Alzheimer's Disease Brain Research Articles

Local functional connectivity abnormalities in mild cognitive impairment and Alzheimer's disease: A meta-analytic investigation using minimum Bayes factor activation likelihood estimation

Functional magnetic resonance imaging research employing regional homogeneity (ReHo) analysis has uncovered aberrant local brain connectivity in individuals with mild cognitive impairment (MCI) and Alzheimer's disease (AD) in comparison with healthy controls. However, the precise localization, extent, and possible overlap of these aberrations are still not fully understood. To bridge this gap, we applied a novel meta-analytic and Bayesian method (minimum Bayes Factor Activation Likelihood Estimation, mBF-ALE) for a systematic exploration of local functional connectivity alterations in MCI and AD brains. We extracted ReHo data via a standardized MEDLINE database search, which included 35 peer-reviewed experiments, 1,256 individuals with AD or MCI, 1,118 healthy controls, and 205 x-y-z coordinates of ReHo variation. We then separated the data into two distinct datasets: one for MCI and the other for AD. Two mBF-ALE analyses were conducted, thresholded at “very strong evidence” (mBF ≥ 150), with a minimum cluster size of 200 mm³. We also assessed the spatial consistency and sensitivity of our Bayesian results using the canonical version of the ALE algorithm. For MCI, we observed two clusters of ReHo decrease and one of ReHo increase. Decreased local connectivity was notable in the left precuneus (Brodmann area – BA 7) and left inferior temporal gyrus (BA 20), while increased connectivity was evident in the right parahippocampal gyrus (BA 36). The canonical ALE confirmed these locations, except for the inferior temporal gyrus. In AD, one cluster each of ReHo decrease and increase were found, with decreased connectivity in the right posterior cingulate cortex (BA 30 extending to BA 23) and increased connectivity in the left posterior cingulate cortex (BA 31). These locations were confirmed by the canonical ALE. The identification of these distinct functional connectivity patterns sheds new light on the complex pathophysiology of MCI and AD, offering promising directions for future neuroimaging-based interventions. Additionally, the use of a Bayesian framework for statistical thresholding enhances the robustness of neuroimaging meta-analyses, broadening its applicability to small datasets.

A Holistic Analysis of Alzheimer’s Disease-Associated lncRNA Communities Reveals Enhanced lncRNA-miRNA-RBP Regulatory Triad Formation Within Functionally Segregated Clusters

Recent studies on the regulatory networks implicated in Alzheimer’s disease (AD) evince long non-coding RNAs (lncRNAs) as crucial regulatory players, albeit a poor understanding of the mechanism. Analyzing differential gene expression in the RNA-seq data from the post-mortem AD brain hippocampus, we categorized a list of AD-dysregulated lncRNA transcripts into functionally similar communities based on their k-mer profiles. Using machine-learning-based algorithms, their subcellular localizations were mapped. We further explored the functional relevance of each community through AD-dysregulated miRNA, RNA-binding protein (RBP) interactors, and pathway enrichment analyses. Further investigation of the miRNA–lncRNA and RBP–lncRNA networks from each community revealed the top RBPs, miRNAs, and lncRNAs for each cluster. The experimental validation community yielded ELAVL4 and miR-16-5p as the predominant RBP and miRNA, respectively. Five lncRNAs emerged as the top-ranking candidates from the RBP/miRNA-lncRNA networks. Further analyses of these networks revealed the presence of multiple regulatory triads where the RBP–lncRNA interactions could be augmented by the enhanced miRNA–lncRNA interactions. Our results advance the understanding of the mechanism of lncRNA-mediated AD regulation through their interacting partners and demonstrate how these functionally segregated but overlapping regulatory networks can modulate the disease holistically.Graphical

Omics-derived biological modules reflect metabolic brain changes in Alzheimer's disease.

