课题组以生物医学大数据作为主要研究方向，利用统计模型和机器学习方法，对医学大数据进行数据分析、数据挖掘，以发现疾病风险因子（环境因素）、生物标志物（遗传因素）、药物靶标（病因发现）为主要研究目标。充分利用多维度、多模态的健康医疗数据，对疾病表型进行关联分析。

（1）基于biobank 等人群队列的机器学习方法研究与应用（Machine Learning for Association/Interaction）：整合临床信息、全基因组信息、血检信息、代谢组数据等，对心脑血管、精神疾病等复杂疾病表型进行关联分析，对疾病进行预测或预警。使用统计模型和机器学习分析不同模态数据间的交互作用。

（2）整合GWAS，QTL，组织特异性网络等数据的因果分析（Graph model for Causal gene）：GWAS刻画表型 （Phenotype）--基因突变关联关系，QTL刻画基因突变 -- 基因表达关联关系，组织特异性网络刻画不同基因表达间作用关系，使用因果模型推演致病的关键核心基因。

（3）人工智能辅助药物靶标发现（AI for Drug Target）：融合蛋白序列，结构，功能信息的数据表征学习，对蛋白--药物，蛋白--疾病，蛋白--蛋白等关联预测；利用生成模型，强化学习等算法 ab initio 设计化合物。

关键词：统计机器学习，多组学大数据，多模态与可解释性

欢迎加入我们！

博士后（全年招，待遇好，快砸简历！）

全日制、非全日制 硕士、博士研究生 （国科大学位，不愁找工作！）

优秀的本科生、研究生可以来做客座实习（接收1年左右的客座实习）

081203-计算机应用技术
085400-电子信息

计算生物学
医学统计学
人工智能

2009-10--2014-02   英国纽卡斯尔大学   博士
2005-09--2009-07   中国科学技术大学   本科

   

2017-02~现在, 中国科学院深圳先进技术研究院, 副研究员
2014-02~2017-02,英国利物浦大学, 博士后

2019-05-18-今,中国医促会健康大数据和数字化医疗分会, 青年学术部委员
2019-04-11-今,深圳市人工智能协会, 会员
2018-01-01-今,国家发改委健康大数据智能分析技术国家地方联合工程研究中心, 副主任
2017-10-31-今,CCF中国计算机协会, 会员
2015-06-01-今,国际遗传流行病学会, 会员
2015-02-01-今,英国皇家统计协会, 会员

   

（1） 英国利物浦大学ITM学院优秀项目和奖金, , 研究所（学校）, 2016
（2） 美国人类遗传学会会议（ASHG）2015 Reviewers’ Choice Abstract, , 其他, 2015
（3） 英国利物浦大学NWCR travel award, 其他, 2015
（4） 英国 Wellcome Trust 资助, 研究所（学校）, 2010
（5） 英国纽卡斯尔大学全额奖学金, 研究所（学校）, 2009

[1] 殷力, 殷鹏. 基因型数据缺失的填充方法、装置及服务器. CN: CN111028884A, 2020-04-17.
[2] 刘志华, 刘晟铭, 艾红, 唐柳, 殷鹏, 马晨光. 心电图检测方法. CN: CN107753014A, 2018-03-06.

   

