人工智能在药物再定位的应用

摘要/Abstract

摘要： 药物再定位是利用已上市药物或临床研究失败的药物等进行药物新适应证探索的一种方法，因其通过缩短研发周期、降低研发成本可解决目前药物研发面临的漫长周期和高昂费用问题，而获得了医药行业的广泛认可。随着医药大数据、计算能力和深度学习算法的巨大进步，人工智能运用于药物再定位在时间和成本方面有明显优势。通过对医药大数据进行采集、加工和处理，并进一步分析和挖掘，可以有效建立起药物-疾病之间的联系，推动药物再定位的发展。本研究将从药物、疾病以及真实世界数据3个方面对人工智能参与药物再定位的方法进行综述，并进一步探讨其中可能面临的挑战，以充分理解人工智能在药物再定位中的应用，推动人工智能与药物研发融合发展。

关键词: font-size:medium, "> , 药物再定位；人工智能；真实世界研究；真实世界数据

Abstract: Drug repurposing is a method for exploring new indications for maketed drugs or drugs that have failed clinical studies，and has been widely recognized by the pharmaceutical industry because it can solve the risk of long cycle and high costs currently faced in drug research and development(R&D) by shortening the R&D cycle and reducing R&D costs.With the tremendous progress of pharmaceutical big data，computing power and deep learning algorithms，the application of artificial intelligence(AI) in drug repurposing has obvious advantages in time and cost.Through the collection，processing and handling of pharmaceutical big data，and further analysis and mining，the connection between drugs and diseases can be effectively established and the development of drug repurposing can be promoted. This review will elaborate the methods of AI participating in drug repurposing from three aspects of drugs， diseases，and real world data，and further discuss the possible challenges， so as to fully understand the application of AI in drug repurposing， and promote the integrated development of AI and drug R&D.

Key words: Drug repurposing, Artificial intelligence, Real world study, Real world data

中图分类号:

陈杨, 陈轶伦, 曾文杰, 廖俊. 人工智能在药物再定位的应用[J]. 中国医药导刊, 2022, 24(4): 334-341.

CHEN Yang, CHEN Yilun, ZENG Wenjie, LIAO Jun. Application of Artificial Intelligence in Drug Repurposing[J]. CHINESE JOURNAL OF MEDICINAL GUIDE, 2022, 24(4): 334-341.