Brain glucose hypometabolism, indexed by the fluorodeoxyglucose positron emission tomography ([18F]FDG-PET) imaging, is a metabolic signature of Alzheimer's disease (AD). However, the underlying biological pathways involved in these metabolic changes remain elusive. Here, we integrated [18F]FDG-PET images with blood and hippocampal transcriptomic data from cognitively unimpaired (CU, n=445) and cognitively impaired (CI, n=749) individuals using modular dimension reduction techniques and voxel-wise linear regression analysis. Our results showed that multiple transcriptomic modules are associated with brain [18F]FDG-PET metabolism, with the top hits being a protein serine/threonine kinase activity gene cluster (peak-t(223)=4.86, P value<0.001) and zinc-finger-related regulatory units (peak-t(223)=3.90, P value<0.001). By integrating transcriptomics with PET imaging data, we identified that serine/threonine kinase activity-associated genes and zinc-finger-related regulatory units are highly associated with brain metabolic changes in AD. We conducted an integrated analysis of system-based transcriptomics and fluorodeoxyglucose positron emission tomography ([18F]FDG-PET) at the voxel level in Alzheimer's disease (AD). The biological process of serine/threonine kinase activity was the most associated with [18F]FDG-PET in the AD brain. Serine/threonine kinase activity alterations are associated with brain vulnerable regions in AD [18F]FDG-PET. Zinc-finger transcription factor targets were associated with AD brain [18F]FDG-PET metabolism.

Impaired cellular copper regulation in the presence of ApoE4.

The strongest genetic risk factor for late-onset Alzheimer's disease (AD) is allelic variation of the APOE gene, with the following risk structure: ε4 > ε3 > ε2. The biochemical basis for this risk profile is unclear. Here, we reveal a new role for the APOE gene product, apolipoprotein E (ApoE) in regulating cellular copper homeostasis, which is perturbed in the AD brain. Exposure of ApoE target replacement (TR) astrocytes (immortalised astrocytes from APOE knock-in mice) to elevated copper concentrations resulted in exacerbated copper accumulation in ApoE4- compared to ApoE2- and ApoE3-TR astrocytes. This effect was also observed in SH-SY5Y neuroblastoma cells treated with conditioned medium from ApoE4-TR astrocytes. Increased intracellular copper levels in the presence of ApoE4 may be explained by reduced levels and delayed trafficking of the copper transport protein, copper-transporting ATPase 1 (ATP7A/Atp7a), potentially leading to impaired cellular copper export. This new role for ApoE in copper regulation lends further biochemical insight into how APOE genotype confers risk for AD and reveals a potential contribution of ApoE4 to the copper dysregulation that is a characteristic pathological feature of the AD brain.

A pentavalent peptide vaccine elicits Aβ and tau antibodies with prophylactic activity in an Alzheimer’s disease mouse model

Amyloid-β (Aβ) and hyperphosphorylated tau protein are targets for Alzheimer’s Disease (AD) immunotherapies, which are generally focused on single epitopes within Aβ or tau. However, due to the complexity of both Aβ and tau in AD pathogenesis, a multipronged approach simultaneously targeting multiple epitopes of both proteins could overcome limitations of monotherapies. Herein, we propose an active AD immunotherapy based on a nanoparticle vaccine comprising two Aβ peptides (1–14 and pyroglutamate pE3-14) and three tau peptides (centered on phosphorylated pT181, pT217 and pS396/404). These correspond to both soluble and aggregated targets and are displayed on the surface of immunogenic liposomes in an orientation that maintains reactivity with epitope-specific monoclonal antibodies. Intramuscular immunization of mice with individual epitopes resulted in minimally cross-reactive antibody induction, while simultaneous co-display of 5 antigens (“5-plex”) induced antibodies against all epitopes without immune interference. Post-immune sera recognized plaques and neurofibrillary tangles from human AD brain tissue. Vaccine administration to 3xTg-AD mice using a prophylactic dosing schedule inhibited tau and amyloid pathologies and resulted in improved cognitive function. Immunization was well tolerated and did not induce antigen-specific cellular responses or persistent inflammatory responses in the peripheral or central nervous system. Antibody levels could be reversed by halting monthly vaccinations. Altogether, these results indicate that active immune therapies based on nanoparticle formulations of multiple Aβ and tau epitopes warrant further study for treating early-stage AD.

Modeling APOE ε4 familial Alzheimer's disease in directly converted 3D brain organoids.

