{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"bioRxiv"}],"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T21:19:17Z","timestamp":1792790357950,"version":"4.5.0"},"posted":{"date-parts":[[2026,9,18]]},"group-title":"Genomics","reference-count":59,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T00:00:00Z","timestamp":1789689600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"id":[{"id":"https:\/\/ror.org\/021nxhr62","id-type":"ROR","asserted-by":"publisher"}]},{"id":[{"id":"https:\/\/ror.org\/000dswa46","id-type":"ROR","asserted-by":"publisher"}]},{"name":"Biswas Family Foundation"},{"name":"Dhaliwal Family"},{"id":[{"id":"https:\/\/ror.org\/038321296","id-type":"ROR","asserted-by":"publisher"}]},{"name":"National Heart Lung and Blood Institute","award":["#U01HL157989"],"award-info":[{"award-number":["#U01HL157989"]}],"id":[{"id":"https:\/\/ror.org\/012pb6c26","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2026,9,18]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:p>\n                  The\n                  <jats:italic>Alu<\/jats:italic>\n                  transposable element is among the most abundant classes of mobile DNA in the human genome and has been linked to gene regulation and chromatin organization. Yet how individual\n                  <jats:italic>Alu<\/jats:italic>\n                  insertions influence nearby chromatin interactions remains poorly understood. To investigate this, we used deep learning to perform a genome-wide\n                  <jats:italic>in silico<\/jats:italic>\n                  deletion screen of \u223c1.1 million\n                  <jats:italic>Alus<\/jats:italic>\n                  , predicting each element\u2019s importance to local genome folding. We identified a subset of high-scoring\n                  <jats:italic>Alus<\/jats:italic>\n                  that span multiple\n                  <jats:italic>Alu<\/jats:italic>\n                  subfamilies and are enriched in loci that are fast-evolving and gene-dense, especially loci encoding genes that are actively transcribed and\/or related to\n                  <jats:italic>Alu<\/jats:italic>\n                  biology. We further found that polymorphic\n                  <jats:italic>Alus<\/jats:italic>\n                  preferentially occur in regions tolerant of sequence variation but predicted to be resistant to changes in chromatin structure. Targeted\n                  <jats:italic>in silico<\/jats:italic>\n                  mutagenesis showed that the importance of individual\n                  <jats:italic>Alus<\/jats:italic>\n                  to local chromatin interactions depends on both intrinsic\n                  <jats:italic>Alu<\/jats:italic>\n                  sequence properties and genomic context. Finally, we identified\n                  <jats:italic>Alu<\/jats:italic>\n                  sequences predicted to alter CTCF-mediated boundary strength and, in some cases, to promote the formation of new loops and boundaries. Together, these results position\n                  <jats:italic>Alus<\/jats:italic>\n                  as key modulators of genome architecture, while underscoring that the fate of a new\n                  <jats:italic>Alu<\/jats:italic>\n                  depends on where it inserts and how it interacts with other determinants of chromatin state and structure.