{"id":"https://openalex.org/W4402253358","doi":"https://doi.org/10.1093/bioinformatics/btae397","title":"Metagenomic functional profiling: to sketch or not to sketch?","display_name":"Metagenomic functional profiling: to sketch or not to sketch?","publication_year":2024,"publication_date":"2024-09-01","ids":{"openalex":"https://openalex.org/W4402253358","doi":"https://doi.org/10.1093/bioinformatics/btae397","pmid":"https://pubmed.ncbi.nlm.nih.gov/39230701"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btae397","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btae397","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1093/bioinformatics/btae397","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050472000","display_name":"Mahmudur Rahman Hera","orcid":"https://orcid.org/0000-0002-5992-9012"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mahmudur Rahman Hera","raw_affiliation_strings":["School of Electrical Engineering and Computer Science, Pennsylvania State University , University Park , Pennsylvania 16802,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Computer Science, Pennsylvania State University , University Park , Pennsylvania 16802,","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101724582","display_name":"Shaopeng Liu","orcid":"https://orcid.org/0000-0003-0539-083X"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shaopeng Liu","raw_affiliation_strings":["Bioinformatics and Genomics, Huck Institutes of the Life Sciences, Pennsylvania State University , University Park , Pennsylvania 16802,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bioinformatics and Genomics, Huck Institutes of the Life Sciences, Pennsylvania State University , University Park , Pennsylvania 16802,","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100323674","display_name":"Wei Wei","orcid":"https://orcid.org/0000-0002-0733-5060"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Wei","raw_affiliation_strings":["Bioinformatics and Genomics, Huck Institutes of the Life Sciences, Pennsylvania State University , University Park , Pennsylvania 16802,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bioinformatics and Genomics, Huck Institutes of the Life Sciences, Pennsylvania State University , University Park , Pennsylvania 16802,","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017057419","display_name":"Judith Rodr\u00edguez","orcid":"https://orcid.org/0000-0002-5109-3054"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Judith S Rodriguez","raw_affiliation_strings":["Bioinformatics and Genomics, Huck Institutes of the Life Sciences, Pennsylvania State University , University Park , Pennsylvania 16802,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bioinformatics and Genomics, Huck Institutes of the Life Sciences, Pennsylvania State University , University Park , Pennsylvania 16802,","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004607409","display_name":"Chunyu Ma","orcid":"https://orcid.org/0000-0001-9731-5153"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chunyu Ma","raw_affiliation_strings":["Bioinformatics and Genomics, Huck Institutes of the Life Sciences, Pennsylvania State University , University Park , Pennsylvania 16802,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bioinformatics and Genomics, Huck Institutes of the Life Sciences, Pennsylvania State University , University Park , Pennsylvania 16802,","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002668669","display_name":"David Koslicki","orcid":"https://orcid.org/0000-0002-0640-954X"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Koslicki","raw_affiliation_strings":["Bioinformatics and Genomics, Huck Institutes of the Life Sciences, Pennsylvania State University , University Park , Pennsylvania 16802,","Department of Biology, Pennsylvania State University , University Park , Pennsylvania 16802,","School of Electrical Engineering and Computer Science, Pennsylvania State University , University Park , Pennsylvania 16802,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bioinformatics and Genomics, Huck Institutes of the Life Sciences, Pennsylvania State University , University Park , Pennsylvania 16802,","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"Department of Biology, Pennsylvania State University , University Park , Pennsylvania 16802,","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"School of Electrical Engineering and Computer Science, Pennsylvania State University , University Park , Pennsylvania 16802,","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":2.3875,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.89177913,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"40","issue":"Supplement_2","first_page":"ii165","last_page":"ii173"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10066","display_name":"Gut microbiota and