Dataset Information

HENA, heterogeneous network-based data set for Alzheimer's disease.

ABSTRACT: Alzheimer's disease and other types of dementia are the top cause for disabilities in later life and various types of experiments have been performed to understand the underlying mechanisms of the disease with the aim of coming up with potential drug targets. These experiments have been carried out by scientists working in different domains such as proteomics, molecular biology, clinical diagnostics and genomics. The results of such experiments are stored in the databases designed for collecting data of similar types. However, in order to get a systematic view of the disease from these independent but complementary data sets, it is necessary to combine them. In this study we describe a heterogeneous network-based data set for Alzheimer's disease (HENA). Additionally, we demonstrate the application of state-of-the-art graph convolutional networks, i.e. deep learning methods for the analysis of such large heterogeneous biological data sets. We expect HENA to allow scientists to explore and analyze their own results in the broader context of Alzheimer's disease research.

SUBMITTER: Sugis E

PROVIDER: S-EPMC6694132 | biostudies-literature | 2019 Aug

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

HENA, heterogeneous network-based data set for Alzheimer's disease.

Sügis Elena E Dauvillier Jerome J Leontjeva Anna A Adler Priit P Hindie Valerie V Moncion Thomas T Collura Vincent V Daudin Rachel R Loe-Mie Yann Y Herault Yann Y Lambert Jean-Charles JC Hermjakob Henning H Pupko Tal T Rain Jean-Christophe JC Xenarios Ioannis I Vilo Jaak J Simonneau Michel M Peterson Hedi H

Scientific data 20190814 1

Alzheimer's disease and other types of dementia are the top cause for disabilities in later life and various types of experiments have been performed to understand the underlying mechanisms of the disease with the aim of coming up with potential drug targets. These experiments have been carried out by scientists working in different domains such as proteomics, molecular biology, clinical diagnostics and genomics. The results of such experiments are stored in the databases designed for collecting ...[more]

PMID: 31413325

Similar Datasets

Project description:BackgroundEvidence on the relative risk of death across all stages of Alzheimer's disease (AD) is lacking but greatly needed for the evaluation of new interventions. We used data from the Uniform Data Set (UDS) of the National Alzheimer's Coordinating Center (NACC) to assess the expected survival of a person progressing to a particular stage of AD and the relative risk of death for a person in a particular stage of AD compared with cognitively normal (CN) people.MethodsThis was a retrospective observational cohort study of mortality and its determinants in participants with incident mild cognitive impairment (MCI) due to AD or AD dementia compared with CN participants. Overall survival and hazard ratios of all-cause mortality in participants ≥ 50 years of age with clinically assessed or diagnosed MCI due to AD, or mild, moderate, or severe AD dementia, confirmed by Clinical Dementia Rating scores, versus CN participants were estimated, using NACC UDS data. Participants were followed until death, censoring, or until information to determine disease stage was missing.ResultsAged between 50 and 104 years, 12,414 participants met the eligibility criteria for the study. Participants progressing to MCI due to AD or AD dementia survived a median of 3-12 years, with higher mortality observed in more severe stages. Risk of death increased with the severity of AD dementia, with the increase significantly higher at younger ages. Participants with MCI due to AD and CN participants had a similar risk of death after controlling for confounding factors.ConclusionsRelative all-cause mortality risk increases with AD severity, more so at younger ages. Mortality does not seem to be higher for those remaining in MCI due to AD. Findings might imply potential benefit of lower mortality if preventing or delaying the progression of AD is successful, and importantly, this potential benefit might be greater in relatively younger people. Future research should replicate our study in other samples more representative of the general US population as well as other populations around the world.

Project description:BackgroundThe existing studies show that circRNAs can be used as a biomarker of diseases and play a prominent role in the treatment and diagnosis of diseases. However, the relationships between the vast majority of circRNAs and diseases are still unclear, and more experiments are needed to study the mechanism of circRNAs. Nowadays, some scholars use the attributes between circRNAs and diseases to study and predict their associations. Nonetheless, most of the existing experimental methods use less information about the attributes of circRNAs, which has a certain impact on the accuracy of the final prediction results. On the other hand, some scholars also apply experimental methods to predict the associations between circRNAs and diseases. But such methods are usually expensive and time-consuming. Based on the above shortcomings, follow-up research is needed to propose a more efficient calculation-based method to predict the associations between circRNAs and diseases.ResultsIn this study, a novel algorithm (method) is proposed, which is based on the Graph Convolutional Network (GCN) constructed with Random Walk with Restart (RWR) and Principal Component Analysis (PCA) to predict the associations between circRNAs and diseases (CRPGCN). In the construction of CRPGCN, the RWR algorithm is used to improve the similarity associations of the computed nodes with their neighbours. After that, the PCA method is used to dimensionality reduction and extract features, it makes the connection between circRNAs with higher similarity and diseases closer. Finally, The GCN algorithm is used to learn the features between circRNAs and diseases and calculate the final similarity scores, and the learning datas are constructed from the adjacency matrix, similarity matrix and feature matrix as a heterogeneous adjacency matrix and a heterogeneous feature matrix.ConclusionsAfter 2-fold cross-validation, 5-fold cross-validation and 10-fold cross-validation, the area under the ROC curve of the CRPGCN is 0.9490, 0.9720 and 0.9722, respectively. The CRPGCN method has a valuable effect in predict the associations between circRNAs and diseases.

Dataset Information

HENA, heterogeneous network-based data set for Alzheimer's disease.

Publications

HENA, heterogeneous network-based data set for Alzheimer's disease.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets