{"id":"https://openalex.org/W2964694544","doi":"https://doi.org/10.1609/aaai.v33i01.33019434","title":"A Fast Machine Learning Workflow for Rapid Phenotype Prediction from Whole Shotgun Metagenomes","display_name":"A Fast Machine Learning Workflow for Rapid Phenotype Prediction from Whole Shotgun Metagenomes","publication_year":2019,"publication_date":"2019-07-17","ids":{"openalex":"https://openalex.org/W2964694544","doi":"https://doi.org/10.1609/aaai.v33i01.33019434","mag":"2964694544"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v33i01.33019434","doi":"https://doi.org/10.1609/aaai.v33i01.33019434","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33019434","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v33i01.33019434","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043161270","display_name":"Anna Paola Carrieri","orcid":"https://orcid.org/0000-0003-2349-1896","observed_orcids":["https://orcid.org/0000-0003-2349-1896"]},"institutions":[{"id":"https://openalex.org/I2802015276","display_name":"Daresbury Laboratory","ror":"https://ror.org/0089bg420","country_code":"GB","type":"facility","lineage":["https://openalex.org/I162524378","https://openalex.org/I2802015276","https://openalex.org/I4210087105"]},{"id":"https://openalex.org/I4210102012","display_name":"Sci-Tech Daresbury","ror":"https://ror.org/015ff4823","country_code":"GB","type":"facility","lineage":["https://openalex.org/I4210102012"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Anna Paola Carrieri","raw_affiliation_strings":["IBM","IBM Research UK Sci-Tech Daresbury Warrington, UK","Scientific Computing Dept. STFC Daresbury Lab. Warrington, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM","institution_ids":[]},{"raw_affiliation_string":"IBM Research UK Sci-Tech Daresbury Warrington, UK","institution_ids":["https://openalex.org/I4210102012"]},{"raw_affiliation_string":"Scientific Computing Dept. STFC Daresbury Lab. Warrington, UK","institution_ids":["https://openalex.org/I2802015276"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078257079","display_name":"Will P. M. Rowe","orcid":"https://orcid.org/0000-0003-0384-4463","observed_orcids":["https://orcid.org/0000-0003-0384-4463"]},"institutions":[{"id":"https://openalex.org/I2802015276","display_name":"Daresbury Laboratory","ror":"https://ror.org/0089bg420","country_code":"GB","type":"facility","lineage":["https://openalex.org/I162524378","https://openalex.org/I2802015276","https://openalex.org/I4210087105"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Will PM Rowe","raw_affiliation_strings":["STFC Daresbury Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"STFC Daresbury Laboratory","institution_ids":["https://openalex.org/I2802015276"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052155666","display_name":"Martyn Winn","orcid":"https://orcid.org/0000-0003-0496-6796","observed_orcids":["https://orcid.org/0000-0003-0496-6796"]},"institutions":[{"id":"https://openalex.org/I2802015276","display_name":"Daresbury Laboratory","ror":"https://ror.org/0089bg420","country_code":"GB","type":"facility","lineage":["https://openalex.org/I162524378","https://openalex.org/I2802015276","https://openalex.org/I4210087105"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Martyn Winn","raw_affiliation_strings":["STFC Daresbury Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"STFC Daresbury Laboratory","institution_ids":["https://openalex.org/I2802015276"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084050064","display_name":"Edward O. Pyzer\u2010Knapp","orcid":"https://orcid.org/0000-0002-8232-8282","observed_orcids":["https://orcid.org/0000-0002-8232-8282"]},"institutions":[{"id":"https://openalex.org/I2802015276","display_name":"Daresbury Laboratory","ror":"https://ror.org/0089bg420","country_code":"GB","type":"facility","lineage":["https://openalex.org/I162524378","https://openalex.org/I2802015276","https://openalex.org/I4210087105"]},{"id":"https://openalex.org/I4210102012","display_name":"Sci-Tech Daresbury","ror":"https://ror.org/015ff4823","country_code":"GB","type":"facility","lineage":["https://openalex.org/I4210102012"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Edward O. Pyzer-Knapp","raw_affiliation_strings":["IBM","IBM Research UK Sci-Tech Daresbury Warrington, UK","Scientific Computing Dept. STFC Daresbury Lab. Warrington, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM","institution_ids":[]},{"raw_affiliation_string":"IBM Research UK Sci-Tech Daresbury Warrington, UK","institution_ids":["https://openalex.org/I4210102012"]},{"raw_affiliation_string":"Scientific