参考文献

[1] Ekins S， Puhl AC， Zorn KM， et al. Exploiting machine learning for end-to-end drug discovery and development[J]. Nat Mater， 2019， 18(5):435-441.
     [2]Grabowski HG， Moe JL. Impact of economic， regulatory， and patent policies on innovation in cancer chemoprevention[J]. Cancer Prev Res(Phila)， 2008， 1(2):84-90.
     [3]Fleming N. How artificial intelligence is changing drug discovery[J]. Nature， 2018， 557(7707):S55-S57.
     [4]Ghofrani HA， Osterloh IH， Grimminger F. Sildenafil：from angina to erectile dysfunction to pulmonary hypertension and beyond[J]. Nat Rev Drug Discov， 2006， 5(8):689-702.
     [5]Suchonwanit P， Thammarucha S， Leerunyakul K. Minoxidil and its use in hair disorders：a review[J]. Drug Des Devel Ther， 2019， 13:2777-2786.
     [6]Nosengo N. Can you teach old drugs new tricks?[J]. Nature， 2016， 534(7607):314-316.
     [7]Ashburn TT， Thor KB. Drug repositioning：identifying and developing new uses for existing drugs[J]. Nat Rev Drug Discov， 2004， 3(8):673-683.
     [8]Allarakhia M. Open-source approaches for the repurposing of existing or failed candidate drugs：learning from and applying the lessons across diseases[J]. Drug Des Devel Ther， 2013， 7:753-766.
     [9]Wu C， Liu Y， Yang Y， et al. Analysis of therapeutic targets for SARS-CoV-2 and discovery of potential drugs by computational methods[J]. Acta Pharm Sin B， 2020， 10(5):766-788.
     [10]Mohanty S， Rashid M， Mridul M， et al. Application of artificial intelligence in COVID-19 drug repurposing[J]. Diabetes Metab Syndr， 2020， 14(5):1027-1031.
     [11]Roessler HI， Knoers N， van Haelst MM， et al. Drug repurposing for rare diseases[J]. Trends Pharmacol Sci， 2021， 42(4):255-267.
     [12]Johnson MA， Maggiora GM. Similarity in chemistry.(Book Reviews：concepts and applications of molecular similarity)[J]. Science,1991:252.DOI:10.1126/science.252.5009.1189.
     [13]Dudley JT， Deshpande T， Butte AJ. Exploiting drug-disease relationships for computational drug repositioning[J]. Brief Bioinform， 2011， 12(4):303-311.
     [14]秦雪妮，陈维生，邵华，等. 真实世界研究在医药领域的应用及研究方法[J]. 药学进展， 2021， 45(7):512-523.
     [15]国家药品监督管理局.国家药监局药审中心关于发布《真实世界研究支持儿童药物研发与审评的技术指导原则（试行）》的通告(2020年第22号) [EB/OL].(2020-08-27)[2022-03-14].https://www.nmpa.gov.cn/xxgk/ggtg/qtggtg/20200901104448101.html.
     [16]Liu RQ， Wei L， Zhang P. A deep learning framework for drug repurposing via emulating clinical trials on real-world patient data[J]. Nat Mach Intell， 2021， 3(1):68.
     [17]Pushpakom S， Iorio F， Eyers PA， et al. Drug repurposing：progress， challenges and recommendations[J]. Nat Rev Drug Discov， 2019， 18(1):41-58.
     [18]Thomas KL. Predicting new molecular targets for known drugs[J]. Nature， 2009， 462(7270):175-181.
     [19]Feinberg EN， Sur D， Wu Z， et al. PotentialNet for molecular property prediction[J]. ACS Cent Sci， 2018， 4(11):1520-1530.
     [20]Hochuli J， Helbling A， Skaist T， et al. Visualizing convolutional neural network protein-ligand scoring[J]. J Mol Graph Model， 2018， 84(9):96-108.
     [21]Issa NT， Peters OJ， Byers SW， et al. RepurposeVS：a drug repurposing-focused computational method for accurate drug-target signature predictions[J]. Comb Chem High Throughput Screen， 2015， 18(8):784-794.
     [22]Wigley FM， Flavahan NA. Raynaud′s Phenomenon[J]. N Engl J Med， 2016， 375(6):556-565.
     [23]Khouri C， Lepelley M， Bailly S， et al. Comparative efficacy and safety of treatments for secondary Raynaud′s phenomenon：a systematic review and network meta-analysis of randomised trials[J]. Lancet Rheumatol， 2019， 1(4):E237-E246.
     [24]Zaza P， Matthieu R， Jean-Luc C， et al. Drug repurposing in Raynaud′s phenomenon through adverse event signature matching in the World Health Organization pharmacovigilance database[J]. Br J Clin Pharmacol， 2020， 86(11):2217-2222.
     [25]Pinzi L， Rastelli G. Molecular docking：shifting paradigms in drug discovery[J]. Int J Mol Sci， 2019， 20(18):4331.
     [26]Xu X， Huang M， Zou X. Docking-based inverse virtual screening：methods， applications， and challenges[J]. Biophys Rep， 2018， 4(1):1-16.
