A Comprehensive Machine Learning Framework for the Exact Prediction of the Age of Onset in Familial and Sporadic Alzheimer's Disease.
Ontology highlight
ABSTRACT:
SUBMITTER: Velez JI
PROVIDER: S-EPMC8156402 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:ObjectiveTo determine whether the extent of overlap of the genetic architecture among the sporadic late-onset Alzheimer's Disease (sLOAD), familial late-onset AD (fLOAD), sporadic early-onset AD (sEOAD), and autosomal dominant early-onset AD (eADAD).MethodsPolygenic risk scores (PRSs) were constructed using previously identified 21 genome-wide significant loci for LOAD risk.ResultsWe found that there is an overlap in the genetic architecture among sEOAD, fLOAD, and sLOAD. The highest association of the PRS and risk (odds ratio [OR] = 2.27; P = 1.29 × 10-7) was observed in sEOAD, followed by fLOAD (OR = 1.75; P = 1.12 × 10-7) and sLOAD (OR = 1.40; P = 1.21 × 10-3). The PRS was associated with cerebrospinal fluid ptau181-Aβ42 on eADAD (P = 4.36 × 10-2).ConclusionOur analysis confirms that the genetic factors identified for LOAD modulate risk in sLOAD and fLOAD and also sEOAD cohorts. Specifically, our results suggest that the burden of these risk variants is associated with familial clustering and earlier onset of AD. Although these variants are not associated with risk in the eADAD, they may be modulating age at onset.
| S-EPMC5803427 | biostudies-literature
Project description:Presenilin-1 (PSEN1) mutations cause familial Alzheimer's disease (FAD) characterized by early age of onset (AoO). Examination of a large kindred harboring the PSEN1-E280A mutation reveals a range of AoO spanning 30 years. The pathophysiological drivers and clinical impact of AoO variation in this population are unknown. We examined brains of 23 patients focusing on generation and deposition of beta-amyloid (Aβ) and Tau pathology profile. In 14 patients distributed at the extremes of AoO, we performed whole-exome capture to identify genotype-phenotype correlations. We also studied kinome activity, proteasome activity, and protein polyubiquitination in brain tissue, associating it with Tau phosphorylation profiles. PSEN1-E280A patients showed a bimodal distribution for AoO. Besides AoO, there were no clinical differences between analyzed groups. Despite the effect of mutant PSEN1 on production of Aβ, there were no relevant differences between groups in generation and deposition of Aβ. However, differences were found in hyperphosphorylated Tau (pTau) pathology, where early onset patients showed severe pathology with diffuse aggregation pattern associated with increased activation of stress kinases. In contrast, late-onset patients showed lesser pTau pathology and a distinctive kinase activity. Furthermore, we identified new protective genetic variants affecting ubiquitin-proteasome function in early onset patients, resulting in higher ubiquitin-dependent degradation of differentially phosphorylated Tau. In PSEN1-E280A carriers, altered γ-secretase activity and resulting Aβ accumulation are prerequisites for early AoO. However, Tau hyperphosphorylation pattern, and its degradation by the proteasome, drastically influences disease onset in individuals with otherwise similar Aβ pathology, hinting toward a multifactorial model of disease for FAD. In sporadic AD (SAD), a wide range of heterogeneity, also influenced by Tau pathology, has been identified. Thus, Tau-induced heterogeneity is a common feature in both AD variants, suggesting that a multi-target therapeutic approach should be used to treat AD.
| S-EPMC7847436 | biostudies-literature
Project description:Alzheimer's disease (AD) is characterised by the aggregation of two quite different proteins, namely, amyloid-beta (A?), which forms extracellular plaques, and tau, the main component of cytoplasmic neurofibrillary tangles. The amyloid hypothesis proposes that A? plaques precede tangle formation but there is still much controversy concerning the order of events and the linkage between A? and tau alterations is still unknown. Mathematical modelling has become an essential tool for generating and evaluating hypotheses involving complex systems. We have therefore used this approach to discover the most probable pathway linking A? and tau. The model supports a complex pathway linking A? and tau via GSK3?, p53, and oxidative stress. Importantly, the pathway contains a cycle with multiple points of entry. It is this property of the pathway which enables the model to be consistent with both the amyloid hypothesis for familial AD and a more complex pathway for sporadic forms.