Computing Dept. STFC Daresbury Lab. Warrington, UK","institution_ids":["https://openalex.org/I2802015276"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.4634,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.97636793,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":96},"biblio":{"volume":"33","issue":"01","first_page":"9434","last_page":"9439"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.45559999346733093,"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":0.45559999346733093,"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/T10066","display_name":"Gut microbiota and health","score":0.31520000100135803,"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":0.06780000030994415,"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/microbiome","display_name":"microbiome","score":0.8270000219345093},{"id":"https://openalex.org/keywords/machine-learning-workflow","display_name":"machine learning workflow","score":0.7310000061988831},{"id":"https://openalex.org/keywords/metagenome-classification","display_name":"metagenome classification","score":0.5640000104904175},{"id":"https://openalex.org/keywords/human-microbiome","display_name":"human microbiome","score":0.9919999837875366},{"id":"https://openalex.org/keywords/real-time-diagnosis","display_name":"real-time diagnosis","score":0.7120000123977661},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"cloud computing","score":0.4259999990463257}],"concepts":[{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.894041895866394},{"id":"https://openalex.org/C15151743","wikidata":"https://www.wikidata.org/wiki/Q903778","display_name":"Metagenomics","level":3,"score":0.7561851143836975},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6922892332077026},{"id":"https://openalex.org/C143121216","wikidata":"https://www.wikidata.org/wiki/Q1330402","display_name":"Microbiome","level":2,"score":0.6700639128684998},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5718420147895813},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5365806221961975},{"id":"https://openalex.org/C126831891","wikidata":"https://www.wikidata.org/wiki/Q221673","display_name":"Host (biology)","level":2,"score":0.4584815204143524},{"id":"https://openalex.org/C101985253","wikidata":"https://www.wikidata.org/wiki/Q1073526","display_name":"Shotgun sequencing","level":4,"score":0.44938603043556213},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.40273618698120117},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3738974928855896},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.2722325325012207},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.22045662999153137},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.19490882754325867},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.1666455864906311},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.10415780544281006},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1609/aaai.v33i01.33019434","doi":"https://doi.org/10.1609/aaai.v33i01.33019434","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33019434","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/4994","doi":null,"is_oa":true,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/4994","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4994/4867","source":{"id":"https://openalex.org/S4306400155","display_name":"AAAI Publications (The Association for the Advancement of Artificial Intelligence (AAAI))","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801652627","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/I2801652627"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:purl.org/net/epubs:work/44133672","doi":null,"is_oa":false,"landing_page_url":"http://purl.org/net/epubs/work/44133672","pdf_url":null,"source":{"id":"https://openalex.org/S4306400600","display_name":"ePubs (Science and Technology Facilities Council, Research Councils UK)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I162524378","host_organization_name":"Science and Technology Facilities Council","host_organization_lineage":["https://openalex.org/I162524378"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1609/aaai.v33i01.33019434","doi":"https://doi.org/10.1609/aaai.v33i01.33019434","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33019434","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/3","score":0.504800021648407,"display_name":"Good health and well-being"}],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334632","display_name":"Science and Technology Facilities Council","ror":"https://ror.org/057g20z61"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2964694544.pdf","grobid_xml":"https://content.openalex.org/works/W2964694544.