|
 |
|
 |
| |
Bayesian Machine Learning for Deciphering Gene Regulation
Speaker:
Dr. Alan Qi
Assistant professor
iDepartments of computer science and statistics and biology (by courtesy)
Purdue University
Time: 2-3pm, Tuesday June 19
Location: Room 208, New Life Science Building, Peking University
Abstract:
Gene regulation plays a fundamental role in biological systems. As more
high-throughput biological data becomes available it is possible to
quantitatively study gene regulation in a systematic way. In this talk I
present our work on three related problems on gene regulation including:
(1) identifying genes that affect organism development; (2) detecting
protein-DNA binding events and cis-regulatory elements; (3) and
deciphering regulatory cascades at the transcriptional level for
embryonic stem cell development. To address these problems, we must
overcome many computational challenges, including little prior
biological knowledge, joint effect of many biological variables, and
large model spaces for learning.
Facing these computational challenges, we developed novel Bayesian
methods to analyze high-throughput data, in order to deepen our
understanding of gene regulation for organism development. Specifically,
we first devised a novel Bayesian semi-supervised classification method
to identify candidate genes specific to certain lineages and cell-types
of /C. elegans/ embryos. My computational predictions about some
previously uncharacterized genes were experimentally confirmed by my
biologist collaborators. Second, we built a new Bayesian graphical model
of protein-DNA binding and developed an approximate inference algorithm
to efficiently estimate binding events in high spatial-resolution and
guide motif discovery. The software implementation of this algorithm is
being used by research groups worldwide. Third, we developed a novel
nonparametric Bayesian model that enables the reconstruction of a
regulatory cascade for the development of embryonic stem cells, without
predefining the level of the cascade or the branching number at each
level. Some predictions were experimentally confirmed by our
collaborators and independently by other research groups.
About the speaker:
Yuan Alan Qi (漆远) received the Ph.D. degree from the MIT Media
Laboratory in 2005 and worked as a postdoctoral associate at MIT
Computer Science and Artificial Intelligence Laboratory. In 2007 Summer,
he joins Purdue as an assistant professor in departments of computer
science and statistics. He also holds a courtesy faculty position in
biology. His main research interests include statistical machine
learning and computational biology. He has also worked on computer
vision and wireless communications.
His work has been published in the top journals and conferences in
machine learning, computational biology, computer vision, and wireless
communications, including Nature Biotechnology, Bioinformatics, PLos
Computational Biology, Neural Information Processing Systems,
International Conference on Machine Learning, IEEE conference on
Computer Vision & Pattern Recognition, IEEE Trans. Wireless
Communication, and IEEE Trans. Medical Imaging. He has a patent with
Microsoft Research Cambridge, UK. His collaborative research projects
have been reported by the Discovery channel, Washington Post, United
Press International, and Xinhua News.
|
|
 |
|
 |
|