[1] Zhu, M, Yin, P, Hu, F, Jiang, J, Yin, L, Li, Y, Wang, S. Integrating genome-wide association and transcriptome prediction model identifies novel target genes for osteoporosis. OSTEOPOROSIS INTERNATIONAL[J]. 2021, 32(12): 2493-2503, http://dx.doi.org/10.1007/s00198-021-06024-z.
[2] Hu, Fan, Wang, Lei, Hu, Yishen, Wang, Dongqi, Wang, Weijie, Jiang, Jianbing, Li, Nan, Yin, Peng. A Novel Framework Integrating AI Model and Enzymological Experiments Promotes Identification of SARS-CoV-2 3CL Protease Inhibitors and Activity-based Probe. Briefings in Bioinformatics[J]. 2021, http://arxiv.org/abs/2105.14224.
[3] Hu, Fan, Jiang, Jiaxin, Wang, Dongqi, Zhu, Muchun, Yin, Peng. Multi-PLI: interpretable multi-task deep learning model for unifying protein-ligand interaction datasets. JOURNAL OF CHEMINFORMATICS[J]. 2021, 13(1): https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8051026/.
[4] Hu, Fan, Jiang, Jiaxin, Yin, Peng. Prediction of potential commercially inhibitors against SARS-CoV-2 by multi-task deep model. 2021, http://arxiv.org/abs/2003.00728.
[5] Yin, Peng, Meng, Juan, Chen, Jincheng, Gao, Junxiao, Wang, Dongqi, Liu, Shuyan, Guo, Qinglong, Zhu, Muchun, Zhang, Gengwei, Liu, Yingxia, Li, Ye, Zhang, Guoliang. Antiviral drugs arbidol and interferon alpha-1b contribute to reducing the severity of COVID-19 patients: a retrospective cohort study. VIROLOGY JOURNAL[J]. 2021, 18(1): http://dx.doi.org/10.1186/s12985-021-01617-w.
[6] 殷鹏. Structure Enhanced Protein-Drug Interaction Prediction using Transformer and Graph Embedding. IEEE International Conference on Bioinformatics and Biomedicine. 2020, [7] 殷鹏. Generating Novel Compounds Targeting SARS-CoV-2 Main Protease Based on Imbalanced Dataset. IEEE International Conference on Bioinformatics and Biomedicine. 2020, [8] Turner, Richard M, Fontana, Vanessa, Zhang, Jieying E, Carr, Daniel, Yin, Peng, FitzGerald, Richard, Morris, Andrew P, Pirmohamed, Munir. A Genome-wide Association Study of Circulating Levels of Atorvastatin and Its Major Metabolites. CLINICAL PHARMACOLOGY & THERAPEUTICS[J]. 2020, 108(2): 287-297, https://www.webofscience.com/wos/woscc/full-record/WOS:000524906400001.
[9] Yin, Peng, Shi, Jian Q. Simulation-based sensitivity analysis for non-ignorably missing data. STATISTICAL METHODS IN MEDICAL RESEARCH[J]. 2019, 28(1): 289-308, [10] Zhang, Haiping, Liao, Linbu, Saravanan, Konda Mani, Yin, Peng, Wei, Yanjie. DeepBindRG: a deep learning based method for estimating effective protein-ligand affinity. PEERJ[J]. 2019, 7: https://doaj.org/article/c3a06a2ffbe246f9ba02206d847ef4f2.
[11] Hu, Fan, Jiang, Jiaxin, Yin, Peng, Yoo, IH, Bi, JB, Hu, X. Interpretable Prediction of Protein-Ligand Interaction by Convolutional Neural Network. 2019 IEEE INTERNATIONAL CONFERENCE ON BIOINFORMATICS AND BIOMEDICINE (BIBM)null. 2019, 656-659, [12] Zhang, Jianye, Yin, Peng, Yoo, IH, Bi, JB, Hu, X. Multivariate Time Series Missing Data Imputation Using Recurrent Denoising Autoencoder. 2019 IEEE INTERNATIONAL CONFERENCE ON BIOINFORMATICS AND BIOMEDICINE (BIBM)null. 2019, 760-764, [13] Hawcutt, Daniel B, Francis, Ben, Carr, Daniel F, Jorgensen, Andrea L, Yin, Peng, Wallin, Naomi, OHara, Natalie, Zhang, Eunice J, Bloch, Katarzyna M, Ganguli, Amitava, Thompson, Ben, McEvoy, Laurence, Peak, Matthew, Crawford, Andrew A, Walker, Brian R, Blair, Joanne C, Couriel, Jonathan, Smyth, Rosalind L, Pirmohamed, Munir. Susceptibility to corticosteroid-induced adrenal suppression: a genome-wide association study. LANCET RESPIRATORY MEDICINE[J]. 2018, 6(6): 442-450, https://www.webofscience.com/wos/woscc/full-record/WOS:000433245200027.