| S-EPMC3296276 | biostudies-literature
Project description:Alzheimer's disease (AD) is a common, genetically complex, fatal neurodegenerative disorder of late life. Although several genes are known to play a role in early-onset AD, identification of the genetic basis of late onset AD (LOAD) has been challenging, with only the APOE gene known to have a high contribution to both AD risk and age-at-onset. Here, we present the first genome-scan analysis of the complete, well-characterized University of Washington LOAD sample of 119 pedigrees, using age-at-onset as the trait of interest. The analysis approach used allows for a multilocus trait model while at the same time accommodating age censoring, effects of APOE as a known genetic covariate, and full pedigree and marker information. The results provide strong evidence for linkage of loci contributing to age-at-onset to genomic regions on chromosome 6q16.3, and to 19q13.42 in the region of the APOE locus. There was evidence for interaction between APOE and the locus on chromosome 6q and suggestive evidence for linkage to chromosomes 11p13, 15q12-14, and 19p13.12. These results provide the first independent confirmation of an AD age-at-onset locus on chromosome 6 and suggest that further efforts towards identifying the underlying causal locus or loci are warranted.
| S-EPMC3654841 | biostudies-literature
Project description:Mild cognitive impairment (MCI) is a transitional stage between age-related cognitive decline and Alzheimer's disease (AD). For the effective treatment of AD, it would be important to identify MCI patients at high risk for conversion to AD. In this study, we present a novel magnetic resonance imaging (MRI)-based method for predicting the MCI-to-AD conversion from one to three years before the clinical diagnosis. First, we developed a novel MRI biomarker of MCI-to-AD conversion using semi-supervised learning and then integrated it with age and cognitive measures about the subjects using a supervised learning algorithm resulting in what we call the aggregate biomarker. The novel characteristics of the methods for learning the biomarkers are as follows: 1) We used a semi-supervised learning method (low density separation) for the construction of MRI biomarker as opposed to more typical supervised methods; 2) We performed a feature selection on MRI data from AD subjects and normal controls without using data from MCI subjects via regularized logistic regression; 3) We removed the aging effects from the MRI data before the classifier training to prevent possible confounding between AD and age related atrophies; and 4) We constructed the aggregate biomarker by first learning a separate MRI biomarker and then combining it with age and cognitive measures about the MCI subjects at the baseline by applying a random forest classifier. We experimentally demonstrated the added value of these novel characteristics in predicting the MCI-to-AD conversion on data obtained from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. With the ADNI data, the MRI biomarker achieved a 10-fold cross-validated area under the receiver operating characteristic curve (AUC) of 0.7661 in discriminating progressive MCI patients (pMCI) from stable MCI patients (sMCI). Our aggregate biomarker based on MRI data together with baseline cognitive measurements and age achieved a 10-fold cross-validated AUC score of 0.9020 in discriminating pMCI from sMCI. The results presented in this study demonstrate the potential of the suggested approach for early AD diagnosis and an important role of MRI in the MCI-to-AD conversion prediction. However, it is evident based on our results that combining MRI data with cognitive test results improved the accuracy of the MCI-to-AD conversion prediction.
| S-EPMC5957071 | biostudies-literature
Project description:BackgroundLate-Onset Alzheimer's Disease (LOAD) is a leading form of dementia. There is no effective cure for LOAD, leaving the treatment efforts to depend on preventive cognitive therapies, which stand to benefit from the timely estimation of the risk of developing the disease. Fortunately, a growing number of Machine Learning methods that are well positioned to address this challenge are becoming available.ResultsWe conducted systematic comparisons of representative Machine Learning models for predicting LOAD from genetic variation data provided by the Alzheimer's Disease Neuroimaging Initiative (ADNI) cohort. Our experimental results demonstrate that the classification performance of the best models tested yielded ∼72% of area under the ROC curve.ConclusionsMachine learning models are promising alternatives for estimating the genetic risk of LOAD. Systematic machine learning model selection also provides the opportunity to identify new genetic markers potentially associated with the disease.
| S-EPMC6915925 | biostudies-literature
Project description:Most approaches to machine learning from electronic health data can only predict a single endpoint. The ability to simultaneously simulate dozens of patient characteristics is a crucial step towards personalized medicine for Alzheimer's Disease. Here, we use an unsupervised machine learning model called a Conditional Restricted Boltzmann Machine (CRBM) to simulate detailed patient trajectories. We use data comprising 18-month trajectories of 44 clinical variables from 1909 patients with Mild Cognitive Impairment or Alzheimer's Disease to train a model for personalized forecasting of disease progression. We simulate synthetic patient data including the evolution of each sub-component of cognitive exams, laboratory tests, and their associations with baseline clinical characteristics. Synthetic patient data generated by the CRBM accurately reflect the means, standard deviations, and correlations of each variable over time to the extent that synthetic data cannot be distinguished from actual data by a logistic regression. Moreover, our unsupervised model predicts changes in total ADAS-Cog scores with the same accuracy as specifically trained supervised models, additionally capturing the correlation structure in the components of ADAS-Cog, and identifies sub-components associated with word recall as predictive of progression.