Brain organoids have become a valuable tool for studying human brain development, disease modeling, and drug testing. However, generating brain organoids with mature neurons is time-intensive and often incomplete, limiting their utility in studying age-related neurodegenerative diseases such as Alzheimer's disease (AD). Here, we report the generation of 3D brain organoids from human fibroblasts through direct reprogramming, with simplicity, efficiency, and reduced variability. We also demonstrate that induced brain organoids from APOE ε4 AD patient fibroblasts capture some disease-specific features and pathologies associated with APOE ε4 AD. Moreover, APOE ε4-induced brain organoids with mutant APP overexpression faithfully recapitulate the acceleration of AD-related pathologies, providing a more physiologically relevant and patient-specific model of familial AD. Importantly, transcriptome analysis reveals that gene sets specific to APOE ε4 patient-induced brain organoids are highly similar to those of APOE ε4 post-mortem AD brains. Overall, induced brain organoids from direct reprogramming offer a promising approach for more efficient and controlled studies of neurodegenerative disease modeling.

Ligand-Based Virtual Screening as a Path to New Chemotypes for Candidate PET Radioligands for Imaging Tauopathies.

Ligand-based virtual screening (LBVS) has rarely been tested as a method for discovering new structural scaffolds for PET radioligand development. This study used LBVS to discover potential chemotype leads for developing radioligands for PET imaging of tauopathies. ZINC12, a free database of over 12 million commercially available compounds, was searched to discover novel scaffolds based on similarities to four query compounds. Thirteen high-ranking hits were purchased and assayed for their ability to compete against three tritiated radioligands at their distinct binding sites in Alzheimer's disease brain tissue. Three hits were 2-substituted 6-methoxy naphthalenes. Synthetic elaboration of this new chemotype yielded three new ligands (25, 26, and 28) with high affinity for the [3H]6 (flortaucipur) neurofibrillary tangle binding site. Compound 28 showed remarkably high affinity (Ki, 7 nM) and other desirable properties for a candidate PET radioligand, including low topological polar surface area, moderate computed log D, and amenability for labeling with carbon-11. LBVS appears to be uniquely valuable for discovering new chemotypes for candidate PET radioligands.

A Comprehensive Exploration of the Multifaceted Neuroprotective Role of Cannabinoids in Alzheimer's Disease across a Decade of Research.

Alzheimer's disease (AD), a progressive neurodegenerative disorder, manifests through dysregulation of brain function and subsequent loss of bodily control, attributed to β-amyloid plaque deposition and TAU protein hyperphosphorylation and aggregation, leading to neuronal death. Concurrently, similar cannabinoids to the ones derived from Cannabis sativa are present in the endocannabinoid system, acting through receptors CB1R and CB2R and other related receptors such as Trpv-1 and GPR-55, and are being extensively investigated for AD therapy. Given the limited efficacy and adverse effects of current available treatments, alternative approaches are crucial. Therefore, this review aims to identify effective natural and synthetic cannabinoids and elucidate their beneficial actions for AD treatment. PubMed and Scopus databases were queried (2014-2024) using keywords such as "Alzheimer's disease" and "cannabinoids". The majority of natural (Δ9-THC, CBD, AEA, etc.) and synthetic (JWH-133, WIN55,212-2, CP55-940, etc.) cannabinoids included showed promise in improving memory, cognition, and behavioral symptoms, potentially via pathways involving antioxidant effects of selective CB1R agonists (such as the BDNF/TrkB/Akt pathway) and immunomodulatory effects of selective CB2R agonists (TLR4/NF-κB p65 pathway). Combining anticholinesterase properties with a cannabinoid moiety may enhance therapeutic responses, addressing cholinergic deficits of AD brains. Thus, the positive outcomes of the vast majority of studies discussed support further advancing cannabinoids in clinical trials for AD treatment.

A Case for the Use of Open Data as a Tool to Incorporate Socioscientific Topics into Neuroscience Education.

Education scholars have called for an increased focus on developing curricula based on culturally relevant pedagogy (Ladson-Billings, 1995). A key tenet of Ladson-Billings' (1995; 2014) theory of culturally relevant pedagogy is the development of students' sociopolitical consciousness, whereby students feel empowered and encouraged to evaluate and solve real-world interdisciplinary problems. Here, we propose that open science datasets could serve as a valuable tool for neuroscience educators to foster their students' sociopolitical consciousness. Using the open data available through the Seattle Alzheimer's Disease Brain Cell Atlas (SEA-AD) as a case study, this article will explore how open science can be leveraged as a tool to encourage socioscientific thinking amongst neuroscience students. We overview a collection of lessons created by the Allen Institute's Education & Engagement team that provides a scaffolded exploration of an open science resource through a socioscientific lens. We supplement our discussion of the lessons with feedback from students who completed the lessons during a day-long workshop hosted at the Allen Institute in Seattle, WA. We conclude by reflecting on the future role this type of interdisciplinary, open science-based approach to curricula could have across neuroscience education more broadly.

