{"id":"https://openalex.org/W4394852219","doi":"https://doi.org/10.1101/2024.04.12.589306","title":"An Efficient and Principled Model to Jointly Learn the Agnostic and Multifactorial Effect in Large-Scale Biological Data","display_name":"An Efficient and Principled Model to Jointly Learn the Agnostic and Multifactorial Effect in Large-Scale Biological Data","publication_year":2024,"publication_date":"2024-04-15","ids":{"openalex":"https://openalex.org/W4394852219","doi":"https://doi.org/10.1101/2024.04.12.589306"},"language":"en","primary_location":{"id":"doi:10.1101/2024.04.12.589306","doi":"https://doi.org/10.1101/2024.04.12.589306","is_oa":true,"landing_page_url":"https://doi.org/10.1101/2024.04.12.589306","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2024/04/15/2024.04.12.589306.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2024/04/15/2024.04.12.589306.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100372044","display_name":"Zuolin Cheng","orcid":"https://orcid.org/0000-0002-5197-5874","observed_orcids":["https://orcid.org/0000-0002-5197-5874"]},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zuolin Cheng","raw_affiliation_strings":["Virginia Tech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Virginia Tech","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084454649","display_name":"Songtao Wei","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Songtao Wei","raw_affiliation_strings":["Virginia Tech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Virginia Tech","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040372961","display_name":"Yinxue Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yinxue Wang","raw_affiliation_strings":["Virginia Polytechnic Institute and State University","Virginia Tech;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Virginia Polytechnic Institute and State University","institution_ids":["https://openalex.org/I859038795"]},{"raw_affiliation_string":"Virginia Tech;","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074857897","display_name":"Yizhi Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yizhi Wang","raw_affiliation_strings":["Virginia Polytechnic Institute and State University;","Virginia Tech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Virginia Polytechnic Institute and State University;","institution_ids":["https://openalex.org/I859038795"]},{"raw_affiliation_string":"Virginia Tech","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101658549","display_name":"Qing Richard Lu","orcid":"https://orcid.org/0000-0001-6846-9014","observed_orcids":["https://orcid.org/0000-0001-6846-9014"]},"institutions":[{"id":"https://openalex.org/I1285204247","display_name":"Cincinnati Children's Hospital Medical Center","ror":"https://ror.org/01hcyya48","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1285204247"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Q Richard Lu","raw_affiliation_strings":["Cincinnati Children's Hospital"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cincinnati Children's Hospital","institution_ids":["https://openalex.org/I1285204247"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100372149","display_name":"Yue Wang","orcid":"https://orcid.org/0009-0009-9422-5780","observed_orcids":["https://orcid.org/0009-0009-9422-5780"]},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yue Wang","raw_affiliation_strings":["Virginia Polytechnic Institute and State University;","Virginia Tech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Virginia Polytechnic Institute and State University;","institution_ids":["https://openalex.org/I859038795"]},{"raw_affiliation_string":"Virginia Tech","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"last","author":{"id":null,"display_name":"Guoqiang Yu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Guoqiang Yu","raw_affiliation_strings":["Virginia Tech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Virginia Tech","institution_ids":["https://openalex.org/I859038795"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I859038795"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12303","display_name":"Tensor decomposition and applications","score":0.22130000591278076,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12303","display_name":"Tensor decomposition and applications","score":0.22130000591278076,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.20509999990463257,"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/T10885","display_name":"Gene expression and cancer classification","score":0.20340000092983246,"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/maximum-entropy","display_name":"maximum entropy","score":0.796999990940094},{"id":"https://openalex.org/keywords/factor-interactions","display_name":"factor interactions","score":0.4300000071525574},{"id":"https://openalex.org/keywords/convex-optimization","display_name":"convex optimization","score":0.625},{"id":"https://openalex.org/keywords/iterative-optimization-algorithm","display_name":"iterative optimization algorithm","score":0.675000011920929}],"concepts":[{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.6242854595184326},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5412485599517822},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.47940465807914734},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.12467551231384277},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0905943512916565}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1101/2024.04.12.589306","doi":"https://doi.org/10.1101/2024.04.12.589306","is_oa":true,"landing_page_url":"https://doi.org/10.1101/2024.04.12.589306","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2024/04/15/2024.04.12.589306.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.1101/2024.04.12.589306","doi":"https://doi.org/10.1101/2024.04.12.589306","is_oa":true,"landing_page_url":"https://doi.org/10.1101/2024.04.12.589306","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2024/04/15/2024.04.12.589306.