| S-EPMC6754403 | biostudies-other
Project description:Trisomy 21 and the consequent extra copy of the amyloid precursor protein (APP) gene and increased beta-amyloid (Aβ) peptide production underlie the universal development of Alzheimer's disease (AD) pathology and high risk of AD dementia in people with Down syndrome (DS). Trisomy 21 and other forms of aneuploidy also arise among neurons and peripheral cells in both sporadic and familial AD and in mouse and cell models thereof, reinforcing the conclusion that AD and DS are two sides of the same coin. The demonstration that 90% of the neurodegeneration in AD can be attributed to the selective loss of aneuploid neurons generated over the course of the disease indicates that aneuploidy is an essential feature of the pathogenic pathway leading to the depletion of neuronal cell populations. Trisomy 21 mosaicism also occurs in neurons and other cells from patients with Niemann-Pick C1 disease and from patients with familial or sporadic frontotemporal lobar degeneration (FTLD), as well as in their corresponding mouse and cell models. Biochemical studies have shown that Aβ induces mitotic spindle defects, chromosome mis-segregation, and aneuploidy in cultured cells by inhibiting specific microtubule motors required for mitosis. These data indicate that neuronal trisomy 21 and other types of aneuploidy characterize and likely contribute to multiple neurodegenerative diseases and are a valid target for therapeutic intervention. For example, reducing extracellular calcium or treating cells with lithium chloride (LiCl) blocks the induction of trisomy 21 by Aβ. The latter finding is relevant in light of recent reports of a lowered risk of dementia in bipolar patients treated with LiCl and in the stabilization of cognition in AD patients treated with LiCl.
| S-EPMC5570437 | biostudies-other
Project description:INTRODUCTION:Developing cross-validated multi-biomarker models for the prediction of the rate of cognitive decline in Alzheimer's disease (AD) is a critical yet unmet clinical challenge. METHODS:We applied support vector regression to AD biomarkers derived from cerebrospinal fluid, structural magnetic resonance imaging (MRI), amyloid-PET and fluorodeoxyglucose positron-emission tomography (FDG-PET) to predict rates of cognitive decline. Prediction models were trained in autosomal-dominant Alzheimer's disease (ADAD, n = 121) and subsequently cross-validated in sporadic prodromal AD (n = 216). The sample size needed to detect treatment effects when using model-based risk enrichment was estimated. RESULTS:A model combining all biomarker modalities and established in ADAD predicted the 4-year rate of decline in global cognition (R2 = 24%) and memory (R2 = 25%) in sporadic AD. Model-based risk-enrichment reduced the sample size required for detecting simulated intervention effects by 50%-75%. DISCUSSION:Our independently validated machine-learning model predicted cognitive decline in sporadic prodromal AD and may substantially reduce sample size needed in clinical trials in AD.
| S-EPMC7222030 | biostudies-literature
Project description:Our understanding of Alzheimer's disease pathogenesis is currently limited by difficulties in obtaining live neurons from patients and the inability to model the sporadic form of the disease. It may be possible to overcome these challenges by reprogramming primary cells from patients into induced pluripotent stem cells (iPSCs). Here we reprogrammed primary fibroblasts from two patients with familial Alzheimer's disease, both caused by a duplication of the amyloid-? precursor protein gene (APP; termed APP(Dp)), two with sporadic Alzheimer's disease (termed sAD1, sAD2) and two non-demented control individuals into iPSC lines. Neurons from differentiated cultures were purified with fluorescence-activated cell sorting and characterized. Purified cultures contained more than 90% neurons, clustered with fetal brain messenger RNA samples by microarray criteria, and could form functional synaptic contacts. Virtually all cells exhibited normal electrophysiological activity. Relative to controls, iPSC-derived, purified neurons from the two APP(Dp) patients and patient sAD2 exhibited significantly higher levels of the pathological markers amyloid-?(1-40), phospho-tau(Thr?231) and active glycogen synthase kinase-3? (aGSK-3?). Neurons from APP(Dp) and sAD2 patients also accumulated large RAB5-positive early endosomes compared to controls. Treatment of purified neurons with ?-secretase inhibitors, but not ?-secretase inhibitors, caused significant reductions in phospho-Tau(Thr?231) and aGSK-3? levels. These results suggest a direct relationship between APP proteolytic processing, but not amyloid-?, in GSK-3? activation and tau phosphorylation in human neurons. Additionally, we observed that neurons with the genome of one sAD patient exhibited the phenotypes seen in familial Alzheimer's disease samples. More generally, we demonstrate that iPSC technology can be used to observe phenotypes relevant to Alzheimer's disease, even though it can take decades for overt disease to manifest in patients.
| S-EPMC3338985 | biostudies-literature