数据与技术双轮驱动的生物医学信息学发展与展望

doi:10.11871/jfdc.issn.2096-742X.2023.01.004

数据与计算发展前沿 ›› 2023, Vol. 5 ›› Issue (1): 41-54.

CSTR: 32002.14.jfdc.CN10-1649/TP.2023.01.004

doi: 10.11871/jfdc.issn.2096-742X.2023.01.004

• 专刊:科学数据资源、技术与政策联合专刊 • 上一篇下一篇

数据与技术双轮驱动的生物医学信息学发展与展望

范少萍¹(),张志强^2,^3,^*()

1.中国医学科学院医学信息研究所，北京 100020
2.中国科学院成都文献情报中心，四川成都 610041
3.中国科学院大学经济与管理学院，图书情报与档案系，北京 100049

收稿日期:2022-03-14 出版日期:2023-02-20 发布日期:2023-02-20
通讯作者: 张志强
作者简介:范少萍，中国医学科学院医学信息研究所，副研究员，长期从事生物医学领域文本挖掘、信息分析与科技评价研究，主要研究方向为生物医学文本挖掘与科技评价。
本文中负责论文起草、撰写与修改。
FAN Shaoping, Associate researcher, Institute of Medical Infor-mation & Library, Chinese Academy of Medical Sciences, has long been engaged in text mining, information analysis, and science and technology evaluation in the biomedical field. Her research interests include biomedical text mining, and science and technology evaluation.
In this paper, she is responsible for the drafting, writing, and revision.
E-mail: fan.shaoping@imicams.ac.cn|张志强，中国科学院大学经济与管理学院，教授，中国科学院成都文献情报中心，研究员，四川省委省政府决策咨询委员会委员，四川省学术和技术带头人。独立或合作出版专编著30部、出版译著13部、发表论文400余篇。获得省部级科技进步奖、社会科学优秀成果奖等科技成果奖励20项。主要研究领域为科技战略与政策、科学计量与评价、学科信息学与知识发现、科技情报学、智库理论与实践、区域发展战略规划与政策等。
本文中负责提出研究思路，论文修改与指导，论文最终版本修订。
ZHANG Zhiqiang, Professor of School of Economics and Man-agement of University of the Chinese Academy of Sciences, Professor of Chengdu Library and Information Center of the Chinese Academy of Sciences. He is a Member of the Adv-isory Committee for Decision-making of Sichuan Province. He is also an Academic and Technological Professionals in Sichuan Province. He has published 30 monographs, 13 translated works, and more than 400 papers independently or jointly, and won 20 awards for scientific and technological achievements such as the provincial and ministerial scientific and technological progress award and social science excellent achievement award. His major research fields are the strategy and policy of science and technology, scientometrics and eva-luation, subject informatics and knowledge discovery, science and technology information science, think tank theory and practice, the strategy and policy of regional development, etc.
In this paper, he is mainly responsible for proposing research ideas, revising and guiding the paper, and revising the final version of the paper.
E-mail: zhangzq@clas.ac.cn
基金资助:
国家社会科学基金重点项目“面向领域知识发现的学科信息学理论与应用研究”(17ATQ008)

The Development and Prospect of Biomedical Informatics Driven by Data and Technology

FAN Shaoping¹(),ZHANG Zhiqiang^2,^3,^*()

1. Institute of Medical Information & Library, Chinese Academy of Medical Sciences, Beijing 100020, China
2. Chengdu Library and Information Center, Chinese Academy of Sciences, Chengdu, Sichuan 610041, China
3. Department of Library, Information and Archives Management, School of Economics and Management, University of Chinese Academy of Sciences, Beijing 100049, China

Received:2022-03-14 Online:2023-02-20 Published:2023-02-20
Contact: ZHANG Zhiqiang

