Jeonghee Jo

Jeonghee Jo

Auto-generated profile, based on publicly available information

Jeonghee Jo

Center for Semiconductor Technology Korea Institute of Science and Technology (KIST) Seoul South Korea

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
27 January 2022 in ACS Omega
Verified
Journal Article
Open access
JJJeonghee Jo
Jeonghee Jo
BKBumju Kwak
Bumju Kwak
BLByunghan Lee
Byunghan Lee
SYSungroh Yoon
Sungroh Yoon
A molecule is a complex of heterogeneous components, and the spatial arrangements of these components determine the whole molecular properties and characteristics. With the advent of deep learning in computational chemistry, several studies have focused on how to predict molecular properties based on molecular configurations. MA message-passing neural network provides an effective framework for capturing molecular geometric features with the perspective of a molecule as a graph. However, most of these studies assumed that all heterogeneous molecular features, such as atomic charge, bond length, or other geometric features, always contribute equivalently to the target prediction, regardless of the task type. In this study, we propose a dual-branched neural network for molecular property prediction based on both the message-passing framework and standard multilayer perceptron neural networks. Our model learns heterogeneous molecular features with different scales, which are trained flexibly according to each prediction target. In addition, we introduce a discrete branch to learn single-atom features without local aggregation, apart from message-passing steps. We verify that this novel structure can improve the model performance. The proposed model outperforms other recent models with sparser representations. Our experimental results indicate that, in the chemical property prediction tasks, the diverse chemical nature of targets should be carefully considered for both model performance and generalizability. Finally, we provide the intuitive analysis between the experimental results and the chemical meaning of the target.

9 October 2023 in ACS Omega
Verified
Journal Article
Open access
BKBumju Kwak
Bumju Kwak
JPJiwon Park
Jiwon Park
TKTaewon Kang
Taewon Kang
JJJeonghee Jo
Jeonghee Jo
BLByunghan Lee
Byunghan Lee
SYSungroh Yoon
Sungroh Yoon
In recent years, molecular representation learning has emerged as a key area of focus in various chemical tasks. However, many existing models fail to fully consider the geometric information on molecular structures, resulting in less intuitive representations. Moreover, the widely used message passing mechanism is limited to providing the interpretation of experimental results from a chemical perspective. To address these challenges, we introduce a novel transformer-based framework for molecular representation learning, named the geometry-aware transformer (GeoT). The GeoT learns molecular graph structures through attention-based mechanisms specifically designed to offer reliable interpretability as well as molecular property prediction. Consequently, the GeoT can generate attention maps of the interatomic relationships associated with training objectives. In addition, the GeoT demonstrates performance comparable to that of MPNN-based models while achieving reduced computational complexity. Our comprehensive experiments, including an empirical simulation, reveal that the GeoT effectively learns chemical insights into molecular structures, bridging the gap between artificial intelligence and molecular sciences.

21 June 2023 in Frontiers in Cardiovascular Medicine
Verified
Journal Article
Open access
HLHeesun Lee
Heesun Lee
BKBong Gyun Kang
Bong Gyun Kang
JJJeonghee Jo
Jeonghee Jo
HPHyo Eun Park
Hyo Eun Park
SYSungroh Yoon
Sungroh Yoon
MKMin Joo Kim
Min Joo Kim
Background: Although coronary computed tomography angiography (CCTA) is currently utilized as the frontline test to accurately diagnose coronary artery disease (CAD) in clinical practice, there are still debates regarding its use as a screening tool for the asymptomatic population. Using deep learning (DL), we sought to develop a prediction model for significant coronary artery stenosis on CCTA and identify the individuals who would benefit from undergoing CCTA among apparently healthy asymptomatic adults.Methods: We retrospectively reviewed 11,180 individuals who underwent CCTA as part of routine health check-ups between 2012 and 2019. The main outcome was the presence of coronary artery stenosis of ≥70% on CCTA. We developed a prediction model using machine learning (ML), including DL. Its performance was compared with pretest probabilities, including the pooled cohort equation (PCE), CAD consortium, and updated Diamond-Forrester (UDF) scores.Results: In the cohort of 11,180 apparently healthy asymptomatic individuals (mean age 56.1 years; men 69.8%), 516 (4.6%) presented with significant coronary artery stenosis on CCTA. Among the ML methods employed, a neural network with multi-task learning (19 selected features), one of the DL methods, was selected due to its superior performance, with an area under the curve (AUC) of 0.782 and a high diagnostic accuracy of 71.6%. Our DL-based model demonstrated a better prediction than the PCE (AUC, 0.719), CAD consortium score (AUC, 0.696), and UDF score (AUC, 0.705). Age, sex, HbA1c, and HDL cholesterol were highly ranked features. Personal education and monthly income levels were also included as important features of the model.Conclusion: We successfully developed the neural network with multi-task learning for the detection of CCTA-derived stenosis of ≥70% in asymptomatic populations. Our findings suggest that this model may provide more precise indications for the use of CCTA as a screening tool to identify individuals at a higher risk, even in asymptomatic populations, in clinical practice.

