Dare to Think

News

Center for Biotech Data Science
16/02/22 14:03 | PR | View 7946 | Comments 0

 

The Center for Biotech Data Science was established to pursue the development of new mathematical and computational approaches for extracting knowledge from huge sets of biotech data (e.g., omics data and medical imagery), paying attention to technical challenges like predictive analysis and complexity reduction of biochemical systems. The newly developed approaches will have a variety of applications, ranging from cancer research to medical diagnosis and drug development.

 

      

 

 

Profile: Mijung Kim

 

Mijung Kim is a doctoral researcher at GUGC’s Center for Biotech Data Science. Her research focuses on deep machine learning and bioinformatics. In December 2015, she received a best poster award at the Ph.D. symposium of the Faculty of Engineering and Architecture of Ghent University, for a research proposal titled “Exploring Deep Learning for Automatic Right Whale Recognition and Novel Drug Design.”

 

 

         

 

We recently asked Mijung a few questions about her research at the Center for Biotech Data Science.

 

Could you tell us a bit more about your educational and professional background?

 

I studied mathematics as an undergraduate at Yonsei University and I majored in computer science as a graduate at SUNY Korea. In-between my undergraduate and graduate studies, I have been working as a project manager at a number of Korean government agencies.

 

What does it mean for you to be a doctoral researcher?

 

To answer this question, I would like to paraphrase Steve Jobs: for me, doctoral research is about connecting the dots from yesterday to tomorrow. Indeed, I have various educational and professional backgrounds, each of which now work together to come up with good research results. In particular, I hope to see these different interactions converge to a solution for a major problem in the field of biotech.

 

What are some of the research efforts you are currently working on?

 

My research is at the intersection of deep machine learning and bioinformatics, two of the fastest growing fields of study in computer science. In that regard, I am currently focusing on two tracks. First, I am reading a lot of academic papers, reproducing their experiments to the extent possible. That way, I am able to become familiar with the many new theories and techniques that have recently been introduced in the aforementioned fields of study. Second, I am participating in a number of data science competitions available on the online Kaggle platform, including the recognition of endangered North whales in aerial photographs and the diagnosis of heart disease in MRI images. So, apart from reading academic papers, I am spending quite a bit of time on the creation of new ideas and methods to tackle a couple of real-world data science challenges.

 

How do you see the impact of computer science on the field of biology?

 

Biology is about the study of complex interactions among for instance cells and organs. In the past, it took a lot of time to figure out these interactions, through the use of expensive, slow, and error-prone experiments. Nowadays, thanks to the availability of vast amounts of data and computational power, deep machine learning for instance facilitates (complementary) experiments that are cheap, fast, and more accurate. So, I believe that computer science is about to become an important component of modern biology, driving further scientific breakthroughs.

 

How are you experiencing your current stay at the home campus in Belgium?

 

My stay at the home campus in Belgium has thus far been a great experience, not only in terms of knowledge acquisition but also in terms of research collaboration. In particular, I am able to stay in the Data Science Lab, a large research group with highly experienced graduate students. These graduate students are working on similar research topics, thus making it possible to share a lot of ideas and practical insights. Furthermore, some of these graduate students will also join me in tackling the Kaggle data science challenges.

 

What are you planning to do after the completion of your Ph.D.?

 

I love teaching because it gives me the opportunity to share my knowledge and experience with students, while at the same time also getting new ideas from discussions with students. Furthermore, I also want to contribute with my work and my research to society. So, after the completion of my doctoral research, working as a scientist or a professor would be perfect for me.