{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"bioRxiv"}],"indexed":{"date-parts":[[2026,8,9]],"date-time":"2026-08-09T08:41:31Z","timestamp":1786264891442,"version":"build-2736575974"},"posted":{"date-parts":[[2026,8,6]]},"group-title":"Bioinformatics","reference-count":57,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T00:00:00Z","timestamp":1785974400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"name":"Next Generation EU funding","award":["Grant CN00000013 \u201cNational Centre for HPC, Big Data and Quantum Computing\u201d"],"award-info":[{"award-number":["Grant CN00000013 \u201cNational Centre for HPC, Big Data and Quantum Computing\u201d"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2026,8,6]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:p>Whole-exome case-control studies contain rare and common variation, yet analytical methods usually partition the frequency spectrum, discard positional context, or depend on fixed annotations. We present SIEVE, a deep-learning framework for interpretable variant and gene prioritisation. It reads every observed exonic variant without a frequency filter, represents genomic position through self-attention, and calibrates attributions against a permuted-label null. Across coronary artery disease, early-onset myocardial infarction and Crohn\u2019s disease, discrimination matches the liability-threshold expectation for each trait, while recovery of catalogued associations rises with annotation depth. Against burden testing, single-variant association and polygenic scoring, SIEVE recovers overlapping but largely distinct candidates.<\/jats:p>","DOI":"10.64898\/2026.08.01.742212","type":"posted-content","created":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T04:40:27Z","timestamp":1786077627000},"source":"Crossref","is-referenced-by-count":0,"title":["SIEVE: Sparse Interpretable Exome Variant Explainer"],"prefix":"10.64898","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-1018-9076","authenticated-orcid":false,"given":"Davide","family":"Bagordo","sequence":"first","affiliation":[{"name":"Department of Biology and Biotechnology \u201cL. Spallanzani\u201d, University of Pavia, Pavia, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cezar","family":"Grigorean","sequence":"additional","affiliation":[{"name":"Department of Biology and Biotechnology \u201cL. Spallanzani\u201d, University of Pavia, Pavia, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0208-2172","authenticated-orcid":false,"given":"Andrea","family":"Mazzanti","sequence":"additional","affiliation":[{"name":"Department of Molecular Medicine, University of Pavia, Pavia, Italy"},{"name":"U.O. Molecular Cardiology, Clinical Scientific Institutes Maugeri IRCCS, Pavia, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7038-5362","authenticated-orcid":false,"given":"Massimiliano","family":"Ruocco","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Norwegian University of Science and Technology, Trondheim, Norway"},{"name":"SINTEF Digital, SINTEF, Trondheim, Norway"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6399-9101","authenticated-orcid":false,"given":"Francesco","family":"Lescai","sequence":"additional","affiliation":[{"name":"Department of Biology and Biotechnology \u201cL. Spallanzani\u201d, University of Pavia, Pavia, Italy"},{"name":"Host-pathogen Interactions and Immunotherapy Unit, University-Hospital joint research platform. Fondazione IRCCS Hospital San