CCF@U1036：CCF生物信息学专委走进复旦大学

CCF走进高校第1036场

敬请关注

由中国计算机学会（CCF）主办，CCF生物信息学专委、复旦大学承办的CCF走进高校活动，将于2023年12月16日在复旦大学召开，敬请关注。

时间：2023年12月16日（周日）13:30-17:00

活动地点：复旦大学光华楼东主楼2401

报告信息：

报告题目：Reconstruction of complex genomes with long error prone reads

摘要：Genome is the carrier that carries all the mysteries of life. Therefore, obtaining the genome is the key to deciphering the mysteries of life. The rapid development of sequencing technology and computing technology has made it possible to accurately calculate and predict the genome of all species. Taking this opportunity, the speaker, Professor Guojun Li, will introduce the historical process of sequencing data, the application of graph theory and combinatorial optimization to biological data analysis, and share their latest progress in genome reconstruction using long error prone sequencing data.

个人简介：李国君，山东大学特聘教授，山东省首批泰山特聘教授。1996年获中科院数学与系统科学研究所博士学位。2004和2006年分别受聘中科院软件所研究员和美国佐治亚大学研究教授。研究领域涉及图论、组合最优化和生物信息学。在图论领域：有论文分别发表在JCTB, Combinatorica和JGT等; 在组合最优化领域：有论文分别发表在SIAM J Compt和ACM Trans Algorithms等；在生物信息学领域：以第一或通讯作者在生物信息学相关的顶刊Genome Biology, Genome Research, Nucleic Acids Research, Advanced Science和Bioinformatics发表论文20+篇。主持国家自然科学基金委基金项目13项，其中主持2项重点项目。参与1项国家自然科学基金委重点项目和1项国家科技部重点研发项目。

报告题目：Efficient Biomedical Data Analysis Platform

摘要：We have developed a platform BMAP for analyze multi-omics multi-modal biomedical data. BMAP covers around 40-60% of data analysis job, and we have been using it to study cancer, genetics diseases, psychological diseases, among others.

个人简介：吕晖，上海交通大学生物信息与生物统计系特聘教授和系主任，交大-耶鲁生物统计与数据科学中心联席主任，上海检验医学研究院生物信息研究所所长，国家重点研发计划首席科学家。长期从事生物信息、生物统计、医学人工智能研究。在分子组学数据分析、生物大分子结构功能研究、临床研究以及疾病辅助诊断领域有多项原创成果及专利。

报告题目：AI-driven methods for optimizing biological sequences and its application in antigen peptides

摘要：Some key properties of biological macromolecules in nature, such as enzymes, antibodies, peptides, and nucleic acids, often cannot meet the actual needs in industrial or medical applications. In this talk, I will first introduce the research progress of AI-driven methods for optimization of biomolecular sequences. Second, I will present the computational framework and the results developed by our team on the task of antigen peptide sequence optimization.

个人简介：熊毅，上海交通大学生命科学技术学院/张江高等研究院副研究员/博士生导师。国家级青年人才计划入选者（2022）。上海人工智能实验室顾问科学家（2022 -）。本硕博毕业于武汉大学计算机学院（2002-2011），美国普渡大学博士后（2012-2013）。主要研究方向：(1) 生物大分子功能预测、序列设计与优化；(2) AI驱动药物、疫苗设计与发现。近5年，主持国家重点研发计划课题、国家自然科学基金面上项目，并以通讯作者（含共同）在Nature Machine Intelligence、Protein Science、Journal of Cheminformatics等期刊发表论文20余篇。

报告题目：Explainable Artificial Intelligence for Discovery of Anti-Cancer Drug Targets

摘要：The discovery of anti-cancer drug targets is of fundamental importance for cancer medicine. Synthetic lethality (SL) is a type of genetic interaction typically between two genes, which is that perturbations to both genes will kill a cell but perturbation to one gene will not. It is a gold mine of anti-cancer drug targets since targeting an SL partner of a gene with cancer-specific abnormality can selectively kill cancer cells without harming normal cells. Current wet-lab screening methods usually have high cost, while statistical and machine learning methods cannot fully utilize the prior knowledge or lack clear explanations. We have developed a series of deep learning methods using Knowledge Graphs (KGs) and Explainable Artificial Intelligence (XAI) to predict SLs and understand mechanisms behind. SynLethDB is a comprehensive database including many SL gene pairs and a knowledge graph named SynLethKG. KG4SL is the first method using KG for SL prediction (ISMB/ECCB 2021). PiLSL further focuses on pairwise interaction learning from KGs for predicting SLs with interpretability (ECCB 2022). Recently, we proposed KR4SL, which employs path-based knowledge reasoning to rank SL candidate partners for given primary genes, and is able to explain the SL prediction and biological mechanisms clearly (ISMB/ECCB 2023). Our ongoing work combines pre-trained Language Models (e.g. GPT) and KGs to explain SLs in natural languages. In future, we aim to unlock the power of XAI by integrating more data and knowledge, and promoting closer collaborations with wet-lab biologists, clinical scientists and pharmaceutical researchers, to catalyze advancements of AI for cancer precision medicine.

