Dataset Information

An adaptive genetic algorithm for selection of blood-based biomarkers for prediction of Alzheimer's disease progression.

ABSTRACT:

Background

Alzheimer's disease is a multifactorial disorder that may be diagnosed earlier using a combination of tests rather than any single test. Search algorithms and optimization techniques in combination with model evaluation techniques have been used previously to perform the selection of suitable feature sets. Previously we successfully applied GA with LR to neuropsychological data contained within the The Australian Imaging, Biomarkers and Lifestyle (AIBL) study of aging, to select cognitive tests for prediction of progression of AD. This research addresses an Adaptive Genetic Algorithm (AGA) in combination with LR for identifying the best biomarker combination for prediction of the progression to AD.

Results

The model has been explored in terms of parameter optimization to predict conversion from healthy stage to AD with high accuracy. Several feature sets were selected - the resulting prediction moddels showed higher area under the ROC values (0.83-0.89). The results has shown consistency with some of the medical research reported in literature.

Conclusion

The AGA has proven useful in selecting the best combination of biomarkers for prediction of AD progression. The algorithm presented here is generic and can be extended to other data sets generated in projects that seek to identify combination of biomarkers or other features that are predictive of disease onset or progression.

SUBMITTER: Vandewater L

PROVIDER: S-EPMC4682419 | biostudies-literature | 2015

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

An adaptive genetic algorithm for selection of blood-based biomarkers for prediction of Alzheimer's disease progression.

Vandewater Luke L Brusic Vladimir V Wilson William W Macaulay Lance L Zhang Ping P Zhang Ping P

BMC bioinformatics 20151209

<h4>Background</h4>Alzheimer's disease is a multifactorial disorder that may be diagnosed earlier using a combination of tests rather than any single test. Search algorithms and optimization techniques in combination with model evaluation techniques have been used previously to perform the selection of suitable feature sets. Previously we successfully applied GA with LR to neuropsychological data contained within the The Australian Imaging, Biomarkers and Lifestyle (AIBL) study of aging, to sele ...[more]

PMID: 26680269

Similar Datasets

Project description:BackgroundBlood circulating microRNAs that are specific for Alzheimer's disease (AD) can be identified from differentially expressed microRNAs (DEmiRNAs). However, non-reproducible and inconsistent reports of DEmiRNAs hinder biomarker development. The most reliable DEmiRNAs can be identified by meta-analysis. To enrich the pool of DEmiRNAs for potential AD biomarkers, we used a machine learning method called adaptive boosting for miRNA disease association (ABMDA) to identify eligible candidates that share similar characteristics with the DEmiRNAs identified from meta-analysis. This study aimed to identify blood circulating DEmiRNAs as potential AD biomarkers by augmenting meta-analysis with the ABMDA ensemble learning method.MethodsStudies on DEmiRNAs and their dysregulation states were corroborated with one another by meta-analysis based on a random-effects model. DEmiRNAs identified by meta-analysis were collected as positive examples of miRNA-AD pairs for ABMDA ensemble learning. ABMDA identified similar DEmiRNAs according to a set of predefined criteria. The biological significance of all resulting DEmiRNAs was determined by their target genes according to pathway enrichment analyses. The target genes common to both meta-analysis- and ABMDA-identified DEmiRNAs were collected to construct a network to investigate their biological functions.ResultsA systematic database search found 7841 studies for an extensive meta-analysis, covering 54 independent comparisons of 47 differential miRNA expression studies, and identified 18 reliable DEmiRNAs. ABMDA ensemble learning was conducted based on the meta-analysis results and the Human MicroRNA Disease Database, which identified 10 additional AD-related DEmiRNAs. These 28 DEmiRNAs and their dysregulated pathways were related to neuroinflammation. The dysregulated pathway related to neuronal cell cycle re-entry (CCR) was the only statistically significant pathway of the ABMDA-identified DEmiRNAs. In the biological network constructed from 1865 common target genes of the identified DEmiRNAs, the multiple core ubiquitin-proteasome system, that is involved in neuroinflammation and CCR, was highly connected.ConclusionThis study identified 28 DEmiRNAs as potential AD biomarkers in blood, by meta-analysis and ABMDA ensemble learning in tandem. The DEmiRNAs identified by meta-analysis and ABMDA were significantly related to neuroinflammation, and the ABMDA-identified DEmiRNAs were related to neuronal CCR.