摘要/Abstract

摘要：

【目的】生物医学信息学是发展最快的代表性专业信息学之一。梳理生物医学信息学理论体系与最新进展，展望学科未来发展路径尤为重要。【方法】通过文献计量与调研，我们分析了生物医学信息学主要研究内容，并对数据资源体系、数据分析算法与模型、数据分析工具与软件等方面的最新进展进行了详细梳理。【结果】该领域逐渐形成了以大数据资源为基础、以技术为手段、以人才为核心、以应用为导向的学科发展路径，预计这一新的范式将有效支撑生物医学信息学的高速、深入发展。【局限】基于篇幅，一些生物医学数据资源与方法等的分析广度有限。【结论】数据与技术是生物医学信息学发展的两个关键环节，通过本文的梳理与展望，以期为我国生物医学信息学学科完善与发展提供参考。

关键词: 生物医学信息学, 知识发现, 数据资源, 算法与模型, 工具与软件

Abstract:

[Objective] Biomedical informatics is one of the fastest specialized developing disciplines of information sciences. Our review summarizes the latest progress and future development of theoretical systems, platforms, and tools of biomedical informatics. [Methods] This review teases out the development of data resource construction, data analysis algorithms and models, tools, and software in biomedical informatics through bibliometrics and literature research. [Results] It will effectively support the development of biomedical informatics by forming a discipline development path, which is resource-based, technology-supported, talent-centered, and application-oriented. [Limitations] Limited by word count, some biomedical data resources and methods are not thoroughly involved. [Conclusions] Data and technology are key elements in the development of biomedical informatics. We hope to provide a literature review and references for the improvement of biomedical informatics in China.

Key words: Biomedical Informatics, knowledge discovery, data resource, computing models, algorithms and tools

范少萍,张志强. 数据与技术双轮驱动的生物医学信息学发展与展望[J]. 数据与计算发展前沿, 2023, 5(1): 41-54.

FAN Shaoping,ZHANG Zhiqiang. The Development and Prospect of Biomedical Informatics Driven by Data and Technology[J]. Frontiers of Data and Computing, 2023, 5(1): 41-54, https://cstr.cn/32002.14.jfdc.CN10-1649/TP.2023.01.004.

