Challenges of Integrative Disease Modeling in Alzheimer's Disease

A computational approach to identify phytochemicals as potential inhibitor of acetylcholinesterase: Molecular docking, ADME profiling and molecular dynamics simulations

Inhibition of acetylcholinesterase (AChE) is a crucial target in the treatment of Alzheimer's disease (AD). Common anti-acetylcholinesterase drugs such as Galantamine, Rivastigmine, Donepezil, and Tacrine have significant inhibition potential. Due to side effects and safety concerns, we aimed to investigate a wide range of phytochemicals and structural analogues of these compounds. Compounds similar to the established drugs, and phytochemicals were investigated as potential inhibitors for AChE in treating AD. A total of 2,270 compound libraries were generated for further analysis. Initial virtual screening was performed using Pyrx software, resulting in 638 molecules showing higher binding affinities compared to positive controls Tacrine (-9.0 kcal/mol), Donepezil (-7.3 kcal/mol), Galantamine (-8.3 kcal/mol), and Rivastigmine (-6.4 kcal/mol). Subsequently, ADME properties were assessed, including blood-brain barrier permeability and Lipinski's rule of five violations, leading to 88 compounds passing the ADME analysis. Among the rivastigmine analogous, [3-(1-methylpiperidin-2-yl)phenyl] N,N-diethylcarbamate showed interaction with Tyr123, Tyr336, Tyr340, Phe337, Trp285 residues of AChE. Tacrine similar compounds, such as 4-amino-2-styrylquinoline, exhibited bindings with Tyr123, Phe337, Tyr336, Trp285, Trp85, Gly119, and Gly120 residues. A phytocompound (bisdemethoxycurcumin) showed interaction with Trp285, Tyr340, Trp85, Tyr71, and His446 residues of AChE with favourable binding. These findings underscore the potential of these compounds as novel inhibitors of AChE, offering insights into alternative therapeutic avenues for AD. A 100ns simulation analysis confirmed the stability of protein-ligand complex based on the RMSD, RMSF, ligand properties, PCA, DCCM and MMGBS parameters. The investigation suggested 3 ligands as a potent inhibitor of AChE which are [3-(1-methylpiperidin-2-yl)phenyl] N,N-diethylcarbamate, 4-Amino-2-styrylquinoline and bisdemethoxycurcumin. Furthermore, investigation, including in-vitro and in-vivo studies, is needed to validate the efficacy, safety profiles, and therapeutic potential of these compounds for AD treatment.

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.

Harnessing the potential of machine learning and artificial intelligence for dementia research

Progress in dementia research has been limited, with substantial gaps in our knowledge of targets for prevention, mechanisms for disease progression, and disease-modifying treatments. The growing availability of multimodal data sets opens possibilities for the application of machine learning and artificial intelligence (AI) to help answer key questions in the field. We provide an overview of the state of the science, highlighting current challenges and opportunities for utilisation of AI approaches to move the field forward in the areas of genetics, experimental medicine, drug discovery and trials optimisation, imaging, and prevention. Machine learning methods can enhance results of genetic studies, help determine biological effects and facilitate the identification of drug targets based on genetic and transcriptomic information. The use of unsupervised learning for understanding disease mechanisms for drug discovery is promising, while analysis of multimodal data sets to characterise and quantify disease severity and subtype are also beginning to contribute to optimisation of clinical trial recruitment. Data-driven experimental medicine is needed to analyse data across modalities and develop novel algorithms to translate insights from animal models to human disease biology. AI methods in neuroimaging outperform traditional approaches for diagnostic classification, and although challenges around validation and translation remain, there is optimism for their meaningful integration to clinical practice in the near future. AI-based models can also clarify our understanding of the causality and commonality of dementia risk factors, informing and improving risk prediction models along with the development of preventative interventions. The complexity and heterogeneity of dementia requires an alternative approach beyond traditional design and analytical approaches. Although not yet widely used in dementia research, machine learning and AI have the potential to unlock current challenges and advance precision dementia medicine.

