CONFERENCES
2025
2.
Subhin Seomun; Sunyong Yoo
Abstract | Links | BibTeX | Tags: ADME, Bioinformatics, Deep learning
@conference{Seomun2025,
title = {Cross-species multi-task learning with molecular and ADME descriptors for liver microsomal metabolic stability},
author = {Subhin Seomun and Sunyong Yoo},
url = {https://bmil.jnu.ac.kr/wp-content/uploads/2025/12/Subhin-Seomun-Sunyong-Yoo-Cross-species-multi-task-learning-with-molecular-and-ADME-descriptors-for-liver-microsomal-metabolic-stability.pdf},
year = {2025},
date = {2025-12-17},
urldate = {2025-12-17},
publisher = {The 19th International Conference on Data and Text Mining in Biomedical Informatics},
abstract = {Liver microsomal stability is a key determinant of in vivo compound exposure and efficacy. Although metabolic stability has been extensively studied, linking substructure destabilizing features to absorption, distribution, metabolism, and excretion (ADME) properties remains challenging. Moreover, single-species, single-modality models often generalize poorly. To address these limitations, we propose a cross-species multi-task learning framework that integrates multi-modal molecular representations to predict liver microsomal stability. Specifically, the model leverages three complementary modalities: SMILES-derived fingerprints, molecular graphs, and in silico ADME descriptors. These modalities are learned in a shared network using data from multiple species and subsequently fused via attention mechanisms to form a shared molecular representation, which captures conserved structuremetabolism relationships common across species. Species-specific network capture individual metabolic characteristics and stability predictions for human (HLM), rat (RLM), and mouse liver microsomal (MLM). Under stratified 10-fold cross-validation, mean AUROC was 0.770 ± 0.001 (HLM), 0.785 ± 0.001 (RLM), and 0.766 ± 0.001 (MLM). To understand the chemical basis of metabolic liability, we examined three multi-level perspectives. At the molecular property level, physicochemical descriptors related to enzyme interaction, permeability/transport, and the lipophilicity-polarity axis emerged as dominant predictive drivers. At the substructure level, to pinpoint specific sites of metabolic vulnerability, recurring destabilizing features were identified at alkenes and allylic/benzylic positions, while amide and carbamate carbonyl motifs conferred stability. To elucidate the underlying physicochemical mechanisms, these structural motifs were linked to systematic shifts in logP, solubility, bloodbrain barrier propensity, and efflux liability. Overall, these results indicate that the cross-species integrative model accurately predicts microsomal stability across human, rat, and mouse while providing chemically grounded explanations.},
keywords = {ADME, Bioinformatics, Deep learning},
pubstate = {published},
tppubtype = {conference}
}
Liver microsomal stability is a key determinant of in vivo compound exposure and efficacy. Although metabolic stability has been extensively studied, linking substructure destabilizing features to absorption, distribution, metabolism, and excretion (ADME) properties remains challenging. Moreover, single-species, single-modality models often generalize poorly. To address these limitations, we propose a cross-species multi-task learning framework that integrates multi-modal molecular representations to predict liver microsomal stability. Specifically, the model leverages three complementary modalities: SMILES-derived fingerprints, molecular graphs, and in silico ADME descriptors. These modalities are learned in a shared network using data from multiple species and subsequently fused via attention mechanisms to form a shared molecular representation, which captures conserved structuremetabolism relationships common across species. Species-specific network capture individual metabolic characteristics and stability predictions for human (HLM), rat (RLM), and mouse liver microsomal (MLM). Under stratified 10-fold cross-validation, mean AUROC was 0.770 ± 0.001 (HLM), 0.785 ± 0.001 (RLM), and 0.766 ± 0.001 (MLM). To understand the chemical basis of metabolic liability, we examined three multi-level perspectives. At the molecular property level, physicochemical descriptors related to enzyme interaction, permeability/transport, and the lipophilicity-polarity axis emerged as dominant predictive drivers. At the substructure level, to pinpoint specific sites of metabolic vulnerability, recurring destabilizing features were identified at alkenes and allylic/benzylic positions, while amide and carbamate carbonyl motifs conferred stability. To elucidate the underlying physicochemical mechanisms, these structural motifs were linked to systematic shifts in logP, solubility, bloodbrain barrier propensity, and efflux liability. Overall, these results indicate that the cross-species integrative model accurately predicts microsomal stability across human, rat, and mouse while providing chemically grounded explanations.
2015
1.
Moonshik Shin; Sungyoung Yoo; Suhyun Ha; Kyungrin Noh; Doheon Lee
Abstract | Links | BibTeX | Dimensions | Tags: ADME, Bioinformatics, Natural product
@conference{shin2015identifying,
title = {Identifying Potential Bioactive Compounds of Natural Products by Combining ADMET Prediction Methods},
author = {Moonshik Shin and Sungyoung Yoo and Suhyun Ha and Kyungrin Noh and Doheon Lee},
url = {https://dl.acm.org/doi/abs/10.1145/2811163.2811168},
doi = {10.1145/2811163.2811168},
year = {2015},
date = {2015-01-01},
urldate = {2015-01-01},
booktitle = {Proceedings of the ACM Ninth International Workshop on Data and Text Mining in Biomedical Informatics},
pages = {19–19},
publisher = {CIKM},
abstract = {Herbs consist of various chemical compounds. Thus, identifying potential bioactive compounds from those diversity is an important task for studies in the herb, food and natural products. Even though various computational approaches are developed for predicting bioactive compounds, the prediction performances are diverse due to different methods and dataset. Therefore, there is urgent demand for an approach that connotes the previous methods and identify potential bioactive compounds with high accuracy. To meet the demand, we proposed a filtering strategy that identifies potential bioactive compounds by combining previously developed computational methods which predict ADMET, such as Human Intestinal Absorption (HIA) and Caco-2 permeability. Our approach was evaluated on 930 compounds that are known as bioactive compounds, which were extracted from literature, DrugBank and Dr. Dukes phytochemical databases. By applying our filtering strategy, 97.5% of the known bioactive compounds were correctly predicted as bioactive. We examined whether our approach can distinguish the potential bioactive compound from the non-potential bioactive compounds with Fishers' exact test, and a reasonable p-value (3.806 x 10-9) was derived. For the next step, we are planning to develop a machine-learning based method to improve our filtering approach.},
keywords = {ADME, Bioinformatics, Natural product},
pubstate = {published},
tppubtype = {conference}
}
Herbs consist of various chemical compounds. Thus, identifying potential bioactive compounds from those diversity is an important task for studies in the herb, food and natural products. Even though various computational approaches are developed for predicting bioactive compounds, the prediction performances are diverse due to different methods and dataset. Therefore, there is urgent demand for an approach that connotes the previous methods and identify potential bioactive compounds with high accuracy. To meet the demand, we proposed a filtering strategy that identifies potential bioactive compounds by combining previously developed computational methods which predict ADMET, such as Human Intestinal Absorption (HIA) and Caco-2 permeability. Our approach was evaluated on 930 compounds that are known as bioactive compounds, which were extracted from literature, DrugBank and Dr. Dukes phytochemical databases. By applying our filtering strategy, 97.5% of the known bioactive compounds were correctly predicted as bioactive. We examined whether our approach can distinguish the potential bioactive compound from the non-potential bioactive compounds with Fishers' exact test, and a reasonable p-value (3.806 x 10-9) was derived. For the next step, we are planning to develop a machine-learning based method to improve our filtering approach.