{"id":"https://openalex.org/W4414154132","doi":"https://doi.org/10.1371/journal.pcbi.1013470","title":"kMermaid: Ultrafast metagenomic read assignment to protein clusters by hashing of amino acid k-mer frequencies","display_name":"kMermaid: Ultrafast metagenomic read assignment to protein clusters by hashing of amino acid k-mer frequencies","publication_year":2025,"publication_date":"2025-09-11","ids":{"openalex":"https://openalex.org/W4414154132","doi":"https://doi.org/10.1371/journal.pcbi.1013470","pmid":"https://pubmed.ncbi.nlm.nih.gov/40934284"},"language":"en","primary_location":{"id":"doi:10.1371/journal.pcbi.1013470","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1013470","pdf_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1013470&type=printable","source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS Computational Biology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1013470&type=printable","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033717249","display_name":"Anastasia Lucas","orcid":null},"institutions":[{"id":"https://openalex.org/I102322052","display_name":"The Wistar Institute","ror":"https://ror.org/04wncat98","country_code":"US","type":"facility","lineage":["https://openalex.org/I102322052"]},{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anastasia Lucas","raw_affiliation_strings":["Genomics and Computational Biology Graduate Group, University of Pennsylvania - Perelman School of Medicine, Philadelphia, Pennsylvania, United States of America","Molecular and Cellular Oncogenesis Program, Ellen and Ronald Caplan Cancer Center, The Wistar Institute, Philadelphia, Pennsylvania, United States of America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Genomics and Computational Biology Graduate Group, University of Pennsylvania - Perelman School of Medicine, Philadelphia, Pennsylvania, United States of America","institution_ids":["https://openalex.org/I79576946"]},{"raw_affiliation_string":"Molecular and Cellular Oncogenesis Program, Ellen and Ronald Caplan Cancer Center, The Wistar Institute, Philadelphia, Pennsylvania, United States of America","institution_ids":["https://openalex.org/I102322052"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002407952","display_name":"Daniel E. Sch\u00e4ffer","orcid":"https://orcid.org/0000-0003-3608-152X"},"institutions":[{"id":"https://openalex.org/I102322052","display_name":"The Wistar Institute","ror":"https://ror.org/04wncat98","country_code":"US","type":"facility","lineage":["https://openalex.org/I102322052"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel E. Sch\u00e4ffer","raw_affiliation_strings":["Computer Science and Artificial Intelligence Laboratory & Computational and Systems Biology Program, Massachusetts Institute of Technology, Cambridge, Massachusetts, United States of America","Molecular and Cellular Oncogenesis Program, Ellen and Ronald Caplan Cancer Center, The Wistar Institute, Philadelphia, Pennsylvania, United States of America"],"raw_orcid":"https://orcid.org/0000-0003-3608-152X","affiliations":[{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory & Computational and Systems Biology Program, Massachusetts Institute of Technology, Cambridge, Massachusetts, United States of America","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"Molecular and Cellular Oncogenesis Program, Ellen and Ronald Caplan Cancer Center, The Wistar Institute, Philadelphia, Pennsylvania, United States of America","institution_ids":["https://openalex.org/I102322052"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108833494","display_name":"Jayamanna Wickramasinghe","orcid":null},"institutions":[{"id":"https://openalex.org/I102322052","display_name":"The Wistar Institute","ror":"https://ror.org/04wncat98","country_code":"US","type":"facility","lineage":["https://openalex.org/I102322052"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jayamanna Wickramasinghe","raw_affiliation_strings":["Bioinformatics Facility, The Wistar Institute, Philadelphia, Pennsylvania, United States of America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bioinformatics Facility, The Wistar Institute, Philadelphia, Pennsylvania, United States of America","institution_ids":["https://openalex.org/I102322052"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020874644","display_name":"Noam Auslander","orcid":"https://orcid.org/0000-0002-2037-1517"},"institutions":[{"id":"https://openalex.org/I102322052","display_name":"The Wistar Institute","ror":"https://ror.org/04wncat98","country_code":"US","type":"facility","lineage":["https://openalex.org/I102322052"]},{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Noam Auslander","raw_affiliation_strings":["Department