ATTNSOM: Learning Cross-Isoform Attention for Cytochrome P450 Site-of-Metabolism

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Kim, Hajung, Lee, Eunha, Chung, Sohyun, Park, Jueon, Baek, Seungheun, Kang, Jaewoo
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917230201012224
author Kim, Hajung
Lee, Eunha
Chung, Sohyun
Park, Jueon
Baek, Seungheun
Kang, Jaewoo
author_facet Kim, Hajung
Lee, Eunha
Chung, Sohyun
Park, Jueon
Baek, Seungheun
Kang, Jaewoo
contents 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. 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. The code and datasets are available at https://github.com/dmis-lab/ATTNSOM.
format Preprint
id arxiv_https___arxiv_org_abs_2601_20891
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle ATTNSOM: Learning Cross-Isoform Attention for Cytochrome P450 Site-of-Metabolism
Kim, Hajung
Lee, Eunha
Chung, Sohyun
Park, Jueon
Baek, Seungheun
Kang, Jaewoo
Quantitative Methods
Machine Learning
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. 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. The code and datasets are available at https://github.com/dmis-lab/ATTNSOM.
title ATTNSOM: Learning Cross-Isoform Attention for Cytochrome P450 Site-of-Metabolism
topic Quantitative Methods
Machine Learning
url https://arxiv.org/abs/2601.20891