanger Institute","ror":"https://ror.org/05cy4wa09","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I2802476451","https://openalex.org/I87048295"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Stephen D. Bentley","raw_affiliation_strings":["Parasites and Microbes, Wellcome Sanger Institute, Cambridge CB10 1RQ, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0001-8094-3751","affiliations":[{"raw_affiliation_string":"Parasites and Microbes, Wellcome Sanger Institute, Cambridge CB10 1RQ, United Kingdom","institution_ids":["https://openalex.org/I2802476451"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012148931","display_name":"John A. Lees","orcid":"https://orcid.org/0000-0001-5360-1254","observed_orcids":["https://orcid.org/0000-0001-5360-1254","https://orcid.org/0000-0002-2476-4385"]},"institutions":[{"id":"https://openalex.org/I1303153112","display_name":"European Bioinformatics Institute","ror":"https://ror.org/02catss52","country_code":"GB","type":"facility","lineage":["https://openalex.org/I1303153112","https://openalex.org/I4210138560"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"John A. Lees","raw_affiliation_strings":["European Bioinformatics Institute, European Molecular Biology Laboratory, Wellcome Genome Campus, Hinxton, Cambridge CB10 1SD, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0001-5360-1254","affiliations":[{"raw_affiliation_string":"European Bioinformatics Institute, European Molecular Biology Laboratory, Wellcome Genome Campus, Hinxton, Cambridge CB10 1SD, United Kingdom","institution_ids":["https://openalex.org/I1303153112"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088474720","display_name":"Samuel Horsfield","orcid":"https://orcid.org/0000-0002-3859-4073","observed_orcids":["https://orcid.org/0000-0002-3859-4073"]},"institutions":[{"id":"https://openalex.org/I1303153112","display_name":"European Bioinformatics Institute","ror":"https://ror.org/02catss52","country_code":"GB","type":"facility","lineage":["https://openalex.org/I1303153112","https://openalex.org/I4210138560"]},{"id":"https://openalex.org/I57825437","display_name":"University of Neuch\u00e2tel","ror":"https://ror.org/00vasag41","country_code":"CH","type":"education","lineage":["https://openalex.org/I57825437"]}],"countries":["CH","GB"],"is_corresponding":true,"raw_author_name":"Samuel T. Horsfield","raw_affiliation_strings":["European Bioinformatics Institute, European Molecular Biology Laboratory, Wellcome Genome Campus, Hinxton, Cambridge CB10 1SD, United Kingdom","Institute of Biology, University of Neuch\u00e2tel, Rue Emile-Argand 11, 2000 Neuch\u00e2tel, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-3859-4073","affiliations":[{"raw_affiliation_string":"European Bioinformatics Institute, European Molecular Biology Laboratory, Wellcome Genome Campus, Hinxton, Cambridge CB10 1SD, United Kingdom","institution_ids":["https://openalex.org/I1303153112"]},{"raw_affiliation_string":"Institute of Biology, University of Neuch\u00e2tel, Rue Emile-Argand 11, 2000 Neuch\u00e2tel, Switzerland","institution_ids":["https://openalex.org/I57825437"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5088474720"],"corresponding_institution_ids":["https://openalex.org/I1303153112","https://openalex.org/I57825437"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10654","display_name":"Pneumonia and Respiratory Infections","score":0.86080002784729,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T10654","display_name":"Pneumonia and Respiratory Infections","score":0.86080002784729,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11688","display_name":"Microbial infections and disease research","score":0.04830000177025795,"subfield":{"id":"https://openalex.org/subfields/2404","display_name":"Microbiology"},"field":{"id":"https://openalex.org/fields/24","display_name":"Immunology and Microbiology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12167","display_name":"Bacterial Identification and Susceptibility Testing","score":0.046799998730421066,"subfield":{"id":"https://openalex.org/subfields/2726","display_name":"Microbiology (medical)"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/streptococcus-pneumoniae","display_name":"Streptococcus pneumoniae","score":0.8899999856948853},{"id":"https://openalex.org/keywords/pneumococcal-serotyping","display_name":"pneumococcal serotyping","score":0.9259999990463257},{"id":"https://openalex.org/keywords/deep-learning","display_name":"deep learning","score":0.8989999890327454},{"id":"https://openalex.org/keywords/vaccine-formulation","display_name":"vaccine