of Cancer Biology, University of Pennsylvania, Philadelphia, Pennsylvania, United States of America","Molecular and Cellular Oncogenesis Program, Ellen and Ronald Caplan Cancer Center, The Wistar Institute, Philadelphia, Pennsylvania, United States of America"],"raw_orcid":"https://orcid.org/0000-0002-2037-1517","affiliations":[{"raw_affiliation_string":"Department of Cancer Biology, University of Pennsylvania, Philadelphia, Pennsylvania, United States of America","institution_ids":["https://openalex.org/I79576946"]},{"raw_affiliation_string":"Molecular and Cellular Oncogenesis Program, Ellen and Ronald Caplan Cancer Center, The Wistar Institute, Philadelphia, Pennsylvania, United States of America","institution_ids":["https://openalex.org/I102322052"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5020874644"],"corresponding_institution_ids":["https://openalex.org/I102322052","https://openalex.org/I79576946"],"apc_list":{"value":2655,"currency":"USD","value_usd":2655},"apc_paid":{"value":2655,"currency":"USD","value_usd":2655},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14481979,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"21","issue":"9","first_page":"e1013470","last_page":"e1013470"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9987999796867371,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9987999796867371,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9983999729156494,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.9944999814033508,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/metagenomics","display_name":"Metagenomics","score":0.8722000122070312},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.5339999794960022},{"id":"https://openalex.org/keywords/shotgun","display_name":"Shotgun","score":0.45179998874664307},{"id":"https://openalex.org/keywords/protein-sequencing","display_name":"Protein sequencing","score":0.3637999892234802},{"id":"https://openalex.org/keywords/amino-acid","display_name":"Amino acid","score":0.3465000092983246},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.34290000796318054},{"id":"https://openalex.org/keywords/proteomics","display_name":"Proteomics","score":0.3246999979019165},{"id":"https://openalex.org/keywords/amino-acid-residue","display_name":"Amino acid residue","score":0.3068000078201294}],"concepts":[{"id":"https://openalex.org/C15151743","wikidata":"https://www.wikidata.org/wiki/Q903778","display_name":"Metagenomics","level":3,"score":0.8722000122070312},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.6539000272750854},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.5339999794960022},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5041000247001648},{"id":"https://openalex.org/C2781434637","wikidata":"https://www.wikidata.org/wiki/Q486396","display_name":"Shotgun","level":3,"score":0.45179998874664307},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.38989999890327454},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.3637999892234802},{"id":"https://openalex.org/C515207424","wikidata":"https://www.wikidata.org/wiki/Q8066","display_name":"Amino acid","level":2,"score":0.3465000092983246},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.34290000796318054},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3391000032424927},{"id":"https://openalex.org/C46111723","wikidata":"https://www.wikidata.org/wiki/Q471857","display_name":"Proteomics","level":3,"score":0.3246999979019165},{"id":"https://openalex.org/C2994376932","wikidata":"https://www.wikidata.org/wiki/Q735188","display_name":"Amino acid residue","level":4,"score":0.3068000078201294},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3050999939441681},{"id":"https://openalex.org/C64869954","wikidata":"https://www.wikidata.org/wiki/Q1859747","display_name":"False positive paradox","level":2,"score":0.2985999882221222},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2913999855518341},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.2872999906539917},{"id":"https://openalex.org/C101985253","wikidata":"https://www.wikidata.org/wiki/Q1073526","display_name":"Shotgun sequencing","level":4,"score":0.28700000047683716},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.2799000144004822},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.27799999713897705},{"id":"https://openalex.org/C68289359","wikidata":"https://www.wikidata.org/wiki/Q7502514","display_name":"Shotgun proteomics","level":4,"score":0.26350000500679016},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.2574999928474426},{"id":"https://openalex.org/C147816474","wikidata":"https://www.wikidata.org/wiki/Q169525","display_name":"Protein