\n                <\/jats:p>","DOI":"10.64898\/2026.09.16.752217","type":"posted-content","created":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T18:25:19Z","timestamp":1789755919000},"source":"Crossref","is-referenced-by-count":0,"title":["Machine learning reveals sequence and genomic context features underlying\n                  <i>Alu<\/i>\n                  -specific effects on genome folding"],"prefix":"10.64898","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-6592-118X","authenticated-orcid":false,"given":"Shu","family":"Zhang","sequence":"first","affiliation":[{"name":"Gladstone Institute of Data Science and Biotechnology, San Francisco, CA 94158"},{"name":"Biological and Medical Informatics Graduate Program, University of California, San Francisco, San Francisco, CA 94158"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9870-6196","authenticated-orcid":false,"given":"Katherine S.","family":"Pollard","sequence":"additional","affiliation":[{"name":"Gladstone Institute of Data Science and Biotechnology, San Francisco, CA 94158"},{"name":"Department of Epidemiology & Biostatistics, University of California, San Francisco, San Francisco, CA 94158"},{"name":"Biohub, San Francisco, CA 94158"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"key":"2026092217501483000_2026.09.16.752217v1.1","doi-asserted-by":"crossref","unstructured":"Liao, X. et al. Repetitive DNA sequence detection and its role in the human genome. Commun . Biol. 6, 954 (2023).","DOI":"10.1038\/s42003-023-05322-y"},{"key":"2026092217501483000_2026.09.16.752217v1.2","doi-asserted-by":"publisher","DOI":"10.1016\/j.celrep.2016.04.085"},{"key":"2026092217501483000_2026.09.16.752217v1.3","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2017.09.026"},{"key":"2026092217501483000_2026.09.16.752217v1.4","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-genom-083115-022339"},{"key":"2026092217501483000_2026.09.16.752217v1.5","doi-asserted-by":"crossref","unstructured":"Choudhary, M. N. K. , Quaid, K. , Xing, X. , Schmidt, H. & Wang, T . Widespread contribution of transposable elements to the rewiring of mammalian 3D genomes. Nat. Commun. 14, 634 (2023).","DOI":"10.1038\/s41467-023-36364-9"},{"key":"2026092217501483000_2026.09.16.752217v1.6","doi-asserted-by":"publisher","DOI":"10.64898\/2026.01.19.697799"},{"key":"2026092217501483000_2026.09.16.752217v1.7","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.81567"},{"key":"2026092217501483000_2026.09.16.752217v1.8","doi-asserted-by":"crossref","unstructured":"Choudhary, M. N. et al. Co-opted transposons help perpetuate conserved higher-order chromosomal structures. Genome Biol. 21, 16 (2020).","DOI":"10.1186\/s13059-019-1916-8"},{"key":"2026092217501483000_2026.09.16.752217v1.9","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-020-15520-5"},{"key":"2026092217501483000_2026.09.16.752217v1.10","doi-asserted-by":"publisher","DOI":"10.1038\/nrg798"},{"key":"2026092217501483000_2026.09.16.752217v1.11","doi-asserted-by":"crossref","unstructured":"Deininger, P . Alu elements: know the SINEs. Genome Biol. 12, 236 (2011).","DOI":"10.1186\/gb-2011-12-12-236"},{"key":"2026092217501483000_2026.09.16.752217v1.12","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06323-x"},{"key":"2026092217501483000_2026.09.16.752217v1.13","doi-asserted-by":"publisher","DOI":"10.1016\/j.tcb.2017.01.002"},{"key":"2026092217501483000_2026.09.16.752217v1.14","doi-asserted-by":"crossref","unstructured":"Zhang, Y. et al. Transposable elements drive species-specific and tissue-specific transcriptomes in human development. Genome Biol. 26, 379 (2025).","DOI":"10.1186\/s13059-025-03855-5"},{"key":"2026092217501483000_2026.09.16.752217v1.15","doi-asserted-by":"crossref","unstructured":"Gunsalus, L. M. , Keiser, M. J. & Pollard, K. S . In silico discovery of repetitive elements as key sequence determinants of 3D genome folding. Cell Genom. 