三维基因组折叠深度学习模型的方法和要素
Recipes and ingredients for deep learning models of 3D genome folding.
作者信息
Smaruj Paulina N, Xiao Yao, Fudenberg Geoffrey
机构信息
Department of Quantitative and Computational Biology, University of Southern California, Los Angeles, CA, USA.
Department of Quantitative and Computational Biology, University of Southern California, Los Angeles, CA, USA.
出版信息
Curr Opin Genet Dev. 2025 Apr;91:102308. doi: 10.1016/j.gde.2024.102308. Epub 2025 Jan 24.
Abstract
Three-dimensional genome folding plays roles in gene regulation and disease. In this review, we compare and contrast recent deep learning models for predicting genome contact maps. We survey preprocessing, architecture, training, evaluation, and interpretation methods, highlighting the capabilities and limitations of different models. In each area, we highlight challenges, opportunities, and potential future directions for genome-folding models.
摘要
三维基因组折叠在基因调控和疾病中发挥作用。在这篇综述中，我们比较并对比了近期用于预测基因组接触图谱的深度学习模型。我们概述了预处理、架构、训练、评估和解释方法，突出了不同模型的能力和局限性。在每个领域，我们都强调了基因组折叠模型面临的挑战、机遇以及潜在的未来发展方向。
相似文献
1
Recipes and ingredients for deep learning models of 3D genome folding.三维基因组折叠深度学习模型的方法和要素
Curr Opin Genet Dev. 2025 Apr;91:102308. doi: 10.1016/j.gde.2024.102308. Epub 2025 Jan 24.
2
DLoopCaller: A deep learning approach for predicting genome-wide chromatin loops by integrating accessible chromatin landscapes.DLoopCaller：一种通过整合可及染色质景观来预测全基因组染色质环的深度学习方法。
PLoS Comput Biol. 2022 Oct 7;18(10):e1010572. doi: 10.1371/journal.pcbi.1010572. eCollection 2022 Oct.
3
Deep learning for RNA structure prediction.用于RNA结构预测的深度学习
Curr Opin Struct Biol. 2025 Apr;91:102991. doi: 10.1016/j.sbi.2025.102991. Epub 2025 Feb 10.
4
Machine and Deep Learning Methods for Predicting 3D Genome Organization.机器和深度学习方法预测三维基因组结构。
Methods Mol Biol. 2025;2856:357-400. doi: 10.1007/978-1-0716-4136-1_22.
5
A review of deep learning models for the prediction of chromatin interactions with DNA and epigenomic profiles.用于预测染色质与DNA相互作用及表观基因组图谱的深度学习模型综述。
Brief Bioinform. 2024 Nov 22;26(1). doi: 10.1093/bib/bbae651.
6
Predicting RNA SHAPE scores with deep learning.用深度学习预测 RNA SHAPE 分数。
RNA Biol. 2020 Sep;17(9):1324-1330. doi: 10.1080/15476286.2020.1760534. Epub 2020 May 31.
7
Predicting RNA sequence-structure likelihood via structure-aware deep learning.通过结构感知深度学习预测 RNA 序列-结构可能性。
BMC Bioinformatics. 2024 Sep 30;25(1):316. doi: 10.1186/s12859-024-05916-1.
8
A Deep Learning-Driven Sampling Technique to Explore the Phase Space of an RNA Stem-Loop.一种基于深度学习的 RNA 发夹环相空间采样技术。
J Chem Theory Comput. 2024 Oct 22;20(20):9178-9189. doi: 10.1021/acs.jctc.4c00669. Epub 2024 Oct 7.
9
Protein tertiary structure modeling driven by deep learning and contact distance prediction in CASP13.基于深度学习的蛋白质三级结构建模和 CASP13 中的接触距离预测。
Proteins. 2019 Dec;87(12):1165-1178. doi: 10.1002/prot.25697. Epub 2019 Apr 25.
10
RNA structure prediction using deep learning - A comprehensive review.使用深度学习进行RNA结构预测——全面综述。
Comput Biol Med. 2025 Apr;188:109845. doi: 10.1016/j.compbiomed.2025.109845. Epub 2025 Feb 20.
引用本文的文献
1
Machine learning tools for deciphering the regulatory logic of enhancers in health and disease.用于解读健康与疾病中增强子调控逻辑的机器学习工具
Front Genet. 2025 Aug 13;16:1603687. doi: 10.3389/fgene.2025.1603687. eCollection 2025.
2
Genome structure mapping with high-resolution 3D genomics and deep learning.利用高分辨率三维基因组学和深度学习进行基因组结构图谱绘制
bioRxiv. 2025 May 7:2025.05.06.650874. doi: 10.1101/2025.05.06.650874.
本文引用的文献
1
Interpreting the CTCF-mediated sequence grammar of genome folding with AkitaV2.使用AkitaV2解释由CTCF介导的基因组折叠序列语法。
PLoS Comput Biol. 2025 Feb 4;21(2):e1012824. doi: 10.1371/journal.pcbi.1012824. eCollection 2025 Feb.
2
Genomic language models: opportunities and challenges.基因组语言模型：机遇与挑战。
Trends Genet. 2025 Apr;41(4):286-302. doi: 10.1016/j.tig.2024.11.013. Epub 2025 Jan 2.
3
ChromaFold predicts the 3D contact map from single-cell chromatin accessibility.ChromaFold 可从单细胞染色质可及性预测 3D 接触图谱。
Nat Commun. 2024 Nov 1;15(1):9432. doi: 10.1038/s41467-024-53628-0.
4
Machine and Deep Learning Methods for Predicting 3D Genome Organization.机器和深度学习方法预测三维基因组结构。
Methods Mol Biol. 2025;2856:357-400. doi: 10.1007/978-1-0716-4136-1_22.
5
Exploring the roles of RNAs in chromatin architecture using deep learning.利用深度学习探索 RNA 在染色质结构中的作用。
Nat Commun. 2024 Jul 29;15(1):6373. doi: 10.1038/s41467-024-50573-w.
6
Cooltools: Enabling high-resolution Hi-C analysis in Python.酷工具：在 Python 中实现高分辨率 Hi-C 分析。
PLoS Comput Biol. 2024 May 6;20(5):e1012067. doi: 10.1371/journal.pcbi.1012067. eCollection 2024 May.
7
Benchmarking of deep neural networks for predicting personal gene expression from DNA sequence highlights shortcomings.用于从DNA序列预测个人基因表达的深度神经网络基准测试凸显了不足之处。
Nat Genet. 2023 Dec;55(12):2060-2064. doi: 10.1038/s41588-023-01524-6. Epub 2023 Nov 30.
8
Design principles of 3D epigenetic memory systems.三维表观遗传记忆系统的设计原则。
Science. 2023 Nov 17;382(6672):eadg3053. doi: 10.1126/science.adg3053.
9
ExplaiNN: interpretable and transparent neural networks for genomics.ExplaiNN：基因组学的可解释和透明神经网络。
Genome Biol. 2023 Jun 27;24(1):154. doi: 10.1186/s13059-023-02985-y.
10
Epiphany: predicting Hi-C contact maps from 1D epigenomic signals.顿悟：从一维表观基因组信号预测 Hi-C 接触图谱。
Genome Biol. 2023 Jun 6;24(1):134. doi: 10.1186/s13059-023-02934-9.
Zotero 插件