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W1505191356","https://openalex.org/W1510526001","https://openalex.org/W2023615726","https://openalex.org/W2033136694","https://openalex.org/W2093830129","https://openalex.org/W2098824882","https://openalex.org/W2099839022","https://openalex.org/W2101234009","https://openalex.org/W2128769815","https://openalex.org/W2132069633","https://openalex.org/W2135046866","https://openalex.org/W2139360719","https://openalex.org/W2170951896","https://openalex.org/W2254734290","https://openalex.org/W2473355215","https://openalex.org/W2610066872","https://openalex.org/W2760930044","https://openalex.org/W2772632044","https://openalex.org/W2789627023","https://openalex.org/W2800234325","https://openalex.org/W2902812386","https://openalex.org/W2950044153","https://openalex.org/W2950150251","https://openalex.org/W2950287694","https://openalex.org/W2951934242","https://openalex.org/W6679663036"],"related_works":["https://openalex.org/W7223422028","https://openalex.org/W4411313812","https://openalex.org/W7011306298","https://openalex.org/W2473355215","https://openalex.org/W4413612456","https://openalex.org/W4403705498","https://openalex.org/W3105301756","https://openalex.org/W2921789835","https://openalex.org/W4383186706","https://openalex.org/W4225259915"],"abstract_inverted_index":{"Research":[0],"on":[1,136],"the":[2,54,75,125,130,134,144,151,172,203],"microbiome":[3,49,119],"is":[4,67],"an":[5],"emerging":[6],"and":[7,20,33,56,64,94,104,183,210,238,250],"crucial":[8],"science":[9],"that":[10,81,110,156,191,222],"finds":[11],"many":[12],"applications":[13,89],"in":[14,38,205],"healthcare,":[15],"food":[16],"safety,":[17],"precision":[18],"agriculture":[19],"environmental":[21],"studies.":[22],"Huge":[23],"amounts":[24],"of":[25,58,60,113,146,171,187,207,212],"DNA":[26],"from":[27,43,116,162,185,236],"microbial":[28],"communities":[29],"are":[30],"being":[31],"sequenced":[32],"analyzed":[34],"by":[35,166],"scientists":[36],"interested":[37],"extracting":[39],"meaningful":[40],"biological":[41],"information":[42],"this":[44,141],"big":[45],"data.":[46],"Analyzing":[47],"massive":[48],"sequencing":[50,189],"datasets,":[51],"which":[52],"embed":[53],"functions":[55],"interactions":[57],"thousands":[59],"different":[61,216],"bacterial,":[62],"fungal":[63],"viral":[65],"species,":[66],"a":[68,243,251],"significant":[69],"computational":[70],"challenge.":[71],"Artificial":[72],"intelligence":[73],"has":[74],"potential":[76,252],"for":[77,85,214,253],"building":[78],"predictive":[79],"models":[80],"can":[82,226],"provide":[83],"insights":[84],"specific":[86,137],"cutting":[87],"edge":[88],"such":[90,180],"as":[91,98,100,181],"guiding":[92],"diagnostics":[93,249],"developing":[95],"personalised":[96],"treatments,":[97],"well":[99],"maintaining":[101],"soil":[102],"health":[103],"fertility.":[105],"Current":[106],"machine":[107,153],"learning":[108,154],"workflows":[109],"predict":[111],"traits":[112],"host":[114,159],"organisms":[115],"their":[117],"commensal":[118],"do":[120,192],"not":[121,193],"take":[122],"into":[123],"account":[124],"whole":[126,163],"genetic":[127,173],"material":[128],"constituting":[129],"microbiome,":[131],"instead":[132],"basing":[133],"analysis":[135],"marker":[138],"genes.":[139],"In":[140],"paper,":[142],"to":[143],"best":[145],"our":[147,223],"knowledge,":[148],"we":[149,220],"introduce":[150],"first":[152],"workflow":[155,176,225],"efficiently":[157,227],"performs":[158],"phenotype":[160],"prediction":[161,178],"shotgun":[164],"metagenomes":[165],"computing":[167],"similaritypreserving":[168],"compact":[169],"representations":[170],"material.":[174],"Our":[175],"enables":[177],"tasks,":[179],"classification":[182],"regression,":[184],"Terabytes":[186],"raw":[188],"data":[190,230],"necessitate":[194],"any":[195],"pre-prossessing":[196],"through":[197],"expensive":[198],"bioinformatics":[199],"pipelines.":[200],"We":[201],"compare":[202],"performance":[204],"terms":[206],"time,":[208],"accuracy":[209],"uncertainty":[211],"predictions":[213],"four":[215],"classifiers.":[217],"More":[218],"precisely,":[219],"demonstrate":[221],"ML":[224],"classify":[228],"real":[229,247],"with":[231],"high":[232],"accuracy,":[233],"using":[234],"examples":[235],"dog":[237],"human":[239],"metagenomic":[240],"studies,":[241],"representing":[242],"step":[244],"forward":[245],"towards":[246],"time":[248],"cloud":[254],"applications.":[255]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2019-08-13T00:00:00"}