• Research dataclose
• Other research productsclose
• 2014-2023close

This paper presents a comprehensive and quality collection of functional human brain network data for potential research in the intersection of neuroscience, machine learning, and graph analytics. Anatomical and functional MRI images of the brain have been used to understand the functional connectivity of the human brain and are particularly important in identifying underlying neurodegenerative conditions such as Alzheimer's, Parkinson's, and Autism. Recently, the study of the brain in the form of brain networks using machine learning and graph analytics has become increasingly popular, especially to predict the early onset of these conditions. A brain network, represented as a graph, retains richer structural and positional information that traditional examination methods are unable to capture. However, the lack of brain network data transformed from functional MRI images prevents researchers from data-driven explorations. One of the main difficulties lies in the complicated domain-specific preprocessing steps and the exhaustive computation required to convert data from MRI images into brain networks. We bridge this gap by collecting a large amount of available MRI images from existing studies, working with domain experts to make sensible design choices, and preprocessing the MRI images to produce a collection of brain network datasets. The datasets originate from 5 different sources, cover 3 neurodegenerative conditions, and consist of a total of 2,642 subjects. We test our graph datasets on 5 machine learning models commonly used in neuroscience and on a recent graph-based analysis model to validate the data quality and to provide domain baselines. To lower the barrier to entry and promote the research in this interdisciplinary field, we release our complete preprocessing details, codes, and brain network data. To stay informed about the new updates of the datasets, kindly provide us with your email address: https://forms.gle/KGAajR6LEysXWKvKA

This paper presents a comprehensive and quality collection of functional human brain network data for potential research in the intersection of neuroscience, machine learning, and graph analytics.Anatomical and functional MRI images of the brain have been used to understand the functional connectivity of the human brain and are particularly important in identifying underlying neurodegenerative conditions such as Alzheimer's, Parkinson's, and Autism. Recently, the study of the brain in the form of brain networks using machine learning and graph analytics has become increasingly popular, especially to predict the early onset of these conditions. A brain network, represented as a graph, retains richer structural and positional information that traditional examination methods are unable to capture. However, the lack of brain network data transformed from functional MRI images prevents researchers from data-driven explorations. One of the main difficulties lies in the complicated domain-specific preprocessing steps and the exhaustive computation required to convert data from MRI images into brain networks. We bridge this gap by collecting a large amount of available MRI images from existing studies, working with domain experts to make sensible design choices, and preprocessing the MRI images to produce a collection of brain network datasets. The datasets originate from 6 different sources, cover 4 neurodegenerative conditions, and consist of a total of 2,702 subjects.Due to the data protocol, we are unable to release the ADNI dataset here. The data will be released via the ADNI external data submissions within their data system.We test our graph datasets on 5 machine learning models commonly used in neuroscience and on a recent graph-based analysis model to validate the data quality and to provide domain baselines. To lower the barrier to entry and promote the research in this interdisciplinary field, we release our complete preprocessing details, codes, and brain network data: https://github.com/brainnetuoa/data_driven_network_neuroscience.To stay informed about the new updates of the datasets, kindly provide us with your email address:https://forms.gle/KGAajR6LEysXWKvKA

