Contact Us

I-X Seminar: Modeling Gene-Gene Interactions for Drug Response Prediction and Biomarker Gene Discovery with Professor Sun Kim

Key Details:

Time: 11.00 – 12.00
Date: Thursday 4  July
Location: Hybrid Event | I-X Lecture Room Theatre 6.12 A+B | Level 6
Translation and Innovation Hub (I-HUB)
Imperial White City Campus
84 Wood Lane
W12 0BZ

Registration is
now closed

Speaker

Professor Sun Kim

Sun Kim is a Professor in the School of Computer Science and Engineering, Adjunct Professor of Biological Sciences, and Director of Bioinformatics Institute (2011-2021) at Seoul National University. He is also currently President of Mogam Institute of Biomedical Research and a member of National Academy of Engineering, Korea. Before joining SNU, he was Chair of Faculty Division C; Director of Center for Bioinformatics Research, an Associate Professor in School of Informatics and Computing at Indiana University (IU), Bloomington. Prior to joining IU in 2001, he worked at DuPont Central Research from 1998 to 2001, and at the University of Illinois at Urbana-Champaign from 1997 to 1998. Sun Kim received B.S and M.S and Ph.D in Computer Science from Seoul National University, KAIST and the University of Iowa, respectively.

Sun Kim is a recipient of Outstanding Junior Faculty Award at Indiana University 2004, US NSF CAREER Award in 2003, and Outstanding Faculty Award in research 2021 in the College of Engineering at Seoul National University. He is actively contributing to the bioinformatics community, having served on the editorial board for journals including editors for the METHODS journal (2013-2022), associate editor-in-chief for ACM/IEEE Transactions on Computational Biology and Bioinformatics (2019-2021) and on the board of directors for ACM SIG Bioinformatics and for education for the IEEE Computer Society Technical Committee on Bioinformatics. Among many service activities in Korea, he served on Samsung Future Technology Committee for 2016-2018, a member of The National Science and Technology Council (NSTC) of the Korean Government for 2019-2020, President of Korea Artificial Intelligence Society (2016-2018) and Vice President of Korea Society of Bioinformatics and Systems Biology (2011-present).

Talk Title

Modeling Gene-Gene Interactions for Drug Response Prediction and Biomarker Gene Discovery

Talk Summary

In this talk, I will share our recent research works on drug response prediction and biomarker gene discovery. These two research problems are of prime importance for drug discovery, but they are challenging unresolved problems. Our strategy for these two problems is to start with precise modeling of gene-gene interaction. The first problem of predicting drug response is a huge topic. In this talk, I will focus on cancer drug response because large molecular, cellular, and patient level databases are available for computational modeling: LINCS, GDSC, and TCGA. However, each of these databases have limited information for predicting drug responses. First, GDSC (Genomics of Drug Sensitivity in Cancer) includes data from 722,057 genomic associations tested in terms of cancer cell death as of June 2024. The major hurdle in using GDSC for response prediction is that gene-level responses after drug treatment is not available. Another database, LINCS, has a large collection of gene-level responses after drug treatment. However, translating LINCS data to cellular level (e.g, GDSC) and to patient level (e.g., TCGA) remains an unresolved research problem. We have been working this problem for years and I will share our recent work on modeling gene-gene interactions for drug response prediction (ISMB/Bioinformatics 2024).

The second topic of identifying gene-level biomarkers also requires precise modeling of gene-gene interactions. To decipher complex interactions among genes, we developed GOAT using network propagation and graph transformer to predict gene-level biomarkers in terms of asthma phenotypes (Bioinformatics 2023). Given biomarker candidates predicted by computational tools such as GOAT, drug response prediction tools can be used for evaluating biomarker candidates, for which my group is developing a comprehensive package. In closing of this talk, I will briefly talk about additional research directions. We show that both drug response prediction and biomarker discovery can be done simultaneously in a single computational framework (In submission). Another important problem is patient stratification for which drug response prediction tools can be useful at the molecular level (In submission).

Networking Opportunity

This talk has been organised jointly by I-X, Department of Bioengineering and the National Heart and Lung Institute. A networking lunch will be provided at the end of the seminar. 

More Events

Dec
12

This talk discusses sparse Principal Component Analysis (PCA) with Multiple Components.

Dec
05

In this talk, Dr Kanta Dihal explores differences in cultural approaches towards AI.

Jan
08

In his Inaugural Lecture, Professor Hamed Haddadi discusses his academic journey towards building networked systems.