3, 100410 (2023).","DOI":"10.1016\/j.xgen.2023.100410"},{"key":"2026092217501483000_2026.09.16.752217v1.16","doi-asserted-by":"publisher","DOI":"10.1038\/s41588-022-01065-4"},{"key":"2026092217501483000_2026.09.16.752217v1.17","doi-asserted-by":"publisher","DOI":"10.1038\/s41587-022-01612-8"},{"key":"2026092217501483000_2026.09.16.752217v1.18","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-025-10014-0"},{"key":"2026092217501483000_2026.09.16.752217v1.19","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-024-02359-7"},{"key":"2026092217501483000_2026.09.16.752217v1.20","doi-asserted-by":"crossref","unstructured":"Gjoni, K. & Pollard, K. S . SuPreMo: a computational tool for streamlining in silico perturbation using sequence-based predictive models. Bioinformatics 40, btae340 (2024).","DOI":"10.1093\/bioinformatics\/btae340"},{"key":"2026092217501483000_2026.09.16.752217v1.21","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-020-0958-x"},{"key":"2026092217501483000_2026.09.16.752217v1.22","doi-asserted-by":"crossref","first-page":"824","DOI":"10.1038\/s41592-025-02630-5","article-title":"Comparing chromatin contact maps at scale: methods and insights","volume":"22","year":"2025","journal-title":"Nat. Methods"},{"key":"2026092217501483000_2026.09.16.752217v1.23","doi-asserted-by":"publisher","DOI":"10.1038\/s41588-025-02498-3"},{"key":"2026092217501483000_2026.09.16.752217v1.24","doi-asserted-by":"publisher","DOI":"10.1101\/gr.2133704"},{"key":"2026092217501483000_2026.09.16.752217v1.25","doi-asserted-by":"crossref","unstructured":"Duan, R. V. et al. Widespread distribution of Alu\/Alu-mediated genomic rearrangement predisposing to a broad range of Mendelian disease and cancer in human populations. Genome Med. 18, (2026).","DOI":"10.1186\/s13073-026-01602-4"},{"key":"2026092217501483000_2026.09.16.752217v1.26","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-34810-8"},{"key":"2026092217501483000_2026.09.16.752217v1.27","doi-asserted-by":"publisher","DOI":"10.1016\/j.molcel.2019.10.020"},{"key":"2026092217501483000_2026.09.16.752217v1.28","doi-asserted-by":"crossref","unstructured":"Zhang, X. , Fang, B. & Huang, Y.-F . Transcription factor binding sites are frequently under accelerated evolution in primates. Nat. Commun. 14, 783 (2023).","DOI":"10.1038\/s41467-023-36421-3"},{"key":"2026092217501483000_2026.09.16.752217v1.29","doi-asserted-by":"crossref","first-page":"442","DOI":"10.1038\/s41586-025-09290-7","article-title":"Structural variation in 1,019 diverse humans based on long-read sequencing","volume":"644","year":"2025","journal-title":"Nature"},{"key":"2026092217501483000_2026.09.16.752217v1.30","doi-asserted-by":"publisher","DOI":"10.1093\/gbe\/evv167"},{"key":"2026092217501483000_2026.09.16.752217v1.31","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1921719117"},{"key":"2026092217501483000_2026.09.16.752217v1.32","doi-asserted-by":"publisher","DOI":"10.1101\/gr.249789.119"},{"key":"2026092217501483000_2026.09.16.752217v1.33","doi-asserted-by":"publisher","DOI":"10.1038\/nrg.2016.139"},{"key":"2026092217501483000_2026.09.16.752217v1.34","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.11418"},{"key":"2026092217501483000_2026.09.16.752217v1.35","doi-asserted-by":"publisher","DOI":"10.1038\/nmeth.1906"},{"key":"2026092217501483000_2026.09.16.752217v1.36","doi-asserted-by":"crossref","first-page":"92","DOI":"10.1038\/hdy.2010.53","article-title":"Transposable elements in the mammalian germline: a comfortable niche or a deadly trap?","volume":"105","year":"2010","journal-title":"Heredity (Edinb"},{"key":"2026092217501483000_2026.09.16.752217v1.37","doi-asserted-by":"publisher","DOI":"10.1016\/j.stem.2019.03.012"},{"key":"2026092217501483000_2026.09.16.752217v1.38","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-2308-7"},{"key":"2026092217501483000_2026.09.16.752217v1.39","doi-asserted-by":"publisher","DOI":"10.1016\/j.molcel.2026.03.031"},{"key":"2026092217501483000_2026.09.16.752217v1.40","doi-asserted-by":"publisher","DOI":"10.1016\/j.ydbio.2009.06.012"},{"key":"2026092217501483000_2026.09.16.752217v1.41","doi-asserted-by":"publisher","DOI":"10.1101\/gad.250704.114"},{"key":"2026092217501483000_2026.09.16.752217v1.42","doi-asserted-by":"publisher","DOI":"10.1038\/nature21683"},{"key":"2026092217501483000_2026.09.16.752217v1.43","doi-asserted-by":"publisher","DOI":"10.1016\/j.celrep.2015.12.064"},{"key":"2026092217501483000_2026.09.16.752217v1.44","doi-asserted-by":"crossref","unstructured":"Storer, J. , Hubley, R. , Rosen, J. , Wheeler, T. J. & Smit, A. F . The Dfam community resource of transposable element families, sequence models, and genome annotations. Mob. DNA 12, 2 (2021).","DOI":"10.1186\/s13100-020-00230-y"},{"key":"2026092217501483000_2026.09.16.752217v1.45","doi-asserted-by":"crossref","unstructured":"Zhu, K. , Zhuo, J. & Zhen, Y . Evolution of CTCF binding sites in the human genome. Mol. Biol. Evol. 43, msag167 (2026).","DOI":"10.1093\/molbev\/msag167"},{"key":"2026092217501483000_2026.09.16.752217v1.46","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2011.11.058"},{"key":"2026092217501483000_2026.09.16.752217v1.47","doi-asserted-by":"crossref","unstructured":"Schwalie, P. C. et al. Co-binding by YY1 identifies the transcriptionally active, highly conserved set of CTCF-bound regions in primate genomes. Genome Biol. 14, R148 (2013).","DOI":"10.1186\/gb-2013-14-12-r148"},{"key":"2026092217501483000_2026.09.16.752217v1.48","doi-asserted-by":"publisher","DOI":"10.64898\/2026.07.21.739710"},{"key":"2026092217501483000_2026.09.16.752217v1.49","doi-asserted-by":"crossref","first-page":"6373","DOI":"10.1038\/s41467-024-50573-w","article-title":"Exploring the roles of RNAs in chromatin architecture using deep learning","volume":"15","year":"2024","journal-title":"Nat. Commun"},{"key":"2026092217501483000_2026.09.16.752217v1.50","doi-asserted-by":"crossref","first-page":"msae209","DOI":"10.1093\/molbev\/msae209","article-title":"Machine learning reveals the diversity of human 3D chromatin contact patterns","volume":"41","year":"2024","journal-title":"Mol. Biol. Evol"},{"key":"2026092217501483000_2026.09.16.752217v1.51","doi-asserted-by":"crossref","first-page":"evae210","DOI":"10.1093\/gbe\/evae210","article-title":"Sequence-based machine learning reveals 3D genome differences between bonobos and chimpanzees","volume":"16","year":"2024","journal-title":"Genome Biol. Evol"},{"key":"2026092217501483000_2026.09.16.752217v1.52","doi-asserted-by":"publisher","DOI":"10.1126\/science.abm1696"},{"key":"2026092217501483000_2026.09.16.752217v1.53","doi-asserted-by":"publisher","DOI":"10.1101\/gr.234096.117"},{"key":"2026092217501483000_2026.09.16.752217v1.54","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.aba3200"},{"key":"2026092217501483000_2026.09.16.752217v1.55","doi-asserted-by":"publisher","DOI":"10.64898\/2025.12.09.693120"},{"key":"2026092217501483000_2026.09.16.752217v1.56","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btad198"},{"key":"2026092217501483000_2026.09.16.752217v1.57","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkv416"},{"key":"2026092217501483000_2026.09.16.752217v1.58","doi-asserted-by":"publisher","DOI":"10.1093\/NAR\/GKAF1209"},{"key":"2026092217501483000_2026.09.16.752217v1.59","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkad1077"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.64898\/2026.09.16.752217","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T00:50:27Z","timestamp":1790124627000},"score":1,"resource":{"primary":{"URL":"http:\/\/biorxiv.org\/lookup\/doi\/10.64898\/2026.09.16.752217"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,18]]},"references-count":59,"URL":"https:\/\/doi.org\/10.64898\/2026.09.16.752217","relation":{},"subject":[],"published":{"date-parts":[[2026,9,18]]},"subtype":"preprint"}}