{"id":"https://openalex.org/W2972820428","doi":null,"title":"The Role of Exploratory Data Analysis and Pre-processing in Omics Studies","display_name":"The Role of Exploratory Data Analysis and Pre-processing in Omics Studies","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2972820428","mag":"2972820428"},"language":"en","primary_location":{"id":"pmh:oai:escholarship.org/ark:/13030/qt7xd95799","doi":null,"is_oa":true,"landing_page_url":"https://escholarship.org/uc/item/7xd95799","pdf_url":"https://escholarship.org/uc/item/7xd95799","source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"etd"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://escholarship.org/uc/item/7xd95799","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081025016","display_name":"Courtney Schiffman","orcid":"https://orcid.org/0000-0003-4126-9033","observed_orcids":["https://orcid.org/0000-0003-4126-9033"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Courtney Schiffman","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-4126-9033","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5081025016"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"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/T11289","display_name":"Single-cell and spatial transcriptomics","score":0.9965999722480774,"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":0.9965999722480774,"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":0.00279999990016222,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.00019999999494757503,"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/exploratory-data-analysis","display_name":"exploratory data analysis","score":0.9340000152587891},{"id":"https://openalex.org/keywords/single-cell-rna-sequencing","display_name":"single-cell RNA sequencing","score":0.8849999904632568},{"id":"https://openalex.org/keywords/cell-subpopulation-identification","display_name":"cell subpopulation identification","score":0.6899999976158142},{"id":"https://openalex.org/keywords/cell-heterogeneity","display_name":"cellular heterogeneity","score":0.746999979019165},{"id":"https://openalex.org/keywords/differential-gene-expression","display_name":"differential gene expression","score":0.6919999718666077},{"id":"https://openalex.org/keywords/ovarian-cancer","display_name":"ovarian cancer","score":0.5299999713897705},{"id":"https://openalex.org/keywords/breast-cancer","display_name":"breast cancer","score":0.36399999260902405},{"id":"https://openalex.org/keywords/breast-cancer-subtypes","display_name":"breast cancer subtypes","score":0.3779999911785126},{"id":"https://openalex.org/keywords/breast-cancer-metastasis","display_name":"breast cancer metastasis","score":0.31299999356269836},{"id":"https://openalex.org/keywords/breast-cancer-recurrence","display_name":"breast cancer recurrence","score":0.5460000038146973}],"concepts":[{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6364923715591431},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.5764227509498596},{"id":"https://openalex.org/C120894424","wikidata":"https://www.wikidata.org/wiki/Q1322871","display_name":"Exploratory data analysis","level":2,"score":0.5623717904090881},{"id":"https://openalex.org/C157585117","wikidata":"https://www.wikidata.org/wiki/Q158666","display_name":"Omics","level":2,"score":0.49750497937202454},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49198076128959656},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.38862505555152893},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3854580223560333},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.288290798664093},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.2287108302116394},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.21627071499824524},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:escholarship.org/ark:/13030/qt7xd95799","doi":null,"is_oa":true,"landing_page_url":"https://escholarship.org/uc/item/7xd95799","pdf_url":"https://escholarship.org/uc/item/7xd95799","source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"etd"},{"id":"mag:2972820428","doi":null,"is_oa":false,"landing_page_url":"https://escholarship.org/content/qt7xd95799/qt7xd95799.pdf