{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"bioRxiv"}],"indexed":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T02:10:48Z","timestamp":1768529448041,"version":"3.49.0"},"posted":{"date-parts":[[2025,10,2]]},"group-title":"Genetics","reference-count":23,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2025,10,2]],"date-time":"2025-10-02T00:00:00Z","timestamp":1759363200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/publicdomain\/zero\/1.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2025,10,2]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:p>Variants of uncertain significance (VUS) are a bottleneck for genetic discovery and complicate clinical decision-making in Alzheimer\u2019s disease and related neurological disorders (ADRD). We developed MoVUS: Model for Variants of Unknown Significance, a random-forest approach that integrates functional predictors to classify missense VUS.<\/jats:p>\n                <jats:p>MoVUS leverages a balanced random forest model trained on dbNSFP v5.1a with high-confidence ClinVar and HGMD labels, using harmonized functional prediction rankscores. MoVUS produced confident, explainable calls, with \u223c98% accuracy (AUC \u223c0.998), prioritizing potentially pathogenic candidates and down-ranked likely benign variants on independent validation sets of ClinVar-only and HGMD-only variants. In our discovery analyses on ADRD-implicated variants in dbNSFP and from independent collaborator cohorts, we achieved high-confidence classifications on a majority of the unknown variants (average of 55% of discovery variants). We also had access to medical records and family trees for some variants, further validating our findings.<\/jats:p>\n                <jats:p>Across held-out and external datasets, MoVUS reports high accuracy alongside confidence scores and helps prioritize actionable candidates, and reduces bias by considering multiple scores for each variant. To facilitate use, we developed a web app for users to browse across 100+ ADRD genes. MoVUS provides transparent, reproducible triage for research follow-up by pairing consensus predictors with SHAP-based visualizations and explanations.<\/jats:p>","DOI":"10.1101\/2025.10.02.680068","type":"posted-content","created":{"date-parts":[[2025,10,3]],"date-time":"2025-10-03T07:50:11Z","timestamp":1759477811000},"source":"Crossref","is-referenced-by-count":0,"title":["Random forest model improves annotation and discovery of variants of uncertain significance in Alzheimer\u2019s and other neurological disorders"],"prefix":"10.64898","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7049-6281","authenticated-orcid":false,"given":"Caroline","family":"Jonson","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mary B.","family":"Makarious","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mathew J.","family":"Koretsky","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dan","family":"Vitale","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liya","family":"Rabkina","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Argentina Lario","family":"Lago","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Manizhe","family":"Eslami-Amirabadi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eliana Marisa","family":"Ramos","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Priyanka","family":"Narayan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jennifer S.","family":"Yokoyama","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrew B.","family":"Singleton","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cornelis","family":"Blauwendraat","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mark R.","family":"Cookson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mike A.","family":"Nalls","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hampton L.","family":"Leonard","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"54368","reference":[{"key":"2025100608100507000_2025.10.02.680068v1.1","first-page":"D886","article-title":"CADD: predicting the deleteriousness of variants throughout the human genome","volume":"47","year":"2018","journal-title":"Nucleic Acids Res"},{"key":"2025100608100507000_2025.10.02.680068v1.2","doi-asserted-by":"crossref","first-page":"e1001025","DOI":"10.1371\/journal.pcbi.1001025","article-title":"Identifying a High Fraction of the Human Genome to be under Selective Constraint Using GERP++","volume":"6","year":"2010","journal-title":"PLOS Computational