个人简介：郑杰，目前在上海科技大学信息科学与技术学院担任长聘副教授、博导、研究员，并担任智能医学信息研究中心联合主任。 他分别在浙江大学和加州大学河滨分校获得计算机科学学士和博士学位，并在美国国立卫生研究院（NIH）下属国家生物技术信息中心（NCBI）从事博士后研究。回国之前，他曾在新加坡南洋理工大学计算机科学与工程学院担任助理教授，并担任新加坡科技研究局（A*STAR）基因组研究所（Genome Institute of Singapore）客座研究员。郑杰博士长期致力于研究生物信息学算法和软件、机器学习模型等信息技术，促进生物医药的发展。目前，郑博士聚焦融合知识与数据的人工智能和数据科学技术，并将其应用于AI for Science、药物靶标预测、精准医疗等。2019年郑博士被选为上海市“东方学者”特聘教授。

报告题目：The whole-brain single-cell spatial transcriptome atlas and cross-species comparison

摘要：The brain is the most complex organ of humans with the highest heterogeneity of cell types. The composition and spatial location of different neuron subtypes, as well as their precise connections, are the basis for brain functions. Rapid advances in spatial transcriptomic technologies allow spatial mapping of gene expression as well as cellular subtypes at single-cell resolution of brain sections. We applied Stereo-Seq technology developed by BGI, to construct the whole-brain cell atlas for macaques, marmoset, and mice, with hundreds of coronal slices of spatial transcriptome across the whole brain per animal. Single-cell spatial transcriptome reveals cell-type organization in the macaque cortex and cross-species comparative analysis identified primate-specific cell types enriched in cortical layer 4, whose marker genes are expressed in a region-dependent manner (Chen et al., Cell 2023). Whole-brain cell atlas provides the cellular and molecular basis for understanding the function, evolution, development, aging, and pathogenesis of the brain.

个人简介：魏武，临港实验室研究员，主要从事基因组学、生物信息学、系统遗传学和脑科学的交叉整合研究，通过整合分析各种高通量遗传分子及表型数据，开发生物信息学方法，研究从 DNA 分子，到转录成 RNA，经过转录后调控翻译成蛋白质的过程中的分子机理；以及大脑不同神经细胞类型组成的大脑空间细胞图谱、单细胞基于静态与动态条形码的谱系追踪等。共发表 SCI 论文 40余篇，被引用 6000 余次，以第一及通讯作者(含并列)在Cell、Nature、Science等期刊上发表论文20余篇(包括Cell 2篇，Nature 2篇，Science 1篇)。

报告题目： The application of multi-omics data integration in brain atlas studies

摘要：The neocortex is greatly expanded in primates compared with rodents, especially the prefrontal cortex. Understanding its brain organization at the cellular level holds the key to deciphering neural circuit functions of the primate brain and to developing treatments for brain disorders. To systematically elucidate the cellular diversity in primates at single-cell and spatial resolution, here we performed large-scale single-nucleus RNA-seq and spatial transcriptome analysis for millions of cells covering 143 cortical regions of cynomolgus monkeys. We derived a comprehensive cell-type taxonomy of neuronal and non-neuronal cells in the macaque cortex. Spatial mapping revealed laminar and regional preferences of various cell types and regional differences in cell-type composition and neighborhood complexity. Further comparative analysis revealed glutamatergic neuron types in the cortex of primates with layer-specific distribution and high expression of functionally important genes. Together, these results demonstrate the increased complexity of glutamatergic neuron subtypes in primates, and provide spatial underpinning for molecular understanding of organizing principles of the primate brain.

个人简介：孙怡迪博士，中国科学院脑科学与智能技术卓越创新中心研究组长，博士生导师。聚焦多组学大数据进行系统生物学研究，开发多组学数据整合算法，并用于大脑结构和功能研究。在Cell、Science、Nature、Nature Methods、Cancer Cell、 Science Translational Medicine、Genome Biology和Nature Communications等国际期刊上发表多篇研究论文。获得上海市启明星、2019年中国生命科学十大进展等奖项。

CCF微信公众号，欢迎关注