There are many active research projects accessing and applying shared ADNI data. Use the search above to find specific research focuses on the active ADNI investigations. This information is requested annually as a requirement for data access.
Principal Investigator | |
Principal Investigator's Name: | Jinhyeong Bae |
Institution: | IUPUI |
Department: | Medical Neuroscience |
Country: | |
Proposed Analysis: | Our research is interdisciplinary research that bridges the predictive performance of the deep learning approach to the identification of Alzheimer’s disease (AD) genetic risk factors and the development of clinical studies for personalized preventive medicine. Many prior studies have utilized computational algorithms in determining AD-genetic risk factors. However, their capability in quantifying epistatic effects between SNPs was limited. Our research, in this regard, developed a novel deep-learning framework by utilizing the Capsule network, which has a theoretical background in identifying spatial relations between SNPs. The model determined potential AD-risk SNPs and quantified their single contribution as well as epistatic interactions in increasing the risk of SNP at the individual level. We showed that these AD-risk SNPs have strong associations with AD progression, i.e., the rate of cognitive decline and cerebrospinal fluid protein changes. Furthermore, we conducted a computational CRISPR simulation by replacing an individual’s genetic variant at a certain locus with a reference genome to produce the expected outcome, i.e., the likelihood of AD occurrence. when CRISPR technology is implemented. Therefore, our research could not only provide an explanation of the genetic dynamics of AD but also help in building personalized preventive medicine. |
Additional Investigators | |
Investigator's Name: | Liana Apostolova |
Proposed Analysis: | Our research is interdisciplinary research that bridges the predictive performance of the deep learning approach to the identification of Alzheimer’s disease (AD) genetic risk factors and the development of clinical studies for personalized preventive medicine. Many prior studies have utilized computational algorithms in determining AD-genetic risk factors. However, their capability in quantifying epistatic effects between SNPs was limited. Our research, in this regard, developed a novel deep-learning framework by utilizing the Capsule network, which has a theoretical background in identifying spatial relations between SNPs. The model determined potential AD-risk SNPs and quantified their single contribution as well as epistatic interactions in increasing the risk of SNP at the individual level. We showed that these AD-risk SNPs have strong associations with AD progression, i.e., the rate of cognitive decline and cerebrospinal fluid protein changes. Furthermore, we conducted a computational CRISPR simulation by replacing an individual’s genetic variant at a certain locus with a reference genome to produce the expected outcome, i.e., the likelihood of AD occurrence. when CRISPR technology is implemented. Therefore, our research could not only provide an explanation of the genetic dynamics of AD but also help in building personalized preventive medicine. |