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4394852219.pdf","grobid_xml":"https://content.openalex.org/works/W4394852219.grobid-xml"},"referenced_works_count":43,"referenced_works":["https://openalex.org/W1494567425","https://openalex.org/W1967327758","https://openalex.org/W2005254597","https://openalex.org/W2009720434","https://openalex.org/W2019552331","https://openalex.org/W2038492487","https://openalex.org/W2039521726","https://openalex.org/W2052958516","https://openalex.org/W2068767807","https://openalex.org/W2069295116","https://openalex.org/W2091117089","https://openalex.org/W2158485480","https://openalex.org/W2165909549","https://openalex.org/W2233603983","https://openalex.org/W2262414037","https://openalex.org/W2275877493","https://openalex.org/W2345356016","https://openalex.org/W2415341492","https://openalex.org/W2554953109","https://openalex.org/W2582033455","https://openalex.org/W2605611918","https://openalex.org/W2622807556","https://openalex.org/W2795686629","https://openalex.org/W2894687190","https://openalex.org/W2901838561","https://openalex.org/W2936068176","https://openalex.org/W2946016273","https://openalex.org/W2949996247","https://openalex.org/W2951869335","https://openalex.org/W2952990620","https://openalex.org/W2996729595","https://openalex.org/W3004544639","https://openalex.org/W3007172120","https://openalex.org/W3047461816","https://openalex.org/W3092538588","https://openalex.org/W3097602738","https://openalex.org/W3136308181","https://openalex.org/W3185694768","https://openalex.org/W3203631316","https://openalex.org/W3216100684","https://openalex.org/W4220966948","https://openalex.org/W4255830679","https://openalex.org/W4305016438"],"related_works":["https://openalex.org/W6980743529","https://openalex.org/W2551261006","https://openalex.org/W2525743689","https://openalex.org/W2995264458","https://openalex.org/W2774724797","https://openalex.org/W7098105793","https://openalex.org/W7111225384","https://openalex.org/W2185566642","https://openalex.org/W3134051997","https://openalex.org/W564523646"],"abstract_inverted_index":{"Abstract":[0],"The":[1],"rich":[2],"information":[3],"contained":[4],"in":[5,36,214,336,343],"biological":[6,40,273,346],"data":[7,41,110,338],"is":[8,24,34,57],"often":[9],"distorted":[10],"by":[11,121,152],"multiple":[12,344],"interacting":[13],"intrinsic":[14],"or":[15,48,89,260],"extrinsic":[16],"factors.":[17,98],"Modeling":[18],"the":[19,28,64,69,82,94,104,109,115,140,146,154,157,161,176,193,209,223,230,238,242,253,276],"effects":[20,179,194,332],"of":[21,44,46,50,133,148,156,226,241,278,292,312,333],"these":[22,61,190],"factors":[23,62,191,335],"necessary":[25],"to":[26,66,138,182,222,258,263,268,305],"uncover":[27],"underlying":[29],"true":[30],"signals.":[31],"However,":[32,220],"this":[33,100],"challenging":[35],"real":[37],"applications,":[38,274],"because":[39],"usually":[42],"consist":[43],"tens":[45],"thousands":[47],"millions":[49],"factors,":[51],"and":[52,151,180,195,212,228,290,339],"no":[53],"reliable":[54],"prior":[55],"knowledge":[56],"available":[58],"on":[59,86,145],"how":[60,75,189],"exert":[63,192],"effect,":[65],"what":[67],"degree":[68],"effect":[70],"is,":[71],"as":[72,74,93,111,314,316],"well":[73,119,315],"they":[76],"interact":[77,196],"with":[78,129,197,204,303],"each":[79,198],"other.":[80,199],"Thus,":[81],"existing":[83,341],"approaches":[84],"rely":[85],"excessive":[87],"simplification":[88],"unrealistic":[90],"assumptions":[91,174],"such":[92],"probabilistic":[95],"independence":[96],"among":[97],"In":[99],"paper,":[101],"we":[102,245],"report":[103],"finding":[105],"that":[106],"after":[107],"reformulating":[108],"a":[112,122,183,215,270],"contingency":[113,158],"tensor":[114,159],"problem":[116,211],"can":[117,320],"be":[118,321],"addressed":[120],"fundamental":[123],"machine":[124],"learning":[125],"principle,":[126],"Maximum":[127],"Entropy,":[128],"an":[130,135,247],"extra":[131],"effort":[132],"designing":[134],"efficient":[136,248],"algorithm":[137],"solve":[139],"large-scale":[141],"optimization":[142],"problem.":[143,219],"Based":[144],"principle":[147],"maximum":[149],"entropy,":[150],"constraining":[153],"marginals":[155],"using":[160],"observed":[162],"values,":[163,206],"our":[164],"Conditional":[165],"Multifactorial":[166],"Contingency":[167],"(CMC)":[168],"model":[169,244],"imposes":[170],"minimum":[171],"but":[172],"essential":[173],"about":[175],"multifactorial":[177],"joint":[178],"leads":[181],"conceptually":[184],"simple":[185],"distribution,":[186],"which":[187,251],"informs":[188],"By":[200],"replacing":[201],"hard":[202],"constraints":[203],"expected":[205],"CMC":[207,243,267,295,313,328],"avoids":[208],"NP-hard":[210],"results":[213],"theoretically":[216],"solvable":[217],"convex":[218,232],"due":[221],"large":[224],"scale":[225],"variables":[227],"constraints,":[229],"standard":[231],"solvers":[233],"do":[234],"not":[235],"work.":[236],"Exploring":[237],"special":[239],"properties":[240],"developed":[246],"iterative":[249],"optimizer,":[250],"reduces":[252],"running":[254],"time":[255],"from":[256,261],"infeasible":[257],"minutes":[259],"days":[262],"seconds.":[264],"We":[265],"applied":[266],"quite":[269],"few":[271],"cutting-edge":[272,345],"including":[275],"detection":[277],"driving":[279],"transcription":[280],"factor,":[281],"scRNA-seq":[282],"normalization,":[283],"cancer-associated":[284],"gene":[285],"identification,":[286],"GO-term":[287],"activity":[288],"transformation,":[289],"quantification":[291],"single-cell-level":[293],"similarity.":[294],"gained":[296],"much":[297],"better":[298],"performance":[299],"than":[300],"other":[301],"methods":[302,342],"respect":[304],"various":[306],"evaluation":[307],"criteria.":[308],"Our":[309],"source":[310],"code":[311],"its":[317],"example":[318],"applications":[319],"found":[322],"at":[323],"https://github.com/yu-lab-vt/CMC":[324],".":[325],"One-Sentence":[326],"Summary":[327],"jointly":[329],"learns":[330],"intertwined":[331],"numerous":[334],"biologival":[337],"outperform":[340],"applications.":[347]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2024-04-17T00:00:00"}