预测调控基因组

IF 52 1区生物学 Q1 GENETICS & HEREDITY

Nature Reviews Genetics Pub Date : 2025-09-16 DOI:10.1038/s41576-025-00887-2

Sarthak Tiwari, Alireza Karbalayghareh, Christina S. Leslie

{"title":"预测调控基因组","authors":"Sarthak Tiwari, Alireza Karbalayghareh, Christina S. Leslie","doi":"10.1038/s41576-025-00887-2","DOIUrl":null,"url":null,"abstract":"Deep learning models have made impressive strides in decoding the regulatory genome, but key challenges remain unsolved. In this Comment, the authors overview the latest deep learning models for predicting regulatory function from genomic sequence and highlight key topics going forward, including the trade-off between specialized and general models, multitasking across cell types, and training on genetic variation and diverse species.","PeriodicalId":19067,"journal":{"name":"Nature Reviews Genetics","volume":"26 10","pages":"659-660"},"PeriodicalIF":52.0000,"publicationDate":"2025-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Predicting the regulatory genome\",\"authors\":\"Sarthak Tiwari, Alireza Karbalayghareh, Christina S. Leslie\",\"doi\":\"10.1038/s41576-025-00887-2\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Deep learning models have made impressive strides in decoding the regulatory genome, but key challenges remain unsolved. In this Comment, the authors overview the latest deep learning models for predicting regulatory function from genomic sequence and highlight key topics going forward, including the trade-off between specialized and general models, multitasking across cell types, and training on genetic variation and diverse species.\",\"PeriodicalId\":19067,\"journal\":{\"name\":\"Nature Reviews Genetics\",\"volume\":\"26 10\",\"pages\":\"659-660\"},\"PeriodicalIF\":52.0000,\"publicationDate\":\"2025-09-16\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Nature Reviews Genetics\",\"FirstCategoryId\":\"99\",\"ListUrlMain\":\"https://www.nature.com/articles/s41576-025-00887-2\",\"RegionNum\":1,\"RegionCategory\":\"生物学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"GENETICS & HEREDITY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Nature Reviews Genetics","FirstCategoryId":"99","ListUrlMain":"https://www.nature.com/articles/s41576-025-00887-2","RegionNum":1,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"GENETICS & HEREDITY","Score":null,"Total":0}

引用次数: 0

摘要

深度学习模型在解码调控基因组方面取得了令人印象深刻的进展，但关键挑战仍未解决。在这篇评论中，作者概述了用于预测基因组序列调控功能的最新深度学习模型，并强调了未来的关键主题，包括专业模型和通用模型之间的权衡，跨细胞类型的多任务处理，以及遗传变异和物种多样性的训练。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Predicting the regulatory genome

Deep learning models have made impressive strides in decoding the regulatory genome, but key challenges remain unsolved. In this Comment, the authors overview the latest deep learning models for predicting regulatory function from genomic sequence and highlight key topics going forward, including the trade-off between specialized and general models, multitasking across cell types, and training on genetic variation and diverse species.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

Nature Reviews Genetics 生物-遗传学

CiteScore

57.40

自引率

0.50%

发文量

113

审稿时长

6-12 weeks

期刊介绍： At Nature Reviews Genetics, our goal is to be the leading source of reviews and commentaries for the scientific communities we serve. We are dedicated to publishing authoritative articles that are easily accessible to our readers. We believe in enhancing our articles with clear and understandable figures, tables, and other display items. Our aim is to provide an unparalleled service to authors, referees, and readers, and we are committed to maximizing the usefulness and impact of each article we publish. Within our journal, we publish a range of content including Research Highlights, Comments, Reviews, and Perspectives that are relevant to geneticists and genomicists. With our broad scope, we ensure that the articles we publish reach the widest possible audience. As part of the Nature Reviews portfolio of journals, we strive to uphold the high standards and reputation associated with this esteemed collection of publications.