engineering","level":3,"score":0.2547999918460846}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000596","descriptor_name":"Amino Acids","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D000596","descriptor_name":"Amino Acids","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D000596","descriptor_name":"Amino Acids","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D000596","descriptor_name":"Amino Acids","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D000596","descriptor_name":"Amino Acids","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D000596","descriptor_name":"Amino Acids","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D000596","descriptor_name":"Amino Acids","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D000596","descriptor_name":"Amino Acids","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D001426","descriptor_name":"Bacterial Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D001426","descriptor_name":"Bacterial Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D001426","descriptor_name":"Bacterial Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D001426","descriptor_name":"Bacterial Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D001426","descriptor_name":"Bacterial Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D001426","descriptor_name":"Bacterial Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D001426","descriptor_name":"Bacterial Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D001426","descriptor_name":"Bacterial Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D005243","descriptor_name":"Feces","qualifier_ui":"Q000382","qualifier_name":"microbiology","is_major_topic":false},{"descriptor_ui":"D005243","descriptor_name":"Feces","qualifier_ui":"Q000382","qualifier_name":"microbiology","is_major_topic":false},{"descriptor_ui":"D005243","descriptor_name":"Feces","qualifier_ui":"Q000382","qualifier_name":"microbiology","is_major_topic":false},{"descriptor_ui":"D005243","descriptor_name":"Feces","qualifier_ui":"Q000382","qualifier_name":"microbiology","is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D054892","descriptor_name":"Metagenome","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D054892","descriptor_name":"Metagenome","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D054892","descriptor_name":"Metagenome","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D054892","descriptor_name":"Metagenome","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D056186","descriptor_name":"Metagenomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D056186","descriptor_name":"Metagenomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D056186","descriptor_name":"Metagenomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D056186","descriptor_name":"Metagenomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":5,"locations":[{"id":"doi:10.1371/journal.pcbi.1013470","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1013470","pdf_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1013470&type=printable","source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS Computational Biology","raw_type":"journal-article"},{"id":"pmid:40934284","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40934284","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":"PLoS computational biology","raw_type":null},{"id":"pmh:oai:doaj.org/article:bcd2b6b347d54c6d8c98b6bb23746aa3","is_oa":true,"landing_page_url":"https://doaj.org/article/bcd2b6b347d54c6d8c98b6bb23746aa3","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,"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":"PLoS Computational Biology, Vol 21, Iss 9, p e1013470 (2025)","raw_type":"article"},{"id":"pmh:oai:europepmc.org:11315119","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12507277","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,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:12507277","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12507277/","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,"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":"PLoS Comput Biol","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1371/journal.pcbi.1013470","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1013470","pdf_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1013470&type=printable","source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS Computational Biology","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2423696333","display_name":null,"funder_award_id":"R01 LM014503","funder_id":"https://openalex.org/F4320337372","funder_display_name":"U.S. National Library of Medicine"},{"id":"https://openalex.org/G6203743530","display_name":null,"funder_award_id":"V2024-006","funder_id":"https://openalex.org/F4320306536","funder_display_name":"V