Matteo"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"key":"2026080900502506000_2026.08.01.742212v1.1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2017.05.038"},{"key":"2026080900502506000_2026.08.01.742212v1.2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-022-04556-w"},{"key":"2026080900502506000_2026.08.01.742212v1.3","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2024.01.023"},{"key":"2026080900502506000_2026.08.01.742212v1.4","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-022-05684-z"},{"key":"2026080900502506000_2026.08.01.742212v1.5","doi-asserted-by":"publisher","DOI":"10.1038\/nature08494"},{"key":"2026080900502506000_2026.08.01.742212v1.6","doi-asserted-by":"publisher","DOI":"10.1016\/j.ajhg.2017.06.005"},{"key":"2026080900502506000_2026.08.01.742212v1.7","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-27930-0"},{"key":"2026080900502506000_2026.08.01.742212v1.8","doi-asserted-by":"publisher","DOI":"10.1038\/s41588-020-0676-4"},{"key":"2026080900502506000_2026.08.01.742212v1.9","doi-asserted-by":"publisher","DOI":"10.1038\/s41588-018-0183-z"},{"key":"2026080900502506000_2026.08.01.742212v1.10","doi-asserted-by":"publisher","DOI":"10.1038\/nrg.2016.27"},{"key":"2026080900502506000_2026.08.01.742212v1.11","doi-asserted-by":"publisher","DOI":"10.1038\/ng.3211"},{"key":"2026080900502506000_2026.08.01.742212v1.12","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-026-72185-2"},{"key":"2026080900502506000_2026.08.01.742212v1.13","doi-asserted-by":"publisher","DOI":"10.1038\/s41576-019-0122-6"},{"key":"2026080900502506000_2026.08.01.742212v1.14","doi-asserted-by":"publisher","DOI":"10.1038\/s41588-018-0295-5"},{"key":"2026080900502506000_2026.08.01.742212v1.15","doi-asserted-by":"publisher","DOI":"10.1038\/s41588-024-01919-z"},{"key":"2026080900502506000_2026.08.01.742212v1.16","doi-asserted-by":"publisher","DOI":"10.1038\/s42003-021-02622-z"},{"key":"2026080900502506000_2026.08.01.742212v1.17","doi-asserted-by":"publisher","DOI":"10.1038\/s42003-022-04186-y"},{"key":"2026080900502506000_2026.08.01.742212v1.18","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-65317-5"},{"key":"2026080900502506000_2026.08.01.742212v1.19","doi-asserted-by":"publisher","DOI":"10.1093\/nargab\/lqaa011"},{"key":"2026080900502506000_2026.08.01.742212v1.20","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-026-05951-9"},{"key":"2026080900502506000_2026.08.01.742212v1.21","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-024-02523-z"},{"key":"2026080900502506000_2026.08.01.742212v1.22","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-025-01016-8"},{"key":"2026080900502506000_2026.08.01.742212v1.23","doi-asserted-by":"publisher","DOI":"10.1101\/2022.07.07.499217"},{"key":"2026080900502506000_2026.08.01.742212v1.24","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-018-0579-z"},{"key":"2026080900502506000_2026.08.01.742212v1.25","doi-asserted-by":"publisher","DOI":"10.1038\/nature05911"},{"key":"2026080900502506000_2026.08.01.742212v1.26","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pgen.1000864"},{"key":"2026080900502506000_2026.08.01.742212v1.27","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","year":"2020","journal-title":"Journal of Machine Learning Research"},{"key":"2026080900502506000_2026.08.01.742212v1.28","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btad535"},{"key":"2026080900502506000_2026.08.01.742212v1.29","doi-asserted-by":"publisher","DOI":"10.1093\/cvr\/cvae161"},{"key":"2026080900502506000_2026.08.01.742212v1.30","doi-asserted-by":"publisher","DOI":"10.1038\/s41588-022-01233-6"},{"key":"2026080900502506000_2026.08.01.742212v1.31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2074"},{"key":"2026080900502506000_2026.08.01.742212v1.32","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0011876"},{"key":"2026080900502506000_2026.08.01.742212v1.33","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-023-02429-x"},{"key":"2026080900502506000_2026.08.01.742212v1.34","doi-asserted-by":"publisher","DOI":"10.1016\/j.jacc.2018.07.079"},{"key":"2026080900502506000_2026.08.01.742212v1.35","doi-asserted-by":"publisher","DOI":"10.1038\/ng1847"},{"key":"2026080900502506000_2026.08.01.742212v1.36","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-026-73776-9"},{"key":"2026080900502506000_2026.08.01.742212v1.37","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.61548"},{"key":"2026080900502506000_2026.08.01.742212v1.38","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0207677"},{"key":"2026080900502506000_2026.08.01.742212v1.39","unstructured":"Sundararajan M , Taly A , Yan Q . Axiomatic attribution for deep networks. Proceedings of the 34th International Conference on Machine Learning [Internet]. 