ADataViewer: exploring semantically harmonized Alzheimer's disease cohort datasets

BACKGROUND

Currently, Alzheimer's disease (AD) cohort datasets are difficult to find and lack across-cohort interoperability, and the actual content of publicly available datasets often only becomes clear to third-party researchers once data access has been granted. These aspects severely hinder the advancement of AD research through emerging data-driven approaches such as machine learning and artificial intelligence and bias current data-driven findings towards the few commonly used, well-explored AD cohorts. To achieve robust and generalizable results, validation across multiple datasets is crucial.

METHODS

We accessed and systematically investigated the content of 20 major AD cohort datasets at the data level. Both, a medical professional and a data specialist, manually curated and semantically harmonized the acquired datasets. Finally, we developed a platform that displays vital information about the available datasets.

RESULTS

Here, we present ADataViewer, an interactive platform that facilitates the exploration of 20 cohort datasets with respect to longitudinal follow-up, demographics, ethnoracial diversity, measured modalities, and statistical properties of individual variables. It allows researchers to quickly identify AD cohorts that meet user-specified requirements for discovery and validation studies regarding available variables, sample sizes, and longitudinal follow-up. Additionally, we publish the underlying variable mapping catalog that harmonizes 1196 unique variables across the 20 cohorts and paves the way for interoperable AD datasets.

CONCLUSIONS

In conclusion, ADataViewer facilitates fast, robust data-driven research by transparently displaying cohort dataset content and supporting researchers in selecting datasets that are suited for their envisioned study. The platform is available at https://adata.scai.fraunhofer.de/ .

Unraveling the heterogeneity in Alzheimer's disease progression across multiple cohorts and the implications for data-driven disease modeling

INTRODUCTION

Given study-specific inclusion and exclusion criteria, Alzheimer's disease (AD) cohort studies effectively sample from different statistical distributions. This heterogeneity can propagate into cohort-specific signals and subsequently bias data-driven investigations of disease progression patterns.

METHODS

We built multi-state models for six independent AD cohort datasets to statistically compare disease progression patterns across them. Additionally, we propose a novel method for clustering cohorts with regard to their progression signals.

RESULTS

We identified significant differences in progression patterns across cohorts. Models trained on cohort data learned cohort-specific effects that bias their estimations. We demonstrated how six cohorts relate to each other regarding their disease progression.

DISCUSSION

Heterogeneity in cohort datasets impedes the reproducibility of data-driven results and validation of progression models generated on single cohorts. To ensure robust scientific insights, it is advisable to externally validate results in independent cohort datasets. The proposed clustering assesses the comparability of cohorts in an unbiased, data-driven manner.

Degenerative adversarial neuroimage nets for brain scan simulations: Application in ageing and dementia

•

We implemented a new deep learning framework capable of synthesising realistic and accurate 4D brain MRI in ageing and Alzheimer’s disease.

•

We proposed a sequence of memory-efficient techniques designed to improve model stability, reduce artefacts, and improve individualization.

•

Synthesised T1w MRI scans contain only minor structural differences with real data, and have minimal noise/texture artefacts.

•

Synthesised MRI scans were diagnostically indistinguishable from real scans.

•

Synthetic MRI can be used for: i) data augmentation, ii) model validation and iii) understanding biological/disease mechanisms in the brain.