     [27]Dakshanamurthy S， Issa NT， Assefnia S， et al. Predicting new indications for approved drugs using a proteochemometric method[J]. J Med Chem， 2012， 55(15):6832-6848.
     [28]Zahler S， Tietze S， Totzke F， et al. Inverse in silico screening for identification of kinase inhibitor targets[J]. Chem Biol， 2007， 14(11):1207-1214.
     [29]Parvathaneni V， Kulkarni NS， Muth A， et al. Drug repurposing：a promising tool to accelerate the drug discovery process[J]. Drug Discov Today， 2019， 24(10):2076-2085.
     [30]Smith SB， Dampier W， Tozeren A， et al. Identification of common biological pathways and drug targets across multiple respiratory viruses based on human host gene expression analysis[J]. PLoS One， 2012， 7(3):e33174.
     [31]Mejia-Pedroza RA， Espinal-Enriquez J， Hernandez-Lemus E. Pathway-based drug repositioning for breast cancer molecular subtypes[J]. Front Pharmacol， 2018， 9:905-917.
     [32]Rivero-Garcia I， Castresana-Aguirre M， Guglielmo L， et al. Drug repurposing improves disease targeting 11-fold and can be augmented by network module targeting， applied to COVID-19[J]. Sci Rep， 2021， 11(1):20687.
     [33]Sanseau P， Agarwal P， Barnes MR， et al. Use of genome-wide association studies for drug repositioning[J]. Nat Biotechnol， 2012， 30(4):317-320.
     [34]Nabirotchkin S， Peluffo AE， Rinaudo P， et al. Next-generation drug repurposing using human genetics and network biology[J]. Curr Opin Pharmacol， 2020， 51:78-92.
     [35]Fang J， Zhang P， Wang Q， et al. Artificial intelligence framework identifies candidate targets for drug repurposing in Alzheimer′s disease[J]. Alzheimer′s Research & Therapy， 2022， 14(1):7.
     [36]Wang Q， Xu R. Drug repositioning for prostate cancer：using a data-driven approach to gain new insights[J]. AMIA Annu Symp Proc， 2017， 2017:1724-1733.
     [37]Sherman RE， Anderson SA， Dal Pan GJ， et al. Real-world evidence - What is it and what can it tell us?[J]. N Engl J Med， 2016， 375(23):2293-2297.
     [38]Hayrinen K， Saranto K， Nykanen P. Definition， structure， content， use and impacts of electronic health records：a review of the research literature[J]. Int J Med Inform， 2008， 77(5):291-304.
     [39]Xu H， Aldrich MC， Chen Q， et al. Validating drug repurposing signals using electronic health records：a case study of metformin associated with reduced cancer mortality[J]. J Am Med Inform Assoc， 2015， 22(1):179-191.
     [40]Ribelles N， Jerez JM， Rodriguez-Brazzarola P， et al. Machine learning and natural language processing(NLP) approach to predict early progression to first-line treatment in real-world hormone receptor-positive(HR+)/HER2-negative advanced breast cancer patients[J]. Eur J Cancer， 2021， 144:224-231.
     [41]Frost J， Okun S， Vaughan T， et al. Patient-reported outcomes as a source of evidence in off-label prescribing：analysis of data from PatientsLikeMe[J]. J Med Internet Res， 2011， 13(1):e6.
     [42]Liu Y， Kohlberger T， Norouzi M， et al. Artificial intelligence-based breast cancer nodal metastasis detection：insights into the black box for pathologists[J]. Arch Pathol Lab Med， 2019， 143(7):859-868.
     [43]Wang F， Kaushal R， Khullar D. Should health care demand interpretable artificial intelligence or accept "black box" medicine?[J]. Ann Intern Med， 2020， 172(1):59-60.
     [44]Lee CY， Chen YP. New insights into drug repurposing for COVID-19 using deep learning[J]. IEEE Trans Neural Netw Learn Syst， 2021， 32(11):4770-4780.
     [45]Shingjergji K， Celebi R， Scholtes J， et al. Relation extraction from DailyMed structured product labels by optimally combining crowd， experts and machines[J]. J Biomed Inform， 2021， 122:103902.
     [46]Azencott CA. Machine learning and genomics：precision medicine versus patient privacy[J]. Philos Trans A Math Phys Eng Sci， 2018， 376(2128) :20170350.
     [47]王旭. 大数据医疗时代的人工智能与隐私保护[J]. 电子产品世界， 2019， 26(6):79-81.
     [48]Hamet P， Tremblay J. Artificial intelligence in medicine[J]. Metabolism， 2017， 69S:S36-S40.
     [49]Hessler G， Baringhaus KH. Artificial intelligence in drug design[J]. Molecules， 2018， 23(10):2520.

快速检索引用检索图表检索高级检索