2017. p. 3319\u201328. https:\/\/arxiv.org\/abs\/1703.01365"},{"key":"2026080900502506000_2026.08.01.742212v1.40","unstructured":"Kokhlikyan N , Miglani V , Martin M , Wang E , Alsallakh B , Reynolds J , et al. Captum: a unified and generic model interpretability library for PyTorch. arXiv preprint [Internet]. 2020; https:\/\/arxiv.org\/abs\/2009.07896"},{"key":"2026080900502506000_2026.08.01.742212v1.41","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-019-0138-9"},{"key":"2026080900502506000_2026.08.01.742212v1.42","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/371"},{"key":"2026080900502506000_2026.08.01.742212v1.43","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btq134"},{"key":"2026080900502506000_2026.08.01.742212v1.44","doi-asserted-by":"publisher","DOI":"10.1093\/biostatistics\/kxn007"},{"key":"2026080900502506000_2026.08.01.742212v1.45","doi-asserted-by":"publisher","DOI":"10.1038\/ng.3396"},{"key":"2026080900502506000_2026.08.01.742212v1.46","doi-asserted-by":"publisher","DOI":"10.3390\/biom15060892"},{"key":"2026080900502506000_2026.08.01.742212v1.47","doi-asserted-by":"crossref","unstructured":"Johnson MT , others. The nonexcitable smooth muscle: remodeling the smooth muscle ion transport toolkit in disease. Physiological Reviews. 2026;","DOI":"10.1152\/physrev.00031.2025"},{"key":"2026080900502506000_2026.08.01.742212v1.48","doi-asserted-by":"publisher","DOI":"10.2741\/4377"},{"key":"2026080900502506000_2026.08.01.742212v1.49","doi-asserted-by":"crossref","unstructured":"Morris AJ , Smyth SS . Lysophosphatidic acid and cardiovascular disease: seeing is believing. Journal of Lipid Research. 2013;","DOI":"10.1194\/jlr.E037887"},{"key":"2026080900502506000_2026.08.01.742212v1.50","doi-asserted-by":"publisher","DOI":"10.1086\/321276"},{"key":"2026080900502506000_2026.08.01.742212v1.51","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2001.04451"},{"key":"2026080900502506000_2026.08.01.742212v1.52","unstructured":"Zaheer M , Guruganesh G , Dubey KA , Ainslie J , Alberti C , Ontanon S , et al. BigBird: transformers for longer sequences. Advances in Neural Information Processing Systems [Internet]. 2020. p. 17283\u201397. https:\/\/arxiv.org\/abs\/2007.14062"},{"key":"2026080900502506000_2026.08.01.742212v1.53","doi-asserted-by":"publisher","DOI":"10.1086\/519795"},{"key":"2026080900502506000_2026.08.01.742212v1.54","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2105-14-128"},{"key":"2026080900502506000_2026.08.01.742212v1.55","doi-asserted-by":"publisher","DOI":"10.1002\/cpz1.90"},{"key":"2026080900502506000_2026.08.01.742212v1.56","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkw377"},{"key":"2026080900502506000_2026.08.01.742212v1.57","doi-asserted-by":"publisher","DOI":"10.1186\/s13742-015-0047-8"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.64898\/2026.08.01.742212","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,9]],"date-time":"2026-08-09T07:50:39Z","timestamp":1786261839000},"score":1,"resource":{"primary":{"URL":"http:\/\/biorxiv.org\/lookup\/doi\/10.64898\/2026.08.01.742212"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,6]]},"references-count":57,"URL":"https:\/\/doi.org\/10.64898\/2026.08.01.742212","relation":{},"subject":[],"published":{"date-parts":[[2026,8,6]]},"subtype":"preprint"}}