生物医学可视机器学习。
Visible Machine Learning for Biomedicine.
机构信息
Division of Genetics, Department of Medicine, University of California San Diego, La Jolla, CA, USA; Cancer Cell Map Initiative, University of California San Diego, La Jolla, CA, USA; UCSD Program in Bioinformatics and Systems Biology, University of California San Diego, La Jolla, CA, USA.
Division of Genetics, Department of Medicine, University of California San Diego, La Jolla, CA, USA; Cancer Cell Map Initiative, University of California San Diego, La Jolla, CA, USA.
出版信息
Cell. 2018 Jun 14;173(7):1562-1565. doi: 10.1016/j.cell.2018.05.056.
Abstract
A major ambition of artificial intelligence lies in translating patient data to successful therapies. Machine learning models face particular challenges in biomedicine, however, including handling of extreme data heterogeneity and lack of mechanistic insight into predictions. Here, we argue for "visible" approaches that guide model structure with experimental biology.
摘要
人工智能的主要目标之一在于将患者数据转化为成功的治疗方法。然而，机器学习模型在生物医学领域面临着特殊的挑战，包括处理极端的数据异质性以及缺乏对预测的机制理解。在这里，我们提倡采用“可见”的方法，用实验生物学指导模型结构。
相似文献
1
Visible Machine Learning for Biomedicine.生物医学可视机器学习。
Cell. 2018 Jun 14;173(7):1562-1565. doi: 10.1016/j.cell.2018.05.056.
2
Rethinking Drug Repositioning and Development with Artificial Intelligence, Machine Learning, and Omics.利用人工智能、机器学习和组学重新思考药物重定位和开发。
OMICS. 2019 Nov;23(11):539-548. doi: 10.1089/omi.2019.0151. Epub 2019 Oct 25.
3
Next-Generation Machine Learning for Biological Networks.下一代生物网络机器学习。
Cell. 2018 Jun 14;173(7):1581-1592. doi: 10.1016/j.cell.2018.05.015. Epub 2018 Jun 7.
4
Machine Learning: An Overview and Applications in Pharmacogenetics.机器学习：概述及其在药物遗传学中的应用。
Genes (Basel). 2021 Sep 26;12(10):1511. doi: 10.3390/genes12101511.
5
Galaxy-ML: An accessible, reproducible, and scalable machine learning toolkit for biomedicine.Galaxy-ML：一个可访问、可重现和可扩展的生物医学机器学习工具包。
PLoS Comput Biol. 2021 Jun 1;17(6):e1009014. doi: 10.1371/journal.pcbi.1009014. eCollection 2021 Jun.
6
Opportunities and challenges using artificial intelligence in ADME/Tox.人工智能在 ADME/Tox 中的机遇与挑战。
Nat Mater. 2019 May;18(5):418-422. doi: 10.1038/s41563-019-0332-5.
7
Incorporating Machine Learning into Established Bioinformatics Frameworks.将机器学习纳入既定的生物信息学框架中。
Int J Mol Sci. 2021 Mar 12;22(6):2903. doi: 10.3390/ijms22062903.
8
Computational Technology with Artificial Intelligence and Machine Learning: What Should a Cytologist Do with It?具备人工智能和机器学习的计算技术：细胞学家应如何应对？
Acta Cytol. 2021;65(4):283-285. doi: 10.1159/000508215. Epub 2020 Jul 8.
9
Machine learning and graph analytics in computational biomedicine.计算生物医学中的机器学习与图形分析
Artif Intell Med. 2017 Nov;83:1. doi: 10.1016/j.artmed.2017.09.003. Epub 2017 Sep 7.
10
Machine learning and artificial intelligence in haematology.机器学习和血液学中的人工智能。
Br J Haematol. 2021 Jan;192(2):239-250. doi: 10.1111/bjh.16915. Epub 2020 Jun 30.
引用本文的文献
1
Fine tuning a logical model of cancer cells to predict drug synergies: combining manual curation and automated parameterization.微调癌细胞逻辑模型以预测药物协同作用：结合人工整理与自动参数化
Front Syst Biol. 2023 Nov 20;3:1252961. doi: 10.3389/fsysb.2023.1252961. eCollection 2023.
2
Challenges and Opportunities in Analyzing Cancer-Associated Microbiomes.分析癌症相关微生物群的挑战与机遇
Cancer Res. 2025 Aug 12. doi: 10.1158/0008-5472.CAN-24-3629.
3
Detecting genetic interactions with visible neural networks.检测与可见神经网络的基因相互作用。
Commun Biol. 2025 Jun 5;8(1):874. doi: 10.1038/s42003-025-08157-x.