Enhanced microglial dynamics and a paucity of tau seeding in the amyloid plaque microenvironment contribute to cognitive resilience in Alzheimer’s disease

Asymptomatic Alzheimer’s disease (AsymAD) describes the status of individuals with preserved cognition but identifiable Alzheimer’s disease (AD) brain pathology (i.e., beta-amyloid (Aβ) deposits, neuritic plaques, and neurofibrillary tangles) at autopsy. In this study, we investigated the postmortem brains of a cohort of AsymAD subjects to gain insight into the mechanisms underlying resilience to AD pathology and cognitive decline. Our results showed that AsymAD cases exhibit enrichment in core plaques, decreased filamentous plaque accumulation, and increased plaque-surrounding microglia. Less pathological tau aggregation in dystrophic neurites was found in AsymAD brains than in AD brains, and tau seeding activity was comparable to that in healthy brains. We used spatial transcriptomics to characterize the plaque niche further and revealed autophagy, endocytosis, and phagocytosis as the pathways associated with the genes upregulated in the AsymAD plaque niche. Furthermore, the levels of ARP2 and CAP1, which are actin-based motility proteins that participate in the dynamics of actin filaments to allow cell motility, were increased in the microglia surrounding amyloid plaques in AsymAD cases. Our findings suggest that the amyloid-plaque microenvironment in AsymAD cases is characterized by the presence of microglia with highly efficient actin-based cell motility mechanisms and decreased tau seeding compared with that in AD brains. These two mechanisms can potentially protect against the toxic cascade initiated by Aβ, preserving brain health, and slowing AD pathology progression.

Pharmacological Potential of Bioactive Peptides for the Treatment of Diseases Associated with Alzheimer's and Brain Disorders.

Bioactive peptides are a promising class of therapeutics for the treatment of diseases associated with Alzheimer's and brain disorders. These peptides are derived from naturally occurring proteins and have been shown to possess a variety of beneficial properties. They may modulate neurotransmitter systems, reduce inflammation, and improve cognitive performance. In addition, bioactive peptides have the potential to target specific molecular pathways involved in the pathogenesis of Alzheimer's and brain disorders. For example, peptides have been shown to interact with amyloid-beta, a major component of amyloid plaques found in Alzheimer's disease, and have been shown to reduce its accumulation in the brain. Furthermore, peptides have been found to modulate the activity of glutamate receptors, which are important for memory and learning, as well as to inhibit the activity of enzymes involved in the formation of toxic amyloid-beta aggregates. Finally, bioactive peptides have the potential to reduce oxidative stress and inflammation, two major components of many neurological disorders. These peptides could be used alone or in combination with traditional pharmacological treatments to improve the management of diseases associated with Alzheimer's and brain disorders.

Monomeric Amyloid Peptide-induced Toxicity in Human Oligodendrocyte Cell Line and Mouse Brain Primary Mixed-glial Cell Cultures: Evidence for a Neuroprotective Effect of Neurosteroid 3α-O-allyl-allopregnanolone.

