{"id":"https://openalex.org/W4387346414","doi":"https://doi.org/10.1145/3584371.3613072","title":"An Ensemble Machine Learning Approach for Benchmarking and Selection of scRNA-seq Integration Methods","display_name":"An Ensemble Machine Learning Approach for Benchmarking and Selection of scRNA-seq Integration Methods","publication_year":2023,"publication_date":"2023-09-03","ids":{"openalex":"https://openalex.org/W4387346414","doi":"https://doi.org/10.1145/3584371.3613072"},"language":"en","primary_location":{"id":"doi:10.1145/3584371.3613072","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3584371.3613072","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3584371.3613072","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3584371.3613072","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069405681","display_name":"Konghao Zhao","orcid":"https://orcid.org/0000-0003-0240-540X"},"institutions":[{"id":"https://openalex.org/I47251452","display_name":"Wake Forest University","ror":"https://ror.org/0207ad724","country_code":"US","type":"education","lineage":["https://openalex.org/I47251452"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Konghao Zhao","raw_affiliation_strings":["Wake Forest University, Winston Salem, USA"],"raw_orcid":"https://orcid.org/0000-0003-0240-540X","affiliations":[{"raw_affiliation_string":"Wake Forest University, Winston Salem, USA","institution_ids":["https://openalex.org/I47251452"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022712038","display_name":"Sapan Bhandari","orcid":"https://orcid.org/0009-0002-4820-9690"},"institutions":[{"id":"https://openalex.org/I47251452","display_name":"Wake Forest University","ror":"https://ror.org/0207ad724","country_code":"US","type":"education","lineage":["https://openalex.org/I47251452"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sapan Bhandari","raw_affiliation_strings":["Wake Forest University, Winston Salem, USA"],"raw_orcid":"https://orcid.org/0009-0002-4820-9690","affiliations":[{"raw_affiliation_string":"Wake Forest University, Winston Salem, USA","institution_ids":["https://openalex.org/I47251452"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047742032","display_name":"Nathan P. Whitener","orcid":"https://orcid.org/0000-0003-4657-9217"},"institutions":[{"id":"https://openalex.org/I47251452","display_name":"Wake Forest University","ror":"https://ror.org/0207ad724","country_code":"US","type":"education","lineage":["https://openalex.org/I47251452"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nathan P Whitener","raw_affiliation_strings":["Wake Forest University, Winston Salem, USA"],"raw_orcid":"https://orcid.org/0000-0003-4657-9217","affiliations":[{"raw_affiliation_string":"Wake Forest University, Winston Salem, USA","institution_ids":["https://openalex.org/I47251452"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048406831","display_name":"Jason M. Grayson","orcid":"https://orcid.org/0000-0003-4524-1601"},"institutions":[{"id":"https://openalex.org/I47251452","display_name":"Wake Forest University","ror":"https://ror.org/0207ad724","country_code":"US","type":"education","lineage":["https://openalex.org/I47251452"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jason M Grayson","raw_affiliation_strings":["Wake Forest School of Medicine, Winston Salem, USA"],"raw_orcid":"https://orcid.org/0000-0003-4524-1601","affiliations":[{"raw_affiliation_string":"Wake Forest School of Medicine, Winston Salem, USA","institution_ids":["https://openalex.org/I47251452"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019570321","display_name":"Natalia Khuri","orcid":"https://orcid.org/0000-0001-9031-8124"},"institutions":[{"id":"https://openalex.org/I47251452","display_name":"Wake Forest University","ror":"https://ror.org/0207ad724","country_code":"US","type":"education","lineage":["https://openalex.org/I47251452"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Natalia Khuri","raw_affiliation_strings":["Wake Forest University, Winston Salem, USA"],"raw_orcid":"https://orcid.org/0000-0001-9031-8124","affiliations":[{"raw_affiliation_string":"Wake Forest University, Winston Salem, USA","institution_ids":["https://openalex.org/I47251452"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5069405681"],"corresponding_institution_ids":["https://openalex.org/I47251452"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.29471647,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11289","display_name":"Single-cell and spatial transcriptomics","score":1.0,"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/T11289","display_name":"Single-cell and spatial transcriptomics","score":1.0,"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/T12859","display_name":"Cell Image Analysis Techniques","score":0.9746000170707703,"subfield":{"id":"https://openalex.org/subfields/1304","display_name":"Biophysics"},"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/T10773","display_name":"Extracellular vesicles in disease","score":0.9574999809265137,"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/benchmarking","display_name":"Benchmarking","score":0.870046854019165},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.8053858280181885},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7763615846633911},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6422512531280518},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6323227286338806},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.6310806274414062},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5604934692382812},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.5552524924278259},{"id":"https://openalex.org/keywords/ensemble-learning","display_name":"Ensemble