ICIC 2021 Invited Speakers

  • Min Li
  • HaiLong Pei
  • AiGuo Wu
  • ZhuHong You
  • JianYang Zeng
  • XiangXiang Zeng
  • XingMing Zhao
    •

    Min Li
    Ph.D & Professor
    Central South University, China.
    HaiLong Pei
    Ph.D & Professor
    South China University of Technology, China.
    AiGuo Wu
    Ph.D & Professor
    Harbin Institute of Technology Shenzhen Graduate School, China.
    ZhuHong You
    Ph.D & Professor
    Northwestern Polytechnical University, China.
    JianYang Zeng
    Ph.D & Professor
    Tsinghua University, China.
    XiangXiang Zeng
    Ph.D & Professor
    Hunan University, China.
    XingMing Zhao
    Ph.D & Professor
    Fudan University, China.

    De novo Genome Assembly and Enhancer-mediated Genome Topology Identification

    Min Li
    Ph.D & Professor
    School of Computer Science and Engineering, Central South University, China.

    Abstract:De novo genome assembly is one of the most important tasks in computational biology and bioinformatics. However, de novo genome assembly is challenging due to (i) sequencing errors, (ii) sequencing bias and (iii) repetitive regions. In this talk, I will present our recent work around these three challenges as follows: (1) how to overcome complex repetitive regions by developing a new score function based on the distributions of insert size and read classification; (2) how to reducing peak memory in the process of genome assembly; (3) how to overcome sequencing errors and sequencing bias. With the development of Hi-C Sequencing and proximity-ligation assays, it is possible to investigate genome topology from a new perspective. However, these are technically challenging, expensive, and time-consuming, making it difficult to investigate enhancer topologies, especially in uncharacterized cell types. In this talk, an ensemble machine learning model LoopPredictor will be introduced to predict the genome topology for any cell type which lacks a 3D profile. LoopPredictor is able to efficiently identify cell type-specific enhancer mediated loops, and promoter-promoter interactions, with a modest feature input requirement. LoopPredictor enables the dissection of cell type-specific long-range gene regulation, and can accelerate the identification of distal disease-associated risk variants. Finally, the future development and what AI could be done in genomics will be discussed.

    Bio-Sketch:Dr. Min Li is currently a Professor and the vice dean at the School of Computer Science and Engineering, Central South University, P. R. China. Her research interests include algorithms for computational biology and bioinformatics, mainly focus on algorithms and tools in de novo genome assembly, biological network analysis and protein bioinformatics, etc. She has published more than 100 technical papers in refereed journals such as Genome Research, Bioinformatics, Briefings in Bioinformatics, and IEEE/ACM Transactions on Computational Biology and Bioinformatics, and conference proceedings such as BIBM, GIW and ISBRA. According to Google scholar, her paper citations is more than 6500 and H-index is 41. Dr. Min Li is a member of ACM, a member of IEEE, and a member of CCF. She is serving as the Editorial Board Member or the Guest Editor of a number of refereed journals such as IEEE/ACM Transactions on Computational Biology and Bioinformatics, BMC Bioinformatics, BMC Genomics, Neurocomputing, Interdisciplinary Sciences: Computational Life Sciences and as the PC co-chairs of several international conferences such as ISBRA 2021, ISBRA2017, amd ICPCSEE2017.

    Coastal Zone Aerial Perception with UAV

    HaiLong Pei
    Ph.D & Professor
    Key Lab of Autonomous Systems and Networked Control, South China University of Technology, China.

    Abstract:The coastal zone is a corridor in which the sea interfaces the land, containing the coast parts, the nearshore water bodies and the underwater bottoms. Because of the extreme terrestrial-aquatic transition environment, it is difficult for personnel to implement the multi-element direct surveying (coast land, waterline, nearshore hydrology, etc.). The existing remote sensing techniques are also not efficient for accurate spatio-temporal measuring under this dynamic circumstance, especially for large region survey. This talk introduces the application of UAV remote sensing technology in coastal zone exploration, focusing on the low-altitude small UAV wave observation and moving inverse mechanism of bathymetry perception, along with the airborne survey system configuration and promising field test practices. Further discussions will show the existing challenges as well as the potential applications.

    Bio-Sketch:HaiLong Pei received his Ph.D degree from the South China University of Technology , China in 1992, and Master and Bachelor degrees from the Northwestern Polytechnical University, China in 1989 and 1986, respectively. Currently, he is a professor of School of Automation Science and Engineering in the South China University of Technology, Director of the Key Lab of Autonomous Systems and Networked Control, Ministry of Education, and Director of the Unmanned Engineering Center of Guangdong Province. He works on unmanned systems and robotic control, and now serves as editor-in-chief of the Journal of Control Theory and Technology, as associate editor of International Journal of Intelligent & Robotic Systems, and as associate editor of Acta Automatica Sinica.