Amyloid-peptide (Aβ) monomeric forms (ABM) occurring in presymptomatic Alzheimer's disease (AD) brain are thought to be devoid of neurotoxicity while the transition/aggregation of ABM into oligomers is determinant for Aβ-induced toxicity since Aβ is predominantly monomeric up to 3µM and aggregates over this concentration. However, recent imaging and/or histopathological investigations revealed alterations of myelin in prodromal AD brain in absence of aggregated Aβ oligomers, suggesting that ABM may induce toxicity in myelin-producing cells in early AD-stages. To check this hypothesis, here we studied ABM effects on the viability of the Human oligodendrocyte cell line (HOG), a reliable oligodendrocyte model producing myelin proteins. Furthermore, to mimic closely interactions between oligodendrocytes and other glial cells regulating myelination, we investigated also ABM effects on mouse brain primary mixed-glial cell cultures. Various methods were combined to show that ABM concentrations (600nM-1µM), extremely lower than 3µM, significantly decreased HOG cell and mouse brain primary mixed-glial cell survival. Interestingly, flow-cytometry studies using specific cell-type markers demonstrated that oligodendrocytes represent the most vulnerable glial cell population affected by ABM toxicity. Our work also shows that the neurosteroid 3α-O-allyl-allopregnanolone BR351 (250 and 500nM) efficiently prevented ABM-induced HOG and brain primary glial cell toxicity. Bicuculline (50-100nM), the GABA-A-receptor antagonist, was unable to block/reduce BR351 effect against ABM-induced HOG and primary glial cell toxicity, suggesting that BR351-evoked neuroprotection of these cells may not depend on GABA-A-receptor allosterically modulated by neurosteroids. Altogether, our results suggest that further exploration of BR351 therapeutic potential may offer interesting perspectives to develop effective neuroprotective strategies.

A novel method for the detection and classification of multiple diseases using transfer learning-based deep learning techniques with improved performance

A disease is a distinct abnormal state that significantly affects the functioning of all or part of an individual and is not caused by external harm. Diseases are frequently understood as medical conditions connected with distinct indications and symptoms. According to a fairly wide categorization, diseases can also be categorized as mental disorders, deficient diseases, genetic diseases, degenerative diseases, self-inflicted diseases, infectious diseases, non-infectious diseases, social diseases, and physical diseases. Prevention of the diseases is of multiple instances. Primary prevention seeks to prevent illness or harm before it ever happens. Secondary prevention tries to lessen the effect of an illness or damage that has already happened. This is done through diagnosing and treating illness or injury as soon as feasible to stop or delay its course, supporting personal ways to avoid recurrence or reinjury, and implementing programs to restore individuals to their previous health and function to prevent long-term difficulties. Tertiary prevention tries to lessen the impact of a continuing sickness or injury that has enduring repercussions. Diagnosis of the disease at an earlier stage is important for the treatment of the disease. Hence, in this study, deep learning algorithms, such as VGG16, EfficientNetB4, and ResNet, are utilized to diagnose various diseases, such as Alzheimer's, brain tumors, skin diseases, and lung diseases. Chest X-rays, MRI scans, CT scans, and skin lesions are used to diagnose the mentioned diseases. Transfer learning algorithms, such as VGG16, VGG19, ResNet, InceptionV3, and EfficientNetB4, are utilized to categorize various diseases. EfficientNetB4 with the learning rate annealing, having obtained an accuracy of 94.04% on the test dataset, is observed. As a consequence, we observed that every network has unique particular skills on the multi-disease dataset, which includes chest X-rays, MRI scans, etc.,

Integrative proteomics identifies a conserved Aβ amyloid responsome, novel plaque proteins, and pathology modifiers in Alzheimer’s disease

Alzheimer's disease (AD) is a complex neurodegenerative disorder that develops over decades. AD brain proteomics reveals vast alterations in protein levels and numerous altered biologic pathways. Here, we compare AD brain proteome and network changes with the brain proteomes of amyloid β (Aβ)-depositing mice to identify conserved and divergent protein networks with the conserved networks identifying an Aβ amyloid responsome. Proteins in the most conserved network (M42) accumulate in plaques, cerebrovascular amyloid (CAA), and/or dystrophic neuronal processes, and overexpression of two M42 proteins, midkine (Mdk) and pleiotrophin (PTN), increases the accumulation of Aβ in plaques and CAA. M42 proteins bind amyloid fibrils invitro, and MDK and PTN co-accumulate with cardiac transthyretin amyloid. M42 proteins appear intimately linked to amyloid deposition and can regulate amyloid deposition, suggesting that they are pathology modifiers and thus putative therapeutic targets. We posit that amyloid-scaffolded accumulation of numerous M42+ proteins is a central mechanism mediating downstream pathophysiology in AD.

B-BIND: Biophysical Bayesian Inference for Neurodegenerative Dynamics.

