{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"medRxiv"}],"indexed":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T04:28:49Z","timestamp":1772598529352,"version":"3.50.1"},"posted":{"date-parts":[[2025,2,27]]},"group-title":"Genetic and Genomic Medicine","reference-count":31,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2025,2,27]],"date-time":"2025-02-27T00:00:00Z","timestamp":1740614400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2025,11,12]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:p>Genetic risk factors for neuropsychiatric disorders are well documented. However, some individuals with high genetic risk remain unaffected, and the mechanisms underlying such resilience remain poorly understood. The presence of protective resilience factors that mitigate risk could help explain the disconnect between predicted risk and reality, particularly when genetic contributions are substantial but incompletely understood. Identifying and studying resilience factors could improve our understanding of pathology, enhance risk prediction, and inform preventive measures or treatment strategies. However, such efforts are complicated by the difficulty of identifying resilience that is separable from low risk. We developed a novel adversarial multi-task neural network model to detect genetic resilience markers. The model learns to separate high-risk unaffected individuals from affected individuals at similar risk while \u201cunlearning\u201d patterns found in low-risk groups using adversarial learning. In simulated and existing Alzheimer\u2019s disease (AD) datasets, we identified markers of resilience with a feature-importance-based approach that prioritized specificity, generated resilience scores, and analyzed associations with polygenic risk scores (PRS). In simulations, our model had high specificity and sensitivity in identifying resilience markers, significantly outperforming traditional approaches. Applied to AD data, the model generated genetic resilience scores protective against AD and independent of PRS. We identified five resilience-associated SNPs, including known AD-associated variants, underscoring their potential involvement in resilience. Our findings support the utility of resilience scores in modifying risk predictions, particularly for high-risk groups. Expanding this method could aid in understanding resilience mechanisms, potentially improving diagnosis, prevention, and treatment strategies for AD and other brain disorders.<\/jats:p>","DOI":"10.1101\/2025.02.26.25322962","type":"posted-content","created":{"date-parts":[[2025,2,27]],"date-time":"2025-02-27T22:56:17Z","timestamp":1740696977000},"source":"Crossref","is-referenced-by-count":1,"title":["A Novel Method to Disentangle Tightly Linked Risk and Resilience Genes for Brain Disorders: Application to Alzheimer\u2019s Disease"],"prefix":"10.64898","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2493-2251","authenticated-orcid":false,"given":"Eric J","family":"Barnett","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8406-632X","authenticated-orcid":false,"given":"Jonathan L","family":"Hess","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiahui","family":"Hou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1784-5483","authenticated-orcid":false,"given":"Valentina","family":"Escott-Price","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6527-6361","authenticated-orcid":false,"given":"Christine","family":"Fennema-Notestine","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8629-5609","authenticated-orcid":false,"given":"William","family":"Kremen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shu-Ju","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2752-1028","authenticated-orcid":false,"given":"Chunling","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7838-8664","authenticated-orcid":false,"given":"Chris","family":"Gaiteri","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5840-1769","authenticated-orcid":false,"given":"Jeremy","family":"Elman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0870-9412","authenticated-orcid":false,"given":"Peter","family":"Holmans","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9217-3982","authenticated-orcid":false,"given":"Stephen