?t=pwzt8l","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:escholarship.org/ark:/13030/qt7xd95799","doi":null,"is_oa":true,"landing_page_url":"https://escholarship.org/uc/item/7xd95799","pdf_url":"https://escholarship.org/uc/item/7xd95799","source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"etd"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2972820428.pdf","grobid_xml":"https://content.openalex.org/works/W2972820428.grobid-xml"},"referenced_works_count":78,"referenced_works":["https://openalex.org/W1125399146","https://openalex.org/W1508955751","https://openalex.org/W1528461042","https://openalex.org/W1631320694","https://openalex.org/W1964010911","https://openalex.org/W1964434000","https://openalex.org/W1971358177","https://openalex.org/W1971697672","https://openalex.org/W1974489494","https://openalex.org/W1977397173","https://openalex.org/W1979283544","https://openalex.org/W1982448585","https://openalex.org/W1982900838","https://openalex.org/W1988391018","https://openalex.org/W1992085043","https://openalex.org/W1994708664","https://openalex.org/W1999914938","https://openalex.org/W2005968685","https://openalex.org/W2014691022","https://openalex.org/W2021341670","https://openalex.org/W2037510517","https://openalex.org/W2039077785","https://openalex.org/W2039521726","https://openalex.org/W2041158708","https://openalex.org/W2072752513","https://openalex.org/W2073939393","https://openalex.org/W2096863518","https://openalex.org/W2099500182","https://openalex.org/W2104057864","https://openalex.org/W2109890799","https://openalex.org/W2119494825","https://openalex.org/W2120865735","https://openalex.org/W2122528658","https://openalex.org/W2123055140","https://openalex.org/W2129915465","https://openalex.org/W2130437228","https://openalex.org/W2132014479","https://openalex.org/W2132027935","https://openalex.org/W2135046866","https://openalex.org/W2145533440","https://openalex.org/W2145734950","https://openalex.org/W2145795890","https://openalex.org/W2149542744","https://openalex.org/W2149874345","https://openalex.org/W2156807105","https://openalex.org/W2157114208","https://openalex.org/W2159299299","https://openalex.org/W2159703296","https://openalex.org/W2168342464","https://openalex.org/W2215673087","https://openalex.org/W2341820027","https://openalex.org/W2343956310","https://openalex.org/W2346143774","https://openalex.org/W2460278139","https://openalex.org/W2473258837","https://openalex.org/W2529012673","https://openalex.org/W2544655068","https://openalex.org/W2583383988","https://openalex.org/W2588977229","https://openalex.org/W2612502013","https://openalex.org/W2614303923","https://openalex.org/W2743576058","https://openalex.org/W2763572134","https://openalex.org/W2766131086","https://openalex.org/W2777966573","https://openalex.org/W2782861423","https://openalex.org/W2783038304","https://openalex.org/W2783644856","https://openalex.org/W2793217266","https://openalex.org/W2803664483","https://openalex.org/W2897716935","https://openalex.org/W2899015035","https://openalex.org/W2910032875","https://openalex.org/W2918073486","https://openalex.org/W2923506657","https://openalex.org/W2950340687","https://openalex.org/W2951337536","https://openalex.org/W3104066961"],"related_works":["https://openalex.org/W2959048234","https://openalex.org/W4282923574","https://openalex.org/W4393315270","https://openalex.org/W7126345192","https://openalex.org/W4323833126","https://openalex.org/W7163522247","https://openalex.org/W6903803560","https://openalex.org/W2616499471","https://openalex.org/W7055598029","https://openalex.org/W4394749467"],"abstract_inverted_index":{"Beginning":[0],"with":[1,63,487,572,623,628,792,852],"microarray":[2],"data":[3,21,51,71,94,101,110,120,144,148,182,225,414,454,588,591,603,666,715,732,846],"in":[4,11,98,121,231,314,344,458,490,517,531,598,646,660,770,807,845],"the":[5,12,44,59,77,80,89,169,187,247,253,288,292,333,365,382,421,459,468,473,542,611,673,719],"90's,":[6],"omics":[7,41,100,119,602],"technologies":[8],"have":[9],"exploded":[10],"last":[13],"three":[14],"decades.":[15],"Proteomic,":[16],"metabolomic,":[17],"genomic":[18],"and":[19,33,50,66,73,96,103,116,129,159,184,216,375,411,432,456,475,492,520