Throughout an organism's life, a multitude of complex and interdependent biological systems transition through biophysical processes that serve as indicators of the underlying biological states. Inferring these latent, unobserved states is a goal of modern biology and neuroscience. However, in many experimental setups, we can at best obtain discrete snapshots of the system at different times and for different individuals. This challenge is particularly relevant in the study of Alzheimer's Disease (AD) progression, where we observe the aggregation of pathology in brain donors, but the underlying disease state is unknown. This paper proposes a biophysically motivated Bayesian framework (B-BIND: Biophysical Bayesian Inference for Neurodegenerative Dynamics), where the disease state is modeled and continuously inferred from observed quantifications of multiple AD pathological proteins. Inspired by biophysical models, we describe pathological burden as an exponential process. The progression of AD is modeled by assigning a latent score, termed pseudotime, to each pathological state, creating a pseudotemporal order of donors based on their pathological burden. We study the theoretical properties of the model using linearization to reveal convergence and identifiability properties. We provide Markov chain Monte Carlo estimation algorithms, illustrating the effectiveness of our approach with multiple simulation studies across various data conditions. Applying this methodology to data from the Seattle Alzheimer's Disease Brain Cell Atlas, we infer the pseudotime ordering of donors. Finally, we analyze the information within each pathological feature to refine the model, focusing on the most informative pathologies. This framework lays the groundwork for continuous pseudotime modeling in the analysis of neurodegenerative diseases.

Role of short chain fatty acids on astrocytes and microglia in Alzheimer's disease brain

SummaryShort‐chain fatty acids (SCFAs) hold exert many nutritional benefits on both physiological and pathological processes, including host metabolism, immune modulation, and appetite control. Originating from the microbial fermentation of resistant starches and dietary fibre in the colon, SCFAs have the capability to traverse the blood–brain barrier (BBB). It is evident that SCFAs play a critical role in the development of neurodegenerative disorders such as Alzheimer's disease (AD). AD is the most common form of dementia and is characterised by the deposition of amyloid β peptides (Aβ) and tau hyperphosphorylation. SCFAs have demonstrated the potential to interfere with the protein–protein interactions required for Aβ peptides to form neurotoxic oligomers. Moreover, research indicates that the SCFAs ability to maintain endothelial integrity and interact with neuroglial cells through the BBB may assist in downregulating excessive neuroinflammatory responses to amyloid peptides. This review summarises the research on SCFAs' potential role in AD and understand their mechanism of actions on astrocytes and microglia.

Contributions of genetic variation in astrocytes to cell and molecular mechanisms of risk and resilience to late onset Alzheimer's disease.

Reactive astrocytes are associated with Alzheimer's disease (AD), and several AD genetic risk variants are associated with genes highly expressed in astrocytes. However, the contribution of genetic risk within astrocytes to cellular processes relevant to the pathogenesis of AD remains ill-defined. Here we present a resource for studying AD genetic risk in astrocytes using a large collection of induced pluripotent stem cell (iPSC) lines from deeply phenotyped individuals with a range of neuropathological and cognitive outcomes. IPSC lines from forty-four individuals were differentiated into astrocytes followed by unbiased molecular profiling using RNA sequencing and tandem mass tag-mass spectrometry. We demonstrate the utility of this resource in examining gene- and pathway-level associations with clinical and neuropathological traits, as well as in analyzing genetic risk and resilience factors through parallel analyses of iPSC-astrocytes and brain tissue from the same individuals. Our analyses reveal that genes and pathways altered in iPSC-derived astrocytes from AD individuals are concordantly dysregulated in AD brain tissue. This includes increased prefoldin proteins, extracellular matrix factors, COPI-mediated trafficking components and reduced proteins involved in cellular respiration and fatty acid oxidation. Additionally, iPSC-derived astrocytes from individuals resilient to high AD neuropathology show elevated basal levels of interferon response proteins and increased secretion of interferon gamma. Correspondingly, higher polygenic risk scores for AD are associated with lower levels of interferon response proteins. This study establishes an experimental system that integrates genetic information with a heterogeneous set of iPSCs to identify genetic contributions to molecular pathways affecting AD risk and resilience.

Screening Targets and Therapeutic Drugs for Alzheimer's Disease Based on Deep Learning Model and Molecular Docking.