Additional file 1: Data S1. Participant characteristics. S1a: Characteristics of individuals with CSF Aβ1-42 and tau measurements available; S1b: Characteristics of individuals with CSF proteomic data. Data S2. Protein annotation and statistics of group comparisons of protein levels. Data S3a. Full list of GO biological processes associated with proteins that differ according to group and clinical stage. Data S3b. SynGO enriched synaptic cellular components and biological processes that differ according to group. Data S4a. Estimated marginal means of AD GWAS-based polygenic risk scores in controls, AD individuals with increased t-tau and AD individuals with normal t-tau. Data S4b. Top 1000 SNPS from GWAS on AD individuals with increased t-tau and normal t-tau in pooled ADNI and EMIF-AD MBD cohorts. Data S4c. Difference in MAGMA gene score between AD individuals with increased t-tau and normal t-tau based on t-tau GWAS in pooled ADNI and EMIF-AD MBD cohorts. Data S4d. Difference in GO biological process MAGMA geneset score between AD individuals with increased t-tau and normal t-tau based on t-tau GWAS in pooled ADNI and EMIF-AD MBD cohorts. Data S5a. Correlation between genetic risk score and CSF protein level in individuals with abnormal Aβ1-42. Data S5b. Association of the number of GMNC rs9877502-A risk alleles and number of APOE-e4 alleles with CSF protein concentrations in a linear model in individuals with AD. Data S5c. GO-BP processes enriched for proteins that have a positive or negative association with the number of rs9877502-A risk alleles in an additive model. Data S6. Annual change in imaging measures.

This paper presents a comprehensive and quality collection of functional human brain network data for potential research in the intersection of neuroscience, machine learning, and graph analytics. Anatomical and functional MRI images of the brain have been used to understand the functional connectivity of the human brain and are particularly important in identifying underlying neurodegenerative conditions such as Alzheimer's, Parkinson's, and Autism. Recently, the study of the brain in the form of brain networks using machine learning and graph analytics has become increasingly popular, especially to predict the early onset of these conditions. A brain network, represented as a graph, retains richer structural and positional information that traditional examination methods are unable to capture. However, the lack of brain network data transformed from functional MRI images prevents researchers from data-driven explorations. One of the main difficulties lies in the complicated domain-specific preprocessing steps and the exhaustive computation required to convert data from MRI images into brain networks. We bridge this gap by collecting a large amount of available MRI images from existing studies, working with domain experts to make sensible design choices, and preprocessing the MRI images to produce a collection of brain network datasets. The datasets originate from 5 different sources, cover 3 neurodegenerative conditions, and consist of a total of 2,642 subjects. We test our graph datasets on 5 machine learning models commonly used in neuroscience and on a recent graph-based analysis model to validate the data quality and to provide domain baselines. To lower the barrier to entry and promote the research in this interdisciplinary field, we release our complete preprocessing details, codes, and brain network data. To stay informed about the new updates of the datasets, kindly provide us with your email address: https://forms.gle/KGAajR6LEysXWKvKA

Additional file 1 The additional tables and figures are presented in the Supplementary file.

Uncovering the heterogeneity in the disease progression of Alzheimer's is a key factor to disease understanding and treatment development, so that interventions can be tailored to target the subgroups that will benefit most from the treatment, which is an important goal of precision medicine. However, in practice, one top methodological challenge hindering the heterogeneity investigation is that the true subgroup membership of each individual is often unknown. In this article, we aim to identify latent subgroups of individuals who share a common disorder progress over time, to predict latent subgroup memberships, and to estimate and infer the heterogeneous trajectories among the subgroups. To achieve these goals, we apply a concave fusion learning method to conduct subgroup analysis for longitudinal trajectories of the Alzheimer's disease data. The heterogeneous trajectories are represented by subject-specific unknown functions which are approximated by B-splines. The concave fusion method can simultaneously estimate the spline coefficients and merge them together for the subjects belonging to the same subgroup to automatically identify subgroups and recover the heterogeneous trajectories. The resulting estimator of the disease trajectory of each subgroup is supported by an asymptotic distribution. It provides a sound theoretical basis for further conducting statistical inference in subgroup analysis.

Additional file 1. Table S1: Significance level of brain regions using imaging-diagnosis analysis. Table S2(a): Significance level of identified genes significantly associated with diagnostic outcome using correlation analysis. Table S2(b): Significance level of identified genes related with AD based on DisGeNET. Table S2(c): Significance level of identified genes unrelated with AD based on DisGeNET.

Additional file 2. Supplementary tables. Includes sequence IDs, geographic provenance data, haplogroup assignment summaries, and statistical test results.

Additional file 2: Table S3. List of mapped genes.