Prediction of Alzheimer's disease using blood gene expression data

A mini review of transforming dementia care in China with data-driven insights: overcoming diagnostic and time-delayed barriers

Introduction

Inadequate primary care infrastructure and training in China and misconceptions about aging lead to high mis-/under-diagnoses and serious time delays for dementia patients, imposing significant burdens on family members and medical carers.

Main body

A flowchart integrating rural and urban areas of China dementia care pathway is proposed, especially spotting the obstacles of mis/under-diagnoses and time delays that can be alleviated by data-driven computational strategies. Artificial intelligence (AI) and machine learning models built on dementia data are succinctly reviewed in terms of the roadmap of dementia care from home, community to hospital settings. Challenges and corresponding recommendations to clinical transformation are then reported from the viewpoint of diverse dementia data integrity and accessibility, as well as models' interpretability, reliability, and transparency.

Discussion

Dementia cohort study along with developing a center-crossed dementia data platform in China should be strongly encouraged, also data should be publicly accessible where appropriate. Only be doing so can the challenges be overcome and can AI-enabled dementia research be enhanced, leading to an optimized pathway of dementia care in China. Future policy-guided cooperation between researchers and multi-stakeholders are urgently called for dementia 4E (early-screening, early-assessment, early-diagnosis, and early-intervention).

Machine Learning-Based Alzheimer's Disease Stage Diagnosis Utilizing Blood Gene Expression and Clinical Data: A Comparative Investigation

Background/Objectives: This study presents a comparative analysis of the multistage diagnosis of Alzheimer's disease (AD), including mild cognitive impairment (MCI), utilizing two distinct types of biomarkers: blood gene expression and clinical biomarker samples. Both of these samples, obtained from participants in the Alzheimer's Disease Neuroimaging Initiative (ADNI), were independently analyzed utilizing machine learning (ML)-based multiclassifiers. This study applied novel machine learning-based data augmentation techniques to gene expression profile data that are high-dimensional, low-sample-size (HDLSS) and inherently highly imbalanced. The investigation obtained the highest multiclassification performance to date in the multistage diagnosis of Alzheimer's disease utilizing the blood gene expression profiles of Alzheimer's Disease Neuroimaging Initiative (ADNI) participants. Based on the performance results obtained, and other factors such as early prediction capabilities, this study compares the efficacies of the two types of biomarkers for multistage diagnosis. This study presents the sole investigation in which multiclassification-based AD stage diagnosis was conducted utilizing blood gene expression data. We obtained the best multiclassification result in both modalities of the ADNI data in terms of F1-score and were able to identify new genetic biomarkers. Methods: The combination of the XGBoost and SFBS (Sequential Floating Backward Selection) methods was used to select the features. We were able to select the 95 most effective gene probe sets out of 49,386. For the clinical study data, eight of the most effective biomarkers were selected using SFBS. A deep learning (DL) classifier was used to identify the stages-cognitive normal (CN), mild cognitive impairment (MCI), and Alzheimer's disease (AD)/dementia. DL, support vector machine (SVM), gradient boosting (GB), and random forest (RF) classifiers were used for the AD stage detection from gene expression profile data. Because of the high data imbalance in genomic data, borderline oversampling/data augmentation was applied in the model training and original samples for validation. Results: Utilizing clinical data, the highest ROC AUC scores attained were 0.989, 0.927, and 0.907 for the identification of the CN, MCI, and dementia stages, respectively. The highest F1 scores achieved were 0.971, 0.939, and 0.886. Employing gene expression data, we obtained ROC AUC scores of 0.763, 0.761, and 0.706 for the CN, MCI, and dementia stages, respectively, and F1 scores of 0.71, 0.77, and 0.53 for CN, MCI, and dementia, respectively. Conclusions: This represents the best outcome to date for AD stage diagnosis from ADNI blood gene expression profile data utilizing multiclassification techniques. The results indicated that our multiclassification model effectively manages the imbalanced data of a high-dimension, low-sample-size (HDLSS) nature to identify samples of the minority class. MAPK14, PLG, FZD2, FXYD6, and TEP1 are among the novel genes identified as being associated with AD risk.

A Comprehensive Review on Deep Learning Techniques in Alzheimer's Disease Diagnosis

Alzheimer's Disease (AD) is a serious neurological illness that causes memory loss gradually by destroying brain cells. This deadly brain illness primarily strikes the elderly, impairing their cognitive and bodily abilities until brain shrinkage occurs. Modern techniques are required for an accurate diagnosis of AD. Machine learning has gained attraction in the medical field as a means of determining a person's risk of developing AD in its early stages. One of the most advanced soft computing neural network-based Deep Learning (DL) methodologies has garnered significant interest among researchers in automating early-stage AD diagnosis. Hence, a comprehensive review is necessary to gain insights into DL techniques for the advancement of more effective methods for diagnosing AD. This review explores multiple biomarkers associated with Alzheimer's Disease (AD) and various DL methodologies, including Deep Neural Networks (DNN), Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), The k-nearest-neighbor (k-NN), Deep Boltzmann Machines (DBM), and Deep Belief Networks (DBN), which have been employed for automating the early diagnosis of AD. Moreover, the unique contributions of this review include the classification of ATN biomarkers for Alzheimer's Disease (AD), systemic description of diverse DL algorithms for early AD assessment, along with a discussion of widely utilized online datasets such as ADNI, OASIS, etc. Additionally, this review provides perspectives on future trends derived from critical evaluation of each variant of DL techniques across different modalities, dataset sources, AUC values, and accuracies.

Meta-Analysis of Transcriptomic Studies of Blood and Six Brain Regions Identifies a Consensus of 15 Cross-Tissue Mechanisms in Alzheimer's Disease and Suggests an Origin of Cross-Study Heterogeneity

The comprehensive genome-wide nature of transcriptome studies in Alzheimer's disease (AD) should provide a reliable description of disease molecular states. However, the genes and molecular systems nominated by transcriptomic studies do not always overlap. Even when results do align, it is not clear if those observations represent true consensus across many studies. A couple of sources of variation have been proposed to explain this variability, including tissue-of-origin and cohort type, but its basis remains uncertain. To address this variability and extract reliable results, we utilized all publicly available blood or brain transcriptomic datasets of AD, comprised of 24 brain studies with 4007 samples from six different brain regions, and eight blood studies with 1566 samples. We identified a consensus of AD-associated genes across brain regions and AD-associated gene-sets across blood and brain, generalizable machine learning and linear scoring classifiers, and significant contributors to biological diversity in AD datasets. While AD-associated genes did not significantly overlap between blood and brain, our findings highlighted 15 dysregulated processes shared across blood and brain in AD. The top five most significantly dysregulated processes were DNA replication, metabolism of proteins, protein localization, cell cycle, and programmed cell death. Conversely, addressing the discord across studies, we found that large-scale gene co-regulation patterns can account for a significant fraction of variability in AD datasets. Overall, this study ranked and characterized a compilation of genes and molecular systems consistently identified across a large assembly of AD transcriptome studies in blood and brain, providing potential candidate biomarkers and therapeutic targets.

A fusion analytic framework for investigating functional brain connectivity differences using resting-state fMRI

Introduction

Functional magnetic resonance imaging (fMRI) data is highly complex and high-dimensional, capturing signals from regions of interest (ROIs) with intricate correlations. Analyzing such data is particularly challenging, especially in resting-state fMRI, where patterns are less identifiable without task-specific contexts. Nonetheless, interconnections among ROIs provide essential insights into brain activity and exhibit unique characteristics across groups.

Methods

To address these challenges, we propose an interpretable fusion analytic framework to identify and understand ROI connectivity differences between two groups, revealing their distinctive features. The framework involves three steps: first, constructing ROI-based Functional Connectivity Networks (FCNs) to manage resting-state fMRI data; second, employing a Self-Attention Deep Learning Model (Self-Attn) for binary classification to generate attention distributions encoding group-level differences; and third, utilizing a Latent Space Item-Response Model (LSIRM) to extract group-representative ROI features, visualized on group summary FCNs.

Results

We applied our framework to analyze four types of cognitive impairments, demonstrating their effectiveness in identifying significant ROIs that contribute to the differences between the two disease groups. The results reveal distinct connectivity patterns and unique ROI features, which differentiate cognitive impairments. Specifically, our framework highlighted group-specific differences in functional connectivity, validating its capability to capture meaningful insights from high-dimensional fMRI data.

Discussion

Our novel interpretable fusion analytic framework addresses the challenges of analyzing high-dimensional, resting-state fMRI data. By integrating FCNs, a Self-Attention Deep Learning Model, and LSIRM, the framework provides an innovative approach to discovering ROI connectivity disparities between groups. The attention distribution and group-representative ROI features offer interpretable insights into brain activity patterns and their variations among cognitive impairment groups. This methodology has significant potential to enhance our understanding of cognitive impairments, paving the way for more targeted therapeutic interventions.

