Explainable Artificial Intelligence to Unveil Patterns of Antioxidant Peptides for Free Radical Regulation.
- 1Departamento de Química, Pontifícia Universidade Católica do Rio de Janeiro, Rio de Janeiro, RJ22453-900Brazil.
Abstract
Antioxidant peptides are emerging as promising therapeutic and nutraceutical agents because of their capacity to neutralize free radicals, modulate oxidative stress, and contribute to disease prevention in fields ranging from oncology to dermatology and food science. However, traditional computational approaches often fail to capture the biochemical semantics and evolutionary context of peptide sequences, limiting the predictive accuracy and mechanistic interpretability. Here, we present an explainable deep learning framework integrating evolutionary scale modeling (ESM) embeddings with a temporal convolutional network (TCN) and long short-term memory (LSTM) architecture to classify antioxidant peptides and uncover key sequence determinants of activity. ESM embeddings provide rich evolutionary and structural priors, enabling the model to capture both local k-mer motifs and global sequence dependencies. To ensure transparency, we employed a multimethod interpretability strategy using Anchor, LIME, and SHAP, which identified robust, potentially biologically meaningful hypotheses containing residues rich in cysteine (C), arginine (R), lysine (K), histidine (H), aspartic acid (D), glutamic acid (E), threonine (T), glutamine (Q), proline (P), methionine (M), tyrosine (Y), and tryptophan (W) as central to antioxidant activity. Anchor offered deterministic, high-precision motif rules, while LIME and SHAP highlighted redundant and context-dependent contributions, together forming a layered interpretability framework. This study not only achieves state-of-the-art classification performance but also bridges black-box modeling and biochemical understanding, offering a generalizable, hypothesis-generating platform for rational peptide design and discovery that is important in human health.
Related
- Explainable artificial intelligence (XAI) in schizophrenia: enhancing transparency in clinical decision-making
- Explainable/interpretable artificial intelligence and knowledge graph neural network for synthetic lethality prediction: overview, challenges, and future directions
- Hantavirus species detection from viral genome sequences using explainable artificial intelligence techniques
- Unraveling the role of RDM1 in head and neck squamous cell carcinoma: insights into DDR regulation and antioxidant response
- Diverse patterns of transcriptional regulation and epigenetic reprogramming within PMDs contribute to ESCC progression by regulating EMT and immunosuppression.
BibTeX
@article{schneider2026explainable,
title = {{Explainable Artificial Intelligence to Unveil Patterns of Antioxidant Peptides for Free Radical Regulation.}},
author = {Maria Carolina J A Schneider and Bárbara Saraiva Souza and Leonardo Vasconcelos Ferreira and Marina Geisiely Damaso and André Silva Pimentel},
journal = {Journal of chemical information and modeling},
year = {2026},
month = oct,
doi = {10.1021/acs.jcim.6c01872},
url = {https://europepmc.org/article/MED/42912901},
note = {CC BY},
}
RIS
TY - JOUR
TI - Explainable Artificial Intelligence to Unveil Patterns of Antioxidant Peptides for Free Radical Regulation.
AU - Maria Carolina J A Schneider
AU - Bárbara Saraiva Souza
AU - Leonardo Vasconcelos Ferreira
AU - Marina Geisiely Damaso
AU - André Silva Pimentel
PY - 2026
DA - 2026/10/01
JO - Journal of chemical information and modeling
DO - 10.1021/acs.jcim.6c01872
UR - https://europepmc.org/article/MED/42912901
AB - Antioxidant peptides are emerging as promising therapeutic and nutraceutical agents because of their capacity to neutralize free radicals, modulate oxidative stress, and contribute to disease prevention in fields ranging from oncology to dermatology and food science. However, traditional computational approaches often fail to capture the biochemical semantics and evolutionary context of peptide sequences, limiting the predictive accuracy and mechanistic interpretability. Here, we present an explainable deep learning framework integrating evolutionary scale modeling (ESM) embeddings with a temporal convolutional network (TCN) and long short-term memory (LSTM) architecture to classify antioxidant peptides and uncover key sequence determinants of activity. ESM embeddings provide rich evolutionary and structural priors, enabling the model to capture both local k-mer motifs and global sequence dependencies. To ensure transparency, we employed a multimethod interpretability strategy using Anchor, LIME, and SHAP, which identified robust, potentially biologically meaningful hypotheses containing residues rich in cysteine (C), arginine (R), lysine (K), histidine (H), aspartic acid (D), glutamic acid (E), threonine (T), glutamine (Q), proline (P), methionine (M), tyrosine (Y), and tryptophan (W) as central to antioxidant activity. Anchor offered deterministic, high-precision motif rules, while LIME and SHAP highlighted redundant and context-dependent contributions, together forming a layered interpretability framework. This study not only achieves state-of-the-art classification performance but also bridges black-box modeling and biochemical understanding, offering a generalizable, hypothesis-generating platform for rational peptide design and discovery that is important in human health.
SN - 1549-9596
SN - 1549-960X
ER -