Deep learning for protein bioinformatics and medicine


主講人:李敏 中南大學教授 博士生導師




主講人介紹:中南大學計算機學院教授、博士生導師、副院長。CCF 生物信息學專業委員會首批委員、中國人工智能學會-生物信息學與人工生命專業委員會常務委員、ACM SIGBIO  China 秘書長。主要從事生物信息學與數據挖掘研究,在Bioinformatics、IEEE/ACM Transactions on  Computational Biology and Bioinformatics等上發表SCI期刊論文80余篇,論文google  scholar總引用3500余次,h指數29,獲國家授權發明專利10項。擔任ISBRA2017、ICPCSEE2017等國際會議的程序委員會主席,是國際期刊Current  Protein & Peptide Science、IJDMB、IJBRA、Interdisciplinary Sciences:  Computational Life Sciences編委及IEEE/ACM TCBB、Neurocomputing、Complexity、BMC  Bioinformatics、BMC Genomics等的客座編委。  2011年被確定為湖南省青年骨干教師培養對象,2012年獲得教育部新世紀優秀人才資助,主持國家自然科學基金重點項目、優秀青年項目、面上和青年項目各一項。獲教育部高等學校科學研究優秀成果獎(自然科學獎)二等獎一項(排名第2)。  

內容介紹:Mining useful information from biomedical data is not only the crucial of life  science, but also the foundation of understanding the development of diseases.  In recent years, a lot of biomedical data have been accumulated from omics  technologies, imaging, electronic health records, and so on. Meanwhile, with the  development of big data and hardware, deep learning techniques have been  successfully used in various fields such as computer version, speech  recognition, and natural language processing. Considering their excellent  performance, we implemented some deep learning models to tackle biomedical data.  In protein bioinformatics, we focus on protein-protein interaction sites  prediction, essential protein prediction, protein function prediction, and  drug-target prediction. We built some deep learning models for extract local and  global features of protein sequences; then combined these features to improve  the predictive performance. For clinic data, we focus on electronic health  records classification and disease prediction. We developed some deep learning  models which capture the features of electronic health records and disease; then  used these features to conduct study. We hope that our studies can promote the  application of deep learning in biomedical data analysis, and provide useful  tools for solving the key problems in life science by using artificial  intelligence techniques.