Deep learning analysis of fMRI data for predicting Alzheimer's Disease: A focus on convolutional neural networks and model interpretability

The early detection of Alzheimer's Disease (AD) is thought to be important for effective intervention and management. Here, we explore deep learning methods for the early detection of AD. We consider both genetic risk factors and functional magnetic resonance imaging (fMRI) data. However, we found that the genetic factors do not notably enhance the AD prediction by imaging. Thus, we focus on building an effective imaging-only model. In particular, we utilize data from the Alzheimer's Disease Neuroimaging Initiative (ADNI), employing a 3D Convolutional Neural Network (CNN) to analyze fMRI scans. Despite the limitations posed by our dataset (small size and imbalanced nature), our CNN model demonstrates accuracy levels reaching 92.8% and an ROC of 0.95. Our research highlights the complexities inherent in integrating multimodal medical datasets. It also demonstrates the potential of deep learning in medical imaging for AD prediction.

Etiology of Late-Onset Alzheimer's Disease, Biomarker Efficacy, and the Role of Machine Learning in Stage Diagnosis

Late-onset Alzheimer's disease (LOAD) is a subtype of dementia that manifests after the age of 65. It is characterized by progressive impairments in cognitive functions, behavioral changes, and learning difficulties. Given the progressive nature of the disease, early diagnosis is crucial. Early-onset Alzheimer's disease (EOAD) is solely attributable to genetic factors, whereas LOAD has multiple contributing factors. A complex pathway mechanism involving multiple factors contributes to LOAD progression. Employing a systems biology approach, our analysis encompassed the genetic, epigenetic, metabolic, and environmental factors that modulate the molecular networks and pathways. These factors affect the brain's structural integrity, functional capacity, and connectivity, ultimately leading to the manifestation of the disease. This study has aggregated diverse biomarkers associated with factors capable of altering the molecular networks and pathways that influence brain structure, functionality, and connectivity. These biomarkers serve as potential early indicators for AD diagnosis and are designated as early biomarkers. The other biomarker datasets associated with the brain structure, functionality, connectivity, and related parameters of an individual are broadly categorized as clinical-stage biomarkers. This study has compiled research papers on Alzheimer's disease (AD) diagnosis utilizing machine learning (ML) methodologies from both categories of biomarker data, including the applications of ML techniques for AD diagnosis. The broad objectives of our study are research gap identification, assessment of biomarker efficacy, and the most effective or prevalent ML technology used in AD diagnosis. This paper examines the predominant use of deep learning (DL) and convolutional neural networks (CNNs) in Alzheimer's disease (AD) diagnosis utilizing various types of biomarker data. Furthermore, this study has addressed the potential scope of using generative AI and the Synthetic Minority Oversampling Technique (SMOTE) for data augmentation.

A review of model evaluation metrics for machine learning in genetics and genomics

Machine learning (ML) has shown great promise in genetics and genomics where large and complex datasets have the potential to provide insight into many aspects of disease risk, pathogenesis of genetic disorders, and prediction of health and wellbeing. However, with this possibility there is a responsibility to exercise caution against biases and inflation of results that can have harmful unintended impacts. Therefore, researchers must understand the metrics used to evaluate ML models which can influence the critical interpretation of results. In this review we provide an overview of ML metrics for clustering, classification, and regression and highlight the advantages and disadvantages of each. We also detail common pitfalls that occur during model evaluation. Finally, we provide examples of how researchers can assess and utilise the results of ML models, specifically from a genomics perspective.

Progress and trends in neurological disorders research based on deep learning

In recent years, deep learning (DL) has emerged as a powerful tool in clinical imaging, offering unprecedented opportunities for the diagnosis and treatment of neurological disorders (NDs). This comprehensive review explores the multifaceted role of DL techniques in leveraging vast datasets to advance our understanding of NDs and improve clinical outcomes. Beginning with a systematic literature review, we delve into the utilization of DL, particularly focusing on multimodal neuroimaging data analysis-a domain that has witnessed rapid progress and garnered significant scientific interest. Our study categorizes and critically analyses numerous DL models, including Convolutional Neural Networks (CNNs), LSTM-CNN, GAN, and VGG, to understand their performance across different types of Neurology Diseases. Through particular analysis, we identify key benchmarks and datasets utilized in training and testing DL models, shedding light on the challenges and opportunities in clinical neuroimaging research. Moreover, we discuss the effectiveness of DL in real-world clinical scenarios, emphasizing its potential to revolutionize ND diagnosis and therapy. By synthesizing existing literature and describing future directions, this review not only provides insights into the current state of DL applications in ND analysis but also covers the way for the development of more efficient and accessible DL techniques. Finally, our findings underscore the transformative impact of DL in reshaping the landscape of clinical neuroimaging, offering hope for enhanced patient care and groundbreaking discoveries in the field of neurology. This review paper is beneficial for neuropathologists and new researchers in this field.

Bayesian genome-wide TWAS with reference transcriptomic data of brain and blood tissues identified 141 risk genes for Alzheimer's disease dementia

BACKGROUND

Transcriptome-wide association study (TWAS) is an influential tool for identifying genes associated with complex diseases whose genetic effects are likely mediated through transcriptome. TWAS utilizes reference genetic and transcriptomic data to estimate effect sizes of genetic variants on gene expression (i.e., effect sizes of a broad sense of expression quantitative trait loci, eQTL). These estimated effect sizes are employed as variant weights in gene-based association tests, facilitating the mapping of risk genes with genome-wide association study (GWAS) data. However, most existing TWAS of Alzheimer's disease (AD) dementia are limited to studying only cis-eQTL proximal to the test gene. To overcome this limitation, we applied the Bayesian Genome-wide TWAS (BGW-TWAS) method to leveraging both cis- and trans- eQTL of brain and blood tissues, in order to enhance mapping risk genes for AD dementia.

METHODS

We first applied BGW-TWAS to the Genotype-Tissue Expression (GTEx) V8 dataset to estimate cis- and trans- eQTL effect sizes of the prefrontal cortex, cortex, and whole blood tissues. Estimated eQTL effect sizes were integrated with the summary data of the most recent GWAS of AD dementia to obtain BGW-TWAS (i.e., gene-based association test) p-values of AD dementia per gene per tissue type. Then we used the aggregated Cauchy association test to combine TWAS p-values across three tissues to obtain omnibus TWAS p-values per gene.

RESULTS

We identified 85 significant genes in prefrontal cortex, 82 in cortex, and 76 in whole blood that were significantly associated with AD dementia. By combining BGW-TWAS p-values across these three tissues, we obtained 141 significant risk genes including 34 genes primarily due to trans-eQTL and 35 mapped risk genes in GWAS Catalog. With these 141 significant risk genes, we detected functional clusters comprised of both known mapped GWAS risk genes of AD in GWAS Catalog and our identified TWAS risk genes by protein-protein interaction network analysis, as well as several enriched phenotypes related to AD.

CONCLUSION

We applied BGW-TWAS and aggregated Cauchy test methods to integrate both cis- and trans- eQTL data of brain and blood tissues with GWAS summary data, identifying 141 TWAS risk genes of AD dementia. These identified risk genes provide novel insights into the underlying biological mechanisms of AD dementia and potential gene targets for therapeutics development.

Single-cell genomics and regulatory networks for 388 human brains

Single-cell genomics is a powerful tool for studying heterogeneous tissues such as the brain. Yet little is understood about how genetic variants influence cell-level gene expression. Addressing this, we uniformly processed single-nuclei, multiomics datasets into a resource comprising >2.8 million nuclei from the prefrontal cortex across 388 individuals. For 28 cell types, we assessed population-level variation in expression and chromatin across gene families and drug targets. We identified >550,000 cell type-specific regulatory elements and >1.4 million single-cell expression quantitative trait loci, which we used to build cell-type regulatory and cell-to-cell communication networks. These networks manifest cellular changes in aging and neuropsychiatric disorders. We further constructed an integrative model accurately imputing single-cell expression and simulating perturbations; the model prioritized ~250 disease-risk genes and drug targets with associated cell types.

Single-cell genomics and regulatory networks for 388 human brains

Single-cell genomics is a powerful tool for studying heterogeneous tissues such as the brain. Yet, little is understood about how genetic variants influence cell-level gene expression. Addressing this, we uniformly processed single-nuclei, multi-omics datasets into a resource comprising >2.8M nuclei from the prefrontal cortex across 388 individuals. For 28 cell types, we assessed population-level variation in expression and chromatin across gene families and drug targets. We identified >550K cell-type-specific regulatory elements and >1.4M single-cell expression-quantitative-trait loci, which we used to build cell-type regulatory and cell-to-cell communication networks. These networks manifest cellular changes in aging and neuropsychiatric disorders. We further constructed an integrative model accurately imputing single-cell expression and simulating perturbations; the model prioritized ~250 disease-risk genes and drug targets with associated cell types.

