Novel whole-genome analysis methods for Alzheimer's risk prediction

Project Summary AbstractAlzheimerandapos s DiseaseADaffects millions of Americansyet there are no treatments that meaningfully affect disease progression once symptoms manifestThis has shifted the focus to early detection and interventionwhich is thought by many researchers to offer the best chance of slowing or stopping the progression of ADHowevertrials aimed at averting the underlying causes of disease have proven difficult because pathological changes in AD happen well in advance of cognitive declineA widely available genetic test for determining AD risk early in lifewhile prevention might still be possiblewould allow early treatment interventionenrollment in clinical trialsand improved patient stratification for testing treatment effectivenessHoweverdespite recent advancementsgenetic risk prediction modelsGRPMsfor late onset ADLOADlack sufficient discrimination ability to support such applicationsGiven the lack of effective treatments once symptoms have manifested and the socioeconomic consequences at stakethere is a serious unmet need for a widely available GRPM able to accurately assess a patientandapos s risk in middle age or earlierbefore neurodegeneration beginsTo address this needParabon has teamed with AD researchers from Washington University and Emory to develop a GRPM able to accurately predict an individualandapos s risk of developing LOAD at various agesPhase I demonstrated that this GRPMwhich exploits diagnostic heterogeneitynon additiveepistaticinteractions among variantsand machine learningsignificantly outperforms traditional risk factorsIn Phase IIthe GRPM will be further optimizedvalidatedand commercialized as a direct to consumerDTCgenetic health risk assessment testIn Aimthousands of new and existing case and control subjects with genotypes and detailed phenotypes will be addedIn Aimnovel approaches to feature selection for epistatic interactions will be implemented to increase the generalizability of selected featuresIn Aimthe selected genomic features will be used to predict imaging and biomarker endophenotypes of LOADIn Aimthe outof sample endophenotype predictions will be combined into a final predictive model for AD diagnosis that can be applied to new subjects at any agewhich will be validated in an independent replication setFinallyin Aimdata and results will be prepared for scientific publication and submission to the FDA for marketing authorization as a DTC genetic health risk assessment system Project Narrative Alzheimerandapos s DiseaseADaffects millions of Americansyet there are no treatments that significantly slow disease progression once symptoms manifestmaking early intervention crucial to reduce the individual and societal burden of this diseaseThis proposal seeks to create a genetic risk prediction model that can predict an individualandapos s AD risk at any agewhich will be made widely available as a direct to consumer genetic health risk assessmentIt will enable early intervention and life planning for at risk individuals and allow researchers to maximize the probability of detecting treatment effects in clinical trials by assessing patientsandaposunderlying disease risk