|Title:||Discovering Deep Knowledge from Biosequence Data|
|Date:||October 12, 2015 (Monday)|
|Time:||5:00 p.m. - 6:00 p.m.|
|Venue:||Room 121, 1/F, Ho Sin-hang Engineering Building,
The Chinese University of Hong Kong,
|Speaker:||Prof. Andrew K.C. Wong
Distinguished Professor Emeritus
(Systems Design Engineering)
University of Waterloo, Canada
With the advance of sequencing technologies, biological sequence data is exponentially increasing. Hence, the bottleneck on omic research and development is no longer the lack of data but the capability of discovering meaningful and useful knowledge from it. This talk presents our novel method P2K (Pattern-to-Knowledge): a Pattern-Directed Knowledge Discovery, Integration and Verification Software System. It is an unsupervised method to discover deep revealing knowledge of provable scientific results from established data/knowledge bases and literature in the Cloud. The presented work includes: 1) discovering statistical significant and functional relevant patterns, the "what" of the important residue/nucleotide association; 2) obtaining Aligned Pattern Clusters (APCs), representing the locally conserved and distance-wise co-occurring regions on the same or different biosequences respectively, the "where" of the hotspots in the sequence data to : a) reveal natural subgroup/class partitions in functional regions of proteins, the "what" and "why" crucial to the regions; b) discover the close binding regions (binding cores) between Protein and DNA sequences, the "what" and "where" of Protein-DNA binding; c) identify and predict interactions between protein partners/sites, the actionable "how" and "where" in protein-protein interaction; 3) applying P2K to explore and conjecture regulatory mechanisms in non-coding regions, the "what", "where", "why" and "how" of the regulatory mechanism. The essence of our capability is to discover deeper revealing knowledge from big biosequence data in an unsupervised way. Its success in applying to a) discovering subgroup patterns for A Scavenger Receptors (cA-SRs); b) PPI partner between a large set of Yeast protein sequences; and, c) exploring and conjecturing regulatory mechanism of HERV-K cancerous gene demonstrate that P2K is able to discover, integrate and verify novel biological knowledge. It promises a great potential for drug discovery and personalized gene therapy. The methodology has also been extended to large relational data sets and multivariate time sequences/series. It thus not only spawns critical biology, drug discovery, medical and healthcare applications, but also opens an important avenue to discover deeper knowledge from other types of data.
Dr. Wong holds a Ph.D. from Carnegie Mellon University; B.Sc (Hons) and M.Sc. from the Hong Kong University. He is an IEEE Fellow for his contribution in machine intelligence, computer vision, and the intelligent robotics areas. Currently, Dr. Wong is a Distinguished Professor Emeritus (Systems Design Engineering). He was the Founding Director of Pattern Analysis and Machine Intelligence Laboratory (PAMI Lab) at UW, now the Centre of PAMI, and a Visiting Distinguished Chair Professor at the Hong Kong Polytechnic University (00-03). His research areas cover machine intelligence, computer vision, intelligence robotics, pattern recognition, data mining and bioinformatics. Dr. Wong has published over 300 papers and chapters and holds six US Patents. He served as the General Chair of International Conferences IASTED (1996) and IROS (1998) and has been an invited speaker in the Distinguished Speaker Program, IEEE Computer Society. Dr. Wong has served as consultant to many high-tech companies in USA, Canada and Hong Kong. Over the years, based on the core technologies of his team, he founded several high tech companies. Dr. Wong is a co-founder, and retired director of Virtek Vision International Corporation, a leader in laser and vision technology, and then a public trading company in TSX. He served as President (87-93), Chairman (93-97) and Director of the Board (97-03). In 1997, he co-founded Pattern Discovery Software Technologies Inc. and has served as its Chairman till 06/2013. In 2008, he cofounded Knowledge Fund Limited.
Enquiries: Miss Evelyn Lee at tel 3943 8444
For more information, please refer to http://www.cse.cuhk.edu.hk/seminar.