Predicting early Alzheimer's with blood biomarkers and clinical features

Alzheimer's disease (AD) is an incurable neurodegenerative disorder that leads to dementia. This study employs explainable machine learning models to detect dementia cases using blood gene expression, single nucleotide polymorphisms (SNPs), and clinical data from Alzheimer's Disease Neuroimaging Initiative (ADNI). Analyzing 623 ADNI participants, we found that the Support Vector Machine classifier with Mutual Information (MI) feature selection, trained on all three data modalities, achieved exceptional performance (accuracy = 0.95, AUC = 0.94). When using gene expression and SNP data separately, we achieved very good performance (AUC = 0.65, AUC = 0.63, respectively). Using SHapley Additive exPlanations (SHAP), we identified significant features, potentially serving as AD biomarkers. Notably, genetic-based biomarkers linked to axon myelination and synaptic vesicle membrane formation could aid early AD detection. In summary, this genetic-based biomarker approach, integrating machine learning and SHAP, shows promise for precise AD diagnosis, biomarker discovery, and offers novel insights for understanding and treating the disease. This approach addresses the challenges of accurate AD diagnosis, which is crucial given the complexities associated with the disease and the need for non-invasive diagnostic methods.

A multi-cohort study of the hippocampal radiomics model and its associated biological changes in Alzheimer's Disease

There have been no previous reports of hippocampal radiomics features associated with biological functions in Alzheimer's Disease (AD). This study aims to develop and validate a hippocampal radiomics model from structural magnetic resonance imaging (MRI) data for identifying patients with AD, and to explore the mechanism underlying the developed radiomics model using peripheral blood gene expression. In this retrospective multi-study, a radiomics model was developed based on the radiomics discovery group (n = 420) and validated in other cohorts. The biological functions underlying the model were identified in the radiogenomic analysis group using paired MRI and peripheral blood transcriptome analyses (n = 266). Mediation analysis and external validation were applied to further validate the key module and hub genes. A 12 radiomics features-based prediction model was constructed and this model showed highly robust predictive power for identifying AD patients in the validation and other three cohorts. Using radiogenomics mapping, myeloid leukocyte and neutrophil activation were enriched, and six hub genes were identified from the key module, which showed the highest correlation with the radiomics model. The correlation between hub genes and cognitive ability was confirmed using the external validation set of the AddneuroMed dataset. Mediation analysis revealed that the hippocampal radiomics model mediated the association between blood gene expression and cognitive ability. The hippocampal radiomics model can accurately identify patients with AD, while the predictive radiomics model may be driven by neutrophil-related biological pathways.

A multiclass extreme gradient boosting model for evaluation of transcriptomic biomarkers in Alzheimer's disease prediction

BACKGROUND

Patients with young-onset Alzheimer's disease (AD) (before the age of 50 years old) often lack obvious imaging changes and amyloid protein deposition, which can lead to misdiagnosis with other cognitive impairments. Considering the association between immunological dysfunction and progression of neurodegenerative disease, recent research has focused on identifying blood transcriptomic signatures for precise prediction of AD.

METHODS

In this study, we extracted blood biomarkers from large-scale transcriptomics to construct multiclass eXtreme Gradient Boosting models (XGBoost), and evaluated their performance in distinguishing AD from cognitive normal (CN) and mild cognitive impairment (MCI).

RESULTS

Independent testing with external dataset revealed that the combination of blood transcriptomic signatures achieved an area under the receiver operating characteristic curve (AUC of ROC) of 0.81 for multiclass classification (sensitivity = 0.81; specificity = 0.63), 0.83 for classification of AD vs. CN (sensitivity = 0.72; specificity = 0.73), and 0.85 for classification of AD vs. MCI (sensitivity = 0.77; specificity = 0.73). These candidate signatures were significantly enriched in 62 chromosome regions, such as Chr.19p12-19p13.3, Chr.1p22.1-1p31.1, and Chr.1q21.2-1p23.1 (adjusted p < 0.05), and significantly overrepresented by 26 transcription factors, including E2F2, FOXO3, and GATA1 (adjusted p < 0.05). Biological analysis of these signatures pointed to systemic dysregulation of immune responses, hematopoiesis, exocytosis, and neuronal support in neurodegenerative disease (adjusted p < 0.05).

CONCLUSIONS

Blood transcriptomic biomarkers hold great promise in clinical use for the accurate assessment and prediction of AD.

Mitochondria-Related Candidate Genes and Diagnostic Model to Predict Late-Onset Alzheimer's Disease and Mild Cognitive Impairment

Background

Late-onset Alzheimer's disease (LOAD) is the most common type of dementia, but its pathogenesis remains unclear, and there is a lack of simple and convenient early diagnostic markers to predict the occurrence.

Objective

Our study aimed to identify diagnostic candidate genes to predict LOAD by machine learning methods.

Methods

Three publicly available datasets from the Gene Expression Omnibus (GEO) database containing peripheral blood gene expression data for LOAD, mild cognitive impairment (MCI), and controls (CN) were downloaded. Differential expression analysis, the least absolute shrinkage and selection operator (LASSO), and support vector machine recursive feature elimination (SVM-RFE) were used to identify LOAD diagnostic candidate genes. These candidate genes were then validated in the validation group and clinical samples, and a LOAD prediction model was established.

Results

LASSO and SVM-RFE analyses identified 3 mitochondria-related genes (MRGs) as candidate genes, including NDUFA1, NDUFS5, and NDUFB3. In the verification of 3 MRGs, the AUC values showed that NDUFA1, NDUFS5 had better predictability. We also verified the candidate MRGs in MCI groups, the AUC values showed good performance. We then used NDUFA1, NDUFS5 and age to build a LOAD diagnostic model and AUC was 0.723. Results of qRT-PCR experiments with clinical blood samples showed that the three candidate genes were expressed significantly lower in the LOAD and MCI groups when compared to CN.

Conclusion

Two mitochondrial-related candidate genes, NDUFA1 and NDUFS5, were identified as diagnostic markers for LOAD and MCI. Combining these two candidate genes with age, a LOAD diagnostic prediction model was successfully constructed.

Transcriptional risk scores in Alzheimer's disease: From pathology to cognition

INTRODUCTION

Our previously developed blood-based transcriptional risk scores (TRS) showed associations with diagnosis and neuroimaging biomarkers for Alzheimer's disease (AD). Here, we developed brain-based TRS.

METHODS

We integrated AD genome-wide association study summary and expression quantitative trait locus data to prioritize target genes using Mendelian randomization. We calculated TRS using brain transcriptome data of two independent cohorts (N = 878) and performed association analysis of TRS with diagnosis, amyloidopathy, tauopathy, and cognition. We compared AD classification performance of TRS with polygenic risk scores (PRS).

RESULTS

Higher TRS values were significantly associated with AD, amyloidopathy, tauopathy, worse cognition, and faster cognitive decline, which were replicated in an independent cohort. The AD classification performance of PRS was increased with the inclusion of TRS up to 16% with the area under the curve value of 0.850.

DISCUSSION

Our results suggest brain-based TRS improves the AD classification of PRS and may be a potential AD biomarker.

HIGHLIGHTS

Transcriptional risk score (TRS) is developed using brain RNA-Seq data. Higher TRS values are shown in Alzheimer's disease (AD). TRS improves the AD classification power of PRS up to 16%. TRS is associated with AD pathology presence. TRS is associated with worse cognitive performance and faster cognitive decline.

Molecular Gene Expression Testing to Identify Alzheimer's Disease with High Accuracy from Fingerstick Blood

Background

There is no molecular test for Alzheimer's disease (AD) using self-collected samples, nor is there a definitive molecular test for AD. We demonstrate an accurate and potentially definitive TempO-Seq® gene expression test for AD using fingerstick blood spotted and dried on filter paper, a sample that can be collected in any doctor's office or can be self-collected.

Objective

Demonstrate the feasibility of developing an accurate test for the classification of persons with AD from a minimally invasive sample of fingerstick blood spotted on filter paper which can be obtained in any doctor's office or self-collected to address health disparities.

Methods

Fingerstick blood samples from patients clinically diagnosed with AD, Parkinson's disease (PD), or asymptomatic controls were spotted onto filter paper in the doctor's office, dried, and shipped to BioSpyder for testing. Three independent patient cohorts were used for training/retraining and testing/retesting AD and PD classification algorithms.

Results

After initially identifying a 770 gene classification signature, a minimum set of 68 genes was identified providing classification test areas under the ROC curve of 0.9 for classifying patients as having AD, and 0.94 for classifying patients as having PD.

Conclusions

These data demonstrate the potential to develop a screening and/or definitive, minimally invasive, molecular diagnostic test for AD and PD using dried fingerstick blood spot samples that are collected in a doctor's office or clinic, or self-collected, and thus, can address health disparities. Whether the test can classify patients with AD earlier then possible with cognitive testing remains to be determined.