Accurate and realistic simulation of high-dimensional medical images has become an important research area relevant to many AI-enabled healthcare applications. However, current state-of-the-art approaches lack the ability to produce satisfactory high-resolution and accurate subject-specific images. In this work, we present a deep learning framework, namely 4D-Degenerative Adversarial NeuroImage Net (4D-DANI-Net), to generate high-resolution, longitudinal MRI scans that mimic subject-specific neurodegeneration in ageing and dementia. 4D-DANI-Net is a modular framework based on adversarial training and a set of novel spatiotemporal, biologically-informed constraints. To ensure efficient training and overcome memory limitations affecting such high-dimensional problems, we rely on three key technological advances: i) a new 3D training consistency mechanism called Profile Weight Functions (PWFs), ii) a 3D super-resolution module and iii) a transfer learning strategy to fine-tune the system for a given individual. To evaluate our approach, we trained the framework on 9852 T1-weighted MRI scans from 876 participants in the Alzheimer’s Disease Neuroimaging Initiative dataset and held out a separate test set of 1283 MRI scans from 170 participants for quantitative and qualitative assessment of the personalised time series of synthetic images. We performed three evaluations: i) image quality assessment; ii) quantifying the accuracy of regional brain volumes over and above benchmark models; and iii) quantifying visual perception of the synthetic images by medical experts. Overall, both quantitative and qualitative results show that 4D-DANI-Net produces realistic, low-artefact, personalised time series of synthetic T1 MRI that outperforms benchmark models.

Disease Modelling of Cognitive Outcomes and Biomarkers in the European Prevention of Alzheimer's Dementia Longitudinal Cohort

A key challenge for the secondary prevention of Alzheimer’s dementia is the need to identify individuals early on in the disease process through sensitive cognitive tests and biomarkers. The European Prevention of Alzheimer’s Dementia (EPAD) consortium recruited participants into a longitudinal cohort study with the aim of building a readiness cohort for a proof-of-concept clinical trial and also to generate a rich longitudinal data-set for disease modelling. Data have been collected on a wide range of measurements including cognitive outcomes, neuroimaging, cerebrospinal fluid biomarkers, genetics and other clinical and environmental risk factors, and are available for 1,828 eligible participants at baseline, 1,567 at 6 months, 1,188 at one-year follow-up, 383 at 2 years, and 89 participants at three-year follow-up visit. We novelly apply state-of-the-art longitudinal modelling and risk stratification approaches to these data in order to characterise disease progression and biological heterogeneity within the cohort. Specifically, we use longitudinal class-specific mixed effects models to characterise the different clinical disease trajectories and a semi-supervised Bayesian clustering approach to explore whether participants can be stratified into homogeneous subgroups that have different patterns of cognitive functioning evolution, while also having subgroup-specific profiles in terms of baseline biomarkers and longitudinal rate of change in biomarkers.

Caution, "normal" BMI: health risks associated with potentially masked individual underweight-EPMA Position Paper 2021

An increasing interest in a healthy lifestyle raises questions about optimal body weight. Evidently, it should be clearly discriminated between the standardised "normal" body weight and individually optimal weight. To this end, the basic principle of personalised medicine "one size does not fit all" has to be applied. Contextually, "normal" but e.g. borderline body mass index might be optimal for one person but apparently suboptimal for another one strongly depending on the individual genetic predisposition, geographic origin, cultural and nutritional habits and relevant lifestyle parameters-all included into comprehensive individual patient profile. Even if only slightly deviant, both overweight and underweight are acknowledged risk factors for a shifted metabolism which, if being not optimised, may strongly contribute to the development and progression of severe pathologies. Development of innovative screening programmes is essential to promote population health by application of health risks assessment, individualised patient profiling and multi-parametric analysis, further used for cost-effective targeted prevention and treatments tailored to the person. The following healthcare areas are considered to be potentially strongly benefiting from the above proposed measures: suboptimal health conditions, sports medicine, stress overload and associated complications, planned pregnancies, periodontal health and dentistry, sleep medicine, eye health and disorders, inflammatory disorders, healing and pain management, metabolic disorders, cardiovascular disease, cancers, psychiatric and neurologic disorders, stroke of known and unknown aetiology, improved individual and population outcomes under pandemic conditions such as COVID-19. In a long-term way, a significantly improved healthcare economy is one of benefits of the proposed paradigm shift from reactive to Predictive, Preventive and Personalised Medicine (PPPM/3PM). A tight collaboration between all stakeholders including scientific community, healthcare givers, patient organisations, policy-makers and educators is essential for the smooth implementation of 3PM concepts in daily practice.