formulation","score":0.4779999852180481},{"id":"https://openalex.org/keywords/serotype-surveillance","display_name":"serotype surveillance","score":0.5099999904632568}],"concepts":[{"id":"https://openalex.org/C2775905019","wikidata":"https://www.wikidata.org/wiki/Q192572","display_name":"In silico","level":3,"score":0.9056000113487244},{"id":"https://openalex.org/C10389963","wikidata":"https://www.wikidata.org/wiki/Q848328","display_name":"Serotype","level":2,"score":0.7721999883651733},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.6552000045776367},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.5842999815940857},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.5403000116348267},{"id":"https://openalex.org/C2781209916","wikidata":"https://www.wikidata.org/wiki/Q3215756","display_name":"Typing","level":2,"score":0.477400004863739},{"id":"https://openalex.org/C2781253189","wikidata":"https://www.wikidata.org/wiki/Q221179","display_name":"Streptococcus pneumoniae","level":3,"score":0.43220001459121704},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4088999927043915},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.39500001072883606},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.350600004196167},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.34880000352859497},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.32589998841285706},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.32510000467300415},{"id":"https://openalex.org/C2777368272","wikidata":"https://www.wikidata.org/wiki/Q418073","display_name":"Ribotyping","level":4,"score":0.32019999623298645},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.30410000681877136},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2802000045776367},{"id":"https://openalex.org/C24432333","wikidata":"https://www.wikidata.org/wiki/Q2068526","display_name":"Whole genome sequencing","level":4,"score":0.2797999978065491},{"id":"https://openalex.org/C3742359","wikidata":"https://www.wikidata.org/wiki/Q4839988","display_name":"Bacterial genome size","level":4,"score":0.2689000070095062},{"id":"https://openalex.org/C127716648","wikidata":"https://www.wikidata.org/wiki/Q104053","display_name":"Phenotype","level":3,"score":0.26750001311302185},{"id":"https://openalex.org/C2776152631","wikidata":"https://www.wikidata.org/wiki/Q4366062","display_name":"Pneumococcal infections","level":4,"score":0.262800008058548},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.10.14.759107","doi":"https://doi.org/10.64898/2026.10.14.759107","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.14.759107","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/20/2026.10.14.759107.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.10.14.759107","doi":"https://doi.org/10.64898/2026.10.14.759107","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.14.759107","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/20/2026.10.14.759107.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[{"display_name":"Good health and well-being","score":0.504800021648407,"id":"https://metadata.un.org/sdg/3"}],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320313288","display_name":"European Bioinformatics Institute","ror":"https://ror.org/02catss52"},{"id":"https://openalex.org/F4320314023","display_name":"European Molecular Biology Laboratory","ror":"https://ror.org/050589e39"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7223070576.pdf","grobid_xml":"https://content.openalex.org/works/W7223070576.grobid-xml"},"referenced_works_count":54,"referenced_works":["https://openalex.org/W1972145956","https://openalex.org/W1972265710","https://openalex.org/W1978450953","https://openalex.org/W2006617902","https://openalex.org/W2009637031","https://openalex.org/W2012457803","https://openalex.org/W2092495308","https://openalex.org/W2120358246","https://openalex.org/W2150562212","https://openalex.org/W2168869993","https://openalex.org/W2325123292","https://openalex.org/W2520501427","https://openalex.org/W2560057613","https://openalex.org/W2661902553","https://openalex.org/W2789843538","https://openalex.org/W2794519236","https://openalex.org/W2908510526","https://openalex.org/W2937635380","https://openalex.org/W2949236085","https://openalex.org/W2950614621","https://openalex.org/W2952568525","https://openalex.org/W2970971581","https://openalex.org/W2980282514","https://openalex.org/W3154953303","https://openalex.org/W3204779498","https://openalex.org/W4223977507","https://openalex.org/W4229441400","https://openalex.org/W4284878969","https://openalex.org/W4285024882","https://openalex.org/W4309503005","https://openalex.org/W4311472910","https://openalex.org/W4379509055","https://openalex.org/W4384156512","https://openalex.org/W4389083107","https://openalex.org/W4391230996","https://openalex.org/W4392740526","https://openalex.org/W4401560064","https://openalex.org/W4401572802","https://openalex.org/W4403415561","https://openalex.org/W4404821554","https://openalex.org/W4405098348","https://openalex.org/W4406928359","https://openalex.org/W4407658461","https://openalex.org/W4408128153","https://openalex.org/W4408339719","https://openalex.org/W4410759023","https://openalex.org/W4411747924","https://openalex.org/W4412151293","https://openalex.org/W4412507858","https://openalex.org/W4414473773","https://openalex.org/W7135034101","https://openalex.org/W7160087429","https://openalex.org/W7170171567","https://openalex.org/W7221762972"],"related_works":["https://openalex.org/W4415300930","https://openalex.org/W2520501427","https://openalex.org/W4379509055","https://openalex.org/W4311165581","https://openalex.org/W4388862175","https://openalex.org/W2952568525","https://openalex.org/W2342395277","https://openalex.org/W2897172993","https://openalex.org/W2613031891","https://openalex.org/W2956151841"],"abstract_inverted_index":{"Abstract":[0],"The":[1],"vast":[2],"number":[3],"of":[4,13,28,58,65,72,78,122,194],"publicly-available":[5],"Streptococcus":[6],"pneumoniae":[7,149],"genomes":[8,150,203,237],"now":[9],"exceeds":[10],"the":[11,26,29,210,217,254,265],"capabilities":[12],"phenotypic":[14,120,152,188],"serotyping":[15,143,153,164,200,212,259],"methods":[16,82,269],"to":[17,61,75,95,115,126,173,185],"analyse":[18],"each":[19,108],"sample.":[20],"In":[21],"silico":[22,88,142,163,258],"methods,":[23],"based":[24,112],"on":[25,56,113,146],"classification":[27],"cps":[30,66,102,124,192],"(capsular":[31],"polysaccharide)":[32],"operon":[33],"sequence,":[34],"provide":[35],"a":[36,62,70,136],"scalable":[37],"and":[38,47,138,190],"automated":[39],"means":[40],"for":[41,90,267],"serotyping,":[42],"supporting":[43],"global":[44],"surveillance":[45],"efforts":[46],"informing":[48],"vaccine":[49],"formulation":[50],"updates.":[51],"Existing":[52],"tools":[53,165],"fundamentally":[54],"rely":[55],"comparison":[57],"query":[59],"sequences":[60],"reference":[63],"database":[64],"sequences,":[67],"often":[68],"with":[69,151,224,238],"set":[71],"rigidly-defined":[73],"rules":[74],"enable":[76],"distinction":[77],"closely-related":[79],"serotypes.":[80,99],"These":[81],"can":[83],"accurately":[84,174],"carry":[85],"out":[86],"in":[87,141,162,166,206,257,261,270],"typing":[89],"known":[91,116,225],"serotypes,":[92,117,246],"but":[93],"fail":[94],"identify":[96,127],"previously":[97],"unrecognised":[98],"Furthermore,":[100],"novel":[101,123,176,240],"variants":[103,125,193],"cannot":[104],"be":[105],"distinguished":[106],"from":[107,204],"other":[109,271],"or":[110],"compared":[111],"similarity":[114],"meaning":[118],"targeted":[119,187],"investigation":[121,189],"new":[128,245],"serotypes":[129,184],"is":[130,156,170,197,253],"not":[131],"possible.":[132],"We":[133],"introduce":[134],"ALLCAPS,":[135],"database-":[137],"rule-free":[139],"deep-learning":[140,256],"tool.":[144],"Trained":[145],"34,125":[147],"S.":[148],"data,":[154],"ALLCAPS":[155,169,196,220,234,252],"highly":[157,198],"accurate,":[158],"outperforming":[159],"many":[160],"state-of-the-art":[161],"serotype":[167,226],"prediction.":[168],"also":[171],"able":[172],"predict":[175],"non-typeable":[177,241],"isolates,":[178],"while":[179],"reporting":[180],"their":[181],"closest":[182],"related":[183],"guide":[186],"verify":[191],"interest.":[195],"scalable,":[199],"119,424":[201],"pneumococcal":[202],"AllTheBacteria":[205,218],"4.7":[207],"hours,":[208],"representing":[209,244],"largest":[211],"effort":[213],"ever":[214],"undertaken.":[215],"Within":[216],"genomes,":[219],"predictions":[221],"were":[222],"consistent":[223],"epidemiology":[227],"across":[228],"Global":[229],"Pneumococcal":[230],"Sequence":[231],"Clusters":[232],"(GPSCs).":[233],"additionally":[235],"flagged":[236],"putative":[239],"operons,":[242],"potentially":[243],"which":[247],"require":[248],"further":[249],"empirical":[250],"validation.":[251],"first":[255],"approach":[260],"any":[262],"bacteria,":[263],"paving":[264],"way":[266],"similar":[268],"encapsulated":[272],"species.":[273]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-10-21T00:00:00"}