Identification of candidate DNA methylation biomarkers related to Alzheimer's disease risk by integrating genome and blood methylome data

Alzheimer disease (AD) is a common neurodegenerative disease with a late onset. It is critical to identify novel blood-based DNA methylation biomarkers to better understand the extent of the molecular pathways affected in AD. Two sets of blood DNA methylation genetic prediction models developed using different reference panels and modelling strategies were leveraged to evaluate associations of genetically predicted DNA methylation levels with AD risk in 111,326 (46,828 proxy) cases and 677,663 controls. A total of 1,168 cytosine-phosphate-guanine (CpG) sites showed a significant association with AD risk at a false discovery rate (FDR) < 0.05. Methylation levels of 196 CpG sites were correlated with expression levels of 130 adjacent genes in blood. Overall, 52 CpG sites of 32 genes showed consistent association directions for the methylation-gene expression-AD risk, including nine genes (CNIH4, THUMPD3, SERPINB9, MTUS1, CISD1, FRAT2, CCDC88B, FES, and SSH2) firstly reported as AD risk genes. Nine of 32 genes were enriched in dementia and AD disease categories (P values ranged from 1.85 × 10-4 to 7.46 × 10-6), and 19 genes in a neurological disease network (score = 54) were also observed. Our findings improve the understanding of genetics and etiology for AD.

Deep Learning-Based Prediction of Alzheimer's Disease Using Microarray Gene Expression Data

Alzheimer's disease is a genetically complex disorder, and microarray technology provides valuable insights into it. However, the high dimensionality of microarray datasets and small sample sizes pose challenges. Gene selection techniques have emerged as a promising solution to this challenge, potentially revolutionizing AD diagnosis. The study aims to investigate deep learning techniques, specifically neural networks, in predicting Alzheimer's disease using microarray gene expression data. The goal is to develop a reliable predictive model for early detection and diagnosis, potentially improving patient care and intervention strategies. This study employed gene selection techniques, including Singular Value Decomposition (SVD) and Principal Component Analysis (PCA), to pinpoint pertinent genes within microarray datasets. Leveraging deep learning principles, we harnessed a Convolutional Neural Network (CNN) as our classifier for Alzheimer's disease (AD) prediction. Our approach involved the utilization of a seven-layer CNN with diverse configurations to process the dataset. Empirical outcomes on the AD dataset underscored the effectiveness of the PCA-CNN model, yielding an accuracy of 96.60% and a loss of 0.3503. Likewise, the SVD-CNN model showcased remarkable accuracy, attaining 97.08% and a loss of 0.2466. These results accentuate the potential of our method for gene dimension reduction and classification accuracy enhancement by selecting a subset of pertinent genes. Integrating gene selection methodologies with deep learning architectures presents a promising framework for elevating AD prediction and promoting precision medicine in neurodegenerative disorders. Ongoing research endeavors aim to generalize this approach for diverse applications, explore alternative gene selection techniques, and investigate a variety of deep learning architectures.

DeepGAMI: deep biologically guided auxiliary learning for multimodal integration and imputation to improve genotype-phenotype prediction

BACKGROUND

Genotypes are strongly associated with disease phenotypes, particularly in brain disorders. However, the molecular and cellular mechanisms behind this association remain elusive. With emerging multimodal data for these mechanisms, machine learning methods can be applied for phenotype prediction at different scales, but due to the black-box nature of machine learning, integrating these modalities and interpreting biological mechanisms can be challenging. Additionally, the partial availability of these multimodal data presents a challenge in developing these predictive models.

METHOD

To address these challenges, we developed DeepGAMI, an interpretable neural network model to improve genotype-phenotype prediction from multimodal data. DeepGAMI leverages functional genomic information, such as eQTLs and gene regulation, to guide neural network connections. Additionally, it includes an auxiliary learning layer for cross-modal imputation allowing the imputation of latent features of missing modalities and thus predicting phenotypes from a single modality. Finally, DeepGAMI uses integrated gradient to prioritize multimodal features for various phenotypes.

RESULTS

We applied DeepGAMI to several multimodal datasets including genotype and bulk and cell-type gene expression data in brain diseases, and gene expression and electrophysiology data of mouse neuronal cells. Using cross-validation and independent validation, DeepGAMI outperformed existing methods for classifying disease types, and cellular and clinical phenotypes, even using single modalities (e.g., AUC score of 0.79 for Schizophrenia and 0.73 for cognitive impairment in Alzheimer's disease).

CONCLUSION

We demonstrated that DeepGAMI improves phenotype prediction and prioritizes phenotypic features and networks in multiple multimodal datasets in complex brains and brain diseases. Also, it prioritized disease-associated variants, genes, and regulatory networks linked to different phenotypes, providing novel insights into the interpretation of gene regulatory mechanisms. DeepGAMI is open-source and available for general use.

Explainable Machine Learning with Pairwise Interactions for Predicting Conversion from Mild Cognitive Impairment to Alzheimer's Disease Utilizing Multi-Modalities Data

BACKGROUND

Predicting cognition decline in patients with mild cognitive impairment (MCI) is crucial for identifying high-risk individuals and implementing effective management. To improve predicting MCI-to-AD conversion, it is necessary to consider various factors using explainable machine learning (XAI) models which provide interpretability while maintaining predictive accuracy. This study used the Explainable Boosting Machine (EBM) model with multimodal features to predict the conversion of MCI to AD during different follow-up periods while providing interpretability.

METHODS

This retrospective case-control study is conducted with data obtained from the ADNI database, with records of 1042 MCI patients from 2006 to 2022 included. The exposures included in this study were MRI biomarkers, cognitive scores, demographics, and clinical features. The main outcome was AD conversion from aMCI during follow-up. The EBM model was utilized to predict aMCI converting to AD based on three feature combinations, obtaining interpretability while ensuring accuracy. Meanwhile, the interaction effect was considered in the model. The three feature combinations were compared in different follow-up periods with accuracy, sensitivity, specificity, and AUC-ROC. The global and local explanations are displayed by importance ranking and feature interpretability plots.

RESULTS

The five-years prediction accuracy reached 85% (AUC = 0.92) using both cognitive scores and MRI markers. Apart from accuracies, we obtained features' importance in different follow-up periods. In early stage of AD, the MRI markers play a major role, while for middle-term, the cognitive scores are more important. Feature risk scoring plots demonstrated insightful nonlinear interactive associations between selected factors and outcome. In one-year prediction, lower right inferior temporal volume (<9000) is significantly associated with AD conversion. For two-year prediction, low left inferior temporal thickness (<2) is most critical. For three-year prediction, higher FAQ scores (>4) is the most important. During four-year prediction, APOE4 is the most critical. For five-year prediction, lower right entorhinal volume (<1000) is the most critical feature.

CONCLUSIONS

The established glass-box model EBMs with multimodal features demonstrated a superior ability with detailed interpretability in predicting AD conversion from MCI. Multi features with significant importance were identified. Further study may be of significance to determine whether the established prediction tool would improve clinical management for AD patients.

Machine Learning Analysis of Alzheimer's Disease Single-Cell RNA-Sequencing Data across Cortex and Hippocampus Regions

Advancements in molecular biology have revolutionized our understanding of complex diseases, with Alzheimer's disease being a prime example. Single-cell sequencing, currently the most suitable technology, facilitates profoundly detailed disease analysis at the cellular level. Prior research has established that the pathology of Alzheimer's disease varies across different brain regions and cell types. In parallel, only machine learning has the capacity to address the myriad challenges presented by such studies, where the integration of large-scale data and numerous experiments is required to extract meaningful knowledge. Our methodology utilizes single-cell RNA sequencing data from healthy and Alzheimer's disease (AD) samples, focused on the cortex and hippocampus regions in mice. We designed three distinct case studies and implemented an ensemble feature selection approach through machine learning, also performing an analysis of distinct age-related datasets to unravel age-specific effects, showing differential gene expression patterns within each condition. Important evidence was reported, such as enrichment in central nervous system development and regulation of oligodendrocyte differentiation between the hippocampus and cortex of 6-month-old AD mice as well as regulation of epinephrine secretion and dendritic spine morphogenesis in 15-month-old AD mice. Our outcomes from all three of our case studies illustrate the capacity of machine learning strategies when applied to single-cell data, revealing critical insights into Alzheimer's disease.

