Bidirectional Long Short-Term Memory (BiLSTM) Neural Networks with Conjoint Fingerprints: Application in Predicting Skin-Sensitizing Agents in Natural Compounds
Journal of Chemical Information and Modeling · 24.03.2025 · 65 (6) · 3035-3047
DOI: 10.1021/acs.jcim.5c00032 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Chemical Information and Modeling, online erschienen am 03.03.2025. Verfasst von Huynh Anh Duy und 1 weiteren Autor:innen. Beteiligte Einrichtung: Graduate School in the Program of Research and Development in Pharmaceuticals, Faculty of Pharmaceutical Sciences, Khon Kaen University, Khon Kaen 40…. Hauptthemen laut MEDLINE: Biological Products, Neural Networks, Computer, Skin. Die Arbeit wurde bisher 22-mal zitiert (Crossref) und nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: The KKU Scholarship for ASEAN and GMS Countries??? Personnel, Faculty of Pharmaceutical Science, Khon Kaen University., This research on skin sensitization prediction has received funding support from the Fundamental Fund of Khon Kaen University from National Science, Research,….
Abstract (Originalsprache)
Skin sensitization, or allergic contact dermatitis, represents a critical end point in toxicity assessment, with profound implications for drug safety and regulatory decision-making. This study aims to develop a robust deep-learning-based quantitative structure-activity relationship framework for accurately predicting skin sensitization toxicity, particularly in the context of natural-product-derived compounds. To achieve this, we explored advanced recurrent neural network architectures, including long short-term memory (LSTM), bidirectional LSTM (BiLSTM), gated recurrent unit (GRU), and bidirectional GRU, to model the intricate structure-toxicity relationships inherent in molecular compounds. We aim to optimize and improve predictive performance by training a cohort of 55 models with a diverse set of molecular fingerprints. Notably, the BiLSTM model, which integrates SMILES tokens with RDKit fingerprints, achieved superior predictive performance, underscoring its capability to effectively capture key molecular determinants of skin sensitization. An extensive applicability domain analysis coupled with an in-depth evaluation of feature importance provided new insights into the key molecular attributes that influence sensitization propensity. We further evaluated the BiLSTM model using a natural product data set, where it demonstrated exceptional generalization capabilities. The model achieved an accuracy of 86.5%, a Matthews correlation coefficient of 75.2%, a sensitivity of 100%, an area under the curve of 88%, a specificity of 75%, and an F1-score of 88.8%. Remarkably, the model effectively categorized natural products by discriminating sensitizing from non-sensitizing agents across various natural product subcategories. These results underscore the potential of BiLSTM-based models as powerful in silico tools for modern drug discovery efforts and regulatory assessments, especially in the field of natural products.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- Graduate School in the Program of Research and Development in Pharmaceuticals, Faculty of Pharmaceutical Sciences, Khon Kaen University, Khon Kaen 40002, Thailand.
- Department of Health Sciences, College of Natural Sciences, Can Tho University, Can Tho 900000, Vietnam.
- Division of Pharmaceutical Chemistry, Faculty of Pharmaceutical Sciences, Khon Kaen University, Khon Kaen 40002, Thailand.
ORCID-Profile: Tarapong Srisongkram
Förderung
- The KKU Scholarship for ASEAN and GMS Countries??? Personnel, Faculty of Pharmaceutical Science, Khon Kaen University.
- This research on skin sensitization prediction has received funding support from the Fundamental Fund of Khon Kaen University from National Science, Research,…
Zitieren
APA
Duy, H. A., & Srisongkram, T. (2025). Bidirectional Long Short-Term Memory (BiLSTM) Neural Networks with Conjoint Fingerprints: Application in Predicting Skin-Sensitizing Agents in Natural Compounds. Journal of Chemical Information and Modeling, 65(6), 3035-3047. https://doi.org/10.1021/acs.jcim.5c00032
Vancouver
Duy HA, Srisongkram T. Bidirectional Long Short-Term Memory (BiLSTM) Neural Networks with Conjoint Fingerprints: Application in Predicting Skin-Sensitizing Agents in Natural Compounds. Journal of Chemical Information and Modeling. 2025;65(6):3035-3047. doi:10.1021/acs.jcim.5c00032
BibTeX
@article{Duy2025,
author = {Duy, Huynh Anh and Srisongkram, Tarapong},
title = {Bidirectional Long Short-Term Memory (BiLSTM) Neural Networks with Conjoint Fingerprints: Application in Predicting Skin-Sensitizing Agents in Natural Compounds},
journal = {Journal of Chemical Information and Modeling},
year = {2025},
volume = {65},
number = {6},
pages = {3035--3047},
doi = {10.1021/acs.jcim.5c00032}
}
EUVIMED