Dataset Information

An Efficient Classifier for Alzheimer's Disease Genes Identification.

ABSTRACT: Alzheimer's disease (AD) is considered to one of 10 key diseases leading to death in humans. AD is considered the main cause of brain degeneration, and will lead to dementia. It is beneficial for affected patients to be diagnosed with the disease at an early stage so that efforts to manage the patient can begin as soon as possible. Most existing protocols diagnose AD by way of magnetic resonance imaging (MRI). However, because the size of the images produced is large, existing techniques that employ MRI technology are expensive and time-consuming to perform. With this in mind, in the current study, AD is predicted instead by the use of a support vector machine (SVM) method based on gene-coding protein sequence information. In our proposed method, the frequency of two consecutive amino acids is used to describe the sequence information. The accuracy of the proposed method for identifying AD is 85.7%, which is demonstrated by the obtained experimental results. The experimental results also show that the sequence information of gene-coding proteins can be used to predict AD.

SUBMITTER: Xu L

PROVIDER: S-EPMC6321377 | biostudies-other | 2018 Nov

REPOSITORIES: biostudies-other

ACCESS DATA

Publications

An Efficient Classifier for Alzheimer's Disease Genes Identification.

Xu Lei L Liang Guangmin G Liao Changrui C Chen Gin-Den GD Chang Chi-Chang CC

Molecules (Basel, Switzerland) 20181129 12

Alzheimer's disease (AD) is considered to one of 10 key diseases leading to death in humans. AD is considered the main cause of brain degeneration, and will lead to dementia. It is beneficial for affected patients to be diagnosed with the disease at an early stage so that efforts to manage the patient can begin as soon as possible. Most existing protocols diagnose AD by way of magnetic resonance imaging (MRI). However, because the size of the images produced is large, existing techniques that em ...[more]

PMID: 30501121

Similar Datasets

Project description:Alzheimer's disease (AD) is the leading cause of dementia worldwide, with recent studies highlighting the potential role of immunogenic cell death (ICD) in the pathogenesis of this neurodegenerative disorder. A total of 52 healthy controls and 64 patients with AD were included. Compared to the controls, the patients with AD exhibited 2392 differentially expressed genes (DEGs), of which 1015 and 1377 were upregulated and downregulated genes, respectively. Among them, nine common genes were identified by intersecting the AD-related module genes with the DEGs and ICD-associated genes. Gene ontology (GO)analysis further revealed "positive regulation of cytokine production" as the most significant term. Moreover, the enriched molecular functions were primarily related to the inflammatory body complex, while the overlapping genes were significantly enriched in lipopolysaccharide binding. Kyoto encyclopedia of genes and genomes (KEGG) analysis also indicated that these overlapping genes were mainly enriched in immunity, inflammation, and lipid metabolism pathways. Furthermore, the following four hub genes were detected using machine learning algorithms: P2RX7, HSP90AA1, NT5E, and NLRP3. These genes demonstrated significant differences in expression between the AD and healthy control groups (P < 0.05). Additionally, the area under the curve values of these four genes were all > 0.7, indicating their potential diagnostic value for AD. We further validated the protein levels of these four genes in the hippocampus of 3xTg-AD and C57BL/6J mice, showing P2RX7 and HSP90AA1 expression levels consistent with the previously analyzed trends. Finally, the single-sample gene set enrichment analysis (ssGSEA) algorithm provided additional evidence by demonstrating the crucial role of immune cell infiltration and its link with the hub genes in AD progression. Our study results suggest that ICD-mediated elevation of HSP90AA1 and P2RX7 levels and the resulting induction of tau hyperphosphorylation and neuroinflammation are vital in the AD pathogenic mechanism.

Project description:Fully automated machine learning methods based on structural magnetic resonance imaging (MRI) data can assist radiologists in the diagnosis of Alzheimer's disease (AD). These algorithms require large data sets to learn the separation of subjects with and without AD. Training and test data may come from heterogeneous hardware settings, which can potentially affect the performance of disease classification. A total of 518 MRI sessions from 226 healthy controls and 191 individuals with probable AD from the multicenter Alzheimer's Disease Neuroimaging Initiative (ADNI) were used to investigate whether grouping data by acquisition hardware (i.e. vendor, field strength, coil system) is beneficial for the performance of a support vector machine (SVM) classifier, compared to the case where data from different hardware is mixed. We compared the change of the SVM decision value resulting from (a) changes in hardware against the effect of disease and (b) changes resulting simply from rescanning the same subject on the same machine. Maximum accuracy of 87% was obtained with a training set of all 417 subjects. Classifiers trained with 95 subjects in each diagnostic group and acquired with heterogeneous scanner settings had an empirical detection accuracy of 84.2±2.4% when tested on an independent set of the same size. These results mirror the accuracy reported in recent studies. Encouragingly, classifiers trained on images acquired with homogenous and heterogeneous hardware settings had equivalent cross-validation performances. Two scans of the same subject acquired on the same machine had very similar decision values and were generally classified into the same group. Higher variation was introduced when two acquisitions of the same subject were performed on two scanners with different field strengths. The variation was unbiased and similar for both diagnostic groups. The findings of the study encourage the pooling of data from different sites to increase the number of training samples and thereby improving performance of disease classifiers. Although small, a change in hardware could lead to a change of the decision value and thus diagnostic grouping. The findings of this study provide estimators for diagnostic accuracy of an automated disease diagnosis method involving scans acquired with different sets of hardware. Furthermore, we show that the level of confidence in the performance estimation significantly depends on the size of the training sample, and hence should be taken into account in a clinical setting.

Project description:Currently, Alzheimer's disease (AD) and type 2 diabetes mellitus (T2DM) are widely prevalent in the elderly population, and accumulating evidence implies a strong link between them. For example, patients with T2DM have a higher risk of developing neurocognitive disorders, including AD, but the exact mechanisms are still unclear. This time, by combining bioinformatics analysis and in vivo experimental validation, we attempted to find a common biological link between AD and T2DM. We firstly downloaded the gene expression profiling (AD: GSE122063; T2DM: GSE161355) derived from the temporal cortex. To find the associations, differentially expressed genes (DEGs) of the two datasets were filtered and intersected. Based on them, enrichment analysis was carried out, and the least absolute shrinkage and selection operator (LASSO) logistic regression and support vector machine-recursive feature elimination (SVM-RFE) algorithms were used to identify the specific genes. After verifying in the external dataset and in the samples from the AD and type 2 diabetes animals, the shared targets of the two diseases were finally determined. Based on them, the ceRNA networks were constructed. Besides, the logistic regression and single-sample gene set enrichment analysis (ssGSEA) were performed. As a result, 62 DEGs were totally identified between AD and T2DM, and the enrichment analysis indicated that they were much related to the function of synaptic vesicle and MAPK signaling pathway. Based on the evidence from external dataset and RT-qPCR, CARTPT, EPHA5, and SERPINA3 were identified as the marker genes in both diseases, and their clinical significance and biological functions were further analyzed. In conclusion, discovering and exploring the marker genes that are dysregulated in both 2 diseases could help us better comprehend the intrinsic relationship between T2DM and AD, which may inspire us to develop new strategies for facing the dilemmas of clinical or basic research in cognitive dysfunction.

Dataset Information

An Efficient Classifier for Alzheimer's Disease Genes Identification.

Publications

An Efficient Classifier for Alzheimer's Disease Genes Identification.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets