Menu:

WeChat QR Code
       

 

SIGBIO CHINA Symposium: Bioinformatics in AI Era


ACM SIGBIO CHINA symposium aims to provide a premier forum for scientists to share their leading-edge research works on intelligent algorithms as well as their applications in accumulating large amount of biological and medical data. The symposium will further organize a panel discussion for excellent young scientists to share their opinions of the challenges brought by bioinformatics to artificial intelligence. The symposium expects to promote the crosstalk between artificial intelligence and bioinformatics.


Program


Afternoon,May 19th: SIGBIO

Time

Program

Speaker

Host

14:00 -14:50

Keynote 1

Low Abundance Peptide Identification by Deep Learning

Ming Li

 

14:50-15:40

Keynote 2

Computational Psychophysiology Based Emotion Analysis for Mental Health

Bin Hu

 

15:40-16:00

Tea Break

16:00-16:50

Keynote 3

Integrating Multi-scale Data for Prediction: Theory and Applications 

Jian Feng Feng

 

16:50-17:30

Panel Discussion

 

 


Organizers


General Chair:
Jianxin Wang (Central South University)

Program Chairs:
Xingming Zhao (Fudan University)
Le Zhang (Sichuan University)
Min Li (Central South University)

 

Speakers



Ming Li (University of Waterloo)
Bio: Dr. Ming Li is a Canada Research Chair in Bioinformatics and a University Professor at the University of Waterloo. He is a fellow of the Royal Society of Canada, ACM, and IEEE. He is a recipient of E.W.R. Steacie Fellowship Award in 1996, the 2001 Killam Fellowship, and the 2010 Killam Prize. Together with Paul Vitanyi they have co-authored the book "An Introduction to Kolmogorov Complexity and Its Applications". Dr. Li is the president of RSVP (薄言)Technologies Inc, a company that is dedicated to natural language understanding (微信号:薄言豆豆),and the president of Bioinformatics Solutions Inc, a pioneering company that is dedicated to protein peptide identification for the past 18 years.
Title: Low Abundance Peptide Identification by Deep Learning
Abstract: Personalized peptide cancer immunotherapy is all the rage, many initial clinical trials have shown very promising results. We are seeing the twilight of cancer treatments, except there are few more last hurdles remaining. Of these, probably the biggest hurdle, is accurate neoantigen discovery.In this talk, we provide the first deep learning model for directly discovering low abundance mutated peptides using Mass Spectrometry. These results promise that it is possible to directly and effectively identify the neoantigens from the surface of the cancer cells.


冯建峰(复旦大学)

Bio: 冯建峰教授现任复旦大学数学科学学院、生命科学学院教授,复旦大学计算系统生物学中心主任,上海数学中心首席科学家,国家“千人计划”专家(第二批),教育部“长江学者”特聘教授。1981−1991年,就读于北京大学数学系、概率统计系,获北京大学理学学士、硕士、博士学位,后留校任教。1993−1996年,由德国洪堡基金会资助,在德国慕尼黑大学、意大利罗马大学工作。1996−2000年,就职于英国剑桥Babraham生物所,获永久职位。2000−2004年,任英国Sussex大学信息科学系Reader。2005年,任英国Warwick大学计算机科学系Chair Professor。目前,主要致力于利用计算方法从事与神经、精神科学相关的生物医学问题的研究。迄今为止,先后主持EPSPC、BBSRC、EU和国家自然科学基金重大研究计划重点支持项目等十余项科研项目。此前,以第一或通讯作者在J Neurosci、Curr Biol、Phys Rev Lett、PLoS Comput Biol等专业类顶尖杂志上发表过多篇有影响力的学术论文。
Title: Integrating multi-scale data for prediction: theory and applications
Abstract: With the available data of huge samples for the whole spectrum of scales both for healthy controls and patients including depression, autism and schizophrenia etc, we are in the position to quantify human brain activities such as creativity, happiness, IQ and EQ etc and search the roots of various mental disorders. With novel machine learning approaches, we first introduced functional entropy and entropy rate of resting state to characterize the dynamic behaviour of our brain. It is further found that the functional entropy is an increasing function of age, but a decreasing function of creativity and IQ. Its biological mechanisms are explored which paves the possible pathway for exploring AI. With the brain wide associate study approach, for the first time in the literature we are able to identify the roots of a few mental disorders. For example, for depression, we found that the most altered regions are located in the lateral and medial orbitofrontal cortex for punishment and reward. Follow up rTMS at the lateral orbitofrontal cortex demonstrated significant outcomes of the treatments.


Bin Hu(Lanzhou University)
Bio
: Dr. Bin Hu, Professor, Dean, School of Information Science and Engineering, Lanzhou University, China,bh@lzu.edu.cn; IET Fellow; Member at Large of ACM China; Vice Chair of International Society for Social Neuroscience (China Committee) and Member of IET Healthcare Technology Network; Chair of IEEE SMC TC on Computational Psychophysiology; Chair Professor of the National Recruitment Programme of Global Experts; Chief Scientist of the National Fundamental Research Program of China (973 Program); Board Member of the Computer Science Committee, Ministry of Education, China; Member of the Division of Computer Science Review Panel, Natural Science Foundation China.His research interests include Computational Psychophysiology, Pervasive Computing, Mental Health Care. His work has been funded by the “973”, National Science Foundation China, Natural Science Foundation China(NSFC), European Framework Programme 7 and HEFCE UK. He has published more than 200 papers in peer reviewed journals, conferences, and book chapters. He has served as associate editor in peer reviewed journalssuch as IEEE Trans. Affective Computing, IET Communications, Cluster Computing, Wireless Communications and Mobile Computing, The Journal of Internet Technology, Wiley’s Security and Communication Networks, Brain Informatics etc.
Title: Computational Psychophysiology Based Emotion Analysis for Mental Health
Abstract: Computational psychophysiology is a new direction that broadens the field of psychophysiology by allowing for the identification and integration of multimodal signals to test specific models of mental states and psychological processes. Additionally, such approaches allows for the extraction of multiple signals from large-scale multidimensional data, with a greater ability to differentiate signals embedded in background noise. Further, these approaches allows for a better understanding of the complex psychophysiological processes underlying brain disorders such as autism spectrum disorder, depression, and anxiety. Given the widely acknowledged limitations of psychiatric nosology and the limited treatment options available, new computational models may provide the basis for a multidimensional diagnostic system and potentially new treatment approaches.