{"title":"OM2Seq:学习光学基因组图谱的检索嵌入。","authors":"Yevgeni Nogin, Danielle Sapir, Tahir Detinis Zur, Nir Weinberger, Yonatan Belinkov, Yuval Ebenstein, Yoav Shechtman","doi":"10.1093/bioadv/vbae079","DOIUrl":null,"url":null,"abstract":"<p><strong>Motivation: </strong>Genomics-based diagnostic methods that are quick, precise, and economical are essential for the advancement of precision medicine, with applications spanning the diagnosis of infectious diseases, cancer, and rare diseases. One technology that holds potential in this field is optical genome mapping (OGM), which is capable of detecting structural variations, epigenomic profiling, and microbial species identification. It is based on imaging of linearized DNA molecules that are stained with fluorescent labels, that are then aligned to a reference genome. However, the computational methods currently available for OGM fall short in terms of accuracy and computational speed.</p><p><strong>Results: </strong>This work introduces OM2Seq, a new approach for the rapid and accurate mapping of DNA fragment images to a reference genome. Based on a Transformer-encoder architecture, OM2Seq is trained on acquired OGM data to efficiently encode DNA fragment images and reference genome segments to a common embedding space, which can be indexed and efficiently queried using a vector database. We show that OM2Seq significantly outperforms the baseline methods in both computational speed (by 2 orders of magnitude) and accuracy.</p><p><strong>Availability and implementation: </strong>https://github.com/yevgenin/om2seq.</p>","PeriodicalId":72368,"journal":{"name":"Bioinformatics advances","volume":null,"pages":null},"PeriodicalIF":2.4000,"publicationDate":"2024-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11194751/pdf/","citationCount":"0","resultStr":"{\"title\":\"OM2Seq: learning retrieval embeddings for optical genome mapping.\",\"authors\":\"Yevgeni Nogin, Danielle Sapir, Tahir Detinis Zur, Nir Weinberger, Yonatan Belinkov, Yuval Ebenstein, Yoav Shechtman\",\"doi\":\"10.1093/bioadv/vbae079\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Motivation: </strong>Genomics-based diagnostic methods that are quick, precise, and economical are essential for the advancement of precision medicine, with applications spanning the diagnosis of infectious diseases, cancer, and rare diseases. One technology that holds potential in this field is optical genome mapping (OGM), which is capable of detecting structural variations, epigenomic profiling, and microbial species identification. It is based on imaging of linearized DNA molecules that are stained with fluorescent labels, that are then aligned to a reference genome. However, the computational methods currently available for OGM fall short in terms of accuracy and computational speed.</p><p><strong>Results: </strong>This work introduces OM2Seq, a new approach for the rapid and accurate mapping of DNA fragment images to a reference genome. Based on a Transformer-encoder architecture, OM2Seq is trained on acquired OGM data to efficiently encode DNA fragment images and reference genome segments to a common embedding space, which can be indexed and efficiently queried using a vector database. We show that OM2Seq significantly outperforms the baseline methods in both computational speed (by 2 orders of magnitude) and accuracy.</p><p><strong>Availability and implementation: </strong>https://github.com/yevgenin/om2seq.</p>\",\"PeriodicalId\":72368,\"journal\":{\"name\":\"Bioinformatics advances\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":2.4000,\"publicationDate\":\"2024-06-05\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11194751/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Bioinformatics advances\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1093/bioadv/vbae079\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2024/1/1 0:00:00\",\"PubModel\":\"eCollection\",\"JCR\":\"Q2\",\"JCRName\":\"MATHEMATICAL & COMPUTATIONAL BIOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Bioinformatics advances","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1093/bioadv/vbae079","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/1/1 0:00:00","PubModel":"eCollection","JCR":"Q2","JCRName":"MATHEMATICAL & COMPUTATIONAL BIOLOGY","Score":null,"Total":0}
引用次数: 0
摘要
动机:快速、精确、经济的基因组学诊断方法对精准医疗的发展至关重要,其应用范围涵盖传染病、癌症和罕见病的诊断。光学基因组图谱(OGM)是这一领域具有潜力的一项技术,它能够检测结构变异、表观基因组剖析和微生物物种鉴定。它基于线性化 DNA 分子的成像,这些分子被荧光标签染色,然后与参考基因组对齐。然而,目前可用于 OGM 的计算方法在准确性和计算速度方面存在不足:这项工作引入了 OM2Seq,这是一种快速、准确地将 DNA 片段图像映射到参考基因组的新方法。OM2Seq 基于变换器编码器架构,通过对获取的 OGM 数据进行训练,可将 DNA 片段图像和参考基因组片段高效编码到一个共同的嵌入空间,该嵌入空间可使用矢量数据库进行索引和高效查询。我们的研究表明,OM2Seq 在计算速度(2 个数量级)和准确性方面都明显优于基线方法。可用性和实现:https://github.com/yevgenin/om2seq。
OM2Seq: learning retrieval embeddings for optical genome mapping.
Motivation: Genomics-based diagnostic methods that are quick, precise, and economical are essential for the advancement of precision medicine, with applications spanning the diagnosis of infectious diseases, cancer, and rare diseases. One technology that holds potential in this field is optical genome mapping (OGM), which is capable of detecting structural variations, epigenomic profiling, and microbial species identification. It is based on imaging of linearized DNA molecules that are stained with fluorescent labels, that are then aligned to a reference genome. However, the computational methods currently available for OGM fall short in terms of accuracy and computational speed.
Results: This work introduces OM2Seq, a new approach for the rapid and accurate mapping of DNA fragment images to a reference genome. Based on a Transformer-encoder architecture, OM2Seq is trained on acquired OGM data to efficiently encode DNA fragment images and reference genome segments to a common embedding space, which can be indexed and efficiently queried using a vector database. We show that OM2Seq significantly outperforms the baseline methods in both computational speed (by 2 orders of magnitude) and accuracy.
Availability and implementation: https://github.com/yevgenin/om2seq.