V","family":"Faraone","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0360-7567","authenticated-orcid":false,"given":"Stephen J","family":"Glatt","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"54368","reference":[{"issue":"9","key":"2025111400350918000_2025.02.26.25322962v3.1","first-page":"1192","article-title":"3rd, Arnsten A","volume":"46","year":"1999","journal-title":"Charney DS. Role of norepinephrine in the pathophysiology and treatment of posttraumatic stress disorder. Biological Psychiatry"},{"key":"2025111400350918000_2025.02.26.25322962v3.2","doi-asserted-by":"crossref","first-page":"834765","DOI":"10.3389\/fnagi.2022.834765","article-title":"Cognitive Reserve and Related Constructs: A Unified Framework Across Cognitive and Brain Dimensions of Aging","volume":"14","year":"2022","journal-title":"Front Aging Neurosci"},{"key":"2025111400350918000_2025.02.26.25322962v3.3","doi-asserted-by":"publisher","DOI":"10.1001\/archpsyc.63.2.168"},{"key":"2025111400350918000_2025.02.26.25322962v3.4","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0281440"},{"issue":"1","key":"2025111400350918000_2025.02.26.25322962v3.5","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1186\/s13024-024-00719-7","article-title":"The concept of resilience to Alzheimer\u2019s Disease: current definitions and cellular and molecular mechanisms","volume":"19","year":"2024","journal-title":"Molecular Neurodegeneration"},{"key":"2025111400350918000_2025.02.26.25322962v3.6","doi-asserted-by":"publisher","DOI":"10.1111\/acel.12779"},{"key":"2025111400350918000_2025.02.26.25322962v3.7","first-page":"1","article-title":"Apolipoprotein CI is an APOE genotype-dependent suppressor of glial activation","volume":"9","year":"2012","journal-title":"Journal of neuroinflammation"},{"issue":"4","key":"2025111400350918000_2025.02.26.25322962v3.8","doi-asserted-by":"crossref","first-page":"2817","DOI":"10.3390\/cimb45040184","article-title":"Apolipoprotein E (APOE) Haplotypes in Healthy Subjects from Worldwide Macroareas: A Population Genetics Perspective for Cardiovascular Disease, Neurodegeneration, and Dementia","volume":"45","year":"2023","journal-title":"Curr Issues Mol Biol"},{"issue":"9","key":"2025111400350918000_2025.02.26.25322962v3.9","doi-asserted-by":"crossref","first-page":"501","DOI":"10.1038\/s41582-019-0228-7","article-title":"Apolipoprotein E and Alzheimer disease: pathobiology and targeting strategies","volume":"15","year":"2019","journal-title":"Nature Reviews Neurology"},{"key":"2025111400350918000_2025.02.26.25322962v3.10","doi-asserted-by":"publisher","DOI":"10.1016\/j.csbj.2017.05.003"},{"issue":"1","key":"2025111400350918000_2025.02.26.25322962v3.11","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1212\/WNL.51.1.131","article-title":"Interaction of the apolipoprotein E and CI loci in predisposing to late-onset Alzheimer\u2019s disease","volume":"51","year":"1998","journal-title":"Neurology"},{"key":"2025111400350918000_2025.02.26.25322962v3.12","doi-asserted-by":"publisher","DOI":"10.1016\/S0304-3940(98)00889-1"},{"key":"2025111400350918000_2025.02.26.25322962v3.13","doi-asserted-by":"publisher","DOI":"10.1371\/JOURNAL.PONE.0087017"},{"issue":"5","key":"2025111400350918000_2025.02.26.25322962v3.14","doi-asserted-by":"crossref","first-page":"692","DOI":"10.1016\/j.jalz.2018.01.015","article-title":"The effects of the TOMM40 poly-T alleles on Alzheimer\u2019s disease phenotypes","volume":"14","year":"2018","journal-title":"Alzheimer\u2019s & Dementia"},{"key":"2025111400350918000_2025.02.26.25322962v3.15","doi-asserted-by":"publisher","DOI":"10.1007\/s40520-020-01661-6"},{"key":"2025111400350918000_2025.02.26.25322962v3.16","doi-asserted-by":"publisher","DOI":"10.1038\/s41380-023-02170-4"},{"issue":"1","key":"2025111400350918000_2025.02.26.25322962v3.17","doi-asserted-by":"crossref","first-page":"296","DOI":"10.1038\/s41398-022-02055-0","article-title":"Polygenic resilience scores capture protective genetic effects for Alzheimer\u2019s disease","volume":"12","year":"2022","journal-title":"Transl Psychiatry"},{"key":"2025111400350918000_2025.02.26.25322962v3.18","unstructured":"Paszke A , Gross S , Massa F , Lerer A , Bradbury J , Chanan G , et al. