Korea University · 情報科学
Professor Junhee Seok's research lab specializes in computational systems biology and data-driven biomedical research, focusing on deciphering complex regulatory networks in inflammatory diseases using multi-omics data and network analysis. The lab develops advanced statistical and machine learning methods to model gene regulatory networks, particularly in the context of host responses to immune challenges such as LPS stimulation. A key focus is improving the translational relevance of mouse models by systematically comparing murine and human immune responses at the genomic level. The lab also explores the impact of corporate social responsibility and ESG initiatives on firm value, integrating social science with data analytics to uncover mediating mechanisms such as customer satisfaction and word-of-mouth.
Figures are computed from collected data and may differ slightly.
A cornerstone of modern biomedical research is the use of mouse models to explore basic pathophysiological mechanisms, evaluate new therapeutic approaches, and make go or no-go decisions to carry new drug candidates forward into clinical trials. Systematic studies evaluating how well murine models mimic human inflammatory diseases are nonexistent. Here, we show that, although acute inflammatory stresses from different etiologies result in highly similar genomic responses in humans, the responses
In contemporary business landscapes, concerns about environmental, social, and governance (ESG) issues are increasingly prominent. Despite the rising public interest in ESG, empirical research assessing its efficacy remains sparse. This research investigates the subtle connection between ESG initiatives and firm value, highlighting the mediating role of customer satisfaction. Utilizing an industry-fixed effects model, our research analyzes an unbalanced panel dataset comprising 168 firms over fi
Using NCA, we were able to build a network that accounted for between 8-11% genes in the known transcriptional response to LPS in humans. The dynamic network illustrated changes of transcription factor activities and gene expressions as well as interactions of signaling proteins, transcription factors and target genes.
Purpose This study clarifies the relationship between corporate social responsibility (CSR) news reports and firm value and identifies the mechanisms that constitute this relationship. Specifically, it identifies the roles of word of mouth (WOM) and traditional advertising in this relationship. Design/methodology/approach The data set used for the analysis covers 77 firms in Korea from 2012 to 2015. The random-effects model is applied to verify three hypotheses. Using a three-step regression ana
JETTA and its demonstrations are freely available at http://igenomed.stanford.edu/~junhee/JETTA/index.html
Mutual information, a general measure of the relatedness between two random variables, has been actively used in the analysis of biomedical data. The mutual information between two discrete variables is conventionally calculated by their joint probabilities estimated from the frequency of observed samples in each combination of variable categories. However, this conventional approach is no longer efficient for discrete variables with many categories, which can be easily found in large-scale biom
Conventional predictive Artificial Neural Networks (ANNs) commonly employ deterministic weight matrices; therefore, their prediction is a point estimate. Such a deterministic nature in ANNs causes the limitations of using ANNs for medical diagnosis, law problems, and portfolio management in which not only discovering the prediction but also the uncertainty of the prediction is essentially required. In order to address such a problem, we propose a predictive probabilistic neural network model, wh
Abstract Owing to the recent explosive expansion of deep learning, several challenging problems in a variety of fields have been handled by deep learning, yet deep learning methods have been limited in their application to the network estimation problem. While network estimation has a possibility to be a useful method in various domains, deep learning-based network estimation has a limitation in that the number of variables must be fixed and the estimation cannot be performed by convolutional la
High quality, comprehensive, and direct knowledge bases, when combined with appropriate bioinformatic algorithms, can significantly improve the discovery of gene regulatory relationships from high throughput gene expression data.
We propose a generative adversarial network (GAN) that introduces an evaluator module using pretrained networks. The proposed model, called a score-guided GAN (ScoreGAN), is trained using an evaluation metric for GANs, i.e., the Inception score, as a rough guide for the training of the generator. Using another pretrained network instead of the Inception network, ScoreGAN circumvents overfitting of the Inception network such that the generated samples do not correspond to adversarial examples of
Open papers in the app to read, cite, and organize with AI.
