Abstract：Artificial intelligence plays an important role in drug discovery field. This paper summarizes artificial intelligence technology applications in the medical field, such as to efficiently screen therapeutic targets and design drugs, saving the costs of drug discovery and shortening the time required for drug discovery; to deal with the problems of molecular characteristics, water-solubility, toxicity and oral absorption potential in preclinical development stage; to analyze issues about drug redirection, patient recruitment, clinical trial design optimization in the drug clinical research stage; as well as to analyze the research information and to make a drug safety evaluation after drug approval and marketing. This paper studies the achievements and problems of artificial intelligence research in the key stages of drug discovery, preclinical development, clinical research and approval for marketing, and looks forward to the trend of new drug research and development driven by artificial intelligence technology. The purpose is to provide reference for relevant scientific research and technical personnel engaged in the landing of artificial intelligence in the field of medicine.
孙雅婧 李春漾 曾筱茜. 人工智能在新药研发领域中的应用[J]. 中国医药导报, 2019, 16(33): 162-166.
SUN Yajing LI Chunyang ZENG Xiaoxi. Application of artificial intelligence in drug discovery. 中国医药导报, 2019, 16(33): 162-166.
[1] Taylor D. The pharmaceutical industry and the future of drug development [J]. Environ Sci Technol，2016（41）：1-33.
[2] Sittampalam GS，Gal-Edd N，Arkin M，et al. Early drug discovery and development guidelines：for academic researchers，collaborators，and start-up companies assay guidance manual [M]. Bethesda（MD）：Eli Lilly & Company and the National Center for Advancing TranslationalSciences，2004：1-46.
[3] Sertkaya A，Wong HH，Jessup A，et al. Key cost drivers of pharmaceutical clinical trials in the United States [J]. Clin Trials，2016，13（2）：117-126.
[4] Silverman E. What does it cost to develop a new drug? latest study says $2.6 billion [N]. Wall Street J，2014-11-20.
[5] Anon. BIO releases largest ever study on clinical development success rates [N]. Business Wire，2016-05-25.
[6] Martin E，Mukherjee P，Sullivan ND，et al. Profile-QSAR：a novel meta-QSAR method that combines activities across the kinase family to accurately predict affinity，selectivity，and cellular activity [J]. J Chem Inf Model，2011， 51（8）：1942-1956.
[7] Merget B，Turk S，Eid S，et al. Profiling prediction of kinase inhibitors：toward the virtual assay [J]. J Med Chem，2017，60（1）：474-485.
[8] Sample I. Google′s DeepMind predicts 3D shapes of proteins [N]. The Guardian，2018-12-02.
[9] 产品与服务组.药物固相筛选与分析[EB/OL].深圳：晶泰科技，2017.http：//www.jingtaikeji.com/products.
[10] Ahneman DT，Estrada JG，Lin S，et al. Predicting reaction performance in C-N cross-coupling using machine learning [J]. Science，2018，360（6385）：186-190.
[11] Cortes CV. Support vector networks [J]. Machine Learning，1995，20（3）：273-297.
[12] Breiman L. Random forests [J]. Machine Learning，2001， 45（1）：5-32.
[13] Svetnik V，Liaw A，Tong C，et al. Random forest：a classification and regression tool for compound classification and QSAR modeling [J]. J Chem Inf Comput Sci，2003， 43（6）：1947-1958.
[14] Rogers D，Brown RD，Hahn M. Using extended-connectivity fingerprints with Laplacian-modified Bayesian analysis in high-throughput screening follow-up [J]. J Biomol Screen，2005，10（7）：682-686.
[15] Cyclica launches ligand expressTM，a disruptive cloud-based platform to revolutionize drug discovery [EB/OL].Toronto，Canada：[November-30，2017]. https：//cyclicarx.com/news/cyclica-launches-ligand-express.
[16] Wang L，Liu ZP，Zhang XS，et al. Prediction of hot spots in protein interfaces using a random forest model with hybrid features [J]. Protein Eng Des Sel，2012，25（3）：119-126.
[17] Liu ZP，Wang Y，Zhang XS，et al. Identifying dysfunctional crosstalk of pathways in various regions of Alzheimer′s disease brains [J]. BMC Syst Biol，2010，4（Suppl2）：S11.
[18] Jing Y，Bian Y，Hu Z，et al. Deep learning for drug design：an artificial intelligence paradigm for drug discovery in the big data era [J]. AAPS J，2018，20（3）：58.
[19] Günter K，Thomas U，Andreas M，et al. DeepTox：toxicity prediction using deep learning [J]. Toxicol Lett，2017， 280：S69.
[20] Shin M，Jang D，Nam H，et al. Predicting the absorption potential of chemical compounds through a deep learning approach [J]. IEEE/ACM Trans Comput Biol Bioinform，2018，15（2）：432-440.
[21] Keiser MJ，Roth BL，Armbruster BN，et al. Relating protein pharmacology by ligand chemistry [J]. Nat Biotechnol，2007，25（2）：197-206.
[22] Pogodin PV，Lagunin AA，Filimonov DA，et al. PASS targets：ligand-based multi-target computational system based on a public data and naive bayes approach [J]. SAR QSAR Environ Res，2015，26（10）：783-793.
[23] Mervin LH，Afzal AM，Drakakis G，et al. Target prediction utilising negative bioactivity data covering large chemical space [J]. J Cheminform，2015，7：51.
[24] Steindl TM，Schuster D，Laggner C，et al. Parallel screening：a novel concept in pharmacophore modeling and virtual screening [J]. J Cheminform，2006，46（5）：2146-2157.
[25] 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.
[26] 动脉网蛋壳研究院.2017医疗大数据和人工智能产业报告[R].2017：101-110.
[27] 金小桃.健康医疗大数据[M].北京：人民卫生出版社，2018：159-160.
2019, Vol. 16 
京公网安备 11010502046598号