活动预告丨“CAAI进校园”系列活动走进电子科技大学

看这里

由中国人工智能学会主办、中国人工智能学会生物信息学与人工生命专业委员会承办的“CAAI进校园”系列活动即将在3月、4月在电子科技大学举行。

生物信息学是分子遗传学和人工智能的交叉学科，近年来蓬勃发展，涌现了一批优秀的华人科学家和学者。此次 “CAAI进校园”活动特别邀请到美国Drexel大学教授胡小华和中国科学院上海生命科学研究院研究员陈洛南两位知名生物信息学专家做报告，同电子科技大学的青年教师和各专业学生分享人工智能在生物信息领域的最新知识与技术。

活动时间

2019年3月29日   14：00

胡小华，美国Drexel大学教授，华中师范大学客座教授

报告题目：The inferring and analysis of microbial interaction network

2019年4月1日   09：30

陈洛南，中国科学院上海生命科学研究院研究员，博士生导师，中国科学院系统生物学重点实验室执行主任

报告题目：Cell-specific Network Constructed by Single-cell RNA Sequencing Data

活动地点

电子科技大学清水河校区经管楼宾诺咖啡

胡小华

美国Drexel大学教授

华中师范大学客座教授

报告题目：The inferring and analysis of microbial interaction network

报告摘要：The interactions and organizations among microbes play key roles in a microbial communities. It is valuable to identify those interactions from multi-omics dataset including sequencing data, abundance data, networks and literature. In this talk, I will introduce several of our recent work in microbial network inferring and analysis. First, a prediction algorithm with high accuracy was proposed for bacteria-virus network based on logistic matrix factorization on a heterogeneous network linking host similarity and virus similarity. Second, we will introduce an automatic system for microbial relation extraction from large-scale literature dataset from which deep learning models were trained on pre-labeled dataset. The system can identify bacteria names and relations with good performance from published papers in PubMed. Third, we will introduce a novel method of network analysis for extracting high-order organization in microbial networks. These studies provide novel approaches to infer the global map of microbes in microbial world.

陈洛南

中国科学院上海生命科学研究院研究员，博士生导师

中国科学院系统生物学重点实验室执行主任

报告题目：Cell-specific Network Constructed by Single-cell RNA Sequencing Data

报告摘要：Single-cell RNA sequencing (scRNA-seq) is able to give an insight into the gene-gene interactions or transcriptional networks among cell populations based on the sequencing of a large number of cells. However, traditional network methods are limited to the grouped cells instead of each single cell, and thus the heterogeneity of single cells will be erased. We present a new method to construct a cell-specific network (CSN) for each single cell from scRNA-seq data (i.e. one network for one cell), which transforms the data from “unstable” gene expression form to “stable” gene association form on a single-cell basis. In particular, it is for the first time that we can identify the gene interactions/network at a single-cell resolution level. By CSN method, scRNA-seq data can be analyzed for clustering and pseudo-trajectory from network perspective by any existing method, which opens a new way to scRNA-seq data analyses. In addition, CSN is able to find key genes from a network viewpoint, find “dark” genes that have no significant difference in gene expression level, but in network degree level, and find new cell types. Experiments on various scRNA-seq datasets demonstrated the improvement of CSN over existing methods in terms of accuracy and robustness.

为扩展师生事业，聆听前沿科学进展，加强学术交流，中国人工智能学会发起了“CAAI进校园”系列活动。自2016年至今该系列活动已经走进多家知名高校，给众多师生带来了丰富精彩的讲座，为传播人工智能多领域知识起到了重要的推动作用。