,581,590,652,668,699,710,759,813,827],"epigenomic":[20],"are":[22,500,734],"used":[23,250,446,585],"to":[24,28,34,75,87,104,113,123,131,135,156,161,165,173,201,209,238,251,262,297,302,387,396,471,508,527,544,594,618,644,649,717],"understand":[25,76,124],"disease":[26,37,657],"etiology,":[27],"detect":[29,509],"diseases":[30],"early":[31],"on":[32,223,447,452,752,797],"identify":[35,132],"novel":[36,258,746],"therapies.":[38],"Almost":[39],"every":[40],"dataset":[42,410],"is":[43,86,200,246,350,424,640,670,705,825,837],"result":[45],"of":[46,107,118,127,153,189,195,220,228,274,283,300,360,367,381,426,461,465,496,512,608,614,634,676,686,756,775,809,842],"a":[47,151,257,272,304,320,339,372,389,397,405,629,706,726],"complicated":[48],"experiment":[49],"collection":[52],"process.":[53],"The":[54,416,801],"unwanted":[55,133],"variation":[56],"introduced":[57],"during":[58,142,556],"experimental":[60],"process,":[61],"along":[62],"biological":[64,137,211,596,721,843],"complexity":[65],"heterogeneity,":[67,215],"requires":[68,319],"extensive":[69,114],"exploratory":[70,93,143,181,453,587,665],"analysis":[72,95,111,145,183,455,589,667,675,694],"pre-processing":[74,97,185,457,592,669],"variability":[78],"within":[79,186,205],"data.The":[81],"goal":[82,194],"throughout":[83],"this":[84,599],"dissertation":[85],"demonstrate":[88,180],"need":[90,707],"for":[91,280,352,364,672,708,713,729,748,840],"appropriate":[92],"various":[99],"types,":[102],"provide":[105],"examples":[106],"such.":[108],"Exploratory":[109],"refers":[112],"visualization":[115],"summarization":[117],"order":[122],"distributional":[125],"properties":[126],"samples":[128,158,774],"features,":[130,160],"variation,":[134],"determine":[136],"patterns,":[138],"etc.":[139],"Work":[140],"done":[141],"informs":[146],"subsequent":[147,692],"pre-processing,":[149],"or":[150,167,434,558],"series":[152],"steps":[154],"taken":[155],"filter":[157],"impute":[162],"missing":[163,757],"values,":[164,758],"normalize":[166],"transform":[168],"data,":[170],"etc.,":[171],"prior":[172,716],"performing":[174],"formal":[175],"statistical":[176,609,693],"analyses.Here,":[177],"we":[178,502,523,540,662,724,786],"first":[179,270],"context":[188,460],"single-cell":[190],"RNA-sequencing":[191,198],"data.":[192,268,463,679],"One":[193],"single":[196],"cell":[197,206,241,369],"(scRNA-seq)":[199],"expose":[202],"possible":[203],"heterogeneity":[204],"populations":[207],"due":[208],"meaningful,":[210],"variation.":[212],"Examining":[213],"cell-to-cell":[214,264],"further,":[217],"identifying":[218,240],"subpopulations":[219,242,362],"cells":[221,330,359,380],"based":[222,751],"scRNA-seq":[224,267,403,409],"has":[226],"been":[227],"common":[229],"interest":[230],"life":[232],"science":[233],"research.":[234],"A":[235],"key":[236],"component":[237],"successfully":[239],"(or":[243],"clustering":[244,316,417],"cells)":[245,301],"(dis)similarity":[248,321,346,443],"measure":[249,306,325,423],"group":[252],"cells.":[254,284,309],"We":[255,393,584],"introduce":[256],"measure,":[259],"named":[260],"SIDEseq,":[261],"assess":[263],"similarity":[265,305,334],"using":[266],"SIDEseq":[269,285,310,395,422],"identifies":[271],"list":[273],"putative":[275],"differentially":[276],"expressed":[277],"(DE)":[278],"genes":[279],"each":[281],"pair":[282],"then":[286,450],"integrates":[287],"information":[289,327,357,377],"from":[290,328,358,371,378,467,549,773,832,848],"all":[291,298,329],"DE":[293],"gene":[294],"lists":[295],"(corresponding":[296],"pairs":[299],"build":[303],"between":[307,335,430,621],"two":[308,337,353,782],"can":[311,690],"be":[312],"implemented":[313],"any":[315,336],"algorithm":[317],"that":[318,420,485,525,654,689,733,767,795],"matrix.":[322],"This":[323,348],"new":[324,601],"incorporates":[326],"when":[331,445],"evaluating":[332],"cells,":[338,431],"characteristic":[340],"not":[341],"commonly":[342],"found":[343,617],"existing":[345],"measures.":[347],"property":[349],"advantageous":[351],"reasons:":[354],"(a)":[355],"borrowing":[356],"different":[361],"allows":[363],"investigation":[366],"pair-wise":[368],"relationships":[370,429],"global":[373],"perspective,":[374],"(b)":[376],"other":[379,582],"same