[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-438589-105":59,"doc-detail-438589-en":130},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","machine-learning-based-prediction-of-human-structural-variation-and-characterization-of-associated-sequence-determinants","Machine learning-based prediction of human structural variation and characterization of associated sequence determinants","","Structural variants (SVs) drive substantial human genetic diversity while strongly influencing disease and evolutionary processes. Local DNA sequence context is suspected to affect where SVs form, but the magnitude and determinants remain insufficiently measured. This study develops machine learning models to predict SV occurrence genome-wide and to characterize associated sequence and genomic determinants, enabling quantification of SV susceptibility and effects in personalized genomics.",{"@graph":69,"@context":122},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/machine-learning-based-prediction-of-human-structural-variation-and-characterization-of-associated-sequence-determinants/438589/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/machine-learning-based-prediction-of-human-structural-variation-and-characterization-of-associated-sequence-determinants/438589.png","ImageObject",300,407,{"name":92,"@type":93},"Finn","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-01","2026-09-29",true,{"@type":102,"interactionType":103,"userInteractionCount":8},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What problem does the study address about structural variants?","Question",{"text":112,"@type":113},"The study targets how local sequence context influences the likelihood of structural variant formation, which remains poorly quantified.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How do the researchers model SV formation?",{"text":117,"@type":113},"They build machine learning models including a sequence-only convolutional neural network and a random forest model integrating diverse genomic annotations.",{"name":119,"@type":110,"acceptedAnswer":120},"What biological insights do the models provide beyond prediction?",{"text":121,"@type":113},"Interpretability analyses identify genomic contributors such as microhomology, non-canonical DNA structures, and SV hotspots, and different SV classes show distinct sequence determinants.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},438589,1790819545,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":8,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":139,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":144,"read_time":145},34359740700684,"https://ap-avatar.wpscdn.com/avatar/1f400023980c374ae676?_k=1777273430885731487","bioRxiv preprint doi: [https://doi.org/10.64898/2025.12.09.693295](https://doi.org/10.64898/2025.12.09.693295); this version posted December 12, 2025. The copyright holder for this preprint (which was not certified by peer review) is the author/funder, who has granted bioRxiv a license to display the preprint in perpetuity. It is made  \navailable under aCC-BY 4.0 International license.  \n1 Machine learning-based prediction of  \n2 human structural variation and  \n3 characterization of associated sequence  \n4 determinants  \n5  \n6 Daven Lim1,2 , Runyang Nicolas Lou3 , Nilah Ioannidis4,5 , Peter H Sudmant3,5 7  \n8 1 Department of Biosystems Science and Engineering, ETH Zürich, Zürich, Switzerland  \n9 2 Department of Electrical Engineering and Computer Sciences, UC Berkeley, Berkeley,  \n10 California, USA  \n11 3 Department of Integrative Biology, University of California Berkeley, Berkeley, CA, USA  \n12 4 Department of Applied Math, University of California Santa Cruz, Santa Cruz, CA, USA  \n13 5 Center for Computational Biology, University of California Berkeley, Berkeley, CA, USA 14  \n15 Correspondence should be addressed to Peter H Sudmant: [psudmant@berkeley.edu](psudmant@berkeley.edu)  \n16 ABSTRACT  \n17 Structural variants (SVs) represent a major source of genetic diversity and play key roles in  \n18 human disease and evolution. Yet, the extent to which local sequence context shapes the  \n19 likelihood of structural variant formation remains poorly quantified. Here, we develop machine  \n20 learning models to predict the occurrence of SVs across the human genome and characterize  \n21 genomic determinants associated with their formation. We developed both a sequence only- 22 based convolutional neural network (CNN) model as well as a random forest approach  \n23 integrating diverse genomic annotations. Both models achieve high predictive performance  \n24 individually (>90% AUROC) which can be further improved in an ensemble. The predictive  \n25 ability of these models demonstrates that SV-prone regions can be accurately inferred from  \n26 sequence context. Model interpretability techniques reveal key genomic contributors to SVs, 27 including effects of sequence motifs such as microhomology and non-canonical DNA structures, 28 as well as the presence of SV hotspots. We find that different classes of SVs exhibit distinct  \n29 sequence determinants, with inversions displaying particularly unique signatures. Moreover, 30 predicted SV probability correlates with allele frequency and gene functional constraint,  \n31 highlighting the utility of the model for variant effect prediction. These findings demonstrate that  \n32 machine learning models trained on local sequence features can identify unstable genomic  \n33 regions and provide a framework for quantifying SV susceptibility and SV variant effects in  \n34 personalized genomics.  \nbioRxiv preprint doi: [https://doi.org/10.64898/2025.12.09.693295](https://doi.org/10.64898/2025.12.09.693295); this version posted December 12, 2025. The copyright holder for this preprint (which was not certified by peer review) is the author/funder, who has granted bioRxiv a license to display the preprint in perpetuity. It is made  \navailable under aCC-BY 4.0 International license.  \n35 INTRODUCTION  \n36 Structural variants (SVs) -including insertions, deletions, duplications, and inversions-are  \n37 large-scale genomic rearrangements that represent a major source of genetic diversity in  \n38 humans1,2 . SVs can affect molecular and cellular processes which can cause genetic diseases, 39 affect gene function, and contribute to evolution and trait complexity3. For example, de novo  \n40 duplications at the 7q11 .23 locus are strongly associated with autism spectrum disorder, and  \n41 the reciprocal deletion causes Williams-Beuren syndrome4 . Rare SVs can alter genes in  \n42 neurodevelopmental pathways and contribute to schizophrenia5 . SVs are also an important  \n43 source of adaptive traits. For instance, ","cbCaicKcRCnuKtng","https://ap.wps.com/l/cbCaicKcRCnuKtng","pdf",2517764,22,"English","# Abstract\n# Introduction","[{\"question\":\"What problem does the study address about structural variants?\",\"answer\":\"The study targets how local sequence context influences the likelihood of structural variant formation, which remains poorly quantified.\"},{\"question\":\"How do the researchers model SV formation?\",\"answer\":\"They build machine learning models including a sequence-only convolutional neural network and a random forest model integrating diverse genomic annotations.\"},{\"question\":\"What biological insights do the models provide beyond prediction?\",\"answer\":\"Interpretability analyses identify genomic contributors such as microhomology, non-canonical DNA structures, and SV hotspots, and different SV classes show distinct sequence determinants.\"}]","Machine learning-based prediction of human structural variation and characterization of associated sequence determinants | PDF",1790685806,55]