报告题目:Recent Advances in Machine Learning Based Large-scale Protein Function Prediction
Abstract:Proteins are building blocks of life, playing many crucial roles within organisms, such as catalysing chemical reactions, coordinating signal pathway and providing structural support to cells. Automated function prediction (AFP) of proteins is thus of great significance in biology.
AFP can be regarded as a problem of the large-scale multi-label classification where a protein can be associated with multiple gene ontology terms as its labels. To boost the development of effective and efficient AFP, Critical Assessment of Functional Annotation (CAFA) has been held four times to date: CAFA1 in 2010–2011, CAFA2 in 2013–2014, CAFA3 in 2015–2016 and CAFA4 in 2019–2020 (under evaluation). In this talk, I will introduce the state-of-the-art methods in large-scale AFP, as well as our recent progress in this topic, such as GOLabeler, NetGO and DeepGraphGO.
报告人简介:朱山风,复旦大学副教授,博士生导师。香港城市大学博士,日本京都大学博士后,美国伊利诺伊大学香槟分校访问学者,日本京都大学访问副教授。UniProt国际科学顾问委员会委员,中国计算机学会生物信息专业委员会创始委员,中国人工智能学会生物信息与人工生命专业委员会创始委员、中国中文信息处理学会医疗健康与生物信息处理专业委员会创始委员,中国细胞生物学会生物信息与系统生物学分会理事,中国运筹学会计算系统生物学分会理事。主持或完成四项国家自然科学基金项目,以及多个国内外企业研发项目。主要研究方向为人工智能与生物医学大数据挖掘,特别是生物医学文本挖掘、蛋白功能预测、宏基因组、药物发现、免疫信息学等。相关论文在生物信息、人工智能、数据挖掘等顶级国际会议和期刊发表,如NeurIPS, KDD,IJCAI, ISMB,, Nucleic Acids Research等。2014年-2020年参加BioASQ大规模生物医学文本自动标注国际竞赛中取得六次第一名的好成绩。2017年参加CAFA大规模蛋白功能自动标注国际竞赛,在全世界50多个实验室中获得第一名。
Reference
1. You et al., NetGO: improving large-scale protein function prediction with massive network information. Nucleic Acids Research 47(W1): W379-W387 (2019)
2. You et al., GOLabeler: improving sequence-based large-scale protein function prediction by learning to rank. Bioinformatics 34:2465–2473 (2018)
3. You et al., DeepGraphGO: graph neural network for large-scale, multispecies protein function prediction. ISMB2021, To appear (2021) |