A New Approach for Multimodal Usage of Gene Expression and Its Image Representation for the Detection of Alzheimer's Disease

Alzheimer's disease (AD) is a complex neurodegenerative disorder and the multifaceted nature of it requires innovative approaches that integrate various data modalities to enhance its detection. However, due to the cost of collecting multimodal data, multimodal datasets suffer from an insufficient number of samples. To mitigate the impact of a limited sample size on classification, we introduce a novel deep learning method (One2MFusion) which combines gene expression data with their corresponding 2D representation as a new modality. The gene vectors were first mapped to a discriminative 2D image for training a convolutional neural network (CNN). In parallel, the gene sequences were used to train a feed forward neural network (FNN) and the outputs of the FNN and CNN were merged, and a joint deep network was trained for the binary classification of AD, normal control (NC), and mild cognitive impairment (MCI) samples. The fusion of the gene expression data and gene-originated 2D image increased the accuracy (area under the curve) from 0.86 (obtained using a 2D image) to 0.91 for AD vs. NC and from 0.76 (obtained using a 2D image) to 0.88 for MCI vs. NC. The results show that representing gene expression data in another discriminative form increases the classification accuracy when fused with base data.

c-Diadem: a constrained dual-input deep learning model to identify novel biomarkers in Alzheimer's disease

BACKGROUND

Alzheimer's disease (AD) is an incurable, debilitating neurodegenerative disorder. Current biomarkers for AD diagnosis require expensive neuroimaging or invasive cerebrospinal fluid sampling, thus precluding early detection. Blood-based biomarker discovery in Alzheimer's can facilitate less-invasive, routine diagnostic tests to aid early intervention. Therefore, we propose "c-Diadem" (constrained dual-input Alzheimer's disease model), a novel deep learning classifier which incorporates KEGG (Kyoto Encyclopedia of Genes and Genomes) pathway constraints on the input genotyping data to predict disease, i.e., mild cognitive impairment (MCI)/AD or cognitively normal (CN). SHAP (SHapley Additive exPlanations) was used to explain the model and identify novel, potential blood-based genetic markers of MCI/AD.

METHODS

We developed a novel constrained deep learning neural network which utilizes SNPs (single nucleotide polymorphisms) and microarray data from ADNI (Alzheimer's Disease Neuroimaging Initiative) to predict the disease status of participants, i.e., CN or with disease (MCI/AD), and identify potential blood-based biomarkers for diagnosis and intervention. The dataset contains samples from 626 participants, of which 212 are CN (average age 74.6 ± 5.4 years) and 414 patients have MCI/AD (average age 72.7 ± 7.6 years). KEGG pathway information was used to generate constraints applied to the input tensors, thus enhancing the interpretability of the model. SHAP scores were used to identify genes which could potentially serve as biomarkers for diagnosis and targets for drug development.

RESULTS

Our model's performance, with accuracy of 69% and AUC of 70% in the test dataset, is superior to previous models. The SHAP scores show that SNPs in PRKCZ, PLCB1 and ITPR2 as well as expression of HLA-DQB1, EIF1AY, HLA-DQA1, and ZFP57 have more impact on model predictions.

CONCLUSIONS

In addition to predicting MCI/AD, our model has been interrogated for potential genetic biomarkers using SHAP. From our analysis, we have identified blood-based genetic markers related to Ca2+ ion release in affected regions of the brain, as well as depression. The findings from our study provides insights into disease mechanisms, and can facilitate innovation in less-invasive, cost-effective diagnostics. To the best of our knowledge, our model is the first to use pathway constraints in a multimodal neural network to identify potential genetic markers for AD.

Blood biomarker-based classification study for neurodegenerative diseases

As the population ages, neurodegenerative diseases are becoming more prevalent, making it crucial to comprehend the underlying disease mechanisms and identify biomarkers to allow for early diagnosis and effective screening for clinical trials. Thanks to advancements in gene expression profiling, it is now possible to search for disease biomarkers on an unprecedented scale.Here we applied a selection of five machine learning (ML) approaches to identify blood-based biomarkers for Alzheimer's (AD) and Parkinson's disease (PD) with the application of multiple feature selection methods. Based on ROC AUC performance, one optimal random forest (RF) model was discovered for AD with 159 gene markers (ROC-AUC = 0.886), while one optimal RF model was discovered for PD (ROC-AUC = 0.743). Additionally, in comparison to traditional ML approaches, deep learning approaches were applied to evaluate their potential applications in future works. We demonstrated that convolutional neural networks perform consistently well across both the Alzheimer's (ROC AUC = 0.810) and Parkinson's (ROC AUC = 0.715) datasets, suggesting its potential in gene expression biomarker detection with increased tuning of their architecture.

Role of TET1-mediated epigenetic modulation in Alzheimer's disease

Alzheimer's disease (AD) is a neurodegenerative disorder influenced by a complex interplay of environmental, epigenetic, and genetic factors. DNA methylation (5mC) and hydroxymethylation (5hmC) are DNA modifications that serve as tissue-specific and temporal regulators of gene expression. TET family enzymes dynamically regulate these epigenetic modifications in response to environmental conditions, connecting environmental factors with gene expression. Previous epigenetic studies have identified 5mC and 5hmC changes associated with AD. In this study, we performed targeted resequencing of TET1 on a cohort of early-onset AD (EOAD) and control samples. Through gene-wise burden analysis, we observed significant enrichment of rare TET1 variants associated with AD (p = 0.04). We also profiled 5hmC in human postmortem brain tissues from AD and control groups. Our analysis identified differentially hydroxymethylated regions (DhMRs) in key genes responsible for regulating the methylome: TET3, DNMT3L, DNMT3A, and MECP2. To further investigate the role of Tet1 in AD pathogenesis, we used the 5xFAD mouse model with a Tet1 KO allele to examine how Tet1 loss influences AD pathogenesis. We observed significant changes in neuropathology, 5hmC, and RNA expression associated with Tet1 loss, while the behavioral alterations were not significant. The loss of Tet1 significantly increased amyloid plaque burden in the 5xFAD mouse (p = 0.044) and lead to a non-significant trend towards exacerbated AD-associated stress response in 5xFAD mice. At the molecular level, we found significant DhMRs enriched in genes involved in pathways responsible for neuronal projection organization, dendritic spine development and organization, and myelin assembly. RNA-Seq analysis revealed a significant increase in the expression of AD-associated genes such as Mpeg1, Ctsd, and Trem2. In conclusion, our results suggest that TET enzymes, particularly TET1, which regulate the methylome, may contribute to AD pathogenesis, as the loss of TET function increases AD-associated pathology.

Dual-specificity protein phosphatase 6 (DUSP6) overexpression reduces amyloid load and improves memory deficits in male 5xFAD mice

Background

Dual specificity protein phosphatase 6 (DUSP6) was recently identified as a key hub gene in a causal network that regulates late-onset Alzheimer's disease. Importantly, decreased DUSP6 levels are correlated with an increased clinical dementia rating in human subjects, and DUSP6 levels are additionally decreased in the 5xFAD amyloidopathy mouse model.

Methods

AAV5-DUSP6 or AAV5-GFP (control) were stereotactically injected into the dorsal hippocampus (dHc) of female and male 5xFAD or wild type mice to overexpress DUSP6 or GFP. Spatial learning memory of these mice was assessed in the Barnes maze, after which hippocampal tissues were isolated for downstream analysis.

Results

Barnes maze testing indicated that DUSP6 overexpression in the dHc of 5xFAD mice improved memory deficits and was associated with reduced amyloid plaque load, Aß 1-40 and Aß 1-42 levels, and amyloid precursor protein processing enzyme BACE1, in male but not in female mice. Microglial activation and microgliosis, which are increased in 5xFAD mice, were significantly reduced by dHc DUSP6 overexpression in both males and females. Transcriptomic profiling of female 5xFAD hippocampus revealed upregulated expression of genes involved in inflammatory and extracellular signal-regulated kinase (ERK) pathways, while dHc DUSP6 overexpression in female 5xFAD mice downregulated a subset of genes in these pathways. A limited number of differentially expressed genes (DEGs) (FDR<0.05) were identified in male mice; gene ontology analysis of DEGs (p<0.05) identified a greater number of synaptic pathways that were regulated by DUSP6 overexpression in male compared to female 5xFAD. Notably, the msh homeobox 3 gene, Msx3 , previously shown to regulate microglial M1/M2 polarization and reduce neuroinflammation, was one of the most robustly upregulated genes in female and male wild type and 5xFAD mice overexpressing DUSP6.

Conclusions

In summary, our data indicate that DUSP6 overexpression in dHc reduced amyloid deposition and memory deficits in male but not female 5xFAD mice, whereas reduced neuroinflammation and microglial activation were observed in both males and females. The sex-dependent regulation of synaptic pathways by DUSP6 overexpression, however, correlated with the improvement of spatial memory deficits in male but not female 5xFAD.

Single-cell sequencing of entorhinal cortex reveals widespread disruption of neuropeptide networks in Alzheimer's disease

INTRODUCTION

Abnormalities of neuropeptides (NPs) that play important roles in modulating neuronal activities are commonly observed in Alzheimer's disease (AD). We hypothesize that NP network disruption is widespread in AD brains.

METHODS

Single-cell transcriptomic data from the entorhinal cortex (EC) were used to investigate the NP network disruption in AD. Bulk RNA-sequencing data generated from the temporal cortex by independent groups and machine learning were employed to identify key NPs involved in AD. The relationship between aging and AD-associated NP (ADNP) expression was studied using GTEx data.

