{"id":"https://openalex.org/W3197666941","doi":"https://doi.org/10.1093/bioinformatics/btab645","title":"Learning sparse log-ratios for high-throughput sequencing data","display_name":"Learning sparse log-ratios for high-throughput sequencing data","publication_year":2021,"publication_date":"2021-09-08","ids":{"openalex":"https://openalex.org/W3197666941","doi":"https://doi.org/10.1093/bioinformatics/btab645","mag":"3197666941","pmid":"https://pubmed.ncbi.nlm.nih.gov/34498030"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btab645","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btab645","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/38/1/157/41891032/btab645.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"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":"hybrid","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/38/1/157/41891032/btab645.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065923620","display_name":"Elliott Gordon-Rodr\u00edguez","orcid":"https://orcid.org/0000-0002-2720-1756"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Elliott Gordon-Rodriguez","raw_affiliation_strings":["Department of Statistics, Columbia University , New York, NY 10025, USA"],"raw_orcid":"https://orcid.org/0000-0002-2720-1756","affiliations":[{"raw_affiliation_string":"Department of Statistics, Columbia University , New York, NY 10025, USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100780236","display_name":"Thomas P. Quinn","orcid":"https://orcid.org/0000-0003-0286-6329"},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Thomas P Quinn","raw_affiliation_strings":["Applied Artificial Intelligence Institute, Deakin University , Geelong, VIC 3126, Australia"],"raw_orcid":"https://orcid.org/0000-0003-0286-6329","affiliations":[{"raw_affiliation_string":"Applied Artificial Intelligence Institute, Deakin University , Geelong, VIC 3126, Australia","institution_ids":["https://openalex.org/I149704539"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030697996","display_name":"John P. Cunningham","orcid":"https://orcid.org/0000-0001-9125-3027"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John P Cunningham","raw_affiliation_strings":["Department of Statistics, Columbia University , New York, NY 10025, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics, Columbia University , New York, NY 10025, USA","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5065923620"],"corresponding_institution_ids":["https://openalex.org/I78577930"],"apc_list":{"value":3478,"currency":"USD","value_usd":3478},"apc_paid":{"value":3478,"currency":"USD","value_usd":3478},"fwci":2.4616,"has_fulltext":true,"cited_by_count":37,"citation_normalized_percentile":{"value":0.90538492,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"38","issue":"1","first_page":"157","last_page":"163"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.16110000014305115,"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":0.16110000014305115,"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/T13664","display_name":"Genome Rearrangement Algorithms","score":0.156700000166893,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/T12157","display_name":"Geochemistry and Geologic Mapping","score":0.09629999846220016,"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/throughput","display_name":"Throughput","score":0.7428932189941406},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6208263635635376},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4514148235321045},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.16730675101280212}],"concepts":[{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.7428932189941406},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6208263635635376},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4514148235321045},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.16730675101280212},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0}],"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":"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":"D056186","descriptor_name":"Metagenomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D056186","descriptor_name":"Metagenomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D056186","descriptor_name":"Metagenomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D056186","descriptor_name":"Metagenomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D064307","descriptor_name":"Microbiota","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D064307","descriptor_name":"Microbiota","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D064307","descriptor_name":"Microbiota","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D064307","descriptor_name":"Microbiota","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btab645","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btab645","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/38/1/157/41891032/btab645.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"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:34498030","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34498030","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":"Journal Article"},{"id":"pmh:oai:pubmedcentral.nih.gov:8696089","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8696089","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":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btab645","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btab645","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/38/1/157/41891032/btab645.