":[383],"subpopulation":[384],"could":[385],"help":[386],"ensure":[388],"robust":[390],"relationship":[391],"assessment.":[392],"applied":[394,541,643],"newly":[398],"generated":[399,735,769],"human":[400,407,513,518,776],"ovarian":[401],"cancer":[402],"dataset,":[404],"public":[406,783],"embryo":[408],"several":[412,441],"simulated":[413],"sets.":[415],"results":[418],"suggest":[419],"capable":[425],"uncovering":[427],"important":[428],"outperforms":[433],"at":[435],"least":[436],"does":[437],"as":[438,440,696,779,781],"well":[439,780],"popular":[442],"measures":[444],"these":[448,497],"datasets.We":[449],"focus":[451],"adductomics":[462,506,638],"Metabolism":[464],"chemicals":[466,651],"diet,":[469],"exposures":[470,648],"xenobiotics,":[472],"microbiome,":[474],"lifestyle":[476],"factors":[477],"(e.g.,":[478,575],"smoking,":[479],"alcohol":[480],"intake)":[481],"produce":[482],"reactive":[483,498,650],"electrophiles":[484],"react":[486],"nucleophilic":[488],"sites":[489],"DNA":[491],"proteins.":[493],"Since":[494],"many":[495],"intermediates":[499],"unknown,":[501],"reported":[503],"an":[504,606],"untargeted":[505,677,833],"method":[507,543,639,791],"Cys34":[510,567,612],"modifications":[511],"serum":[514,519],"albumin":[515],"(HSA)":[516],"plasma.":[521],"Here,":[522,723],"extended":[524],"assay":[526],"investigate":[528],"HSA-Cys34":[529,562],"adducts":[530,563],"archived":[532,546],"newborn":[533],"dried":[534],"blood":[535,777],"spots":[536],"(DBS).":[537],"As":[538],"proof-of-principle,":[539],"49":[545],"DBS":[547],"collected":[548],"newborns":[550,622],"whose":[551],"mothers":[552,627],"either":[553],"actively":[554],"smoked":[555],"pregnancy":[557],"were":[559,564,768],"nonsmokers.":[560],"Twenty-six":[561],"detected,":[565],"including":[566],"oxidation":[568],"products,":[569],"mixed":[570],"disulfides":[571],"low-molecular-weight":[573],"thiols":[574],"cysteine,":[576],"homocysteine,":[577],"glutathione,":[578],"cysteinylglycine,":[579],"etc.),":[580],"modifications.":[583],"careful":[586],"methods":[593,712,747,794],"uncover":[595],"signal":[597],"relatively":[600],"type.":[604],"With":[605],"ensemble":[607],"approaches,":[610],"adduct":[613],"cyanide":[615],"was":[616],"consistently":[619],"discriminate":[620],"smoking":[624],"versus":[625],"nonsmoking":[626],"mean":[630],"fold":[631],"change":[632],"(smoking/nonsmoking)":[633],"1.31.":[635],"Our":[636,742,820],"DBS-based":[637],"currently":[641],"being":[642],"discover":[645],"utero":[647],"metabolites":[653],"may":[655],"influence":[656],"risks":[658],"later":[659],"life.Finally,":[661],"show":[663],"how":[664],"essential":[671],"successful":[674],"metabolomics":[678,681,731,765,834],"Untargeted":[680],"datasets":[682,766],"contain":[683],"large":[684],"proportions":[685,755],"uninformative":[687,830],"features":[688,750,812,831],"impede":[691],"such":[695],"biomarker":[697],"discovery":[698],"metabolic":[700],"pathway":[701],"analysis.":[702],"Thus,":[703],"there":[704],"versatile":[709],"data-adaptive":[711,727,743,789,802,822],"filtering":[714,730,749,790,823],"investigating":[718],"underlying":[720],"phenomena.":[722],"propose":[725],"pipeline":[728,744,824],"by":[736],"liquid":[737],"chromatography-mass":[738],"spectrometry":[739],"(LC-MS)":[740],"platforms.":[741],"includes":[745],"blank":[753],"samples,":[754],"estimated":[760],"intra-class":[761],"correlation":[762],"coefficients.":[763],"Using":[764],"our":[771,788],"laboratory":[772],"serum,":[778],"LC-MS":[784],"datasets,":[785],"compared":[787],"traditional":[793,805],"rely":[796],"non-method":[798],"specific":[799],"thresholds.":[800],"approach":[803],"outperformed":[804],"approaches":[806],"terms":[808],"removing":[810],"noisy":[811],"retaining":[814],"high":[815],"quality,":[816],"biologically":[817],"informative":[818],"ones.":[819],"proposed":[821],"intuitive":[826],"effectively":[828],"removes":[829],"datasets.":[835],"It":[836],"particularly":[838],"relevant":[839],"interrogation":[841],"phenomena":[844],"derived":[847],"complex":[849],"matrices":[850],"associated":[851],"biospecimens.":[853]},"counts_by_year":[],"updated_date":"2026-09-26T08:19:03.415552","created_date":"2019-09-19T00:00:00"}
