|Title:||Genome Informatics: kmerHMM, SNPdryad, and SignalSpider|
|Date:||August 11, 2016 (Thursday)|
|Time:||3:30 p.m. - 4:30 p.m.|
|Venue:||Room 121, 1/F, Ho Sin-hang Engineering Building,
The Chinese University of Hong Kong,
|Speaker:||Dr. Ka-Chun Wong
Department of Computer Science
City University of Hong Kong
In this talk, three genome informatics methods are described. The first method named kmerHMM is a pattern recognition method for discovering DNA motifs bound by proteins from protein binding microarray (PBM) data. The novelty of kmerHMM lies in two aspects. First, it outperforms the existing methods in using Hidden Markov Models (HMMs) for modeling adjacent nucleotide dependency. Secondly, kmerHMM incorporates N-max-product algorithm and can derive multiple motifs. The second method named SNPdryad is a random forest method to predict the deleterious effect of non-synonymous SNPs on human proteins. It has been demonstrated to have better performance than the existing methods (e.g. Harvard PolyPhen2 and JCVI SIFT) on well-studied datasets. In particular, it has been run on the complete human proteome, generating deleterious prediction scores for ALL possible non-synonymous SNPs in human. Lastly, the third method named SignalSpider will be briefly introduced as a probabilistic graphical model for the integrative analysis of multiple ChIP-Seq (next generation sequencing) profiles for probabilistic combinatorial pattern recognition.
Ka-Chun Wong is an Assistant Professor in Computer Science at City University of Hong Kong. He has spent 3.5 years (2012-13 departmental average: 6 years after master degree) to finish a PhD degree in Department of Computer Science at University of Toronto under the supervision of Professor ZHANG ZhaoLei (CCBR) at the end of 2014. After that, he becomes an independent researcher. He is merited as the first and youngest associate editor outside USA and Germany for the open-access journal, BioData Mining, in 2016. In addition, he is on the editorial board of Applied Soft Computing (No. 1 in Evolutionary Computation according to 2016 Google Scholar) since 2016. Remarkably, he has solely edited 2 books published by Springer and CRC Press, attracting 30 peer-reviewed book chapters around the world (i.e. Argentina, Australia, Belgium, Brazil, China, Egypt, France, Germany, Hong Kong, India, Japan, Spain, USA). He got his Early Career Scheme grant for his first trial in 2016. His research interests include computational biology, bioinformatics, applied machine learning, data mining, and high-impact interdisciplinary research.
Enquiries: Miss Ricola Lo at tel 3943 8440
For more information, please refer to http://www.cse.cuhk.edu.hk/seminar.