如果机器可以学习，谁还需要科学家？
If machines can learn, who needs scientists?
机构信息
UConn Health, Farmington, CT 06030-3305, USA.
出版信息
J Magn Reson. 2019 Sep;306:162-166. doi: 10.1016/j.jmr.2019.07.044. Epub 2019 Jul 16.
Abstract
Machine learning has been used in NMR in for decades, but recent developments signal explosive growth is on the horizon. An obstacle to the application of machine learning in NMR is the relative paucity of available training data, despite the existence of numerous public NMR data repositories. Other challenges include the problem of interpreting the results of a machine learning algorithm, and incorporating machine learning into hypothesis-driven research. This perspective imagines the potential of machine learning in NMR and speculates on possible approaches to the hurdles.
摘要
机器学习在 NMR 中已经应用了几十年，但最近的发展表明其即将迎来爆发式增长。尽管存在许多公共 NMR 数据存储库，但机器学习在 NMR 中的应用仍然面临着可用训练数据相对较少的障碍。其他挑战包括解释机器学习算法结果的问题，以及将机器学习纳入假设驱动研究的问题。本文着眼于机器学习在 NMR 中的潜力，并对可能的方法进行了推测。
相似文献
1
If machines can learn, who needs scientists?如果机器可以学习，谁还需要科学家？
J Magn Reson. 2019 Sep;306:162-166. doi: 10.1016/j.jmr.2019.07.044. Epub 2019 Jul 16.
2
Data-driven modeling and prediction of blood glucose dynamics: Machine learning applications in type 1 diabetes.基于数据驱动的血糖动力学建模与预测：机器学习在 1 型糖尿病中的应用。
Artif Intell Med. 2019 Jul;98:109-134. doi: 10.1016/j.artmed.2019.07.007. Epub 2019 Jul 26.
3
Real-World Evidence, Causal Inference, and Machine Learning.真实世界证据、因果推理和机器学习。
Value Health. 2019 May;22(5):587-592. doi: 10.1016/j.jval.2019.03.001.
4
Interpreting Medical Information Using Machine Learning and Individual Conditional Expectation.利用机器学习和个体条件期望解读医学信息。
Stud Health Technol Inform. 2015;216:1073.
5
Transferability of artificial neural networks for clinical document classification across hospitals: A case study on abnormality detection from radiology reports.医院间临床文档分类的人工神经网络可转移性：以放射学报告异常检测为例的研究。
J Biomed Inform. 2018 Sep;85:68-79. doi: 10.1016/j.jbi.2018.07.017. Epub 2018 Jul 17.
6
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.
7
Machine learning in autistic spectrum disorder behavioral research: A review and ways forward.机器学习在自闭症谱系障碍行为研究中的应用：综述与展望。
Inform Health Soc Care. 2019 Sep;44(3):278-297. doi: 10.1080/17538157.2017.1399132. Epub 2018 Feb 13.
8
Comparing different supervised machine learning algorithms for disease prediction.比较不同的监督机器学习算法在疾病预测中的应用。
BMC Med Inform Decis Mak. 2019 Dec 21;19(1):281. doi: 10.1186/s12911-019-1004-8.
9
A community-powered search of machine learning strategy space to find NMR property prediction models.一个基于社区的机器学习策略空间搜索，以找到 NMR 性质预测模型。
PLoS One. 2021 Jul 20;16(7):e0253612. doi: 10.1371/journal.pone.0253612. eCollection 2021.
10
Machine learning methods for the classification of gliomas: Initial results using features extracted from MR spectroscopy.用于胶质瘤分类的机器学习方法：使用从磁共振波谱提取的特征的初步结果。
Neuroradiol J. 2015 Apr;28(2):106-11. doi: 10.1177/1971400915576637. Epub 2015 Apr 28.
引用本文的文献
1
Anomalous amide proton chemical shifts as signatures of hydrogen bonding to aromatic sidechains.异常酰胺质子化学位移作为与芳香族侧链形成氢键的特征。
Magn Reson (Gott). 2021 Oct 25;2(2):765-775. doi: 10.5194/mr-2-765-2021. eCollection 2021.
2
Biological Magnetic Resonance Data Bank.生物磁共振数据库。
Nucleic Acids Res. 2023 Jan 6;51(D1):D368-D376. doi: 10.1093/nar/gkac1050.
3
Simultaneous Prediction, Determination, and Extraction of Four Polycyclic Aromatic Hydrocarbons in the Environment Using a UCON-NaHPO Aqueous Two-Phase Extraction System Combined with High-Performance Liquid Chromatography-Ultraviolet Detection.利用 UCON-NaHPO 双水相萃取系统结合高效液相色谱-紫外检测同时预测、测定和提取环境中的四种多环芳烃。
Molecules. 2022 Sep 30;27(19):6465. doi: 10.3390/molecules27196465.
4
SpecDB: A relational database for archiving biomolecular NMR spectral data.SpecDB：用于存档生物分子 NMR 波谱数据的关系型数据库。
J Magn Reson. 2022 Sep;342:107268. doi: 10.1016/j.jmr.2022.107268. Epub 2022 Jul 16.
本文引用的文献
1
Chemical shifts in molecular solids by machine learning.机器学习在分子固体中的化学位移。
Nat Commun. 2018 Oct 29;9(1):4501. doi: 10.1038/s41467-018-06972-x.
2
Environmental metabolomics with data science for investigating ecosystem homeostasis.环境代谢组学与数据科学研究生态系统内稳性
Prog Nucl Magn Reson Spectrosc. 2018 Feb;104:56-88. doi: 10.1016/j.pnmrs.2017.11.003. Epub 2017 Nov 21.
3
HMDB 4.0: the human metabolome database for 2018.HMDB 4.0：2018 年人类代谢组数据库。
Nucleic Acids Res. 2018 Jan 4;46(D1):D608-D617. doi: 10.1093/nar/gkx1089.
4
Could Big Data be the end of theory in science? A few remarks on the epistemology of data-driven science.大数据会成为科学理论的终结吗？关于数据驱动科学的认识论的几点看法。
EMBO Rep. 2015 Oct;16(10):1250-5. doi: 10.15252/embr.201541001. Epub 2015 Sep 10.
5
Protein structural information derived from NMR chemical shift with the neural network program TALOS-N.通过神经网络程序TALOS-N从核磁共振化学位移中获得的蛋白质结构信息。
Methods Mol Biol. 2015;1260:17-32. doi: 10.1007/978-1-4939-2239-0_2.
6
Critical assessment of methods of protein structure prediction (CASP)--round x.蛋白质结构预测方法的关键评估（CASP）——第x轮
Proteins. 2014 Feb;82 Suppl 2(0 2):1-6. doi: 10.1002/prot.24452. Epub 2013 Dec 17.
7
SHIFTX2: significantly improved protein chemical shift prediction.SHIFTX2：显著提高了蛋白质化学位移预测能力。
J Biomol NMR. 2011 May;50(1):43-57. doi: 10.1007/s10858-011-9478-4. Epub 2011 Mar 30.
8
MetaboAnalyst: a web server for metabolomic data analysis and interpretation.MetaboAnalyst：一个用于代谢组学数据分析与解读的网络服务器。
Nucleic Acids Res. 2009 Jul;37(Web Server issue):W652-60. doi: 10.1093/nar/gkp356. Epub 2009 May 8.
9
BioMagResBank.生物磁共振数据库
Nucleic Acids Res. 2008 Jan;36(Database issue):D402-8. doi: 10.1093/nar/gkm957. Epub 2007 Nov 4.
Zotero 插件