图/表 11

表1

图1

图2

图3

图4

表2

图5

图6

表3

表4

表5

参考文献 56

[1]	Embi P J, Kaufman S E, Payne P R. Biomedical Inform-atics and Outcomes Research: Enabling Knowledge-driven Healthcare[J]. Circulation, 2009, 120(23):2393-2399. doi: 10.1161/CIRCULATIONAHA.108.795526
[2]	Sarkar I N. Biomedical Informatics and Translational Medicine[J]. Journal of Translational Medicine, 2010, 8(1):22. doi: 10.1186/1479-5876-8-22
[3]	Leinonen R, Sugawara H, Shumway M. International Nucleotide Sequence Database Collaboration. The seque-nce read archive[J]. Nucleic Acids Research, 2011, 39: 19-21. doi: 10.1093/nar/gkq1019 pmid: 21062823
[4]	Brown G R, Hem V, Katz K S, et al. Gene: a gene-cent-ered information resource at NCBI[J]. Nucleic Acids Research, 2015, 43: 36-42.
[5]	Kim S, Thiessen P A, Cheng T, et al. Literature infor-mation in PubChem: associations between PubChem records and scientific articles[J]. Journal of Chemin-formatics, 2016, 8: 32.
[6]	Wishart D S, Feunang Y D, Guo A C, et al. DrugBank 5.0: a major update to the DrugBank database for 2018[J]. Nucleic Acids Research, 2018, 46(D1): 1074-1082. doi: 10.1093/nar/gkx1037 pmid: 29126136
[7]	Wu A, Y Peng, Huang B, et al. Genome Composition and Divergence of the Novel Coronavirus (2019-nCoV) Originating in China[J]. Cell Host & Microbe, 2020, 27(3): 325-328.
[8]	Lu I N, Muller C P, He F Q. Applying next-generation sequencing to unravel the mutational landscape in viral quasispecies[J]. Virus Research, 2020, 283: 197963. doi: 10.1016/j.virusres.2020.197963
[9]	Ramírez J D, Muñoz M, Hernández C, et al. Genetic Di-versity Among SARS-CoV2 Strains in South America may Impact Performance of Molecular Detection[J]. Pat-hogens, 2020, 9(7): 580.
[10]	Prasanth D S N B K, Murahari M, Chandramohan V, et al. In silico identification of potential inhibitors from Cinnamon against main protease and spike glycoprotein of SARS CoV-2[J]. Journal of Biomolecular Structure & Dynamics, 2021, 39(13): 4618-4632.
[11]	Ray M, Sable MN, Sarkar S, et al. Essential interpre-tations of bioinformatics in covid-19 pandemic[J]. Meta Gene, 2021, 27:100844. doi: 10.1016/j.mgene.2020.100844
[12]	Wen A, Fu S, Moon S, et al. Desiderata for delivering NLP to accelerate healthcare AI advancement and a Mayo Cli-nic NLP-as-a-service implementation[J]. npj Digital Med-icine, 2019, 2:130.
[13]	Lucila O M. NIH’s Big Data to Knowledge initiative and the advancement of biomedical informatics[J]. Journal of the American Medical Informatics Association, 2014, 21(2): 193. doi: 10.1136/amiajnl-2014-002666
[14]	Kulikowski C A, Shortliffe E H, Currie L M, et al. AMIA Board white paper: definition of biomedical informatics and specification of core competencies for graduate edu-cation in the discipline[J]. Journal of the American Med-ical Informatics Association, 2012, 19(6): 931-938.
[15]	Shortliffe E H, 罗述谦译. 生物医学信息学[M]. 北京: 科学出版社, 2011: 79.
[16]	刘壮, 张悦. 统计学方法在生物信息学分析中的应用[J]. 医学信息学杂志, 2020, 41(6):20-23.
[17]	张志强, 范少萍, 陈秀娟. 面向精准医学知识发现的生物医学信息学发展[J]. 数据分析与知识发现, 2018, 2(1): 1-8.
[18]	Rigden D J, Fernández X M. The 2022 Nucleic Acids Research database issue and the online molecular biology database collection[J]. Nucleic Acids Research, 2022, 50(D1): D1-D10. doi: 10.1093/nar/gkab1195 pmid: 34986604
[19]	Sayers E W, Bolton E E, Brister J R, et al. Database res-ources of the national center for biotechnology infor-mation[J]. Nucleic Acids Research, 2022, 50(D1): D20-D26. doi: 10.1093/nar/gkab1112