    From Matrix Equations to Conjugate Product

    AiGuo Wu
    Ph.D & Professor
    Harbin Institute of Technology Shenzhen Graduate School, China

    Abstract:Theory on polynomials and polynomial matrices plays a vital role in control systems design, such as, design of dynamical compensators, observer design, eigenstructure assignment. In this talk, some applications of polynomial matrices in control theory are firstly introduced, and then the procedure to propose the concept of conjugate product is elaborated in details. In this talk, some interesting properties of conjugate product are introduced, and are compared with those of the ordinary product. The involved properties include left and right coprimeness, greatest common left and right divisors, and so on. In addition, the application of conjugate product in consimilarity of matrices is also introduced. In the last part of this talk, the concept of conjugate product is generalized to the framework of rational fraction.

    Bio-Sketch:Ai-Guo Wu was born in Gong’an County, Hubei Province, P. R. China on September 20, 1980. He received his B.Eng degree in Automation in July 2002, M.Eng degree in Navigation, Guidance and Control in July 2004 and PhD degree in Control Science and Engineering in Nov. 2008 all from Harbin Institute of Technology. In Oct. 2008, he joined Harbin Institute of Technology Shenzhen Graduate School as an assistant professor, and in August 2012 he was promoted to a professor. From Jan. 2018, he is a professor in Harbin Institute of Technology, Shenzhen. Dr. Wu was a Research Fellow with the Department of Manufacturing Engineering and Engineering Management, City University of Hong Kong from March 2009 to March 2011. He was a visiting professor with the Department of Electrical, Electronic and Computer Engineering of The University of Western Australia, Australia from July 2013 to July 2014.His research interests include descriptor systems, conjugate product of polynomials, switched system and robust control. He has authored/co-authored one English monograph and more than 70 SCI journal papers. He received the National Natural Science Award (Second Prize) in 2015 from P. R. China, and the National Excellent Doctoral Dissertation Award in 2011 from the Academic Degrees Committee of the State Council and the Ministry of Education of P. R. China. He was supported by the Program for New Century Excellent Talents in University in 2011, and by the National Natural Science Foundation of China for Excellent Young Scholars in 2018.Dr. Wu is a Reviewer for American Mathematical Review from 2007. He serves as a Regional Editor of Nonlinear Dynamics and Systems Theory from 2015, and an International Subject Editor of Applied Mathematical Modelling from 2017. He was an Outstanding Reviewer for IEEE Transactions on Automatic Control in 2010.


    Graph Representation Learning to Predict Intermolecular Interactions on Large-Scale Heterogeneous Molecular Association Network

    ZhuHong You
    Ph.D & Professor
    School of Computer Sciences, Northwestern Polytechnical University (NPU), China.

    Abstract:Graph is a natural data structure for describing complex systems which contains a set of objects and relationships. Ubiquitous real-life biomedical problems can be modeled as graph analytics tasks. However, rich relational information between biological elements is retained in the non-Euclidean biomedical graphs, which is not learning friendly to classic machine learning methods. Graph representation learning aims to embed graph into a low-dimensional space while preserving graph topology and node properties. It bridges biomedical graphs and modern machine learning methods, and has recently raised widespread interest in both machine learning and bioinformatics communities. Meanwhile, molecular components that are functionally interdependent in human cells constitute molecular association networks. Disease can be caused by disturbance of multiple molecular interactions. New biomolecular regulatory mechanisms can be revealed by discovering new biomolecular interactions. In this talk, we build a heterogeneous molecular association network by systematically integrating comprehensive associations between miRNAs, lncRNAs, circRNAs, mRNAs, proteins, drugs, microbes, and complex diseases. Then, several network embedding models are introduced to fully exploit the network behavior of biomolecules, and attribute features are also calculated. These discriminative features are combined to train a machine learning model to predict intermolecular interactions. The proposed methods achieve outstanding performance in hybrid associations prediction. This work provides systematic landscape and machine learning method to model and infer complex associations between various biological components. It is anticipated that this talk could provide valuable insights for researchers to contribute their knowledge to graph representation learning and future-oriented bioinformatics studies.

    Bio-Sketch:Dr. ZhuHong You is a professor at the School of Computer Sciences, Northwestern Polytechnical University (NPU), China. He received his Ph.D. degree in control science and engineering from University of Science and Technology of China (USTC), Hefei, China, in 2010. From June 2008 to November 2009, he was a visiting research fellow at the Center of Biotechnology and Information, Cornell University. During 2013 and 2015, he went to Hong Kong Polytechnical University for postdoctoral research. In July 2016, he joined the Xinjiang Technical Institute of Physics and Chemistry, Chinese Academy of Sciences as the Recipient of “Hundred Talents Program of CAS”. He has published more than 260 research papers in refereed journals and conferences in the areas of pattern recognition, bioinformatics, and complex-network analysis. He holds more than 10 patents. His Google-scholar citation is more than 8,000, and H-index is more than 47. His current research interests include neural networks, intelligent information processing, sparse representation, and its applications in bioinformatics. He is recipient of China NSFC Excellent Young Scholars Program in 2018 and 2020.


