机器学习在遗传学和基因组学中的应用。
Machine learning applications in genetics and genomics.
作者信息
Libbrecht Maxwell W, Noble William Stafford
机构信息
Department of Computer Science and Engineering, University of Washington, 185 Stevens Way, Seattle, Washington 98195-2350, USA.
1] Department of Computer Science and Engineering, University of Washington, 185 Stevens Way, Seattle, Washington 98195-2350, USA. [2] Department of Genome Sciences, University of Washington, 3720 15th Ave NE Seattle, Washington 98195-5065, USA.
出版信息
Nat Rev Genet. 2015 Jun;16(6):321-32. doi: 10.1038/nrg3920. Epub 2015 May 7.
Abstract
The field of machine learning, which aims to develop computer algorithms that improve with experience, holds promise to enable computers to assist humans in the analysis of large, complex data sets. Here, we provide an overview of machine learning applications for the analysis of genome sequencing data sets, including the annotation of sequence elements and epigenetic, proteomic or metabolomic data. We present considerations and recurrent challenges in the application of supervised, semi-supervised and unsupervised machine learning methods, as well as of generative and discriminative modelling approaches. We provide general guidelines to assist in the selection of these machine learning methods and their practical application for the analysis of genetic and genomic data sets.
摘要
机器学习领域旨在开发能随着经验提升的计算机算法，有望使计算机协助人类分析大型复杂数据集。在此，我们概述机器学习在基因组测序数据集分析中的应用，包括序列元件注释以及表观遗传、蛋白质组或代谢组数据。我们介绍了监督学习、半监督学习和无监督学习方法以及生成式和判别式建模方法应用中的注意事项和常见挑战。我们提供通用指南，以协助选择这些机器学习方法及其在遗传和基因组数据集分析中的实际应用。
相似文献
1
Machine learning applications in genetics and genomics.机器学习在遗传学和基因组学中的应用。
Nat Rev Genet. 2015 Jun;16(6):321-32. doi: 10.1038/nrg3920. Epub 2015 May 7.
2
Deep learning: new computational modelling techniques for genomics.深度学习：基因组学的新计算建模技术。
Nat Rev Genet. 2019 Jul;20(7):389-403. doi: 10.1038/s41576-019-0122-6.
3
Machine learning and genome annotation: a match meant to be?机器学习与基因组注释：天作之合？
Genome Biol. 2013 May 29;14(5):205. doi: 10.1186/gb-2013-14-5-205.
4
From shallow to deep: some lessons learned from application of machine learning for recognition of functional genomic elements in human genome.从浅入深：机器学习在人类基因组功能基因组元件识别应用中的一些经验教训。
Hum Genomics. 2022 Feb 18;16(1):7. doi: 10.1186/s40246-022-00376-1.
5
Combining Supervised and Unsupervised Machine Learning Methods for Phenotypic Functional Genomics Screening.结合监督和无监督机器学习方法进行表型功能基因组学筛选。
SLAS Discov. 2020 Jul;25(6):655-664. doi: 10.1177/2472555220919345. Epub 2020 May 13.
6
Opportunities and Challenges with Artificial Intelligence in Genomics.人工智能在基因组学中的机遇与挑战。
Clin Lab Med. 2023 Mar;43(1):87-97. doi: 10.1016/j.cll.2022.09.007. Epub 2022 Dec 13.
7
Semisupervised learning for a hybrid generative/discriminative classifier based on the maximum entropy principle.基于最大熵原理的混合生成/判别式分类器的半监督学习
IEEE Trans Pattern Anal Mach Intell. 2008 Mar;30(3):424-37. doi: 10.1109/TPAMI.2007.70710.
8
Artificial intelligence and machine learning overview in pathology & laboratory medicine: A general review of data preprocessing and basic supervised concepts.病理学与检验医学中的人工智能和机器学习概述：数据预处理及基本监督概念的综合回顾
Semin Diagn Pathol. 2023 Mar;40(2):71-87. doi: 10.1053/j.semdp.2023.02.002. Epub 2023 Feb 16.
9
Principles of artificial intelligence and its application in cardiovascular medicine.人工智能原理及其在心血管医学中的应用。
Clin Cardiol. 2024 Jan;47(1):e24148. doi: 10.1002/clc.24148. Epub 2023 Sep 18.
10
Machine learning for epigenetics and future medical applications.用于表观遗传学和未来医学应用的机器学习。
Epigenetics. 2017 Jul 3;12(7):505-514. doi: 10.1080/15592294.2017.1329068. Epub 2017 May 19.
引用本文的文献
1
Climate-Resilient Crops: Integrating AI, Multi-Omics, and Advanced Phenotyping to Address Global Agricultural and Societal Challenges.气候适应型作物：整合人工智能、多组学和先进表型分析以应对全球农业和社会挑战
Plants (Basel). 2025 Aug 29;14(17):2699. doi: 10.3390/plants14172699.
2
Artificial Intelligence in Ocular Transcriptomics: Applications of Unsupervised and Supervised Learning.眼科转录组学中的人工智能：无监督学习和监督学习的应用
Cells. 2025 Aug 26;14(17):1315. doi: 10.3390/cells14171315.