[20]	Cantelli G, Bateman A, Brooksbank C, et al. The Eur-opean Bioinformatics Institute (EMBL-EBI) in 2021[J]. Nucleic Acids Research, 2022, 50(D1): D11-D19. doi: 10.1093/nar/gkab1127
[21]	Okido T, Kodama Y, Mashima J, et al. DNA Data Bank of Japan (DDBJ) update report 2021[J]. Nucleic Acids Research, 2022, 50(D1): D102-D105. doi: 10.1093/nar/gkab995
[22]	CNCB-NGDC Members and Partners. Database Resou-rces of the National Genomics Data Center, China Nat-ional Center for Bioinformation in 2022[J]. Nucleic Acids Research, 2022, 50(D1): D27-D38. doi: 10.1093/nar/gkab951
[23]	Zhao S, Su C, Lu Z, et al. Recent advances in biomedical literature mining[J]. Brief in Bioinformatics. 2021, 22(3): bbaa057. doi: 10.1093/bib/bbaa057
[24]	Lee J, Yoon W, Kim S, et al. BioBERT: a pre-trained bio-medical language representation model for biomedical text mining[J]. Bioinformatics, 2020, 36(4): 1234-1240 doi: 10.1093/bioinformatics/btz682
[25]	Naseem U, Musial K, Eklund P, et al. Biomedical named-entity recognition by hierarchically fusing biobert repre-sentations and deep contextual-level word-embedding[C]. 2020 International Joint Conference on Neural Networks (IJCNN), IEEE, 2020:1-8.
[26]	Tian Y, Shen W, Song Y, et al. Improving biomedical named entity recognition with syntactic information[J]. BMC Bioinformatics, 2020, 21(1):539. doi: 10.1186/s12859-020-03834-6 pmid: 33238875
[27]	Xun G, Jha K, Yuan Y, et al. MeSHProbeNet: a self-attentive probe net for MeSH indexing[J]. Bioinformatics, 2019, 35(19): 3794-3802. doi: 10.1093/bioinformatics/btz142 pmid: 30851089
[28]	Dai S, You R, Lu Z, et al. FullMeSH: improving large-scale MeSH indexing with full text[J]. Bioinformatics, 2020, 36(5):1533-1541. doi: 10.1093/bioinformatics/btz756 pmid: 31596475
[29]	You R, Liu Y, Mamitsuka H, et al. BERTMeSH: deep contextual representation learning for large-scale high-performance MeSH indexing with full text[J]. Bioin-formatics, 2021, 37(5): 684-692.
[30]	Zhou H, Lang C, Liu Z, et al. Knowledge-guided con-volutional networks for chemical-disease relation extra-ction[J]. BMC Bioinformatics, 2019, 20(1):260. doi: 10.1186/s12859-019-2873-7
[31]	Sun Y, Wang J, Lin H, et al. Knowledge Guided Attention and Graph Convolutional Networks for Chemical-Disease Relation Extraction[J/OL]. IEEE/ACM Transactions on Computational Biology and Bioinformatics, 2021, https://ieeexplore.ieee.org/document/9663570. doi:10.1109/TCBB.2021.3135844. doi: 10.1109/TCBB.2021.3135844
[32]	Zhu T, Qin Y, Xiang Y, et al. Distantly supervised bio-medical relation extraction using piecewise attentive convolutional neural network and reinforcement learning[J]. Journal of the American Medical Informatics Asso-ciation, 2021, 28(12): 2571-2581.
[33]	Poon H, Toutanova K, Quirk C. Distant supervision for cancer pathway extraction from text[C]. Pacific Sym-posium on Biocomputing 2015, Kohala Coast, Hawaii, USA, 2015: 120-131.
[34]	Feng YH, Zhang SW, Shi JY. DPDDI: a deep predictor for drug-drug interactions[J]. BMC Bioinformatics, 2020, 21(1):419. doi: 10.1186/s12859-020-03724-x
[35]	Masumshah R, Aghdam R, Eslahchi C. A neural net-work-based method for polypharmacy side effects pred-iction[J]. BMC Bioinformatics, 2021, 22(1):385. doi: 10.1186/s12859-021-04298-y pmid: 34303360