Foundation for Cancer Research"}],"funders":[{"id":"https://openalex.org/F4320306536","display_name":"V Foundation for Cancer Research","ror":"https://ror.org/00kbbk236"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337372","display_name":"U.S. National Library of Medicine","ror":"https://ror.org/0060t0j89"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414154132.pdf","grobid_xml":"https://content.openalex.org/works/W4414154132.grobid-xml"},"referenced_works_count":49,"referenced_works":["https://openalex.org/W2003347102","https://openalex.org/W2017608260","https://openalex.org/W2019355614","https://openalex.org/W2045204781","https://openalex.org/W2055043387","https://openalex.org/W2103901746","https://openalex.org/W2114216755","https://openalex.org/W2116412478","https://openalex.org/W2120172561","https://openalex.org/W2130479394","https://openalex.org/W2132801908","https://openalex.org/W2133856765","https://openalex.org/W2156125289","https://openalex.org/W2158714788","https://openalex.org/W2159954944","https://openalex.org/W2170747616","https://openalex.org/W2178043251","https://openalex.org/W2311001730","https://openalex.org/W2337747100","https://openalex.org/W2473355215","https://openalex.org/W2509730012","https://openalex.org/W2557595285","https://openalex.org/W2791355502","https://openalex.org/W2799828084","https://openalex.org/W2907815526","https://openalex.org/W2921789835","https://openalex.org/W2940391028","https://openalex.org/W2950954328","https://openalex.org/W2950964375","https://openalex.org/W2951160681","https://openalex.org/W2963629592","https://openalex.org/W2972411752","https://openalex.org/W2977723904","https://openalex.org/W2979785336","https://openalex.org/W2990618091","https://openalex.org/W3092732807","https://openalex.org/W3128761933","https://openalex.org/W3143063265","https://openalex.org/W3159504416","https://openalex.org/W3203343200","https://openalex.org/W3215433280","https://openalex.org/W4211037082","https://openalex.org/W4220990048","https://openalex.org/W4309306270","https://openalex.org/W4313261720","https://openalex.org/W4320040175","https://openalex.org/W4377565430","https://openalex.org/W4398177119","https://openalex.org/W4402253358"],"related_works":["https://openalex.org/W2210738511","https://openalex.org/W2487541429","https://openalex.org/W1910109602","https://openalex.org/W2080583581","https://openalex.org/W4297131566","https://openalex.org/W2017364432","https://openalex.org/W2329606903","https://openalex.org/W3195915274","https://openalex.org/W4285082713","https://openalex.org/W2344981695"],"abstract_inverted_index":{"Shotgun":[0],"metagenomic":[1,17,150],"sequencing":[2],"can":[3,65,162],"determine":[4],"both":[5],"the":[6,50,101,130],"taxonomic":[7],"and":[8,30,77,120,148,161],"functional":[9,14,81],"content":[10],"of":[11,52,61,103,132],"microbiomes.":[12],"However,":[13],"classification":[15],"for":[16,49,69,96,134,144],"reads":[18,36,57,136],"remains":[19],"highly":[20,111,145],"challenging":[21],"as":[22,74,93,126,128],"protein":[23,97,106,154],"mapping":[24,54,107],"tools":[25,108],"require":[26],"substantial":[27],"computational":[28],"resources":[29],"yield":[31],"ambiguous":[32],"classifications":[33],"when":[34],"short":[35,56],"map":[37,87],"to":[38,58],"homologous":[39,62],"proteins":[40],"originating":[41,137],"from":[42,122,138],"different":[43],"bacteria.":[44],"Here":[45],"we":[46],"introduce":[47],"kMermaid":[48,99,116,133,142],"purpose":[51],"uniquely":[53],"bacterial":[55],"taxa-agnostic":[59],"clusters":[60],"proteins,":[63],"which":[64],"then":[66],"be":[67,164],"used":[68],"downstream":[70],"analysis":[71],"tasks":[72],"such":[73],"read":[75,151],"quantification":[76],"pathway":[78],"or":[79],"global":[80],"analysis.":[82],"Using":[83],"a":[84,94,157,167],"nested":[85],"hash":[86],"containing":[88],"amino":[89],"acid":[90],"k-mer":[91],"profiles":[92],"model":[95],"assignment,":[98],"achieves":[100],"sensitivity":[102],"popular":[104],"existing":[105],"while":[109],"remaining":[110],"resource":[112],"efficient.":[113],"We":[114],"evaluate":[115],"on":[117,166],"simulated":[118],"data":[119,121],"human":[123],"fecal":[124],"samples":[125],"well":[127],"demonstrate":[129],"utility":[131],"classifying":[135],"new,":[139],"unseen":[140],"proteins.":[141],"allows":[143],"accurate,":[146],"unambiguous":[147],"ultrafast":[149],"assignment":[152],"into":[153],"clusters,":[155],"with":[156],"fixed":[158],"memory":[159],"usage,":[160],"easily":[163],"employed":[165],"typical":[168],"computer.":[169]},"counts_by_year":[],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2025-10-10T00:00:00"}