RESULTS

The proportion of cells expressing NPs but not their receptors decreased significantly in AD. Neurons expressing higher level and greater diversity of NPs were disproportionately absent in AD. Increased age coincides with decreased ADNP expression in the hippocampus.

DISCUSSION

NP network disruption is widespread in AD EC. Neurons expressing more NPs may be selectively vulnerable to AD. Decreased expression of NPs participates in early AD pathogenesis. We predict that the NP network can be harnessed for treatment and/or early diagnosis of AD.

PINNet: a deep neural network with pathway prior knowledge for Alzheimer's disease

Introduction

Identification of Alzheimer's Disease (AD)-related transcriptomic signatures from blood is important for early diagnosis of the disease. Deep learning techniques are potent classifiers for AD diagnosis, but most have been unable to identify biomarkers because of their lack of interpretability.

Methods

To address these challenges, we propose a pathway information-based neural network (PINNet) to predict AD patients and analyze blood and brain transcriptomic signatures using an interpretable deep learning model. PINNet is a deep neural network (DNN) model with pathway prior knowledge from either the Gene Ontology or Kyoto Encyclopedia of Genes and Genomes databases. Then, a backpropagation-based model interpretation method was applied to reveal essential pathways and genes for predicting AD.

Results

The performance of PINNet was compared with a DNN model without a pathway. Performances of PINNet outperformed or were similar to those of DNN without a pathway using blood and brain gene expressions, respectively. Moreover, PINNet considers more AD-related genes as essential features than DNN without a pathway in the learning process. Pathway analysis of protein-protein interaction modules of highly contributed genes showed that AD-related genes in blood were enriched with cell migration, PI3K-Akt, MAPK signaling, and apoptosis in blood. The pathways enriched in the brain module included cell migration, PI3K-Akt, MAPK signaling, apoptosis, protein ubiquitination, and t-cell activation.

Discussion

By integrating prior knowledge about pathways, PINNet can reveal essential pathways related to AD. The source codes are available at https://github.com/DMCB-GIST/PINNet.

Development and validation of a 13-gene signature associated with immune function for the detection of Alzheimer's disease

Current knowledge of Alzheimer's disease (AD) etiology and effective therapy remains limited. Thus, the identification of biomarkers is crucial to improve the detection and treatment of patients with AD. Using robust rank aggregation method to analyze the microarray data from Gene Expression Omnibus database, we identified 1138 differentially expressed genes in AD. We then explored 13 hub genes by weighted gene co-expression network analysis, least absolute shrinkage, and selection operator, and logistic regression in the training dataset. The detection model, which composed of CD163, CDC42SE1, CECR6, CSF1R, CYP27A1, EIF4E3, H2AFJ, IFIT2, IL10RA, KIAA1324, PSTPIP1, SLA, and TBC1D2 genes, along with APOE gene, showed that the area under the curve for detecting AD was 0.821 (95% confidence interval [CI] = 0.782-0.861) and the model was validated in ADNI dataset (area under the curve = 0.776; 95%CI = 0.686-0.865). Notably, the 13 genes in the model were highly enriched in immune function. These findings have implications for the detection and therapeutic target of AD.

Classification of Alzheimer's disease using robust TabNet neural networks on genetic data

Alzheimer's disease (AD) is one of the most common neurodegenerative diseases and its onset is significantly associated with genetic factors. Being the capabilities of high specificity and accuracy, genetic testing has been considered as an important technique for AD diagnosis. In this paper, we presented an improved deep learning (DL) algorithm, namely differential genes screening TabNet (DGS-TabNet) for AD binary and multi-class classifications. For performance evaluation, our proposed approach was compared with three novel DLs of multi-layer perceptron (MLP), neural oblivious decision ensembles (NODE), TabNet as well as five classical machine learnings (MLs) including decision tree (DT), random forests (RF), gradient boosting decision tree (GBDT), light gradient boosting machine (LGBM) and support vector machine (SVM) on the public data set of gene expression omnibus (GEO). Moreover, the biological interpretability of global important genetic features implemented for AD classification was revealed by the Kyoto encyclopedia of genes and genomes (KEGG) and gene ontology (GO). The results demonstrated that our proposed DGS-TabNet achieved the best performance with an accuracy of 93.80% for binary classification, and with an accuracy of 88.27% for multi-class classification. Meanwhile, the gene pathway analyses demonstrated that there existed two most important global genetic features of AVIL and NDUFS4 and those obtained 22 feature genes were partially correlated with AD pathogenesis. It was concluded that the proposed DGS-TabNet could be used to detect AD-susceptible genes and the biological interpretability of susceptible genes also revealed the potential possibility of being AD biomarkers.

Genetic and epigenetic signatures associated with plasma oxytocin levels in children and adolescents with autism spectrum disorder

Oxytocin (OT), the brain's most abundant neuropeptide, plays an important role in social salience and motivation. Clinical trials of the efficacy of OT in autism spectrum disorder (ASD) have reported mixed results due in part to ASD's complex etiology. We investigated whether genetic and epigenetic variation contribute to variable endogenous OT levels that modulate sensitivity to OT therapy. To carry out this analysis, we integrated genome-wide profiles of DNA-methylation, transcriptional activity, and genetic variation with plasma OT levels in 290 participants with ASD enrolled in a randomized controlled trial of OT. Our analysis identified genetic variants with novel association with plasma OT, several of which reside in known ASD risk genes. We also show subtle but statistically significant association of plasma OT levels with peripheral transcriptional activity and DNA-methylation profiles across several annotated gene sets. These findings broaden our understanding of the effects of the peripheral oxytocin system and provide novel genetic candidates for future studies to decode the complex etiology of ASD and its interaction with OT signaling and OT-based interventions. LAY SUMMARY: Oxytocin (OT) is an abundant chemical produced by neurons that plays an important role in social interaction and motivation. We investigated whether genetic and epigenetic factors contribute to variable OT levels in the blood. To this, we integrated genetic, gene expression, and non-DNA regulated (epigenetic) signatures with blood OT levels in 290 participants with autism enrolled in an OT clinical trial. We identified genetic association with plasma OT, several of which reside in known autism risk genes. We also show statistically significant association of plasma OT levels with gene expression and epigenetic across several gene pathways. These findings broaden our understanding of the factors that influence OT levels in the blood for future studies to decode the complex presentation of autism and its interaction with OT and OT-based treatment.

Autoencoder Networks Decipher the Association between Lung Cancer and Alzheimer’s Disease

Lung cancer is the most common malignancy and is responsible for the largest cancer-related mortality worldwide. Alzheimer’s disease is a degenerative neurological disease that burdens healthcare worldwide. While the two diseases are distinct, several transcriptomic studies have demonstrated they are linked. However, no concordant conclusion on how they are associated has been drawn. Since these studies utilized conventional bioinformatics methods, such as the differentially expressed gene (DEG) analysis, it is naturally expected that the proportion of DEGs having either the same or inverse directions in lung cancer and Alzheimer’s disease is substantial. This raises the inconsistency. Therefore, a novel bioinformatics method capable of determining the direction of association is desirable. In this study, the moderated t-tests were first used to identify DEGs that are shared by the two diseases. For the shared DEGs, separate autoencoder (AE) networks were trained to extract a one-dimensional representation (pseudogene) for each disease. Based on these pseudogenes, the association direction between lung cancer and Alzheimer’s disease was inferred. AE networks based on 266 shared DEGs revealed a comorbidity relationship between Alzheimer’s disease and lung cancer. Specifically, Spearman’s correlation coefficient between the predicted values using the two AE networks for the Alzheimer’s disease test set was 0.825 and for the lung cancer test set was 0.316. Novel bioinformatics methods such as an AE network may help decipher how distinct diseases are associated by providing the refined representations of dysregulated genes.

Deep learning approaches for noncoding variant prioritization in neurodegenerative diseases

Determining how noncoding genetic variants contribute to neurodegenerative dementias is fundamental to understanding disease pathogenesis, improving patient prognostication, and developing new clinical treatments. Next generation sequencing technologies have produced vast amounts of genomic data on cell type-specific transcription factor binding, gene expression, and three-dimensional chromatin interactions, with the promise of providing key insights into the biological mechanisms underlying disease. However, this data is highly complex, making it challenging for researchers to interpret, assimilate, and dissect. To this end, deep learning has emerged as a powerful tool for genome analysis that can capture the intricate patterns and dependencies within these large datasets. In this review, we organize and discuss the many unique model architectures, development philosophies, and interpretation methods that have emerged in the last few years with a focus on using deep learning to predict the impact of genetic variants on disease pathogenesis. We highlight both broadly-applicable genomic deep learning methods that can be fine-tuned to disease-specific contexts as well as existing neurodegenerative disease research, with an emphasis on Alzheimer's-specific literature. We conclude with an overview of the future of the field at the intersection of neurodegeneration, genomics, and deep learning.