Alzheimer's disease (AD) is a neurodegenerative disorder caused by a complex interplay of various factors. However, a satisfactory cure for AD remains elusive. Pharmacological interventions based on drug targets are considered the most cost-effective therapeutic strategy. Therefore, it is paramount to search potential drug targets and drugs for AD. We aimed to provide novel targets and drugs for the treatment of AD employing transcriptomic data of AD and normal control brain tissues from a new perspective. Our study combined the use of a multi-layer perceptron (MLP) with differential expression analysis, variance assessment and molecular docking to screen targets and drugs for AD. We identified the seven differentially expressed genes (DEGs) with the most significant variation (ANKRD39, CPLX1, FABP3, GABBR2, GNG3, PPM1E, and WDR49) in transcriptomic data from AD brain. A newly built MLP was used to confirm the association between the seven DEGs and AD, establishing these DEGs as potential drug targets. Drug databases and molecular docking results indicated that arbaclofen, baclofen, clozapine, arbaclofen placarbil, BML-259, BRD-K72883421, and YC-1 had high affinity for GABBR2, and FABP3 bound with oleic, palmitic, and stearic acids. Arbaclofen and YC-1 activated GABAB receptor through PI3K/AKT and PKA/CREB pathways, respectively, thereby promoting neuronal anti-apoptotic effect and inhibiting p-tau and Aβ formation. This study provided a new strategy for the identification of targets and drugs for the treatment of AD using deep learning. Seven therapeutic targets and ten drugs were selected by using this method, providing new insight for AD treatment.

Forecasting alzheimer's disease in its early stages with the use of machine learning algorithms

When it comes to dementia in the elderly, Alzheimer's disease (AD) takes the cake. Metabolic disorders impact a huge portion of the global population; as a result, there is a growing interest in using machine learning to better understand these conditions. The annual increase in their incidence rates is quite concerning. Neurodegenerative alterations impact the brain in Alzheimer's disease. Diseases impacting memory and functioning will affect healthcare providers, patients, and families at an increasing rate as the population ages. The monetary, social, and economic spheres will all feel these impacts to a significant degree. It is difficult to foretell the onset of Alzheimer's disease in its early stages. Compared to treatments administered later in the disease's progression, those administered early in the disease's progression are more effective and have less mild side effects. Finding the optimal parameters for Alzheimer's disease prediction has involved the use of several techniques, including Decision Tree, Random Forest, Support Vector Machine, Gradient Boosting, and Voting classifiers. Parameters such as F1-score for ML models, Precision, Recall, and Accuracy are used to evaluate the performance of models that use the Open Access Series of Imaging Studies (OASIS) data to make predictions about Alzheimer's disease. Medical professionals can use the suggested categorization system to identify these illnesses. Reducing yearly mortality rates of Alzheimer's disease through early diagnosis using these ML algorithms is tremendously advantageous. When tested using AD test data, the suggested approach outperforms the competition with an average validation accuracy of more than 90%. In contrast to previous studies, this one achieved a far higher test accuracy score.

Intelligent Data Processing for Alzheimer's Disease Using Deep Learning

Background: With the advancement in Alzheimer's disease (AD) brain, cells start to deteriorate, which eventually creates physical dependency and mental instability that interferes with daily living. Presently, this disease is immedicable. Therefore, the only suitable treatment is early detection and prevention. Although many studies have investigated the usefulness of deep learning in AD detection, relatively few have focused on the necessary image preprocessing processes, which are essential to any computer-aided diagnostic system. Furthermore, an optimal classification strategy that takes into account a diverse handful of prominent features is required. Method: This paper focuses on improving MRI-based AD detection by incorporating image enhancement approaches and deep hybrid learning into a fused framework to harness the power of multiple Deep Learning (DL) architectures and Machine Learning (ML) classifiers. The deep features extracted from three heterogeneous CNN architectures, namely, VGG16, DensetNet169, and MobileNetV1, are fused to produce a more informative and discriminative hybrid feature. Furthermore, the mRMR approach was used to optimise the acquired features, followed by classification via a stack of multiple ML classifiers to predict the target class. Results: The proposed architecture based on feature fusion strategy and ensemble learning resulted in 99.53%(Accuracy), 99.73%(Precision),99.70%(Recall), and 99.72% (F1 score). The presented model outperformed individual deep CNN architectures. Conclusion: Lastly, we present a sobol-based sensitivity analysis that illustrates the concentration of the presented technique upon significant regions of the image and can assist medical professionals in decoding the decisions. The presented technique exeplifies the potency and constancy of categorizing Alzheimer's disease.