Project description:Background: Alzheimer's disease (AD) is the major cause of dementia in population aged over 65 years, accounting up to 70% dementia cases. However, validated peripheral biomarkers for AD diagnosis are not available up to present. In this study, we adopted a new strategy of combination of computational prediction and experimental validation to identify blood protein biomarkers for AD. Methods: First, we collected tissue-based gene expression data of AD patients and healthy controls from GEO database. Second, we analyzed these data and identified differentially expressed genes for AD. Third, we applied a blood-secretory protein prediction program on these genes and predicted AD-related proteins in blood. Finally, we collected blood samples of AD patients and healthy controls to validate the potential AD biomarkers by using ELISA experiments and Western blot analyses. Results: A total of 2754 genes were identified to express differentially in brain tissues of AD, among which 296 genes were predicted to encode AD-related blood-secretory proteins. After careful analysis and literature survey on these predicted blood-secretory proteins, ten proteins were considered as potential AD biomarkers, five of which were experimentally verified with significant change in blood samples of AD vs. controls by ELISA, including GSN, BDNF, TIMP1, VLDLR, and APLP2. ROC analyses showed that VLDLR and TIMP1 had excellent performance in distinguishing AD patients from controls (area under the curve, AUC = 0.932 and 0.903, respectively). Further validation of VLDLR and TIMP1 by Western blot analyses has confirmed the results obtained in ELISA experiments. Conclusion: VLDLR and TIMP1 had better discriminative abilities between ADs and controls, and might serve as potential blood biomarkers for AD. To our knowledge, this is the first time to identify blood protein biomarkers for AD through combination of computational prediction and experimental validation. In addition, VLDLR was first reported here as potential blood protein biomarker for AD. Thus, our findings might provide important information for AD diagnosis and therapies.

Project description:Although 24 Alzheimer's disease (AD) risk loci have been reliably identified, a large portion of the predicted heritability for AD remains unexplained. It is expected that additional loci of small effect will be identified with an increased sample size. However, the cost of a significant increase in Case-Control sample size is prohibitive. The current study tests whether exploring the genetic basis of endophenotypes, in this case based on putative blood biomarkers for AD, can accelerate the identification of susceptibility loci using modest sample sizes. Each endophenotype was used as the outcome variable in an independent GWAS. Endophenotypes were based on circulating concentrations of proteins that contributed significantly to a published blood-based predictive algorithm for AD. Endophenotypes included Monocyte Chemoattractant Protein 1 (MCP1), Vascular Cell Adhesion Molecule 1 (VCAM1), Pancreatic Polypeptide (PP), Beta2 Microglobulin (B2M), Factor VII (F7), Adiponectin (ADN) and Tenascin C (TN-C). Across the seven endophenotypes, 47 SNPs were associated with outcome with a p-value ?1x10(-7). Each signal was further characterized with respect to known genetic loci associated with AD. Signals for several endophenotypes were observed in the vicinity of CR1, MS4A6A/MS4A4E, PICALM, CLU, and PTK2B. The strongest signal was observed in association with Factor VII levels and was located within the F7 gene. Additional signals were observed in MAP3K13, ZNF320, ATP9B and TREM1. Conditional regression analyses suggested that the SNPs contributed to variation in protein concentration independent of AD status. The identification of two putatively novel AD loci (in the Factor VII and ATP9B genes), which have not been located in previous studies despite massive sample sizes, highlights the benefits of an endophenotypic approach for resolving the genetic basis for complex diseases. The coincidence of several of the endophenotypic signals with known AD loci may point to novel genetic interactions and should be further investigated.

Dataset Information

An adaptive genetic algorithm for selection of blood-based biomarkers for prediction of Alzheimer's disease progression.

Background

Results

Conclusion

Publications

An adaptive genetic algorithm for selection of blood-based biomarkers for prediction of Alzheimer's disease progression.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets