报告题目:Protein remote homology detection based on the techniques fromthe natural language processing.
报告日期及时间:2017年3月23号下午4:00
报告地点:外围投注365B403
报告人:刘滨
报告人单位:哈尔滨工业大学深圳研究生院
报告人简介: 刘滨,哈尔滨工业大学深圳研究生院教授、博士生导师。于2010年10月在哈尔滨工业大学深圳研究生院获得博士学位,2010年12月至2012年1月在美国俄亥俄州立大学从事博士后研究工作,2012年1月至今在哈尔滨工业大学深圳研究生院担任助理教授、副教授和教授。刘滨长期从事生物信息学研究工作,致力于基于序列的生物分子结构和功能识别研究。围绕该目标,系统研究了生物序列语言模型,并以此为基础提出基于自然语言处理技术的生物序列模式识别方。在该领域权威期刊发表SCI论文42篇(37篇为第一或通讯作者),包括Bioinformatics(6篇)、Nucleic Acids Research、Briefings in Bioinformatics、BMC Bioinformatics(3篇)、Nature Cell Biology等,Google Scholar引用1780次,2篇论文入选“中国百篇最具影响国际学术论文”。提出的方法被多个国际研究机构作为核心特征提取算法用于设计预测模型。担任国际期刊PLOS ONE和Scientific Reports编委。获得广东省自然科学杰出青年基金、深圳市青年科技奖、哈工大科研工作优秀个人称号、深圳市地方级领军人才和深圳市海外高层次人才(B类)。
报告摘要: Owing to its importance in both basic research (such as molecular evolution and protein attribute prediction) and practical application (such as timely modeling the 3D structures of proteins targeted for drug development), protein remote homology detection has attracted a great deal of interest. Based on the similarities between protein sequences and natural languages, it is intriguing to note that the techniques from the natural language processing is promising and hold very high potential for developing efficient computational approaches for protein remote homology detection. In this talk, the similarities between biological sequences and natural languages will be introduced and discussed. Then, three computational predictors for protein remote homology will be introduced, including SVM-MKL, ProtDec-LTR, and dRHP-PseRA, which are based on Multiple Kernel Learning, Learning to Rank, and Rank Aggregation. Finally, some open questions in this field will be further explored and discussed.
邀请人:刘娟教授,章文副教授