{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/deep-snp-an-end-to-end-deep-neural-network","title":"Deep SNP: An End-to-end Deep Neural Network with Attention-based Localization for Break-point Detection in SNP Array Genomic data","arxiv_id":"1806.08840","date":"2018-06-22","proceeding":null,"authors":["Hamid Eghbal-zadeh","Lukas Fischer","Niko Popitsch","Florian Kromp","Sabine Taschner-Mandl","Khaled Koutini","Teresa Gerber","Eva Bozsaky","Peter F. Ambros","Inge M. Ambros","Gerhard Widmer","Bernhard A. Moser"],"abstract":"Diagnosis and risk stratification of cancer and many other diseases require\nthe detection of genomic breakpoints as a prerequisite of calling copy number\nalterations (CNA). This, however, is still challenging and requires\ntime-consuming manual curation. As deep-learning methods outperformed classical\nstate-of-the-art algorithms in various domains and have also been successfully\napplied to life science problems including medicine and biology, we here\npropose Deep SNP, a novel Deep Neural Network to learn from genomic data.\nSpecifically, we used a manually curated dataset from 12 genomic single\nnucleotide polymorphism array (SNPa) profiles as truth-set and aimed at\npredicting the presence or absence of genomic breakpoints, an indicator of\nstructural chromosomal variations, in windows of 40,000 probes. We compare our\nresults with well-known neural network models as well as Rawcopy though this\ntool is designed to predict breakpoints and in addition genomic segments with\nhigh sensitivity. We show, that Deep SNP is capable of successfully predicting\nthe presence or absence of a breakpoint in large genomic windows and\noutperforms state-of-the-art neural network models. Qualitative examples\nsuggest that integration of a localization unit may enable breakpoint detection\nand prediction of genomic segments, even if the breakpoint coordinates were not\nprovided for network training. These results warrant further evaluation of\nDeepSNP for breakpoint localization and subsequent calling of genomic segments.","url_abs":"http://arxiv.org/abs/1806.08840v1","url_pdf":"http://arxiv.org/pdf/1806.08840v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"deep-snp-an-end-to-end-deep-neural-network","repo_url":"https://github.com/eghbalz/deepsnp","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}