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems. 2019;32."},{"issue":"1","key":"2025111400350918000_2025.02.26.25322962v3.19","first-page":"2096","article-title":"Domain-adversarial training of neural networks","volume":"17","year":"2016","journal-title":"The journal of machine learning research"},{"key":"2025111400350918000_2025.02.26.25322962v3.20","doi-asserted-by":"crossref","unstructured":"Akiba T , Sano S , Yanase T , Ohta T , Koyama M , editors. Optuna: A next-generation hyperparameter optimization framework. Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining; 2019.","DOI":"10.1145\/3292500.3330701"},{"key":"2025111400350918000_2025.02.26.25322962v3.21","unstructured":"Hess JL , Tylee DS , Mattheisen M , Consortium SWGotPG, (iPSYCH) LFIfIPP, Borglum AD , et al. A polygenic resilience score moderates the genetic risk for schizophrenia. Mol Psychiatry. 2019;1038:s41380-019-0463-8."},{"key":"2025111400350918000_2025.02.26.25322962v3.22","unstructured":"Sundararajan M , Taly A , Yan Q , editors. Axiomatic attribution for deep networks. International conference on machine learning; 2017: PMLR."},{"key":"2025111400350918000_2025.02.26.25322962v3.23","doi-asserted-by":"publisher","DOI":"10.1038\/s41588-019-0358-2"},{"key":"2025111400350918000_2025.02.26.25322962v3.24","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-019-09718-5"},{"key":"2025111400350918000_2025.02.26.25322962v3.25","doi-asserted-by":"publisher","DOI":"10.1038\/s41588-021-00921-z"},{"key":"2025111400350918000_2025.02.26.25322962v3.26","doi-asserted-by":"publisher","DOI":"10.1038\/nature15393"},{"issue":"8","key":"2025111400350918000_2025.02.26.25322962v3.27","first-page":"1","article-title":"MatchIt: Nonparametric Preprocessing for Parametric Causal Inference","volume":"42","year":"2011","journal-title":"Journal of Statistical Software"},{"key":"2025111400350918000_2025.02.26.25322962v3.28","doi-asserted-by":"publisher","DOI":"10.1086\/519795"},{"key":"2025111400350918000_2025.02.26.25322962v3.29","doi-asserted-by":"crossref","first-page":"45269","DOI":"10.1038\/srep45269","article-title":"A Hierarchical Feature and Sample Selection Framework and Its Application for Alzheimer\u2019s Disease Diagnosis","volume":"7","year":"2017","journal-title":"Sci Rep"},{"issue":"4","key":"2025111400350918000_2025.02.26.25322962v3.30","doi-asserted-by":"crossref","first-page":"e0232103","DOI":"10.1371\/journal.pone.0232103","article-title":"Improving predictive models for Alzheimer\u2019s disease using GWAS data by incorporating misclassified samples modeling","volume":"15","year":"2020","journal-title":"PLoS One"},{"issue":"1","key":"2025111400350918000_2025.02.26.25322962v3.31","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1186\/s12883-024-03577-4","article-title":"The SNP rs6859 in NECTIN2 gene is associated with underlying heterogeneous trajectories of cognitive changes in older adults","volume":"24","author":"Initiative AsDN","year":"2024","journal-title":"BMC neurology"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1101\/2025.02.26.25322962","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T20:29:21Z","timestamp":1768508961000},"score":1,"resource":{"primary":{"URL":"http:\/\/medrxiv.org\/lookup\/doi\/10.1101\/2025.02.26.25322962"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,27]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1101\/2025.02.26.25322962","relation":{},"subject":[],"published":{"date-parts":[[2025,2,27]]},"subtype":"preprint"}}