3
Artificial Intelligence and Chromothripsis.人工智能与染色体碎裂
Methods Mol Biol. 2025;2968:281-289. doi: 10.1007/978-1-0716-4750-9_16.
4
Shapley additive explanations based feature selection reveals CXCL14 as a key immune-related gene in predicting idiopathic pulmonary fibrosis.基于Shapley值加法解释的特征选择揭示CXCL14是预测特发性肺纤维化的关键免疫相关基因。
Front Med (Lausanne). 2025 Aug 6;12:1608078. doi: 10.3389/fmed.2025.1608078. eCollection 2025.
5
Next generation biobanking ontology: introducing-omics contextual data to biobanking ontology.下一代生物样本库本体：将组学背景数据引入生物样本库本体。
Bioinform Adv. 2025 Aug 7;5(1):vbaf131. doi: 10.1093/bioadv/vbaf131. eCollection 2025.
6
From lab to life: technological innovations in transforming cancer metastasis detection and therapy.从实验室到临床：癌症转移检测与治疗变革中的技术创新
Discov Oncol. 2025 Aug 10;16(1):1517. doi: 10.1007/s12672-025-02910-8.
7
Practicality of training a quantum-classical machine in the noisy intermediate-scale quantum era.在嘈杂的中尺度量子时代训练量子经典机器的实用性。
iScience. 2025 Jul 9;28(8):113058. doi: 10.1016/j.isci.2025.113058. eCollection 2025 Aug 15.
8
Genomic language models with k-mer tokenization strategies for plant genome annotation and regulatory element strength prediction.用于植物基因组注释和调控元件强度预测的采用k-mer分词策略的基因组语言模型。
Plant Mol Biol. 2025 Jul 31;115(4):100. doi: 10.1007/s11103-025-01604-7.
9
Identification of Prognostic and Diagnostic Biomarkers for Glioma Utilizing Immune System Gene Profiling.利用免疫系统基因谱鉴定胶质瘤的预后和诊断生物标志物
Med J Islam Repub Iran. 2025 Apr 1;39:49. doi: 10.47176/mjiri.39.49. eCollection 2025.
10
The Use of Selected Machine Learning Methods in Dairy Cattle Farming: A Review.机器学习方法在奶牛养殖中的应用：综述
Animals (Basel). 2025 Jul 10;15(14):2033. doi: 10.3390/ani15142033.
本文引用的文献
1
An Analysis Pipeline with Statistical and Visualization-Guided Knowledge Discovery for Michigan-Style Learning Classifier Systems.用于密歇根风格学习分类器系统的具有统计和可视化引导知识发现的分析管道。
IEEE Comput Intell Mag. 2012 Nov;7(4):35-45. doi: 10.1109/MCI.2012.2215124.
2
A general framework for estimating the relative pathogenicity of human genetic variants.一种用于估计人类遗传变异相对致病性的通用框架。
Nat Genet. 2014 Mar;46(3):310-5. doi: 10.1038/ng.2892. Epub 2014 Feb 2.
3
Application of machine learning to proteomics data: classification and biomarker identification in postgenomics biology.机器学习在蛋白质组学数据中的应用：后基因组生物学中的分类和生物标志物识别。
OMICS. 2013 Dec;17(12):595-610. doi: 10.1089/omi.2013.0017. Epub 2013 Oct 12.
4
Machine learning and genome annotation: a match meant to be?机器学习与基因组注释：天作之合？
Genome Biol. 2013 May 29;14(5):205. doi: 10.1186/gb-2013-14-5-205.
5
An integrated encyclopedia of DNA elements in the human genome.人类基因组中 DNA 元件的综合百科全书。
Nature. 2012 Sep 6;489(7414):57-74. doi: 10.1038/nature11247.
6
Classification of human genomic regions based on experimentally determined binding sites of more than 100 transcription-related factors.基于超过 100 个与转录相关的因子的实验确定的结合位点对人类基因组区域进行分类。
Genome Biol. 2012 Sep 26;13(9):R48. doi: 10.1186/gb-2012-13-9-r48.
7
Using rule-based machine learning for candidate disease gene prioritization and sample classification of cancer gene expression data.基于规则的机器学习在候选疾病基因优先级和癌症基因表达数据样本分类中的应用。
PLoS One. 2012;7(7):e39932. doi: 10.1371/journal.pone.0039932. Epub 2012 Jul 11.
8
Machine learning approaches for the discovery of gene-gene interactions in disease data.机器学习方法在疾病数据中发现基因-基因相互作用。
Brief Bioinform. 2013 Mar;14(2):251-60. doi: 10.1093/bib/bbs024. Epub 2012 May 18.
9
Unsupervised pattern discovery in human chromatin structure through genomic segmentation.通过基因组分割实现人类染色质结构的无监督模式发现。
Nat Methods. 2012 Mar 18;9(5):473-6. doi: 10.1038/nmeth.1937.
10
ChromHMM: automating chromatin-state discovery and characterization.ChromHMM：染色质状态发现与特征描述自动化
Nat Methods. 2012 Feb 28;9(3):215-6. doi: 10.1038/nmeth.1906.
Zotero 插件