Analysis of Age-Dependent Alterations in Excitability Properties of CA1 Pyramidal Neurons in an APPPS1 Model of Alzheimer's Disease

Age-dependent accumulation of amyloid-β, provoking increasing brain amyloidopathy, triggers abnormal patterns of neuron activity and circuit synchronization in Alzheimer’s disease (AD) as observed in human AD patients and AD mouse models. Recent studies on AD mouse models, mimicking this age-dependent amyloidopathy, identified alterations in CA1 neuron excitability. However, these models generally also overexpress mutated amyloid precursor protein (APP) and presenilin 1 (PS1) and there is a lack of a clear correlation of neuronal excitability alterations with progressive amyloidopathy. The active development of computational models of AD points out the need of collecting such experimental data to build a reliable disease model exhibiting AD-like disease progression. We therefore used the feature extraction tool of the Human Brain Project (HBP) Brain Simulation Platform to systematically analyze the excitability profile of CA1 pyramidal neuron in the APPPS1 mouse model. We identified specific features of neuron excitability that best correlate either with over-expression of mutated APP and PS1 or increasing Aβ amyloidopathy. Notably, we report strong alterations in membrane time constant and action potential width and weak alterations in firing behavior. Also, using a CA1 pyramidal neuron model, we evidence amyloidopathy-dependent alterations in I_h. Finally, cluster analysis of these recordings showed that we could reliably assign a trace to its correct group, opening the door to a more refined, less variable analysis of AD-affected neurons. This inter-disciplinary analysis, bringing together experimentalists and modelers, helps to further unravel the neuronal mechanisms most affected by AD and to build a biologically plausible computational model of the AD brain.

Bridging Scales in Alzheimer's Disease: Biological Framework for Brain Simulation With The Virtual Brain

Despite the acceleration of knowledge and data accumulation in neuroscience over the last years, the highly prevalent neurodegenerative disease of AD remains a growing problem. Alzheimer's Disease (AD) is the most common cause of dementia and represents the most prevalent neurodegenerative disease. For AD, disease-modifying treatments are presently lacking, and the understanding of disease mechanisms continues to be incomplete. In the present review, we discuss candidate contributing factors leading to AD, and evaluate novel computational brain simulation methods to further disentangle their potential roles. We first present an overview of existing computational models for AD that aim to provide a mechanistic understanding of the disease. Next, we outline the potential to link molecular aspects of neurodegeneration in AD with large-scale brain network modeling using The Virtual Brain (www.thevirtualbrain.org), an open-source, multiscale, whole-brain simulation neuroinformatics platform. Finally, we discuss how this methodological approach may contribute to the understanding, improved diagnostics, and treatment optimization of AD.

Disease progression modeling of Alzheimer's disease according to education level

To develop a disease progression model of Alzheimer’s disease (AD) that shows cognitive decline from subjective cognitive impairments (SCI) to the end stage of AD dementia (ADD) and to investigate the effect of education level on the whole disease spectrum, we enrolled 565 patients who were followed up more than three times and had a clinical dementia rating sum of boxes (CDR-SB). Three cohorts, SCI (n = 85), amnestic mild cognitive impairment (AMCI, n = 240), and ADD (n = 240), were overlapped in two consecutive cohorts (SCI and AMCI, AMCI and ADD) to construct a model of disease course, and a model with multiple single-cohorts was estimated using a mixed-effect model. To examine the effect of education level on disease progression, the disease progression model was developed with data from lower (≤ 12) and higher (> 12) education groups. Disease progression takes 274.3 months (22.9 years) to advance from 0 to 18 points using the CDR-SB. Based on our predictive equation, it takes 116.5 months to progress from SCI to AMCI and 56.2 months to progress from AMCI to ADD. The rate of CDR-SB progression was different according to education level. The lower-education group showed faster CDR-SB progression from SCI to AMCI compared to the higher-education group, and this trend disappeared from AMCI to ADD. In the present study, we developed a disease progression model of AD spectrum from SCI to the end stage of ADD. Our disease modeling provides us with more understanding of the effect of education on cognitive trajectories.