{"id":"https://openalex.org/W3046399878","doi":"https://doi.org/10.1145/3377929.3397770","title":"Large scale biomedical data analysis with tree-based automated machine learning","display_name":"Large scale biomedical data analysis with tree-based automated machine learning","publication_year":2020,"publication_date":"2020-07-08","ids":{"openalex":"https://openalex.org/W3046399878","doi":"https://doi.org/10.1145/3377929.3397770","mag":"3046399878"},"language":"en","primary_location":{"id":"doi:10.1145/3377929.3397770","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3377929.3397770","pdf_url":"https://dl.acm.org/action/downloadSupplement?doi=10.1145%2F3377929.3397770&file=p21_le_suppl.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 Genetic and Evolutionary Computation Conference Companion","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/action/downloadSupplement?doi=10.1145%2F3377929.3397770&file=p21_le_suppl.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070238515","display_name":"Trang T. Le","orcid":"https://orcid.org/0000-0003-3737-6565"},"institutions":[{"id":"https://openalex.org/I36788626","display_name":"California University of Pennsylvania","ror":"https://ror.org/01spssf70","country_code":"US","type":"education","lineage":["https://openalex.org/I36788626"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Trang T. Le","raw_affiliation_strings":["University of Pennsylvania"],"affiliations":[{"raw_affiliation_string":"University of Pennsylvania","institution_ids":["https://openalex.org/I36788626"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073641543","display_name":"Weixuan Fu","orcid":"https://orcid.org/0000-0002-6434-5468"},"institutions":[{"id":"https://openalex.org/I36788626","display_name":"California University of Pennsylvania","ror":"https://ror.org/01spssf70","country_code":"US","type":"education","lineage":["https://openalex.org/I36788626"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Weixuan Fu","raw_affiliation_strings":["University of Pennsylvania"],"affiliations":[{"raw_affiliation_string":"University of Pennsylvania","institution_ids":["https://openalex.org/I36788626"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032971510","display_name":"Jason H. Moore","orcid":"https://orcid.org/0000-0002-5015-1099"},"institutions":[{"id":"https://openalex.org/I36788626","display_name":"California University of Pennsylvania","ror":"https://ror.org/01spssf70","country_code":"US","type":"education","lineage":["https://openalex.org/I36788626"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jason H. Moore","raw_affiliation_strings":["University of Pennsylvania"],"affiliations":[{"raw_affiliation_string":"University of Pennsylvania","institution_ids":["https://openalex.org/I36788626"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5070238515"],"corresponding_institution_ids":["https://openalex.org/I36788626"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.08642163,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"21","last_page":"22"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9983999729156494,"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"}},"topics":[{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9983999729156494,"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"}},{"id":"https://openalex.org/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.9943000078201294,"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/computer-science","display_name":"Computer science","score":0.749199390411377},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7394139766693115},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6941812038421631},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.5724870562553406},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5110617876052856},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.4718501567840576},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4639318585395813},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4410247206687927},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4369312524795532},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07841652631759644}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.749199390411377},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7394139766693115},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6941812038421631},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.5724870562553406},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5110617876052856},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4718501567840576},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4639318585395813},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4410247206687927},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4369312524795532},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07841652631759644},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3377929.3397770","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3377929.3397770","pdf_url":"https://dl.acm.org/action/downloadSupplement?doi=10.1145%2F3377929.3397770&file=p21_le_suppl.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 Genetic and Evolutionary Computation Conference Companion","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3377929.3397770","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3377929.3397770","pdf_url":"https://dl.acm.org/action/downloadSupplement?doi=10.1145%2F3377929.3397770&file=p21_le_suppl.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 Genetic and Evolutionary Computation Conference Companion","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G149638561","display_name":null,"funder_award_id":"LM010098, LM012601, AI116794","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G6139746878","display_name":null,"funder_award_id":"LM010098, LM012601, AI116794","funder_id":"https://openalex.org/F4320306080","funder_display_name":"Foundation for the National Institutes of Health"},{"id":"https://openalex.org/G6634558516","display_name":null,"funder_award_id":"AI116794","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G6682602594","display_name":null,"funder_award_id":"LM010098","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G7306283087","display_name":null,"funder_award_id":"LM012601","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G7659322333","display_name":null,"funder_award_id":"LM012601, AI116794","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G770447875","display_name":null,"funder_award_id":"LM010098, LM012601, AI116794.","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320306080","display_name":"Foundation for the National Institutes of Health","ror":"https://ror.org/00k86s890"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3046399878.pdf","grobid_xml":"https://content.openalex.org/works/W3046399878.grobid-xml"},"referenced_works_count":6,"referenced_works":["https://openalex.org/W2100604298","https://openalex.org/W2126105956","https://openalex.org/W2309832917","https://openalex.org/W2593649365","https://openalex.org/W2892252214","https://openalex.org/W2963905884"],"related_works":["https://openalex.org/W4390608645","https://openalex.org/W4247566972","https://openalex.org/W4394895745","https://openalex.org/W2960264696","https://openalex.org/W3090563135","https://openalex.org/W2497432351","https://openalex.org/W4206777497","https://openalex.org/W2910064364","https://openalex.org/W4200136508","https://openalex.org/W2499527417"],"abstract_inverted_index":{"Tree-based":[0],"Pipeline":[1],"Optimization":[2],"Tool":[3],"(TPOT)":[4],"is":[5],"an":[6],"automated":[7],"machine":[8],"learning":[9,18],"(AutoML)":[10],"system":[11],"that":[12],"recommends":[13],"optimal":[14],"pipeline":[15],"for":[16,23,59],"supervised":[17],"problems":[19],"by":[20],"scanning":[21],"data":[22,48,83],"novel":[24,57],"features,":[25],"selecting":[26],"appropriate":[27],"models":[28],"and":[29,64,75],"optimizing":[30],"their":[31],"parameters.":[32],"However,":[33],"like":[34],"other":[35],"AutoML":[36],"systems,":[37],"TPOT":[38],"may":[39],"reach":[40],"computational":[41,73],"resource":[42],"limits":[43],"when":[44],"working":[45],"on":[46],"big":[47,82],"such":[49],"as":[50],"whole-genome":[51],"expression":[52],"data.":[53],"We":[54],"develop":[55],"two":[56],"features":[58],"TPOT,":[60],"Feature":[61],"Set":[62],"Selector":[63],"Template,":[65],"which":[66],"leverage":[67],"domain":[68],"knowledge,":[69],"greatly":[70],"reduce":[71],"the":[72],"expense":[74],"flexibly":[76],"extend":[77],"TPOT's":[78],"application":[79],"to":[80],"biomedical":[81],"analysis.":[84]},"counts_by_year":[],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}