Abstract
With increased research funding for Alzheimer’s disease (AD) and related disorders across the globe, large amounts of data are being generated. Several studies employed machine learning methods to understand the ever-growing omics data to enhance early diagnosis, map complex disease networks, or uncover potential drug targets. We describe results based on a Target Central Resource Database protein knowledge graph and evidence paths transformed into vectors by metapath matching. We extracted features between specific genes and diseases, then trained and optimized our model using XGBoost, termed MPxgb(AD). To determine our MPxgb(AD) prediction performance, we examined the top twenty predicted genes through an experimental screening pipeline. Our analysis identified potential AD risk genes: FRRS1, CTRAM, SCGB3A1, FAM92B/CIBAR2, and TMEFF2. FRRS1 and FAM92B are considered dark genes, while CTRAM, SCGB3A1, and TMEFF2 are connected to TREM2-TYROBP, IL-1β-TNFα, and MTOR-APP AD-risk nodes, suggesting relevance to the pathogenesis of AD.
| Originalsprog | Engelsk |
|---|---|
| Artikelnummer | 125 |
| Tidsskrift | Communications Biology |
| Vol/bind | 5 |
| Udgave nummer | 1 |
| Antal sider | 15 |
| ISSN | 2399-3642 |
| DOI | |
| Status | Udgivet - 2022 |
Bibliografisk note
Funding Information:This work was primarily funded by the NIH Common Fund U24 CA224370-01S1 AD/ADRD supplement. Additional funding for this study was from RF1NS083704-05A1, R01NS083704, R21NS077089, and R21NS093442; UNM Health Sciences Center Bridge Funding, UNM Department of Molecular Genetics and Microbiology intradepartmental grant funding, Dr. Stephanie Ruby travel award (to J.B.). This study was also supported in part by an Alzheimer?s Disease Core Center grant (P30 AG013854) from the National Institute on Aging to Northwestern University, Chicago Illinois. We gratefully acknowledge the assistance of the Northwestern Cognitive Neurology & Alzheimer?s Disease Center (CNADC) Neuropathology Core for postmortem tissue samples. The general machine learning, informatics, and data science framework development was supported by the IDG KMC application from the University of New Mexico (NIH CA224370). Additional funding for T.I.O., C.B., and J.J.Y. was provided by NIH grant U24 TR002278.
Funding Information:
This work was primarily funded by the NIH Common Fund U24 CA224370-01S1 AD/ADRD supplement. Additional funding for this study was from RF1NS083704-05A1, R01NS083704, R21NS077089, and R21NS093442; UNM Health Sciences Center Bridge Funding, UNM Department of Molecular Genetics and Microbiology intradepartmental grant funding, Dr. Stephanie Ruby travel award (to J.B.). This study was also supported in part by an Alzheimer’s Disease Core Center grant (P30 AG013854) from the National Institute on Aging to Northwestern University, Chicago Illinois. We gratefully acknowledge the assistance of the Northwestern Cognitive Neurology & Alzheimer’s Disease Center (CNADC) Neuropathology Core for postmortem tissue samples. The general machine learning, informatics, and data science framework development was supported by the IDG KMC application from the University of New Mexico (NIH CA224370). Additional funding for T.I.O., C.B., and J.J.Y. was provided by NIH grant U24 TR002278.
Publisher Copyright:
© 2022, The Author(s).