{"id":"https://openalex.org/W2585438238","doi":"https://doi.org/10.1109/bigdata.2016.7840731","title":"Using machine learning to identify major shifts in human gut microbiome protein family abundance in disease","display_name":"Using machine learning to identify major shifts in human gut microbiome protein family abundance in disease","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2585438238","doi":"https://doi.org/10.1109/bigdata.2016.7840731","mag":"2585438238"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2016.7840731","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2016.7840731","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112249832","display_name":"Mehrdad Yazdani","orcid":null},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mehrdad Yazdani","raw_affiliation_strings":["California Institute for Telecommunications and Information Technology, UC San Diego, California, USA"],"affiliations":[{"raw_affiliation_string":"California Institute for Telecommunications and Information Technology, UC San Diego, California, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077295852","display_name":"Bryn C. Taylor","orcid":"https://orcid.org/0000-0002-4957-5417"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bryn C. Taylor","raw_affiliation_strings":["California Institute for Telecommunications and Information Technology, UC San Diego, California, USA"],"affiliations":[{"raw_affiliation_string":"California Institute for Telecommunications and Information Technology, UC San Diego, California, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087710431","display_name":"Justine W. Debelius","orcid":"https://orcid.org/0000-0002-8605-3546"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Justine W. Debelius","raw_affiliation_strings":["California Institute for Telecommunications and Information Technology, UC San Diego, California, USA"],"affiliations":[{"raw_affiliation_string":"California Institute for Telecommunications and Information Technology, UC San Diego, California, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027145422","display_name":"Weizhong Li","orcid":"https://orcid.org/0000-0003-1804-9403"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Weizhong Li","raw_affiliation_strings":["California Institute for Telecommunications and Information Technology, UC San Diego, California, USA"],"affiliations":[{"raw_affiliation_string":"California Institute for Telecommunications and Information Technology, UC San Diego, California, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033881627","display_name":"Rob Knight","orcid":"https://orcid.org/0000-0002-0975-9019"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rob Knight","raw_affiliation_strings":["California Institute for Telecommunications and Information Technology, UC San Diego, California, USA"],"affiliations":[{"raw_affiliation_string":"California Institute for Telecommunications and Information Technology, UC San Diego, California, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070236619","display_name":"Larry Smarr","orcid":"https://orcid.org/0000-0003-2003-7700"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Larry Smarr","raw_affiliation_strings":["California Institute for Telecommunications and Information Technology, UC San Diego, California, USA"],"affiliations":[{"raw_affiliation_string":"California Institute for Telecommunications and Information Technology, UC San Diego, California, USA","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5112249832"],"corresponding_institution_ids":["https://openalex.org/I36258959"],"apc_list":null,"apc_paid":null,"fwci":2.0008,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.87082734,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1272","last_page":"1280"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10066","display_name":"Gut microbiota and health","score":0.998199999332428,"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":0.998199999332428,"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/T10276","display_name":"Helicobacter pylori-related gastroenterology studies","score":0.9643999934196472,"subfield":{"id":"https://openalex.org/subfields/2746","display_name":"Surgery"},"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/T13702","display_name":"Machine Learning in Healthcare","score":0.944100022315979,"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/kegg","display_name":"KEGG","score":0.916969895362854},{"id":"https://openalex.org/keywords/microbiome","display_name":"Microbiome","score":0.7303420901298523},{"id":"https://openalex.org/keywords/metagenomics","display_name":"Metagenomics","score":0.5977117419242859},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5579608082771301},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.5398184061050415},{"id":"https://openalex.org/keywords/disease","display_name":"Disease","score":0.5246667861938477},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4661133885383606},{"id":"https://openalex.org/keywords/human-microbiome-project","display_name":"Human Microbiome Project","score":0.44600382447242737},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4455552101135254},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.42598414421081543},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.397585928440094},{"id":"https://openalex.org/keywords/human-microbiome","display_name":"Human