演讲摘要：Precise annotation of gene functions is a central goal of functional genomics. Conventional approaches consider a gene as a single entity, without differentiating the functional differences among isoforms that are generated from a single gene through alternative splicing. Function annotations in Gene Ontology and KEGG are dominantly recorded at gene level. Towards understanding gene functions at higher resolution, recent efforts have focused on predicting isoform functions by interrogating isoform-level data with machine learning approaches. However, the performance of existing methods is far from satisfactory mainly because of the lack of isoform-level functional annotation.
First, we present IsoResolve, a novel approach for isoform function prediction, which leverages the information from gene function prediction models with domain adaptation (DA). IsoResolve treats gene-level and isoform-level features as source and target domains, respectively. It employs DA to project the two domains into a latent variable space in such a way that the latent variables from the two domains have similar distribution, which enables the gene domain information to be leveraged for isoform function prediction. We systematically evaluated the performance of IsoResolve in predicting functions. Compared with five state-of-the-art methods, IsoResolve achieved significantly better performance. IsoResolve was further validated by case studies of genes with isoform-level functional annotation.
Second, we studied on intron retention, a historically under-appreciated mode of alternative splicing. We proposed an approach, called iREAD (intron REtention Analysis and Detection), for detecting intron retention events from RNA-seq data. With this approach, we performed a proteogenome-wide analysis of intron retention in 84 human Alzheimer’s disease (AD) and 80 control brain samples, and two mouse models with AD. We found potential implications of intron retention in Alzheimer’s disease.
讲者简介：中南大学计算机学院特聘副教授，主要研究方向为可变剪接异构体功能预测和疾病基因预测。2010年到芬兰Oulu大学合作研究。2012年博士毕业于中南大学，然后加入密歇根大学，安娜堡(University of Michigan, Ann Arbor)医学院从事计算生物学博士后研究至2015年5月, 随后以Research Scientist职位加入位于西雅图的系统生物学研究所(Institute for Systems Biology, Seattle), 从事系统生物学/蛋白组学研究。目前，在Trends in Genetics, Brief Bioinform, PLOS Comput Biol, Bioinformatics, TCBB, J. Proteome Res, Nat. Genet (co-author), Nat. Commun (co-author)等杂志上发表SCI文章60余篇，据Google Scholar, 总引用3700余次，单篇最高引用600余次 (ESI前1%高引论文), H指数29；合著英文专著一本(美国CRC Press出版);2014年获人类蛋白组世界大会(Spain) Young Investigator Award(青年研究者奖)；主持国家自然科学基金青年项目一项，作为合作方负责人获国家自然科学基金地区项目和面上项目各一项。
第五届中国计算机学会生物信息学会议
分会场邀请报告
京公网安备11010802032778号