[36]	Coşkun M, Koyutürk M. Node similarity-based graph convolution for link prediction in biological networks[J]. Bioinformatics, 2021, 37(23):4501-4508. doi: 10.1093/bioinformatics/btab464
[37]	Boratyn GM, Camacho C, Cooper PS, et al. BLAST: a more efficient report with usability improvements[J]. Nucleic Acids Research, 2013, 41(W1): W29-W33. doi: 10.1093/nar/gkt282
[38]	Boratyn GM, Thierry-Mieg J, Thierry-Mieg D, et al. Magic-BLAST, an accurate RNA-seq aligner for long and short reads[J]. BMC Bioinformatics, 2019, 20(1):405. doi: 10.1186/s12859-019-2996-x pmid: 31345161
[39]	Taeyong P, Jonghun W, Minkyung B, et al. Galaxy-Heteromer: protein heterodimer structure pre-diction by template-based and ab initio docking[J]. Nucleic Acids Research, 2021, 49(W1): W237-W241. doi: 10.1093/nar/gkab422
[40]	Maxat, K, Fernando, Z C, Robert, H. DeepGOWeb: fast and accurate protein function prediction on the (Semantic) Web[J]. Nucleic Acids Research, 2021, 49(W1): W140-W146. doi: 10.1093/nar/gkab373
[41]	Ding J, Montgomery B, Thien N, et al. Mergeomics 2.0: a web server for multi-omics data integration to elucidate disease networks and predict therapeutics[J]. Nucleic Acids Research, 2021, 49(W1): W375-W387. doi: 10.1093/nar/gkab405 pmid: 34048577
[42]	Arif M, Zhang C, Li X Y, et al. iNetModels 2.0: an interactive visualization and database of multi-omics data[J]. Nucleic Acids Research, 2021, 49(W1): W271-W276. doi: 10.1093/nar/gkab254 pmid: 33849075
[43]	Zheng S, Aldahdooh J, Shadbahr T, et al. DrugComb update: a more comprehensive drug sensitivity data repository and analysis portal[J]. Nucleic Acids Research, 2021, 49(W1): W174-W184. doi: 10.1093/nar/gkab438 pmid: 34060634
[44]	Luca P, Annachiara T, Luca G, et al. LigAdvisor: a versatile and user-friendly web-platform for drug design[J]. Nucleic Acids Research, 2021, 49(W1): W326-W335. doi: 10.1093/nar/gkab385
[45]	胡正银, 刘蕾蕾, 代冰, 覃筱楚. 基于领域知识图谱的生命医学学科知识发现探析[J]. 数据分析与知识发现, 2020, 4(11): 1-14.
[46]	王安然, 吴思竹. 美国癌症数据标准注册存储库的实践与启示[J]. 中华医学图书情报杂志, 2020, 29(10): 15-23.
[47]	李伟, 孙学会, 徐萍, 等. 美国All of Us队列项目建设模式与特点分析[J]. 世界科技研究与发展, 2022, 44(2):265-274.
[48]	Wilkinson M, Dumontier M, Aalbersberg I, et al. The FAIR Guiding Principles for scientific data management and stewardship[J]. Scientific Data, 2016, 3: 160018. doi: 10.1038/sdata.2016.18
[49]	樊代明. 生物医学大数据是重要战略资源[J]. 科学新闻, 2019, (06):34.
[50]	张国庆, 李亦学, 王泽峰, 赵国屏. 生物医学大数据发展的新挑战与趋势[J]. 中国科学院院刊, 2018, 33(8): 853-860.
[51]	Esteva A, Kuprel B, Novoa R A, et al. Corrigendum: Der-matologist-level classification of skin cancer with deep neural networks[J]. Nature, 2017, 546(7660): 686.
[52]	Amoroso N, Diacono D, Fanizzi A, et al. Deep learning reveals Alzheimer’s disease onset in MCI subjects: res-ults from an international challenge[J]. Journal of Neur-oscience Methods, 2018, 302: 3-9.
[53]	Li H, Zhu L, Shen M, et al. Blockchain-Based Data Pre-servation System for Medical Data[J]. Journal of Medical Systems, 2018, 42(8): 141. doi: 10.1007/s10916-018-0997-3
[54]	钱庆, 薛伟. 医学信息学发展现状与展望[J]. 中华医学信息导报, 2020, 35 (18): 10.
[55]	Savova G K, Masanz J J, Ogren P V, et al. Mayo clinical Text Analysis and Knowledge Extraction System (cT-AKES): architecture, component evaluation and app-lications[J]. Journal of the American Medical Inform-atics Association, 2010, 17:507-513.
[56]	关于生物医学新技术临床应用管理条例(征求意见稿)公开征求意见的公告[EB/OL]. [2022-01-20]. http://www.nhc.gov.cn/yzygj/s7659/201902/0f24ddc242c24212abc42aa8b539584d.shtml.