Biology"},{"key":"2025100608100507000_2025.10.02.680068v1.3","doi-asserted-by":"publisher","DOI":"10.1038\/ng.3477"},{"key":"2025100608100507000_2025.10.02.680068v1.4","doi-asserted-by":"publisher","DOI":"10.1126\/science.adg7492"},{"key":"2025100608100507000_2025.10.02.680068v1.5","doi-asserted-by":"crossref","unstructured":"Dereli, O. et al. PHACTboost: A Phylogeny-Aware Pathogenicity Predictor for Missense Mutations via Boosting. Mol Biol Evol 41, (2024).","DOI":"10.1093\/molbev\/msae136"},{"key":"2025100608100507000_2025.10.02.680068v1.6","doi-asserted-by":"publisher","DOI":"10.1038\/s41588-023-01465-0"},{"key":"2025100608100507000_2025.10.02.680068v1.7","first-page":"1","article-title":"SIFT missense predictions for genomes","volume":"11","year":"2015","journal-title":"Nature Protocols"},{"key":"2025100608100507000_2025.10.02.680068v1.8","doi-asserted-by":"crossref","first-page":"248","DOI":"10.1038\/nmeth0410-248","article-title":"A method and server for predicting damaging missense mutations","volume":"7","year":"2010","journal-title":"Nature Methods"},{"key":"2025100608100507000_2025.10.02.680068v1.9","doi-asserted-by":"crossref","first-page":"575","DOI":"10.1038\/nmeth0810-575","article-title":"MutationTaster evaluates disease-causing potential of sequence alterations","volume":"7","year":"2010","journal-title":"Nature Methods"},{"key":"2025100608100507000_2025.10.02.680068v1.10","doi-asserted-by":"publisher","DOI":"10.1016\/j.ajhg.2018.08.005"},{"key":"2025100608100507000_2025.10.02.680068v1.11","doi-asserted-by":"publisher","DOI":"10.1016\/j.ajhg.2016.08.016"},{"key":"2025100608100507000_2025.10.02.680068v1.12","doi-asserted-by":"publisher","DOI":"10.1038\/s41588-018-0167-z"},{"key":"2025100608100507000_2025.10.02.680068v1.13","doi-asserted-by":"publisher","DOI":"10.1101\/gr.097857.109"},{"key":"2025100608100507000_2025.10.02.680068v1.14","doi-asserted-by":"crossref","first-page":"813","DOI":"10.1007\/s00401-017-1764-0","article-title":"Linking tuberous sclerosis complex, excessive mTOR signaling, and age-related neurodegeneration: a new association between TSC1 mutation and frontotemporal dementia","volume":"134","year":"2017","journal-title":"Acta Neuropathol"},{"key":"2025100608100507000_2025.10.02.680068v1.15","doi-asserted-by":"crossref","first-page":"553","DOI":"10.1016\/j.jalz.2018.10.009","article-title":"Genetic screen in a large series of patients with primary progressive aphasia","volume":"15","year":"2019","journal-title":"Alzheimers Dement"},{"key":"2025100608100507000_2025.10.02.680068v1.16","doi-asserted-by":"publisher","DOI":"10.5555\/3122009.3122048"},{"key":"2025100608100507000_2025.10.02.680068v1.17","unstructured":"von Luxburg, U. 31st Annual Conference on Neural Information Processing Systems 2017 ; Long Beach, California, 4-9 December 2017: Editors: Ulrike Von Luxburg, Isabelle Guyon, Samy Bengio, Hanna Wallach, Rob Fergus, Roman Garnett,S.V.N. Vishwanathan. (Curran Associates, Incorporated, 2017)."},{"key":"2025100608100507000_2025.10.02.680068v1.18","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2024.09.015"},{"key":"2025100608100507000_2025.10.02.680068v1.19","doi-asserted-by":"publisher","DOI":"10.1016\/S1474-4422(24)00121-2"},{"key":"2025100608100507000_2025.10.02.680068v1.20","doi-asserted-by":"publisher","DOI":"10.1016\/j.cub.2018.02.010"},{"key":"2025100608100507000_2025.10.02.680068v1.21","doi-asserted-by":"crossref","unstructured":"Arrazola Sastre, A. , Luque Montoro, M. , Lacerda, H. M. , Llavero, F. & Zugaza, J. L. Small GTPases of the Rab and Arf Families: Key Regulators of Intracellular Trafficking in Neurodegeneration. Int J Mol Sci 22, (2021).","DOI":"10.3390\/ijms22094425"},{"key":"2025100608100507000_2025.10.02.680068v1.22","doi-asserted-by":"crossref","first-page":"962","DOI":"10.1016\/S1474-4422(24)00325-9","article-title":"RAB32 mutation in Parkinson\u2019s disease","volume":"23","year":"2024","journal-title":"Lancet Neurol"},{"key":"2025100608100507000_2025.10.02.680068v1.23","doi-asserted-by":"publisher","DOI":"10.1038\/nn.3688"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1101\/2025.10.02.680068","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T09:43:06Z","timestamp":1768470186000},"score":1,"resource":{"primary":{"URL":"http:\/\/biorxiv.org\/lookup\/doi\/10.1101\/2025.10.02.680068"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,2]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1101\/2025.10.02.680068","relation":{},"subject":[],"published":{"date-parts":[[2025,10,2]]},"subtype":"preprint"}}