ATTNSOM: learning cross-isoform attention for cytochrome P450 site-of-metabolism prediction
Bioinformatics · 2026
DOI: 10.1093/bioinformatics/btag314 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioinformatics, 2026. Verfasst von Hajung Kim und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science and Engineering, Korea University, Seoul, 02841, South Korea. Hauptthemen laut MEDLINE: Cytochrome P-450 Enzyme System, Computational Biology, Software. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Research Foundation of Korea, Ministry of Science and ICT, Ministry of Education.
Abstract (Originalsprache)
Motivation Identifying metabolic sites where cytochrome P450 enzymes metabolize small-molecule drugs is essential for drug discovery. Although existing computational approaches have been proposed for site-of-metabolism prediction, they typically ignore cytochrome P450 isoform identity or model isoforms independently, thereby failing to fully capture inherent cross-isoform metabolic patterns. In addition, prior evaluations often rely on top-k metrics, where false positive atoms may be included among the top predictions, underscoring the need for complementary metrics that more directly assess binary atom-level discrimination under severe class imbalance. Results We propose ATTNSOM, an atom-level site-of-metabolism prediction framework that integrates intrinsic molecular reactivity with cross-isoform relationships. The model combines a shared graph encoder, molecule-conditioned atom representations, and a cross-attention mechanism to capture correlated metabolic patterns across cytochrome P450 isoforms. The model is evaluated on two benchmark datasets annotated with site-of-metabolism labels at atom resolution. Across these benchmarks, the model achieves consistently strong top-k performance across multiple cytochrome P450 isoforms. Relative to ablated variants, the model yields higher Matthews correlation coefficient, indicating improved discrimination of true metabolic sites. These results support the importance of explicitly modeling cross-isoform relationships for site-of-metabolism prediction. Availability and implementation The code and datasets are available at https://github.com/dmis-lab/ATTNSOM.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- Department of Computer Science and Engineering, Korea University, Seoul, 02841, South Korea.
- AIGEN Sciences, Seoul, 04778, South Korea.
ORCID-Profile: Hajung Kim, Jaewoo Kang
Förderung
- National Research Foundation of Korea
- Ministry of Science and ICT
- Ministry of Education
- Korea Machine Learning Ledger Orchestration for Drug Discovery
- Ministry of Health and Welfare
- Republic of Korea
Zitieren
APA
Kim, H., Lee, E., Chung, S., Park, J., Baek, S., & Kang, J. (2026). ATTNSOM: learning cross-isoform attention for cytochrome P450 site-of-metabolism prediction. Bioinformatics. https://doi.org/10.1093/bioinformatics/btag314
Vancouver
Kim H, Lee E, Chung S, Park J, Baek S, Kang J. ATTNSOM: learning cross-isoform attention for cytochrome P450 site-of-metabolism prediction. Bioinformatics. 2026. doi:10.1093/bioinformatics/btag314
BibTeX
@article{Kim2026,
author = {Kim, Hajung and Lee, Eunha and Chung, Sohyun and Park, Jueon and Baek, Seungheun and Kang, Jaewoo},
title = {ATTNSOM: learning cross-isoform attention for cytochrome P450 site-of-metabolism prediction},
journal = {Bioinformatics},
year = {2026},
doi = {10.1093/bioinformatics/btag314}
}
EUVIMED