界定	内容
学科范围	研究并支持从分子到个体乃至人群，从生物到社会系统的推理、建模、模拟、实验和翻译，将基础和临床研究与实践同医疗卫生企业联系起来。
理论方法	开发、研究和应用理论、方法和过程以生成、存储、检索、使用、管理和共享生物医学数据、信息和知识。
技术方法	建立在计算机、通信和信息科学与技术基础上并对其做出贡献，强调它们在生物医学中的应用。
社会背景	认识到人类是生物医学信息学的最终用户，利用社会和行为科学，为技术解决方案、政策设计和评估以及经济、伦理、社会、教育和组织系统的演变提供信息。

序号	类团名称	主要关键词
1	癌症研究的生物医学信息学	表达、肿瘤、小RNA、乳腺癌、长链非编码RNA、转移、突变、细胞、生物标志物、激活、肝细胞癌、信使RNA、RNA、特异性、甲基化等
2	组学数据库等资源研究	数据库、识别、发现、网络、资源、基因组学、全基因组关联、蛋白质组学、代谢组学、转录组学等
3	算法与模型研究	蛋白质、预测、机器学习、算法、分类、模型、2019冠状病毒疾病、多序列比对、SARS冠状病毒2型、大数据、神经网络等
4	分析工具/软件研究	序列、工具、基因组、对齐、宏基因组学、软件、网络服务器、遗传学、搜索等

序号	数据库名称	URL
1	COVID19db	http://www.biomedical-web.com/cov-id19db or http://hpcc.siat.ac.cn/cov-id19db
2	Ensembl COVID-19 resource	https://covid-19.ensembl.org
3	ESC	http://clingen.igib.res.in/esc
4	SCoV2-MD	http://www.scov2-md.org
5	SCovid	http://bio-annotation.cn/scovid
6	T-cell COVID-19 Atlas	https://t-cov.hse.ru
7	VarEPS	https://nmdc.cn/ncovn

任务	模型/方法	语料库	最佳F1值
命名实体识别	BioBERT^[24]	NCBI Disease	89.71%
		2010 i2b2/VA	86.73%
		BC5CDR（Disease）	87.15%
		BC5CDR（Drug/Chem）	93.47%
		BC4CHEMD	92.36%
		BC2GM	84.72%
		JNLPBA	77.49%
		LINNAEUS	88.24%
		Species-800	74.06%
	BioBERT+Attention-based BiLSTM-CRF^[25]	BC5CDR（Disease）	88.34%
		NCBI Disease	91.23%
		BC5CDR（Drug/Chem）	94.23%
		BC4CHEMD	92.28%
		JNLPBA	79.97%
		BC2GM	86.05%
	BIOKMNER^[26]	BC2GM	85.29%
		JNLPBA	77.83%
		BC5CDR（Drug/Chem）	94.22%
		NCBI Disease	89.63%
		LINNAEUS	89.24%
		Species-800	76.33%
文本分类	MeSHProbeNet^[27]	2018 BioASQ	68.80%
	FullMeSH^[28]	PMC	66.76%
	BERTMeSH^[29]	PMC	69.20%
关系抽取	KCN^[30]	BioCreative V CDR	71.28%
	KGAGN^[31]	BioCreative V CDR	73.30%
	PACNN+RL^[32]	Prevent	55.92%
		Treat	66.66%
		DDI corpus	38.38%
		AIMed	44.72%
		BioInfer	52.09%
		HPRD50	65.40%
		IEPA	65.54%
		LLL	67.09%
通路提取	远程监督方法^[33]	PubMed	精度为25%
预测	DPDDI^[34]	DB2	84.00%
	NNPS^[35]	TWOSIDES	93.60%
	Node similarity-based-NN^[36]	Drug Bank DDI	AUC为0.933±0.003
		CTD DDA	AUC为0.950±0.004
		NDFRT DDA	AUC为0.943±0.004
		STRING PPI	AUC为0.952±0.004

任务	工具	URL
蛋白质结构/功能预测工具	GalaxyHeteromer	http://galaxy.seoklab.org/heteromer
蛋白质结构/功能预测工具	DeepGOWeb	https://deepgo.cbrc.kaust.edu.sa/deepgo/
多组学分析工具	Mergeomics	http://mergeomics.research.idre.ucla.edu/
多组学分析工具	iNetModels	https://inetmodels.com
药物分析工具	DrugComb	https://drugcomb.org/
药物分析工具	LigAdvisor	https://ligadvisor.unimore.it/

数据与技术双轮驱动的生物医学信息学发展与展望

The Development and Prospect of Biomedical Informatics Driven by Data and Technology

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 11

参考文献 56

相关文章 1

编辑推荐

Metrics

本文评价