A new study published in a journal Nature Communications We describe the potential for using machine learning (ML) approaches to detect genetic variants that can predict Alzheimer’s disease (AD) risk in men and women.
prologue
Less than 1 percent of Alzheimer’s disease cases are caused by dominantly inherited mutations. Sporadic late-onset AD (LOAD) is the major type of hereditary AD, with 60-80% of LOAD risk attributable to genetic mutations.
Genome-wide association studies (GWAS) show that approximately one-third of the genetic risk for LOAD comes from more than 30 loci. Most of these loci are APOEε4 genes; however, many are located in non-coding parts of the genome, making it difficult to understand their contribution to disease processes.
Women suffer from cognitive decline, brain atrophy, and lose more hippocampal neurons faster than men with the same disease. Apoe Genetic mutation and age. However, men are more likely to die from Alzheimer’s disease.
The increased risk of Alzheimer’s disease in women may be partially explained by the increased prevalence of depression, sleep alterations, and cardiometabolic abnormalities associated with profound hormonal changes due to menopause. moreover, APOEε4 It also increases the risk of Alzheimer’s disease in women.
Sex-specific genes that have been shown to influence Alzheimer’s disease risk include ACE, BDNF, and REN.
Identifying the genetic contributors underlying gender differences in AD is of great importance as it may lead to more accurate disease risk assessment and more individualized therapeutic approaches.“
What did the study show?
In the current study, researchers built a ML platform based on mutations in the genetic code that could functionally affect Alzheimer’s disease. Data are based on whole-exome sequencing (WES) performed for the Alzheimer’s Disease Sequencing Project (ADSP).
Using WES data from 2,700 AD patients and 2,400 controls, we identified functionally significant nonsynonymous coding variants in genes associated with AD. Most of these variants are of unknown importance. However, evolutionary action (EA) scores were used to estimate the potential impact of each mutation on gene function.
Identification of AD genes
A total of 98 genes were identified. Apoe top gene. Therefore, the EAML approach is able to distinguish gene sequences of AD cases from those of controls, even with small datasets.
EAML genes were found to be expressed at higher levels in cellular pathways associated with AD. Of the 98 individuals, about half also showed significant dysregulation in AD compared to controls, indicating their role in AD-associated neuronal damage.
Further exploration identified 22 genes expressed at higher levels in immune response pathways in both sexes, some of which include cytokine signaling and microglial phagocytosis.
A total of 45 dysregulated genes were also enriched in immune response pathways. This supports early studies showing that neuroinflammation is the primary cause of Alzheimer’s disease through various genetic pathways.
Improved predictive ability
These genes were incorporated into a computational model aimed at predicting Alzheimer’s disease risk. The results showed that using these genetic parameters improved risk prediction compared to age of onset and risk prediction based on age of onset. Apoe Mutant.
ML predictors trained using gene features selected by EAML may have prognostic value for risk of developing AD“
EAML was also able to identify more than half of the candidate genes in a smaller cohort compared to other models that identified only about 10% of the genes. The top genes consistently maintained their ranking even when the cohort size was reduced.
Most of these top genes have been identified as either dysregulated or contributing to the development of AD. Therefore, EAML appears to be a reliable predictive approach for AD risk, even with sample sizes unsuitable for other methods.
neurodegenerative modifier gene
Results were tested in Drosophila Drosophila Two laboratory mutants expressing abnormal tau or secreted Aβ42 protein. 73 out of 98 genes were tested by introducing loss-of-function homologues.
Of these, 36 were found to modulate tau-related neurodegenerative pathways. More specifically, the loss of function of 24 genes slowed neurodegeneration in the presence of tau, whereas neurodegeneration was accelerated in the remaining 12 loss-of-function mutants.
In the secretory Aβ42 model, 17 loss-of-function gene homologues were associated with enhanced neurodegeneration and 12 with amelioration. Thus, the 27 genes identified in this study attenuated the adverse effects of neuropathy when knocked down. The findings obtained in this way are in vivo Validation of this platform.
sex-specific genes
Sex-specific genes were identified when female and male sequences were processed separately. The ML approach showed that stress response genes were emphasized in males, whereas cell cycle genes were higher in females. In fact, 21 of her 50 genes that were duplicated identified by separate male–female analyzes were identified by the combined analysis.
In women, five genes associated with both Alzheimer’s disease and tau/Aβ42-induced neuropathy were dysregulated in women with Alzheimer’s disease. This may reflect the higher risk of Alzheimer’s disease in women than in men, which is associated with disturbances in cell cycle pathways.
What is the impact?
These proof-of-concept findings support a general approach to identifying genetic mechanisms associated with complex diseases by machine learning on case-control sequence data using phylogenetic evolutionary information.“
Identification of 27 genes that regulate neuronal defects by attenuation Drosophila may be therapeutically important.
Several drugs are now available that act on the 11 genes identified in this study. In fact, one of the two male-specific genes is currently being evaluated in preclinical and clinical trials.
Of the four female-specific genes that have drug candidates targeting their activity, several have shown beneficial effects in mouse models. Future gender-based clinical trials may help define which treatments are more effective in both genders.
Furthermore, the results of this study may help improve the accuracy of risk prediction based on genomic profiles, especially in men. Moreover, in the future, the use of his EAML on larger datasets may lead to a better understanding of sex-specific mechanisms contributing to AD.
ML’s general approach to functionally impacting variants enables the discovery of sex-specific candidates for diagnostic biomarkers and therapeutic targets“
Reference magazines:
- Bulkar, T., Kwanghyuk, L., Al Ramahhi, I., other. (2023). Functional mutations identify sex-specific genes and pathways in Alzheimer’s disease. Nature Communications. Doi: 10.1038/s41467-023-38374-z.
Quote
To cite this article in your essay, paper or report, please use one of the following formats:
-
Apa
Thomas, Lizzie. (May 16, 2023). Machine learning reveals gender-specific Alzheimer’s disease risk genes. news medical. Retrieved May 16, 2023 from https://www.news-medical.net/news/20230516/Machine-learning-reveals-sex-specific-Alzheimers-risk-genes.aspx.
-
MLA
Thomas, Lizzie. “Machine learning reveals sex-specific Alzheimer’s risk genes.” News – Medical. May 16, 2023.
-
Chicago
Thomas, Lizzie. “Machine learning reveals sex-specific Alzheimer’s disease risk genes.” News Medical. https://www.news-medical.net/news/20230516/Machine-learning-reveals-sex-specific-Alzheimers-risk-genes.aspx. (Accessed May 16, 2023).
-
Harvard University
Thomas, Lizzie. 2023. Machine learning reveals sex-specific Alzheimer’s disease risk genes. News-Medical, accessed May 16, 2023, https://www.news-medical.net/news/20230516/Machine-learning-reveals-sex-specific-Alzheimers-risk-genes.aspx.