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"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/G3007344424","display_name":null,"funder_award_id":"DBI-1707398","funder_id":"https://openalex.org/F4320337398","funder_display_name":"Division of Biological Infrastructure"},{"id":"https://openalex.org/G4253858762","display_name":"NeuroNex Theory Team: Columbia University Theoretical Neuroscience Center","funder_award_id":"1707398","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4969685445","display_name":null,"funder_award_id":"DBI-1707398","funder_id":"https://openalex.org/F4320320033","funder_display_name":"Gatsby Charitable Foundation"},{"id":"https://openalex.org/G5805940406","display_name":null,"funder_award_id":"1707398","funder_id":"https://openalex.org/F4320320033","funder_display_name":"Gatsby Charitable Foundation"},{"id":"https://openalex.org/G6659127819","display_name":null,"funder_award_id":"542963","funder_id":"https://openalex.org/F4320306164","funder_display_name":"Simons Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306151","display_name":"Alfred P. Sloan Foundation","ror":"https://ror.org/052csg198"},{"id":"https://openalex.org/F4320306164","display_name":"Simons Foundation","ror":"https://ror.org/01cmst727"},{"id":"https://openalex.org/F4320308324","display_name":"McKnight Foundation","ror":"https://ror.org/003ghvj67"},{"id":"https://openalex.org/F4320320033","display_name":"Gatsby Charitable Foundation","ror":"https://ror.org/0290hax27"},{"id":"https://openalex.org/F4320337398","display_name":"Division of Biological Infrastructure","ror":"https://ror.org/04qn9mx93"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3197666941.pdf","grobid_xml":"https://content.openalex.org/works/W3197666941.grobid-xml"},"referenced_works_count":51,"referenced_works":["https://openalex.org/W571770348","https://openalex.org/W1988177479","https://openalex.org/W1991669423","https://openalex.org/W2005825070","https://openalex.org/W2078112764","https://openalex.org/W2078917209","https://openalex.org/W2112408821","https://openalex.org/W2113758107","https://openalex.org/W2153796345","https://openalex.org/W2156975150","https://openalex.org/W2157820287","https://openalex.org/W2163903604","https://openalex.org/W2165909549","https://openalex.org/W2167662727","https://openalex.org/W2294395959","https://openalex.org/W2326641739","https://openalex.org/W2340700016","https://openalex.org/W2493343568","https://openalex.org/W2510675082","https://openalex.org/W2573450200","https://openalex.org/W2575771770","https://openalex.org/W2590954301","https://openalex.org/W2753863377","https://openalex.org/W2754896703","https://openalex.org/W2769542288","https://openalex.org/W2785509713","https://openalex.org/W2835402366","https://openalex.org/W2901354583","https://openalex.org/W2904250115","https://openalex.org/W2930816179","https://openalex.org/W2943091811","https://openalex.org/W2949960840","https://openalex.org/W2950746887","https://openalex.org/W2951061751","https://openalex.org/W2956406338","https://openalex.org/W2962797912","https://openalex.org/W2963899886","https://openalex.org/W2975619549","https://openalex.org/W2995895849","https://openalex.org/W3011527816","https://openalex.org/W3013708148","https://openalex.org/W3014325341","https://openalex.org/W3025053000","https://openalex.org/W3027118763","https://openalex.org/W3040925197","https://openalex.org/W3089544298","https://openalex.org/W3090361282","https://openalex.org/W4293854362","https://openalex.org/W6723408873","https://openalex.org/W6771673375","https://openalex.org/W6783511340"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"MOTIVATION:":[0],"The":[1,208],"automatic":[2],"discovery":[3],"of":[4,13,19,24,38,76,98,152,165,174,180],"sparse":[5,201],"biomarkers":[6,39,51],"that":[7,108,194],"are":[8,40,66,222,230],"associated":[9],"with":[10,73],"an":[11,35],"outcome":[12],"interest":[14],"is":[15,55,61,195,211],"a":[16,56,104,119,146,177,190],"central":[17],"goal":[18],"bioinformatics.":[20],"In":[21],"the":[22,41,44,74,77,96,124,137,172],"context":[23],"high-throughput":[25],"sequencing":[26],"(HTS)":[27],"data,":[28],"and":[29,70,86,112,168,183,216],"compositional":[30],"data":[31,54,229],"(CoDa)":[32],"more":[33],"generally,":[34],"important":[36],"class":[37],"log-ratios":[42],"between":[43],"input":[45],"variables.":[46],"However,":[47],"identifying":[48],"predictive":[49,113,166],"log-ratio":[50,114,202],"from":[52,95],"HTS":[53],"combinatorial":[57,126],"optimization":[58,127],"problem,":[59],"which":[60,79],"computationally":[62,197],"challenging.":[63],"Existing":[64],"methods":[65],"slow":[67],"to":[68,84,122],"run":[69],"scale":[71],"poorly":[72],"dimension":[75],"input,":[78],"has":[80],"limited":[81],"their":[82],"application":[83],"low-":[85],"moderate-dimensional":[87],"metagenomic":[88],"datasets.":[89],"RESULTS:":[90],"Building":[91],"on":[92],"recent":[93],"advances":[94],"field":[97],"deep":[99],"learning,":[100],"we":[101],"present":[102],"CoDaCoRe,":[103],"novel":[105],"learning":[106],"algorithm":[107,117],"identifies":[109],"sparse,":[110],"interpretable":[111],"biomarkers.":[115],"Our":[116],"exploits":[118],"continuous":[120],"relaxation":[121,130],"approximate":[123],"underlying":[125],"problem.":[128],"This":[129],"can":[131],"then":[132],"be":[133],"optimized":[134],"efficiently":[135],"using":[136],"modern":[138],"ML":[139],"toolbox,":[140],"in":[141,163],"particular,":[142],"gradient":[143],"descent.":[144],"As":[145],"result,":[147],"CoDaCoRe":[148,175,209],"runs":[149],"several":[150],"orders":[151],"magnitude":[153],"faster":[154],"than":[155],"competing":[156],"methods,":[157],"all":[158],"while":[159],"achieving":[160],"state-of-the-art":[161],"performance":[162],"terms":[164],"accuracy":[167],"sparsity.":[169],"We":[170],"verify":[171],"outperformance":[173],"across":[176],"wide":[178],"range":[179],"microbiome,":[181],"metabolite":[182],"microRNA":[184],"benchmark":[185],"datasets,":[186],"as":[187,189],"well":[188],"particularly":[191],"high-dimensional":[192],"dataset":[193],"outright":[196],"intractable":[198],"for":[199,218],"existing":[200],"selection":[203],"methods.":[204],"AVAILABILITY":[205],"AND":[206],"IMPLEMENTATION:":[207],"package":[210],"available":[212,223,231],"at":[213,224,232],"https://github.com/egr95/R-codacore.":[214],"Code":[215],"instructions":[217],"reproducing":[219],"our":[220],"results":[221],"https://github.com/cunningham-lab/codacore.":[225],"SUPPLEMENTARY":[226],"INFORMATION:":[227],"Supplementary":[228],"Bioinformatics":[233],"online.":[234]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":4}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2025-10-10T00:00:00"}