4
MethPriorGCN: a deep learning tool for inferring DNA methylation prior knowledge and guiding personalized medicine.MethPriorGCN：一种用于推断DNA甲基化先验知识并指导个性化医疗的深度学习工具。
Brief Bioinform. 2025 Mar 4;26(2). doi: 10.1093/bib/bbaf131.
5
Prognostic prediction models for postoperative patients with stage I to III colorectal cancer based on machine learning.基于机器学习的Ⅰ至Ⅲ期结直肠癌术后患者预后预测模型
World J Gastrointest Oncol. 2024 Dec 15;16(12):4597-4613. doi: 10.4251/wjgo.v16.i12.4597.
6
mosGraphGen: a novel tool to generate multi-omics signaling graphs to facilitate integrative and interpretable graph AI model development.mosGraphGen：一种用于生成多组学信号图以促进集成且可解释的图人工智能模型开发的新型工具。
Bioinform Adv. 2024 Oct 8;4(1):vbae151. doi: 10.1093/bioadv/vbae151. eCollection 2024.
7
AI-readiness for Biomedical Data: Bridge2AI Recommendations.生物医学数据的人工智能准备情况：Bridge2AI 建议
bioRxiv. 2024 Nov 24:2024.10.23.619844. doi: 10.1101/2024.10.23.619844.
8
How to Build the Virtual Cell with Artificial Intelligence: Priorities and Opportunities.如何利用人工智能构建虚拟细胞：优先事项与机遇
ArXiv. 2024 Oct 14:arXiv:2409.11654v2.
9
Designing interpretable deep learning applications for functional genomics: a quantitative analysis.设计可解释的深度学习应用于功能基因组学：一项定量分析。
Brief Bioinform. 2024 Jul 25;25(5). doi: 10.1093/bib/bbae449.
10
An interpretable survival model for diffuse large B-cell lymphoma patients using a biologically informed visible neural network.一种使用具有生物学信息的可视神经网络的弥漫性大B细胞淋巴瘤患者可解释生存模型。
Comput Struct Biotechnol J. 2024 Jul 24;24:523-532. doi: 10.1016/j.csbj.2024.07.019. eCollection 2024 Dec.
本文引用的文献
1
Using deep learning to model the hierarchical structure and function of a cell.利用深度学习来模拟细胞的层次结构和功能。
Nat Methods. 2018 Apr;15(4):290-298. doi: 10.1038/nmeth.4627. Epub 2018 Mar 5.
2
Using neural networks for reducing the dimensions of single-cell RNA-Seq data.使用神经网络降低单细胞RNA测序数据的维度。
Nucleic Acids Res. 2017 Sep 29;45(17):e156. doi: 10.1093/nar/gkx681.
3
High-Definition Medicine.高清医学
Cell. 2017 Aug 24;170(5):828-843. doi: 10.1016/j.cell.2017.08.007.
4
An Expanded View of Complex Traits: From Polygenic to Omnigenic.复杂性状的扩展观点：从多基因到泛基因
Cell. 2017 Jun 15;169(7):1177-1186. doi: 10.1016/j.cell.2017.05.038.
5
Functional characterization of somatic mutations in cancer using network-based inference of protein activity.利用基于网络的蛋白质活性推断对癌症中的体细胞突变进行功能表征。
Nat Genet. 2016 Aug;48(8):838-47. doi: 10.1038/ng.3593. Epub 2016 Jun 20.
6
Mastering the game of Go with deep neural networks and tree search.用深度神经网络和树搜索掌握围棋游戏。
Nature. 2016 Jan 28;529(7587):484-9. doi: 10.1038/nature16961.
7
Deep learning.深度学习。
Nature. 2015 May 28;521(7553):436-44. doi: 10.1038/nature14539.
8
Machine learning applications in cancer prognosis and prediction.机器学习在癌症预后和预测中的应用。
Comput Struct Biotechnol J. 2014 Nov 15;13:8-17. doi: 10.1016/j.csbj.2014.11.005. eCollection 2015.
9
Network analysis of GWAS data.GWAS 数据的网络分析。
Curr Opin Genet Dev. 2013 Dec;23(6):602-10. doi: 10.1016/j.gde.2013.09.003. Epub 2013 Nov 26.
10
A whole-cell computational model predicts phenotype from genotype.全细胞计算模型从基因型预测表型。
Cell. 2012 Jul 20;150(2):389-401. doi: 10.1016/j.cell.2012.05.044.
Zotero 插件