RNASE6 is a novel modifier of APOE-ε4 effects on cognition

Apolipoprotein E4 (APOE-ε4), the strongest common genetic risk factor for Alzheimer's disease (AD), contributes to worse cognition in older adults. However, many APOE-ε4 carriers remain cognitively normal throughout life, suggesting that neuroprotective factors may be present in these individuals. In this study, we leverage whole-blood RNA sequencing (RNAseq) from 324 older adults to identify genetic modifiers of APOE-ε4 effects on cognition. Expression of RNASE6 interacted with APOE-ε4 status (p = 4.35 × 10-8) whereby higher RNASE6 expression was associated with worse memory at baseline among APOE-ε4 carriers. This interaction was replicated using RNAseq data from the prefrontal cortex in an independent dataset (N = 535; p = 0.002), suggesting the peripheral effect of RNASE6 is also present in brain tissue. RNASE6 encodes an antimicrobial peptide involved in innate immune response and has been previously observed in a gene co-expression network module with other AD-related inflammatory genes, including TREM2 and MS4A. Together, these data implicate neuroinflammation in cognitive decline, and suggest that innate immune signaling may be detectable in blood and confer differential susceptibility to AD depending on APOE-ε4.

Identification of Cardiovascular Disease-Related Genes Based on the Co-Expression Network Analysis of Genome-Wide Blood Transcriptome

Inference of co-expression network and identification of disease-related modules and gene sets can help us understand disease-related molecular pathophysiology. We aimed to identify a cardiovascular disease (CVD)-related transcriptomic signature, specifically, in peripheral blood tissue, based on differential expression (DE) and differential co-expression (DcoE) analyses. Publicly available blood sample datasets for coronary artery disease (CAD) and acute coronary syndrome (ACS) statuses were integrated to establish a co-expression network. A weighted gene co-expression network analysis was used to construct modules that include genes with highly correlated expression values. The DE criterion is a linear regression with module eigengenes for module-specific genes calculated from principal component analysis and disease status as the dependent and independent variables, respectively. The DcoE criterion is a paired t-test for intramodular connectivity between disease and matched control statuses. A total of 21 and 23 modules were established from CAD status- and ACS-related datasets, respectively, of which six modules per disease status (i.e., obstructive CAD and ACS) were selected based on the DE and DcoE criteria. For each module, gene-gene interactions with extremely high correlation coefficients were individually selected under the two conditions. Genes displaying a significant change in the number of edges (gene-gene interaction) were selected. A total of 6, 10, and 7 genes in each of the three modules were identified as potential CAD status-related genes, and 14 and 8 genes in each of the two modules were selected as ACS-related genes. Our study identified gene sets and genes that were dysregulated in CVD blood samples. These findings may contribute to the understanding of CVD pathophysiology.

Classification Model for Diabetic Foot, Necrotizing Fasciitis, and Osteomyelitis

Simple Summary

Necrotizing fasciitis (NF) and osteomyelitis (OM) are severe complications in patients with diabetic foot ulcers (DFUs). Although NF and OM often cause results including limb amputation and death, definite diagnoses of these are challenging. To aid the prompt and proper diagnosis of NF and OM in patients with DFU, we developed and evaluated a novel prediction model based on machine learning technology. In summary, our prediction model appropriately discriminated the NF and OM from diabetic foot. Moreover, this prediction model has advantages in that it is based on the demographic data and routine laboratory results, which requires no additional examinations which are complicated or expensive.

Abstract

Diabetic foot ulcers (DFUs) and their life-threatening complications, such as necrotizing fasciitis (NF) and osteomyelitis (OM), increase the healthcare cost, morbidity and mortality in patients with diabetes mellitus. While the early recognition of these complications could improve the clinical outcome of diabetic patients, it is not straightforward to achieve in the usual clinical settings. In this study, we proposed a classification model for diabetic foot, NF and OM. To select features for the classification model, multidisciplinary teams were organized and data were collected based on a literature search and automatic platform. A dataset of 1581 patients (728 diabetic foot, 76 NF, and 777 OM) was divided into training and validation datasets at a ratio of 7:3 to be analyzed. The final prediction models based on training dataset exhibited areas under the receiver operating curve (AUC) of the 0.80 and 0.73 for NF model and OM model, respectively, in validation sets. In conclusion, our classification models for NF and OM showed remarkable discriminatory power and easy applicability in patients with DFU.

Cellular transcriptional alterations of peripheral blood in Alzheimer's disease

BACKGROUND

Alzheimer's disease (AD), a progressive neurodegenerative disease, is the most common cause of dementia worldwide. Accumulating data support the contributions of the peripheral immune system in AD pathogenesis. However, there is a lack of comprehensive understanding about the molecular characteristics of peripheral immune cells in AD.

METHODS

To explore the alterations of cellular composition and the alterations of intrinsic expression of individual cell types in peripheral blood, we performed cellular deconvolution in a large-scale bulk blood expression cohort and identified cell-intrinsic differentially expressed genes in individual cell types with adjusting for cellular proportion.

RESULTS

We detected a significant increase and decrease in the proportion of neutrophils and B lymphocytes in AD blood, respectively, which had a robust replicability across other three AD cohorts, as well as using alternative algorithms. The differentially expressed genes in AD neutrophils were enriched for some AD-associated pathways, such as ATP metabolic process and mitochondrion organization. We also found a significant enrichment of protein-protein interaction network modules of leukocyte cell-cell activation, mitochondrion organization, and cytokine-mediated signaling pathway in neutrophils for AD risk genes including CD33 and IL1B. Both changes in cellular composition and expression levels of specific genes were significantly associated with the clinical and pathological alterations. A similar pattern of perturbations on the cellular proportion and gene expression levels of neutrophils could be also observed in mild cognitive impairment (MCI). Moreover, we noticed an elevation of neutrophil abundance in the AD brains.

CONCLUSIONS

We revealed the landscape of molecular perturbations at the cellular level for AD. These alterations highlight the putative roles of neutrophils in AD pathobiology.

Prediction of Alzheimer’s Disease by a Novel Image-Based Representation of Gene Expression

Early intervention can delay the progress of Alzheimer’s Disease (AD), but currently, there are no effective prediction tools. The goal of this study is to generate a reliable artificial intelligence (AI) model capable of detecting the high risk of AD, based on gene expression arrays from blood samples. To that end, a novel image-formation method is proposed to transform single-dimension gene expressions into a discriminative 2-dimensional (2D) image to use convolutional neural networks (CNNs) for classification. Three publicly available datasets were pooled, and a total of 11,618 common genes’ expression values were obtained. The genes were then categorized for their discriminating power using the Fisher distance (AD vs. control (CTL)) and mapped to a 2D image by linear discriminant analysis (LDA). Then, a six-layer CNN model with 292,493 parameters were used for classification. An accuracy of 0.842 and an area under curve (AUC) of 0.875 were achieved for the AD vs. CTL classification. The proposed method obtained higher accuracy and AUC compared with other reported methods. The conversion to 2D in CNN offers a unique advantage for improving accuracy and can be easily transferred to the clinic to drastically improve AD (or any disease) early detection.

Alzheimer's Disease Blood Biomarkers Associated With Neuroinflammation as Therapeutic Targets for Early Personalized Intervention

The definitive diagnosis of Alzheimer's Disease (AD) without the need for neuropathological confirmation remains a challenge in AD research today, despite efforts to uncover the molecular and biological underpinnings of the disease process. Furthermore, the potential for therapeutic intervention is limited upon the onset of symptoms, providing motivation for studying and treating the AD precursor mild cognitive impairment (MCI), the prodromal stage of AD instead. Applying machine learning classification to transcriptomic data of MCI, AD, and cognitively normal (CN) control patients, we identified differentially expressed genes that serve as biomarkers for the characterization and classification of subjects into MCI or AD groups. Predictive models employing these biomarker genes exhibited good classification performances for CN, MCI, and AD, significantly above random chance. The PI3K-Akt, IL-17, JAK-STAT, TNF, and Ras signaling pathways were also enriched in these biomarker genes, indicating their diagnostic potential and pathophysiological roles in MCI and AD. These findings could aid in the recognition of MCI and AD risk in clinical settings, allow for the tracking of disease progression over time in individuals as part of a therapeutic approach, and provide possible personalized drug targets for early intervention of MCI and AD.

Gestational age-specific serum creatinine can predict adverse pregnancy outcomes

Serum creatinine level (SCr) typically decreases during pregnancy due to physiologic glomerular hyperfiltration. Therefore, the clinical practice of estimated glomerular filtration rate (eGFR) based on SCr concentrations might be inapplicable to pregnant women with kidney disease since it does not take into account of the pregnancy-related biological changes. We integrated the Wonju Severance Christian Hospital (WSCH)-based findings and prior knowledge from big data to reveal the relationship between the abnormal but hidden SCr level and adverse pregnancy outcomes. We analyzed 4004 pregnant women who visited in WSCH. Adverse pregnancy outcomes included preterm birth, preeclampsia, fetal growth retardation, and intrauterine fetal demise. We categorized the pregnant women into four groups based on the gestational age (GA)-unadjusted raw distribution (Q1–4_raw), and then GA-specific (Q1–4_adj) SCr distribution. Linear regression analysis revealed that Q1-4_adj groups had better predictive outcomes than the Q1–4_raw groups. In logistic regression model, the Q1–4_adj groups exhibited a robust non-linear U-shaped relationship with the risk of adverse pregnancy outcomes, compared to the Q1–4_raw groups. The integrative analysis on SCr with respect to GA-specific distribution could be used to screen out pregnant women with a normal SCr coupled with a decreased renal function.

