Deep learning-based polygenic risk analysis for Alzheimer's disease prediction

Biomarker-Based Precision Therapy for Alzheimer's Disease: Multidimensional Evidence Leading a New Breakthrough in Personalized Medicine

(1) Background: Alzheimer's disease (AD) is a worldwide neurodegenerative disorder characterized by the buildup of abnormal proteins in the central nervous system and cognitive decline. Since no radical therapy exists, only symptomatic treatments alleviate symptoms temporarily. In this review, we will explore the latest advancements in precision medicine and biomarkers for AD, including their potential to revolutionize the way we diagnose and treat this devastating condition. (2) Methods: A literature search was performed combining the following Medical Subject Heading (MeSH) terms on PubMed: "Alzheimer's disease", "biomarkers", "APOE", "APP", "GWAS", "cerebrospinal fluid", "polygenic risk score", "Aβ42", "τP-181", " p-tau217", "ptau231", "proteomics", "total tau protein", and "precision medicine" using Boolean operators. (3) Results: Genome-wide association studies (GWAS) have identified numerous genetic variants associated with AD risk, while a transcriptomic analysis has revealed dysregulated gene expression patterns in the brains of individuals with AD. The proteomic and metabolomic profiling of biological fluids, such as blood, urine, and CSF, and neuroimaging biomarkers have also yielded potential biomarkers of AD that could be used for the early diagnosis and monitoring of disease progression. (4) Conclusion: By leveraging a combination of the above biomarkers, novel ultrasensitive immunoassays, mass spectrometry methods, and metabolomics, researchers are making significant strides towards personalized healthcare for individuals with AD.

Optimizing clinico-genomic disease prediction across ancestries: a machine learning strategy with Pareto improvement

BACKGROUND

Accurate prediction of an individual's predisposition to diseases is vital for preventive medicine and early intervention. Various statistical and machine learning models have been developed for disease prediction using clinico-genomic data. However, the accuracy of clinico-genomic prediction of diseases may vary significantly across ancestry groups due to their unequal representation in clinical genomic datasets.

METHODS

We introduced a deep transfer learning approach to improve the performance of clinico-genomic prediction models for data-disadvantaged ancestry groups. We conducted machine learning experiments on multi-ancestral genomic datasets of lung cancer, prostate cancer, and Alzheimer's disease, as well as on synthetic datasets with built-in data inequality and distribution shifts across ancestry groups.

RESULTS

Deep transfer learning significantly improved disease prediction accuracy for data-disadvantaged populations in our multi-ancestral machine learning experiments. In contrast, transfer learning based on linear frameworks did not achieve comparable improvements for these data-disadvantaged populations.

CONCLUSIONS

This study shows that deep transfer learning can enhance fairness in multi-ancestral machine learning by improving prediction accuracy for data-disadvantaged populations without compromising prediction accuracy for other populations, thus providing a Pareto improvement towards equitable clinico-genomic prediction of diseases.

Stacked neural network for predicting polygenic risk score

In recent years, the utility of polygenic risk scores (PRS) in forecasting disease susceptibility from genome-wide association studies (GWAS) results has been widely recognised. Yet, these models face limitations due to overfitting and the potential overestimation of effect sizes in correlated variants. To surmount these obstacles, we devised the Stacked Neural Network Polygenic Risk Score (SNPRS). This novel approach synthesises outputs from multiple neural network models, each calibrated using genetic variants chosen based on diverse p-value thresholds. By doing so, SNPRS captures a broader array of genetic variants, enabling a more nuanced interpretation of the combined effects of these variants. We assessed the efficacy of SNPRS using the UK Biobank data, focusing on the genetic risks associated with breast and prostate cancers, as well as quantitative traits like height and BMI. We also extended our analysis to the Korea Genome and Epidemiology Study (KoGES) dataset. Impressively, our results indicate that SNPRS surpasses traditional PRS models and an isolated deep neural network in terms of accuracy, highlighting its promise in refining the efficacy and relevance of PRS in genetic studies.

Artificial intelligence in neurology: opportunities, challenges, and policy implications

Neurological conditions are the leading cause of disability and mortality combined, demanding innovative, scalable, and sustainable solutions. Brain health has become a global priority with adoption of the World Health Organization's Intersectoral Global Action Plan in 2022. Simultaneously, rapid advancements in artificial intelligence (AI) are revolutionizing neurological research and practice. This scoping review of 66 original articles explores the value of AI in neurology and brain health, systematizing the landscape for emergent clinical opportunities and future trends across the care trajectory: prevention, risk stratification, early detection, diagnosis, management, and rehabilitation. AI's potential to advance personalized precision neurology and global brain health directives hinges on resolving core challenges across four pillars-models, data, feasibility/equity, and regulation/innovation-through concerted pursuit of targeted recommendations. Paramount actions include swift, ethical, equity-focused integration of novel technologies into clinical workflows, mitigating data-related issues, counteracting digital inequity gaps, and establishing robust governance frameworks balancing safety and innovation.

Machine Learning to Advance Human Genome-Wide Association Studies

Machine learning, including deep learning, reinforcement learning, and generative artificial intelligence are revolutionising every area of our lives when data are made available. With the help of these methods, we can decipher information from larger datasets while addressing the complex nature of biological systems in a more efficient way. Although machine learning methods have been introduced to human genetic epidemiological research as early as 2004, those were never used to their full capacity. In this review, we outline some of the main applications of machine learning to assigning human genetic loci to health outcomes. We summarise widely used methods and discuss their advantages and challenges. We also identify several tools, such as Combi, GenNet, and GMSTool, specifically designed to integrate these methods for hypothesis-free analysis of genetic variation data. We elaborate on the additional value and limitations of these tools from a geneticist's perspective. Finally, we discuss the fast-moving field of foundation models and large multi-modal omics biobank initiatives.

Increased Maternal Compared to Paternal Transmission of Alzheimer's Disease May Be Due to Increased Incidence of Depression in Women

BACKGROUND

Mothers transmit Alzheimer's disease (AD) more frequently than fathers. Factors other than female longevity may be at work to promote maternal transmission of AD. Among these are the X chromosome, mitochondrial DNA, and AD comorbidities, especially depression. A recent study associated mitochondrial SNP rs2853499 with AD.

MATERIALS AND METHODS

We used UK Biobank (UKBB) data to investigate the relation of mitochondrial SNP rs2853499, with AD. To identify cases of AD we used ICD10 code G30.9. Data processing was performed on Minerva, a Linux mainframe with Centos 7.6, at the Icahn School of Medicine at Mount Sinai. We used PLINK, a whole-genome association analysis toolset, to analyze the UKB22418 mitochondrial hard-called chromosome file.

RESULTS

Of 953 AD cases, 493 were male (51.7%) and 460 were female (48.3%). Mothers were twice as likely to transmit AD compared to fathers. We found that in individuals with AD, 22.3% (n=201) carried the A allele of SNP rs2853499, 77.7% (n=700) carried the G allele. In individuals without AD, 22.2% (n=10,7726) carried the A allele of SNP rs2853499, 77.8% (n=378,535) carried the G allele. This difference was not significant (p=0.91, two-tailed Fisher exact test). Therefore, factors other than mitochondrial SNP rs2853499 may be at work to promote maternal transmission of AD.

CONCLUSION

We conclude that depression, a multigenic illness, in the mother is most likely the basis for the fact that mothers transmit AD twice as often as fathers.