25 August 2025 in Journal of Chemical Theory and Computation
Verified
Journal Article
Open access
BKBumju Kwak
Bumju Kwak
JJJeonghee Jo
Jeonghee Jo
Recent equivariant models embed a molecule as a set of atoms fixed in three-dimensional space, which is analogous to a ball-and-stick view. This perspective provides a concise view of molecular configurations; however, these representations may be limited in incorporating the surrounding environments of atomic nuclei, including electron configurations. To overcome this limitation, we propose neural polarization (NP), a novel method that extends equivariant networks by embedding each atom as a pair of an atom and virtual points. Motivated by electron density configurations, NP represents each atom as a pair comprising the original fixed atom and a virtual atom whose position is updated through parameterization during model training. NP can be flexibly applied to most types of existing equivariant models. We showed that NP can improve the prediction performance of existing models over a wide range of targets, including electron density. Our experimental results on various benchmarks suggest new insights, indicating that the extended atomic representations can improve the overall molecular tasks.

28 November 2025 in Pharmacology Research & Perspectives
Verified
Journal Article
Open access
MCMun Young Chang
Mun Young Chang
JJJeonghee Jo
Jeonghee Jo
JAJunyong Ahn
Junyong Ahn
BKBong Gyun Kang
Bong Gyun Kang
SNSun Mo Nam
Sun Mo Nam
SYSungroh Yoon
Sungroh Yoon
We developed a computational model, called “Unbiased microRNA–disease association predictor (UBMDA),” to predict microRNA–disease associations. UBMDA has two major differences from those reported previously. First, we did not apply a similarity‐based feature extraction method, which is the main basis of previous studies. Instead, we used International Classification of Diseases 11th Revision disease codes and microRNA nucleotide sequences as input features. Thus, UBMDA can be applied to newly discovered or poorly studied microRNAs and diseases. Second, we constructed an appropriate negative sample dataset. A positive sample dataset consisting of microRNAs and diseases pairs with proven associations between microRNAs and diseases is publicly available. However, datasets reporting no associations between microRNAs and diseases are rare. Therefore, a negative sample dataset was created by combining microRNAs and diseases. Because more commonly studied microRNAs and diseases are more likely to be included in the positive sample dataset, creating a negative sample dataset without taking this bias into consideration could cause an imbalance in disease and microRNA frequencies between positive and negative sample datasets, leading to biased prediction. To prevent such an imbalance, we created a negative sample dataset considering the frequency of each microRNA and disease in the positive sample dataset, such that these frequencies were similar between the negative and positive sample datasets. We successfully developed a computational model with a simple and intuitive structure. UBMDA will contribute to accelerating the development of microRNA‐related biomarkers and therapeutics.

28 June 2023 in arXiv
Verified
Preprint
Open access
PDF file
BKBumju Kwak
Bumju Kwak
JPJiwon Park
Jiwon Park
TKTaewon Kang
Taewon Kang
JJJeonghee Jo
Jeonghee Jo
BLByunghan Lee
Byunghan Lee
SYSungroh Yoon
Sungroh Yoon
In recent years, molecular representation learning has emerged as a key area of focus in various chemical tasks. However, many existing models fail to fully consider the geometric information of molecular structures, resulting in less intuitive representations. Moreover, the widely used message-passing mechanism is limited to provide the interpretation of experimental results from a chemical perspective. To address these challenges, we introduce a novel Transformer-based framework for molecular representation learning, named the Geometry-aware Transformer (GeoT). GeoT learns molecular graph structures through attention-based mechanisms specifically designed to offer reliable interpretability, as well as molecular property prediction. Consequently, GeoT can generate attention maps of interatomic relationships associated with training objectives. In addition, GeoT demonstrates comparable performance to MPNN-based models while achieving reduced computational complexity. Our comprehensive experiments, including an empirical simulation, reveal that GeoT effectively learns the chemical insights into molecular structures, bridging the gap between artificial intelligence and molecular sciences.