learning","score":0.5391147136688232},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5152319073677063},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.45762643218040466}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.870046854019165},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8053858280181885},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7763615846633911},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6422512531280518},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6323227286338806},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.6310806274414062},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5604934692382812},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.5552524924278259},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.5391147136688232},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5152319073677063},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.45762643218040466},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","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},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3584371.3613072","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3584371.3613072","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3584371.3613072","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3584371.3613072","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3584371.3613072","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3584371.3613072","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309558","display_name":"Wake Forest University","ror":"https://ror.org/0207ad724"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387346414.pdf","grobid_xml":"https://content.openalex.org/works/W4387346414.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W1995875735","https://openalex.org/W2101234009","https://openalex.org/W2102212449","https://openalex.org/W2295598076","https://openalex.org/W2472063172","https://openalex.org/W2753908609","https://openalex.org/W2774307122","https://openalex.org/W2794480084","https://openalex.org/W2794521141","https://openalex.org/W2794891507","https://openalex.org/W2800392236","https://openalex.org/W2810097927","https://openalex.org/W2898821675","https://openalex.org/W2898824002","https://openalex.org/W2905317377","https://openalex.org/W2912390237","https://openalex.org/W2949177718","https://openalex.org/W2951506174","https://openalex.org/W2951638683","https://openalex.org/W2964643116","https://openalex.org/W2967177832","https://openalex.org/W2984472267","https://openalex.org/W2997280954","https://openalex.org/W3002417351","https://openalex.org/W3009302866","https://openalex.org/W3015184839","https://openalex.org/W3117537317","https://openalex.org/W3126492421","https://openalex.org/W3127061676","https://openalex.org/W3192982573","https://openalex.org/W4220837089","https://openalex.org/W4225598893","https://openalex.org/W4317617524","https://openalex.org/W4387346435","https://openalex.org/W6675354045"],"related_works":["https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2059640416","https://openalex.org/W1490753184","https://openalex.org/W2284465472","https://openalex.org/W2291782699","https://openalex.org/W1993948687","https://openalex.org/W4399363378","https://openalex.org/W2155094138"],"abstract_inverted_index":{"Accurate":[0],"integration":[1,25,54,85,106],"of":[2,12,19,24,51,67,78,120,135],"high-dimensional":[3],"single-cell":[4],"sequencing":[5],"datasets":[6],"is":[7,36],"important":[8,37],"for":[9,16,46],"the":[10,17,22,47,52,84,87,129,136],"construction":[11],"cell":[13],"atlases":[14],"and":[15,31,49,81,92,98,108,113,118,133],"discovery":[18],"biomarkers.":[20],"Because":[21],"performance":[23],"methods":[26,107],"varies":[27],"in":[28],"different":[29,33],"scenarios":[30],"on":[32],"datasets,":[34],"it":[35],"to":[38],"provide":[39],"end":[40],"users":[41],"with":[42,86],"an":[43,65],"automated":[44],"system":[45,62],"benchmarking":[48],"selection":[50],"best":[53],"among":[55],"several":[56],"alternatives.":[57],"Here,":[58],"we":[59],"present":[60],"a":[61],"that":[63],"uses":[64],"ensemble":[66],"auditors,":[68],"trained":[69],"by":[70],"supervised":[71],"machine":[72],"learning,":[73],"which":[74],"quantifies":[75],"residual":[76],"variability":[77],"integrated":[79],"data":[80,114],"automatically":[82],"selects":[83],"smallest":[88],"difference":[89],"between":[90],"observed":[91],"expected":[93],"batch":[94],"effects.":[95],"A":[96],"rigorous":[97],"systematic":[99],"validation":[100,122],"was":[101],"performed":[102],"using":[103],"6":[104],"popular":[105],"52":[109],"benchmark":[110],"datasets.":[111],"Algorithmic":[112],"biases":[115],"were":[116,124],"uncovered":[117],"shortcomings":[119],"existing":[121],"metrics":[123],"examined.":[125],"Our":[126],"results":[127],"demonstrate":[128],"utility,":[130],"validity,":[131],"flexibility":[132],"consistency":[134],"proposed":[137],"approach.":[138]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}