Mogan Gim

Mogan Gim

Auto-generated profile, based on publicly available information

Mogan Gim

Hankuk University of Foreign Studies, Yongin, Republic of Korea

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
1 June 2023 in Bioinformatics
Verified
Journal Article
Open access
PDF file
MGMogan Gim
Mogan Gim
JCJunseok Choe
Junseok Choe
SBSeungheun Baek
Seungheun Baek
JPJueon Park
Jueon Park
CLChaeeun Lee
Chaeeun Lee
JKJaewoo Kang
Jaewoo Kang
Motivation: Protein–ligand binding affinity prediction is a central task in drug design and development. Cross-modal attention mechanism has recently become a core component of many deep learning models due to its potential to improve model explainability. Non-covalent interactions (NCIs), one of the most critical domain knowledge in binding affinity prediction task, should be incorporated into protein–ligand attention mechanism for more explainable deep drug–target interaction models. We propose ArkDTA, a novel deep neural architecture for explainable binding affinity prediction guided by NCIs. Results: Experimental results show that ArkDTA achieves predictive performance comparable to current state-of-the-art models while significantly improving model explainability. Qualitative investigation into our novel attention mechanism reveals that ArkDTA can identify potential regions for NCIs between candidate drug compounds and target proteins, as well as guiding internal operations of the model in a more interpretable and domain-aware manner. Availability: ArkDTA is available at https://github.com/dmis-lab/ArkDTA Contact: kangj@korea.ac.kr

14 October 2021 in IEEE Access
Verified
Journal Article
Open access
MGMogan Gim
Mogan Gim
DPDonghyeon Park
Donghyeon Park
MSMichael Spranger
Michael Spranger
KMKana Maruyama
Kana Maruyama
JKJaewoo Kang
Jaewoo Kang
Countless possibilities of recipe combinations challenge us to determine which additional ingredient goes well with others. In this work, we propose RecipeBowl which is a cooking recommendation system that takes a set of ingredients and cooking tags as input and suggests possible ingredient and recipe choices. We formulate a recipe completion task to train RecipeBowl on our constructed dataset where the model predicts a target ingredient previously eliminated from the original recipe. The RecipeBowl consists of a set encoder and a 2-way decoder for prediction. For the set encoder, we utilize the Set Transformer that builds meaningful set representations. Overall, our model builds a set representation of an leave-one-out recipe and maps it to the ingredient and recipe embedding space. Experimental results demonstrate the effectiveness of our approach. Furthermore, analysis on model predictions and interpretations show interesting insights related to cooking knowledge.

6 April 2023 in Expert Systems with Applications
Verified
Journal Article
Closed access
DCDonghee Choi
Donghee Choi
MGMogan Gim
Mogan Gim
SBSamy Badreddine
Samy Badreddine
HKHajung Kim
Hajung Kim
DPDonghyeon Park
Donghyeon Park
JKJaewoo Kang
Jaewoo Kang

21 October 2024
Verified
Conference Paper
Open access
HKHeedou Kim
Heedou Kim
DKDain Kim
Dain Kim
JLJiwoo Lee
Jiwoo Lee
CYChanwoong Yoon
Chanwoong Yoon
DCDonghee Choi
Donghee Choi
JKJaewoo Kang
Jaewoo Kang
Crime situations are race against time. An AI-assisted criminal investigation system, providing prompt but precise legal counsel is in need for police officers. We introduce LAPIS (Language Model Augmented Police Investigation System), an automated system that assists police officers to perform rational and legal investigative actions. We constructed a finetuning dataset and retrieval knowledgebase specialized in crime investigation legal reasoning task. We extended the dataset's quality by incorporating manual curation efforts done by a group of domain experts. We then finetuned the pretrained weights of a smaller Korean language model to the newly constructed dataset and integrated it with the crime investigation knowledgebase retrieval approach. Experimental results show LAPIS' potential in providing reliable legal guidance for police officers, even better than the proprietary GPT-4 model. Qualitative analysis on the rationales generated by LAPIS demonstrate the model's reasoning ability to leverage the premises and derive legally correct conclusions.

13 June 2023 in IEEE Access
Verified
Journal Article
Open access
JKJinkyu Kim
Jinkyu Kim
DCDonghee Choi
Donghee Choi
MGMogan Gim
Mogan Gim
JKJaewoo Kang
Jaewoo Kang
Multi-asset portfolio selection is an asset allocation strategy involving a variety of assets. Adaptive investment strategies which consider the dynamic market characteristics of individual assets and asset classes are vital for maximizing returns and minimizing risks. We introduce HADAPS , a novel computational method for multi-asset portfolio selection which utilizes the Soft-Actor-Critic (SAC) framework enhanced with Hierarchical Policy Network. Contrary to previous approaches that have relied on heuristics for constructing asset allocations, HADAPS directly outputs a continuous vector of action values depending on current market conditions. In addition, HADAPS performs multi-asset portfolio selection involving multiple asset classes. Experimental results show that HADAPS outperforms baseline approaches in not only cumulative returns but also risk-adjusted metrics. These results are based on market price data from sectors with various behavioral characteristics. Furthermore, qualitative analysis shows HADAPS ’ ability to adaptively shift portfolio selection strategies in dynamic market conditions where asset classes and different assets are uncorrelated to each other.

10 November 2025
Verified
Conference Paper
Open access
JKJinkyu Kim
Jinkyu Kim
HYHyungjung Yi
Hyungjung Yi
MGMogan Gim
Mogan Gim
DCDonghee Choi
Donghee Choi
JKJaewoo Kang
Jaewoo Kang