health","score":0.3303999900817871,"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/T10066","display_name":"Gut microbiota and health","score":0.3303999900817871,"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/T11791","display_name":"Microbial Community Ecology and Physiology","score":0.24210000038146973,"subfield":{"id":"https://openalex.org/subfields/2303","display_name":"Ecology"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.2134000062942505,"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/sketch","display_name":"Sketch","score":0.9512432813644409},{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.8169245719909668},{"id":"https://openalex.org/keywords/metagenomics","display_name":"Metagenomics","score":0.711645245552063},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6663006544113159},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.35358884930610657},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.15113139152526855},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.14390632510185242},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1365363895893097},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.06302022933959961}],"concepts":[{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.9512432813644409},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.8169245719909668},{"id":"https://openalex.org/C15151743","wikidata":"https://www.wikidata.org/wiki/Q903778","display_name":"Metagenomics","level":3,"score":0.711645245552063},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6663006544113159},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.35358884930610657},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.15113139152526855},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.14390632510185242},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1365363895893097},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.06302022933959961},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"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":"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":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D054892","descriptor_name":"Metagenome","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D054892","descriptor_name":"Metagenome","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D054892","descriptor_name":"Metagenome","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D054892","descriptor_name":"Metagenome","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D054892","descriptor_name":"Metagenome","qualifier_ui":"Q000235","qualifier_name":"genetics","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},{"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":"D064307","descriptor_name":"Microbiota","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D064307","descriptor_name":"Microbiota","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D064307","descriptor_name":"Microbiota","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D064307","descriptor_name":"Microbiota","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D064307","descriptor_name":"Microbiota","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btae397","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btae397","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:39230701","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39230701","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":"Bioinformatics (Oxford, England)","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:11373326","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11373326","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11373326/pdf/btae397.pdf","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":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btae397","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btae397","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G347575844","display_name":null,"funder_award_id":"R01 GM146462","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"},{"id":"https://openalex.org/G4423814381","display_name":null,"funder_award_id":"R01GM146462","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":70,"referenced_works":["https://openalex.org/W1979966476","https://openalex.org/W1983922226","https://openalex.org/W1985224052","https://openalex.org/W2010562878","https://openalex.org/W2014102314","https://openalex.org/W2041117131","https://openalex.org/W2041386815","https://openalex.org/W2045204781","https://openalex.org/W2045534443","https://openalex.org/W2048673910","https://openalex.org/W2069458148","https://openalex.org/W2126045294","https://openalex.org/W2129930407","https://openalex.org/W2130998671","https://openalex.org/W2131186249","https://openalex.org/W2133856765","https://openalex.org/W2136632285","https://openalex.org/W2145100181","https://openalex.org/W2146071936","https://openalex.org/W2146771637","https://openalex.org/W2152869198","https://openalex.org/W2156701707","https://openalex.org/W2159482845","https://openalex.org/W2165627817","https://openalex.org/W2178043251","https://openalex.org/W2281531600","https://openalex.org/W2409427249","https://openalex.org/W2519890620","https://openalex.org/W2531227267","https://openalex.org/W2559588208","https://openalex.org/W2735061408","https://openalex.org/W2755653983","https://openalex.org/W2767589056","https://openalex.org/W2773939681","https://openalex.org/W2887228696","https://openalex.org/W2897611961","https://openalex.org/W2899600207","https://openalex.org/W2912990896","https://openalex.org/W2949841808","https://openalex.org/W2950150251","https://openalex.org/W2950287694","https://openalex.org/W2950954328","https://openalex.org/W2951254987","https://openalex.org/W2952204926","https://openalex.org/W2955167895","https://openalex.org/W2955323986","https://openalex.org/W2967441839","https://openalex.org/W2979981906","https://openalex.org/W2987650093","https://openalex.org/W2991239467","https://openalex.org/W3009533854","https://openalex.org/W3081286367","https://openalex.org/W3093627059","https://openalex.org/W3143063265","https://openalex.org/W3195542925","https://openalex.org/W3208827236","https://openalex.org/W4211124654","https://openalex.org/W4221104280","https://openalex.org/W4225258284","https://openalex.org/W4226052879","https://openalex.org/W4286715803","https://openalex.org/W4294216483","https://openalex.org/W4317660914","https://openalex.org/W4362524037","https://openalex.org/W4380608045","https://openalex.org/W4381489623","https://openalex.org/W4386256981","https://openalex.org/W4386282944","https://openalex.org/W6743220242","https://openalex.org/W6854068008"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2378994405","https://openalex.org/W2385974820","https://openalex.org/W2373478030","https://openalex.org/W2378679551","https://openalex.org/W3149739944","https://openalex.org/W2392363776","https://openalex.org/W2063051341","https://openalex.org/W2591066345"],"abstract_inverted_index":{"MOTIVATION:":[0],"Functional":[1],"profiling":[2],"of":[3,13,26,90,98,219],"metagenomic":[4,118,154,205],"samples":[5],"is":[6,47,161,208],"essential":[7],"to":[8,61,86,114,142,152,170],"decipher":[9],"the":[10,24,99,103,128,143,176,193,220],"functional":[11,21,88,129,206],"capabilities":[12],"microbial":[14],"communities.":[15],"Traditional":[16],"and":[17,44,138,167,203,211],"more":[18],"widely":[19],"used":[20,58],"profilers":[22],"in":[23,59,66,77,111,164,224],"context":[25],"metagenomics":[27,60],"rely":[28],"on":[29,230],"aligning":[30,38],"reads":[31,40],"against":[32,41],"a":[33,42,79,83,112,117],"known":[34],"reference":[35],"database.":[36],"However,":[37],"sequencing":[39],"large":[43],"fast-growing":[45],"database":[46],"computationally":[48],"expensive.":[49],"In":[50,69],"general,":[51],"k-mer-based":[52],"sketching":[53],"techniques":[54],"have":[55],"been":[56],"successfully":[57],"address":[62],"this":[63,70,133,179,225],"bottleneck,":[64],"notably":[65],"taxonomic":[67],"profiling.":[68],"work,":[71],"we":[72,222],"describe":[73],"leveraging":[74],"FracMinHash":[75,105],"(implemented":[76],"sourmash,":[78],"publicly":[80],"available":[81,210],"software),":[82],"k-mer-sketching":[84],"algorithm,":[85],"obtain":[87],"profiles":[89,130,144],"metagenome":[91],"samples.":[92],"RESULTS:":[93],"We":[94,120,125,156],"show":[95],"how":[96],"pieces":[97],"sourmash":[100],"software":[101],"(and":[102],"resulting":[104],"sketches)":[106],"can":[107,212,227],"be":[108,213,228],"put":[109],"together":[110],"pipeline":[113,123,134],"functionally":[115],"profile":[116],"sample.":[119],"named":[121],"our":[122],"fmh-funprofiler.":[124],"report":[126,158],"that":[127,159],"obtained":[131,145],"using":[132,146],"demonstrate":[135],"comparable":[136],"completeness":[137],"better":[139],"purity":[140],"compared":[141],"other":[147],"alignment-based":[148],"methods":[149],"when":[150],"applied":[151],"simulated":[153],"data.":[155],"also":[157,188],"fmh-funprofiler":[160],"39-99\u00d7":[162],"faster":[163],"wall-clock":[165],"time,":[166],"consumes":[168],"up":[169],"40-55\u00d7":[171],"less":[172],"memory.":[173],"Coupled":[174],"with":[175],"KEGG":[177],"database,":[178],"method":[180],"not":[181],"only":[182],"replicates":[183],"fundamental":[184],"biological":[185],"insights":[186],"but":[187],"highlights":[189],"novel":[190],"signals":[191],"from":[192],"Human":[194],"Microbiome":[195],"Project":[196],"datasets.":[197],"AVAILABILITY":[198],"AND":[199],"IMPLEMENTATION:":[200],"This":[201],"fast":[202],"lightweight":[204],"profiler":[207],"freely":[209],"accessed":[214],"here:":[215],"https://github.com/KoslickiLab/fmh-funprofiler.":[216],"All":[217],"scripts":[218],"analyses":[221],"present":[223],"manuscript":[226],"found":[229],"GitHub.":[231]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":8}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}