[14] Smith, Eve M D, Yin, Peng, Jorgensen, Andrea L, Beresford, Michael W, UK JSLE Study Grp. Clinical predictors of proteinuric remission following an LN flare - evidence from the UK JSLE cohort study. PEDIATRIC RHEUMATOLOGY[J]. 2018, 16: http://ir.siat.ac.cn:8080/handle/172644/14028.
[15] Wang, Shuqiang, Shen, Yanyan, Shi, Changhong, Yin, Peng, Wang, Zuhui, Cheung, Prudence WingHang, Cheung, Jason Pui Yin, Luk, Keith DipKei, Hu, Yong. Skeletal Maturity Recognition Using a Fully Automated System With Convolutional Neural Networks. IEEE ACCESS[J]. 2018, 6: 29979-29993, https://doaj.org/article/7c8c80d929a94f798fd09a9ee34b57c3.
[16] Smith, E M D, Yin, P, Jorgensen, A L, Beresford, M W. Clinical predictors of active LN development in children - evidence from the UK JSLE Cohort Study. LUPUS[J]. 2018, 27(13): 2020-2028, http://ir.siat.ac.cn:8080/handle/172644/14046.
[17] Thiesen, Signe, Yin, Peng, Jorgensen, Andrea L, Zhang, Jieying E, Manzo, Valentina, McEvoy, Laurence, Barton, Christopher, Picton, Susan, Bailey, Simon, Brock, Penelope, Vyas, Harish, Walker, David, Makin, Guy, Bandi, Srinivas, Pizer, Barry, Hawcutt, Daniel B, Pirmohamed, Munir. TPMT, COMT and ACYP2 genetic variants in paediatric cancer patients with cisplatin-induced ototoxicity. PHARMACOGENETICS AND GENOMICS[J]. 2017, 27(6): 213-222, [18] 殷鹏. Investigating the prevalence, predictors and prognosis of suboptimal statin therapy early after a non-ST elevation acute coronary syndrome. Journal of Clinical Lipidology. 2017, [19] Wei, Dan, Peng, Yin, Wei, Yanjie, Jiang, Qingshan, Fang, Jinglong. A hybrid method for splice site prediction based on Markov model and codon information. INTERNATIONAL JOURNAL OF DATA MINING AND BIOINFORMATICS[J]. 2016, 16(4): 345-362, http://www.chinair.org.cn/handle/1471x/1747894.
[20] Francis, Ben, Yin, Peng, Cook, James, Jorgensen, Andrea, Hutton, Jane, Morris, Andrew. A Genome-Wide two-Component Mixture Model Expectation-Maximization Algorithm for Time to Event Data. GENETIC EPIDEMIOLOGYnull. 2016, 40(7): 637-637, https://www.webofscience.com/wos/woscc/full-record/WOS:000386034800083.
[21] 殷鹏. Study on the Optimal Mode of Foreign Investment Based on Simulated Annealing Algorithm. Journal of Computational and Theoretical Nanoscience. 2016, [22] Yin, Peng, Jorgensen, Andrea, Morris, Andrew, Turner, Richard, Fitzgerald, Richard, Stables, Rod, Hanson, Anita, Pirmohamed, Munir. SNP-Treatment Interactions of Cardiovascular Medications and Risk of Acute Coronary Syndrome Recurrence. GENETIC EPIDEMIOLOGYnull. 2016, 40(7): 672-672, https://www.webofscience.com/wos/woscc/full-record/WOS:000386034800176.
[23] 殷鹏. Pharmacogenetics on the time to acute coronary syndrome recurrence (PhACS): a UK cohort study. Hum Hered. 2016, [24] Lu, H, Yin, P, Yue, R X, Shi, J Q. Robust confidence intervals for trend estimation in meta-analysis with publication bias. JOURNAL OF APPLIED STATISTICS[J]. 2015, 42(12): 2715-2733, https://www.webofscience.com/wos/woscc/full-record/WOS:000365609900015.
[25] Yin, Peng, Jorgensen, Andrea, Morris, Andrew P, Turner, Richard, Fitzgerald, Richard, Stables, Rod, Hanson, Anita, Pirmohamed, Munir. Pharmacogenetics of Acute Coronary Syndrome. GENETIC EPIDEMIOLOGYnull. 2015, 39(7): 596-596, https://www.webofscience.com/wos/woscc/full-record/WOS:000363340500186.

长期与生物医学专家合作，IT与BT交叉融合。与蛋白质组学生物学家开展组学研究；与卫健委慢病防控，慢病科心血管医生等开展长期合作，进行疾病队列构建与数据挖掘，利用基因组等组学数据对疾病机制进行研究。

已指导学生

殷力  硕士研究生  085208-电子与通信工程  

李婉莹  硕士研究生  085210-控制工程  

现指导学生

胡奕绅  硕士研究生  085211-计算机技术  

王东奇  硕士研究生  085211-计算机技术  

宫长威  硕士研究生  081200-计算机科学与技术  

黄华振  硕士研究生  085400-电子信息  

荆常宏  硕士研究生  085400-电子信息  

叶翔鹏  硕士研究生  085400-电子信息  

王中昊  硕士研究生  085400-电子信息