biostudies-literatureJohnstone DNCATS NIH HHSNIA NIH HHSe34341https://www.ebi.ac.uk/biostudies/studies/S-EPMC3317783biostudies-literatureUnknown7(4)<h4>Background</h4>Recent Alzheimer's disease (AD) research has focused on finding biomarkers to identify disease at the pre-clinical stage of mild cognitive impairment (MCI), allowing treatment to be initiated before irreversible damage occurs. Many studies have examined brain imaging or cerebrospinal fluid but there is also growing interest in blood biomarkers. The Alzheimer's Disease Neuroimaging Initiative (ADNI) has generated data on 190 plasma analytes in 566 individuals with MCI, AD or normal cognition. We conducted independent analyses of this dataset to identify plasma protein signatures predicting pre-clinical AD.<h4>Methods and findings</h4>We focused on identifying signatures that discriminate cognitively normal controls (n = 54) from individuals with MCI who subsequently progress to AD (n = 163). Based on p value, apolipoprotein E (APOE) showed the strongest difference between these groups (p = 2.3 × 10(-13)). We applied a multivariate approach based on combinatorial optimization ((?,?)-k Feature Set Selection), which retains information about individual participants and maintains the context of interrelationships between different analytes, to identify the optimal set of analytes (signature) to discriminate these two groups. We identified 11-analyte signatures achieving values of sensitivity and specificity between 65% and 86% for both MCI and AD groups, depending on whether APOE was included and other factors. Classification accuracy was improved by considering "meta-features," representing the difference in relative abundance of two analytes, with an 8-meta-feature signature consistently achieving sensitivity and specificity both over 85%. Generating signatures based on longitudinal rather than cross-sectional data further improved classification accuracy, returning sensitivities and specificities of approximately 90%.<h4>Conclusions</h4>Applying these novel analysis approaches to the powerful and well-characterized ADNI dataset has identified sets of plasma biomarkers for pre-clinical AD. While studies of independent test sets are required to validate the signatures, these analyses provide a starting point for developing a cost-effective and minimally invasive test capable of diagnosing AD in its pre-clinical stages.PloS oneMultivariate protein signatures of pre-clinical Alzheimer's disease in the Alzheimer's disease neuroimaging initiative (ADNI) plasma proteome dataset.PMC3317783P30 AG013846P30 AG019610UL1 TR001998U01 AG024904UL1 TR000117R01 AG012101K01 AG030514U19 AG010483P30 AG010129R01 AG022374Crawford KCarmichael OLee VMGrossman HBrewer JRosen HJChertkow HDeCarli CLeon SLord JLMontine TVillanueva-Meyer JWolk DTaylor-Reinwald LPetrella JRMathis CFrank RDuara RWatkins FReeder Sde Leon MJCelmins DDoraiswamy PWu CKPawluczyk SRomirowsky AFletcher ELah JJHsiung GYDeVous MMunic DSalloway SKarlawish JHMintun MATurner RSCapote HNeu SFeldman HJohnson KALee TYBernick CPreda AMoscato PAsthana SAisen PHosein COtt BRBurns JMMacAvoy MGQuinn JSmith CDMintzer JRoberts PSwerdlow RHTremont GKoeppe RAVaron DFarlow MJicha GReynolds BKowall NGreen RCReiman EMdeToledo-Morrell LChen KBrand CSilverman DHBell KLCarlsson CMZimmerman EAFleisher AMilward EASadowsky CAnderson HSPorsteinsson APMiller BLJohnson KJohnson NSchuff NJohnson SDiaz-Arrastia RRusinek HMartinez WKertesz AHonig LSShah RCLerner AMorris JKerwin DLind BVillena TJohnson HJagust WSaykin AJGamst ADale AHeidebrink JLGessert DRosen AScharre DWAlbert MAnderson KAlzheimer's Disease Neuroimaging InitiativeApostolova LPotkin SGThompson PBandy DBelden CKittur SLiu ESchwartz ESPetersen RShen LKornak JBudson AEClark DTinklenberg JOnyike CFox NVanderswag HColeman RMartin KSather TFrey MSpann BMStern YBartzokis GKaye JSabbagh MBartha RMitsis ENorbash ATrost DWalter SKielb SJacobson SBernstein MKilliany RMolchan SKataki MCairns NJOakley MToga AWSantulli RBFelmlee JShaw LLongmire CFHake AMForoud TMSchneider SWeiner MSnyder PJBlank KArnold SESperling RACarson REHudson LBlack SRainka MCaldwell CPearlson GDBeckett LCarroll MJack CRHerring SLopez OLMesulam MMLipowski KGraff-Radford NRJohnstone DDolen SWolday SFoster NOgrocki Pvan Dyck CHBerretta RQuerfurth HMulnard RAStefanovic BKachaturian ZMalloy PGriffith RBates VLu PHGarg PMc-Adams-Ortiz CMarson DGlodzik LSimpson DMWilliamson JDKorecka MHarvey DCorreia SHardy PMartin-Cook KIsmail MHendin BAAnces BDoody RSChowdhury MBrown ADAlexander GPotkin SBorrie MBergman HOlichney JRogers JThai GMakino KMCellar JSBwayo SKSchneider LSSpicer KLevey AIObisesan TOTrojanowki JQMarshall GParfitt FDonohue MMorris JCJohnson PLNguyen DAssaly MTariot PGoldstein BSSink KMThomas RGfalseMultivariate protein signatures of pre-clinical Alzheimer's disease in the Alzheimer's disease neuroimaging initiative (ADNI) plasma proteome dataset.<h4>Background</h4>Recent Alzheimer's disease (AD) research has focused on finding biomarkers to identify disease at the pre-clinical stage of mild cognitive impairment (MCI), allowing treatment to be initiated before irreversible damage occurs. Many studies have examined brain imaging or cerebrospinal fluid but there is also growing interest in blood biomarkers. The Alzheimer's Disease Neuroimaging Initiative (ADNI) has generated data on 190 plasma analytes in 566 individuals with MCI, AD or normal cognition. We conducted independent analyses of this dataset to identify plasma protein signatures predicting pre-clinical AD.<h4>Methods and findings</h4>We focused on identifying signatures that discriminate cognitively normal controls (n = 54) from individuals with MCI who subsequently progress to AD (n = 163). Based on p value, apolipoprotein E (APOE) showed the strongest difference between these groups (p = 2.3 × 10(-13)). We applied a multivariate approach based on combinatorial optimization ((?,?)-k Feature Set Selection), which retains information about individual participants and maintains the context of interrelationships between different analytes, to identify the optimal set of analytes (signature) to discriminate these two groups. We identified 11-analyte signatures achieving values of sensitivity and specificity between 65% and 86% for both MCI and AD groups, depending on whether APOE was included and other factors. Classification accuracy was improved by considering "meta-features," representing the difference in relative abundance of two analytes, with an 8-meta-feature signature consistently achieving sensitivity and specificity both over 85%. Generating signatures based on longitudinal rather than cross-sectional data further improved classification accuracy, returning sensitivities and specificities of approximately 90%.<h4>Conclusions</h4>Applying these novel analysis approaches to the powerful and well-characterized ADNI dataset has identified sets of plasma biomarkers for pre-clinical AD. While studies of independent test sets are required to validate the signatures, these analyses provide a starting point for developing a cost-effective and minimally invasive test capable of diagnosing AD in its pre-clinical stages.2012-01-01T00:00:00Z20122021-03-18T08:07:23Z2019-03-26T23:12:58ZS-EPMC33177832248516810.1371/journal.pone.0034341