    Machine Intelligence for Drug Discovery

    JianYang Zeng
    Ph.D & Professor
    Institute for Interdisciplinary Information Sciences, Tsinghua University, China.

    Abstract:Identification of molecular recognition patterns is an essential problem in biology and pharmacology. Identifying the interactions between protein targets and small-molecule compounds plays an important role in small-molecule drug discovery. In recent years, the emerging high throughput experimental techniques together with the massive biological data, and advanced AI technology provide a new opportunity for one to investigate molecular recognition mechanisms, as well as posing challenges to computational models. Through information integration, feature extraction and heterogeneous network representation, we have developed several new machine learning models to elucidate the molecular recognition patterns between small molecules and proteins, which can provide useful insights for understanding the mechanisms of gene regulation, improving the prediction of drug-target interactions, and thus advancing biomedical researches and drug discovery processes.

    Bio-Sketch:Dr. JianYang Zeng is an Associate Professor with Tenure at the Institute for Interdisciplinary Information Sciences, Tsinghua University, China. He received B.S. and M.S. from Zhejiang University in 1999 and 2002 respectively, and Ph.D. in Computer Science from Duke University in 2011. He has over 70 publications, including those on Nature Machine Intelligence, Nature Communications, PNAS, Cell Systems, and Nucleic Acids Research. His received multiple awards for his research, including ESI Highly Cited Paper, Wuwenjun AI Science and Technology Award Third Prize for the Natural Science track 2019, China’s Top Ten Bioinformatics Advances of 2019 and 2020, China’s Top Ten Bioinformatics Algorithms and Instruments, World Artificial Intelligence Conference Youth Outstanding Paper Award, ICIBM Best Paper Award 2019, and PDCAT Best Paper Award 2005. He is an Associate Editor of IEEE/ACM Transactions on Computational Biology and Bioinformatics and was on the program committee of top computational biology conferences such as ISMB and RECOMB.


    Deep Graph Learning for Drug Discovery

    XiangXiang Zeng
    Ph.D & Professor
    College of Information Science and Engineering, Hunan University, China.

    Abstract:Deep graph learning (graph neural network) has received great attention from artificial intelligence researchers in recent years. This talk will introduce the latest progress of deep graph learning, and its applications in drug repurposing. Specifically, we built a comprehensive knowledge graph that includes 15 million edges across 39 types of relationships connecting drugs, diseases, proteins/genes, pathways, and expression from a large scientific corpus of 24 million PubMed publications. Using Amazon’s AWS computing resources and a network-based, deep-learning framework, we identified 41 repurposable drugs (including dexamethasone, indomethacin, niclosamide, and toremifene) whose therapeutic associations with COVID-19 were validated by transcriptomic and proteomics data in SARS-CoV-2-infected human cells and data from ongoing clinical trials.

    Bio-Sketch:Prof. Zeng is right now a Yuelu distinguished Professor at the College of Information Science and Engineering, Hunan University, Changsha, China. Before joining Hunan University in 2019, he worked at the Department of Computer Science in Xiamen University. He received his Ph.D. degree in system engineering from Huazhong University of Science and Technology, China, in 2011. He has served as a visiting scholar in Harard Medical School, Indiana University, Chinese University of Hongkong, and Oklahoma State University. He has published more than 100 papers on journals and conferences such as Nucleic Acids Research, Bioinformatics, Chemical Science. His research work is relevant about machine learning, data mining, computational intelligence, bioinformatics and drug discovery. According to google scholar citation, his research works were cited more than 5,000 times. He received the Wu Wenjun Artificial Intelligence Excellent Youth Award in 2019, and the Amazon AWS Machine Learning Research Award in 2020.


    Exploring Brain and Brain Diseases via Multi-modal Omics and Imaging Data

    XingMing Zhao
    Ph.D & Professor, IEEE Senior member
    Institute of Science and Technology for Brain Inspired Intelligence, Fudan University, China.

    Abstract:In this talk, I’ll introduce our recent work on brain science. Especially, I’ll present our works on the spatial-temporal cell atlas across brain development as well as the gene signatures regulating brain structure and function during brain development. I’ll also introduce two subtypes identified for autism, a developmental brain disorder, based on gut microbiome, image and behavior data, which is important for future precise intervention and prevention of the disorder.

    Bio-Sketch:XingMing Zhao received his PhD degree from the University of Science and Technology of China. Currently, he is a full professor at the Institute of Science and Technology for Brain Inspired Intelligence, Fudan University, China, and serves as a Vice Director of the Key Laboratory of Computational Neuroscience and Brain-Inspired Intelligence (Fudan University), Ministry of Education, China. His research interests include data mining and bioinformatics. He has published more than 110 papers in peer-reviewed journals, e.g. Cell Metabolism and Nature Communications. He is the senior member of IEEE, Co-Chair of IEEE SMC Technical Committee on Systems Biology and Vice-Chair of ACM SIGBIO China. He is also the lead guest editor and the editorial member of several journals, e.g. IEEE/ACM TCBB, Neurocomputing, Journal of Theoretical Biology, IET Systems Biology, and so on.