microbiome","score":0.3394443392753601},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3247837424278259},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.2087569534778595},{"id":"https://openalex.org/keywords/transcriptome","display_name":"Transcriptome","score":0.2063189148902893},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.18973636627197266},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.16491129994392395},{"id":"https://openalex.org/keywords/pathology","display_name":"Pathology","score":0.11178931593894958}],"concepts":[{"id":"https://openalex.org/C152724338","wikidata":"https://www.wikidata.org/wiki/Q909442","display_name":"KEGG","level":5,"score":0.916969895362854},{"id":"https://openalex.org/C143121216","wikidata":"https://www.wikidata.org/wiki/Q1330402","display_name":"Microbiome","level":2,"score":0.7303420901298523},{"id":"https://openalex.org/C15151743","wikidata":"https://www.wikidata.org/wiki/Q903778","display_name":"Metagenomics","level":3,"score":0.5977117419242859},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5579608082771301},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5398184061050415},{"id":"https://openalex.org/C2779134260","wikidata":"https://www.wikidata.org/wiki/Q12136","display_name":"Disease","level":2,"score":0.5246667861938477},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4661133885383606},{"id":"https://openalex.org/C190944805","wikidata":"https://www.wikidata.org/wiki/Q3922751","display_name":"Human Microbiome Project","level":4,"score":0.44600382447242737},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4455552101135254},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.42598414421081543},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.397585928440094},{"id":"https://openalex.org/C91478284","wikidata":"https://www.wikidata.org/wiki/Q6623796","display_name":"Human microbiome","level":3,"score":0.3394443392753601},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3247837424278259},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.2087569534778595},{"id":"https://openalex.org/C162317418","wikidata":"https://www.wikidata.org/wiki/Q252857","display_name":"Transcriptome","level":4,"score":0.2063189148902893},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.18973636627197266},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.16491129994392395},{"id":"https://openalex.org/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","level":1,"score":0.11178931593894958},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata.2016.7840731","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2016.7840731","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332603","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W86004046","https://openalex.org/W1614298861","https://openalex.org/W1880262756","https://openalex.org/W1979672417","https://openalex.org/W1982388837","https://openalex.org/W1983414515","https://openalex.org/W2005741884","https://openalex.org/W2007153665","https://openalex.org/W2037279825","https://openalex.org/W2079196839","https://openalex.org/W2088209062","https://openalex.org/W2097804645","https://openalex.org/W2101234009","https://openalex.org/W2107805776","https://openalex.org/W2110256992","https://openalex.org/W2119073376","https://openalex.org/W2125826054","https://openalex.org/W2128769815","https://openalex.org/W2131186249","https://openalex.org/W2143777796","https://openalex.org/W2149573313","https://openalex.org/W2149960646","https://openalex.org/W2157253968","https://openalex.org/W2158462536","https://openalex.org/W2159482845","https://openalex.org/W2160969485","https://openalex.org/W2161377277","https://openalex.org/W2162704968","https://openalex.org/W2164175488","https://openalex.org/W2170747616","https://openalex.org/W2250539671","https://openalex.org/W2950577311","https://openalex.org/W4231510805","https://openalex.org/W4294216483","https://openalex.org/W6636510571","https://openalex.org/W6639619044","https://openalex.org/W6675354045"],"related_works":["https://openalex.org/W1222064643","https://openalex.org/W1994105594","https://openalex.org/W4232165964","https://openalex.org/W2502616020","https://openalex.org/W3118380721","https://openalex.org/W3127148346","https://openalex.org/W4384497819","https://openalex.org/W2969529002","https://openalex.org/W2197368019","https://openalex.org/W4210316040"],"abstract_inverted_index":{"Inflammatory":[0],"Bowel":[1],"Disease":[2],"(IBD)":[3],"is":[4,9],"an":[5],"autoimmune":[6],"condition":[7],"that":[8],"observed":[10],"to":[11,43,81,107,134,150],"be":[12,172],"associated":[13],"with":[14],"major":[15,26],"alterations":[16],"in":[17,28,58,89,155],"the":[18,59,78,83,90,110,130,156],"gut":[19,60,157],"microbiome":[20,29,61],"taxonomic":[21],"composition.":[22],"Here":[23],"we":[24,94,122,141],"classify":[25],"changes":[27],"protein":[30,56,148],"family":[31],"abundances":[32],"between":[33,166],"healthy":[34,66,119],"subjects":[35],"and":[36,68,118,168],"IBD":[37,69],"patients.":[38,70],"We":[39,71],"use":[40,95],"machine":[41,74],"learning":[42,75],"analyze":[44],"results":[45],"obtained":[46],"previously":[47],"from":[48,145],"computing":[49],"relative":[50,137],"abundance":[51],"of":[52,62,65,129,178],"~10,000":[53],"KEGG":[54,91,131,136,147],"orthologous":[55],"families":[57,149],"a":[63,73,99,103,124],"set":[64,101],"individuals":[67],"develop":[72],"pipeline,":[76],"involving":[77],"Kolomogorv-Smirnov":[79],"test,":[80],"identify":[82],"100":[84,97],"most":[85],"statistically":[86],"significant":[87],"entries":[88],"database.":[92],"Then":[93],"these":[96],"as":[98],"training":[100],"for":[102,161,175],"Random":[104],"Forest":[105],"classifier":[106,128],"determine":[108],"~5%":[109],"KEGGs":[111],"which":[112],"are":[113],"best":[114],"at":[115],"separating":[116],"disease":[117,169],"states.":[120],"Lastly,":[121],"developed":[123],"Natural":[125],"Language":[126],"Processing":[127],"description":[132],"files":[133],"predict":[135],"over-or":[138],"under-abundance.":[139],"As":[140],"expand":[142],"our":[143],"analysis":[144],"10,000":[146],"one":[151],"million":[152],"proteins":[153],"identified":[154],"microbiome,":[158],"scalable":[159],"methods":[160],"quickly":[162],"identifying":[163],"such":[164],"anomalies":[165],"health":[167],"states":[170],"will":[171],"increasingly":[173],"valuable":[174],"biological":[176],"interpretation":[177],"sequence":[179],"data.":[180]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}