[Theory] REMINDER: 2/16 Talks at TTIC: Sai Zhang, Stanford University

[Mary Marre]

*When:*        Wednesday, February 16th at* 11:30 am CT*


*Where:*       Zoom Virtual Talk (*register in advance here
<https://uchicagogroup.zoom.us/webinar/register/WN_JFaznBfdRSe3KcvNoN78Dg>*)


*Who: *         Sai Zhang, Stanford University



*Title:*          Machine learning for decoding complex human diseases

*Abstract:*  In the era of big biomedical data, millions of genomes have
been sequenced which provides an unprecedented opportunity to
systematically investigate the molecular components underlying complex
diseases. However, the complexity and heterogeneity of the biological data
substantially challenge traditional methodologies for effective analysis
and discovery. In this talk, I will introduce my effort on developing novel
machine learning algorithms for disease genome analysis. First, I will
describe RefMap, a Bayesian network that pinpoints disease risk genes by
integrating genetic data with epigenetic profiling. The increased discovery
power of RefMap has been demonstrated in several diseases including
amyotrophic lateral sclerosis, severe COVID-19, and preterm birth. Next, I
will discuss a series of models that leverage techniques in probabilistic
graphical models and deep learning to predict disease risk from personal
genomes. I will also present successful applications of these models on
several diseases such as abdominal aortic aneurysm, thoracic aortic
dissection, and cardiomyopathy. I will conclude my talk with future plans
on building data-driven frameworks to assist mechanism discovery,
therapeutic development, and clinical decision making.

*Bio:* Sai Zhang (https://sai-zhang.com/) is an Instructor in the
Department of Genetics at Stanford University School of Medicine. He
received postdoctoral training in Dr. Michael Snyder’s group at Stanford
Genetics from 2017 to 2021. Prior to that, he got a Ph.D. in Computer
Science from Tsinghua University in 2017. His main research focus is the
development of machine learning algorithms (e.g., deep learning and
probabilistic graphical models) which exploit massive genetic, multiomic,
and clinical data to uncover the genomic basis of complex human diseases.
The long-term goal of his research is to build advanced artificial
intelligence systems to assist scientific discovery, clinical decision
making, and personal health management. As the first author, Sai has
published multiple research papers in top journals such as Cell, Neuron,
and Cell Systems, as well as in top conferences in computational biology
such as RECOMB and ISMB. Some of his studies have been highlighted by
Nature, Nature Reviews Neurology, NIH Research Matters, etc.

*Host:* *Jinbo Xu* <j3xu at ttic.edu>



Mary C. Marre
Faculty Administrative Support
*Toyota Technological Institute*
*6045 S. Kenwood Avenue*
*Chicago, IL  60637*
*mmarre at ttic.edu <mmarre at ttic.edu>*


On Thu, Feb 10, 2022 at 8:22 AM Mary Marre <mmarre at ttic.edu> wrote:

> *When:*        Wednesday, February 16th at* 11:30 am CT*
>
>
> *Where:*       Zoom Virtual Talk (*register in advance here
> <https://uchicagogroup.zoom.us/webinar/register/WN_JFaznBfdRSe3KcvNoN78Dg>*
> )
>
>
> *Who: *         Sai Zhang, Stanford University
>
>
>
> *Title:*          Machine learning for decoding complex human diseases
>
> *Abstract:*  In the era of big biomedical data, millions of genomes have
> been sequenced which provides an unprecedented opportunity to
> systematically investigate the molecular components underlying complex
> diseases. However, the complexity and heterogeneity of the biological data
> substantially challenge traditional methodologies for effective analysis
> and discovery. In this talk, I will introduce my effort on developing novel
> machine learning algorithms for disease genome analysis. First, I will
> describe RefMap, a Bayesian network that pinpoints disease risk genes by
> integrating genetic data with epigenetic profiling. The increased discovery
> power of RefMap has been demonstrated in several diseases including
> amyotrophic lateral sclerosis, severe COVID-19, and preterm birth. Next, I
> will discuss a series of models that leverage techniques in probabilistic
> graphical models and deep learning to predict disease risk from personal
> genomes. I will also present successful applications of these models on
> several diseases such as abdominal aortic aneurysm, thoracic aortic
> dissection, and cardiomyopathy. I will conclude my talk with future plans
> on building data-driven frameworks to assist mechanism discovery,
> therapeutic development, and clinical decision making.
>
> *Bio:* Sai Zhang (https://sai-zhang.com/) is an Instructor in the
> Department of Genetics at Stanford University School of Medicine. He
> received postdoctoral training in Dr. Michael Snyder’s group at Stanford
> Genetics from 2017 to 2021. Prior to that, he got a Ph.D. in Computer
> Science from Tsinghua University in 2017. His main research focus is the
> development of machine learning algorithms (e.g., deep learning and
> probabilistic graphical models) which exploit massive genetic, multiomic,
> and clinical data to uncover the genomic basis of complex human diseases.
> The long-term goal of his research is to build advanced artificial
> intelligence systems to assist scientific discovery, clinical decision
> making, and personal health management. As the first author, Sai has
> published multiple research papers in top journals such as Cell, Neuron,
> and Cell Systems, as well as in top conferences in computational biology
> such as RECOMB and ISMB. Some of his studies have been highlighted by
> Nature, Nature Reviews Neurology, NIH Research Matters, etc.
>
> *Host:* *Jinbo Xu* <j3xu at ttic.edu>
>
>
>
>
> Mary C. Marre
> Faculty Administrative Support
> *Toyota Technological Institute*
> *6045 S. Kenwood Avenue*
> *Chicago, IL  60637*
> *mmarre at ttic.edu <mmarre at ttic.edu>*
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.cs.uchicago.edu/pipermail/theory/attachments/20220216/5735cd88/attachment.html>