Association Study and Meta-Analysis of Polymorphisms and Blood mRNA Expression of the ALDH2 Gene in Patients with Alzheimer’s Disease

Background:

Late-onset Alzheimer’s disease (LOAD) is a complex disease in which neuroinflammation plays an important pathophysiological role, and exposure to neurotoxic substrates such as aldehydes may contribute. Blood mRNA expression levels of neuroinflammation-related genes appear to be potential biological markers of LOAD. A relationship between ALDH2 and LOAD has been suggested.

Objective:

Our objective was to examine blood ALDH2 expression in Japanese LOAD patients, conduct a genetic association study, and add new studies to an extended meta-analysis of the Asian population.

Methods:

A blood expression study (45 AD subjects, 54 controls) in which total RNA was isolated from whole peripheral blood samples and ALDH2 expression measured was conducted. In addition, a genetic association study (271 AD subjects, 492 controls) using genomic DNA from whole peripheral blood samples was conducted. Finally, a meta-analysis examined the relationship between ALDH2^*2 frequency and the risk of LOAD.

Results:

ALDH2 mRNA expression was significantly higher in LOAD than in controls, and also higher in men with LOAD than in women with LOAD (p = 0.043). The genotypes in the two classified groups and the allele frequency were significantly different between AD and control subjects. The meta-analysis showed a significant difference in the ALDH2^*2 allele, with an increased AD risk (OR = 1.38; 95% CI = 1.02–1.85; p = 0.0348, I² = 81.1%).

Conclusion:

There was a significant increase in blood ALDH2 expression, and a genetic association with ALDH2^*2 in LOAD. ALDH2 may have significant roles in the pathogenesis of LOAD in the Asian population.

Using the Alzheimer's Disease Neuroimaging Initiative to improve early detection, diagnosis, and treatment of Alzheimer's disease

INTRODUCTION

The Alzheimer's Disease Neuroimaging Initiative (ADNI) has accumulated 15 years of clinical, neuroimaging, cognitive, biofluid biomarker and genetic data, and biofluid samples available to researchers, resulting in more than 3500 publications. This review covers studies from 2018 to 2020.

METHODS

We identified 1442 publications using ADNI data by conventional search methods and selected impactful studies for inclusion.

RESULTS

Disease progression studies supported pivotal roles for regional amyloid beta (Aβ) and tau deposition, and identified underlying genetic contributions to Alzheimer's disease (AD). Vascular disease, immune response, inflammation, resilience, and sex modulated disease course. Biologically coherent subgroups were identified at all clinical stages. Practical algorithms and methodological changes improved determination of Aβ status. Plasma Aβ, phosphorylated tau181, and neurofilament light were promising noninvasive biomarkers. Prognostic and diagnostic models were externally validated in ADNI but studies are limited by lack of ethnocultural cohort diversity.

DISCUSSION

ADNI has had a profound impact in improving clinical trials for AD.

Augmenting Imaging Biomarker Performance with Blood-Based Gene Expression Levels for Predicting Alzheimer’s Disease Progression

Background: Structural brain imaging metrics and gene expression biomarkers have previously been used for Alzheimer’s disease (AD) diagnosis and prognosis, but none of these studies explored integration of imaging and gene expression biomarkers for predicting mild cognitive impairment (MCI)-to-AD conversion 1-2 years into the future. Objective: We investigated advantages of combining gene expression and structural brain imaging features for predicting MCI-to-AD conversion. Selection of the differentially expressed genes (DEGs) for classifying cognitively normal (CN) controls and AD patients was benchmarked against previously reported results. Methods: The current work proposes integrating brain imaging and blood gene expression data from two public datasets (ADNI and ANM) to predict MCI-to-AD conversion. A novel pipeline for combining gene expression data from multiple platforms is proposed and evaluated in the two independents patient cohorts. Results: Combining DEGs and imaging biomarkers for predicting MCI-to-AD conversion yielded 0.832-0.876 receiver operating characteristic (ROC) area under the curve (AUC), which exceeded the 0.808-0.840 AUC from using the imaging features alone. With using only three DEGs, the CN versus AD predictive model achieved 0.718, 0.858, and 0.873 cross-validation AUC for the ADNI, ANM1, and ANM2 datasets. Conclusion: For the first time we show that combining gene expression and imaging biomarkers yields better predictive performance than using imaging metrics alone. A novel pipeline for combining gene expression data from multiple platforms is proposed and evaluated to produce consistent results in the two independents patient cohorts. Using an improved feature selection, we show that predictive models with fewer gene expression probes can achieve competitive performance.

Machine Learning Framework for the Prediction of Alzheimer’s Disease Using Gene Expression Data Based on Efficient Gene Selection

In recent years, much research has focused on using machine learning (ML) for disease prediction based on gene expression (GE) data. However, many diseases have received considerable attention, whereas some, including Alzheimer’s disease (AD), have not, perhaps due to data shortage. The present work is intended to fill this gap by introducing a symmetric framework to predict AD from GE data, with the aim to produce the most accurate prediction using the smallest number of genes. The framework works in four stages after it receives a training dataset: pre-processing, gene selection (GS), classification, and AD prediction. The symmetry of the model is manifested in all of its stages. In the pre-processing stage gene columns in the training dataset are pre-processed identically. In the GS stage, the same user-defined filter metrics are invoked on every gene individually, and so are the same user-defined wrapper metrics. In the classification stage, a number of user-defined ML models are applied identically using the minimal set of genes selected in the preceding stage. The core of the proposed framework is a meticulous GS algorithm which we have designed to nominate eight subsets of the original set of genes provided in the training dataset. Exploring the eight subsets, the algorithm selects the best one to describe AD, and also the best ML model to predict the disease using this subset. For credible results, the framework calculates performance metrics using repeated stratified k-fold cross validation. To evaluate the framework, we used an AD dataset of 1157 cases and 39,280 genes, obtained by combining a number of smaller public datasets. The cases were split in two partitions, 1000 for training/testing, using 10-fold CV repeated 30 times, and 157 for validation. From the testing/training phase, the framework identified only 1058 genes to be the most relevant and the support vector machine (SVM) model to be the most accurate with these genes. In the final validation, we used the 157 cases that were never seen by the SVM classifier. For credible performance evaluation, we evaluated the classifier via six metrics, for which we obtained impressive values. Specifically, we obtained 0.97, 0.97, 0.98, 0.945, 0.972, and 0.975 for the sensitivity (recall), specificity, precision, kappa index, AUC, and accuracy, respectively.

Assessment of the Risk of Severe Dengue Using Intrahost Viral Population in Dengue Virus Serotype 2 Patients via Machine Learning

Dengue virus, a positive-sense single-stranded RNA virus, continuously threatens human health. Although several criteria for evaluation of severe dengue have been recently established, the ability to prognose the risk of severe outcomes for dengue patients remains limited. Mutant spectra of RNA viruses, including single nucleotide variants (SNVs) and defective virus genomes (DVGs), contribute to viral virulence and growth. Here, we determine the potency of intrahost viral population in dengue patients with primary infection that progresses into severe dengue. A total of 65 dengue virus serotype 2 infected patients in primary infection including 17 severe cases were enrolled. We utilized deep sequencing to directly define the frequency of SNVs and detection times of DVGs in sera of dengue patients and analyzed their associations with severe dengue. Among the detected SNVs and DVGs, the frequencies of 9 SNVs and the detection time of 1 DVG exhibited statistically significant differences between patients with dengue fever and those with severe dengue. By utilizing the detected frequencies/times of the selected SNVs/DVG as features, the machine learning model showed high average with a value of area under the receiver operating characteristic curve (AUROC, 0.966 ± 0.064). The elevation of the frequency of SNVs at E (nucleotide position 995 and 2216), NS2A (nucleotide position 4105), NS3 (nucleotide position 4536, 4606), and NS5 protein (nucleotide position 7643 and 10067) and the detection times of the selected DVG that had a deletion junction in the E protein region (nucleotide positions of the junction: between 969 and 1022) increased the possibility of dengue patients for severe dengue. In summary, we demonstrated the detected frequencies/times of SNVs/DVG in dengue patients associated with severe disease and successfully utilized them to discriminate severe patients using machine learning algorithm. The identified SNVs and DVGs that are associated with severe dengue will expand our understanding of intrahost viral population in dengue pathogenesis.