QSAR Modeling of Analgesic Cannabinoids via Dual Feature Selection and Support Vector Machines: A Cheminformatics Case Study
Revista Brasileira de Computação Aplicada · 29.04.2026 · 18 (1) · 23-32
DOI: 10.5335/rbca.v18i1.16853 ↗Kurz gefasst
Fachartikel in der Zeitschrift Revista Brasileira de Computação Aplicada, online erschienen am 29.04.2026. Verfasst von Rosalvo Ferreira De Oliveira Neto und 3 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
This study aimed to develop an accessible Quantitative Structure–Activity Relationship model based on Machine Learning techniques for a set of analgesic cannabinoid compounds. It represents a cheminformatics contribution to the promising field of endocannabinoid system modulation. Three-dimensional molecular structures and biological activity data were retrieved from PubChem. Molecular descriptors were calculated using Dragon7 software and subjected to variable selection through two complementary feature selection strategies: Wrapper and Filter methods. The final predictive model was constructed using Support Vector Machines and validated through both K-fold cross-validation and leave-one-out approaches. A robust and predictive model comprising 29 molecular descriptors was obtained, enabling the prediction of novel thiophenyl-acetamide analogs. The combined use of two feature selection techniques proved effective in capturing relevant molecular information and enhancing model performance. This model offers valuable support for the synthetic optimization and design of more potent cannabinoid-based analgesics.
Zitieren
APA
Neto, R. F. D. O., Filho, E. B. D. A., Ferreira, A. L. D. S., & Carvalho, D. A. P. (2026). QSAR Modeling of Analgesic Cannabinoids via Dual Feature Selection and Support Vector Machines: A Cheminformatics Case Study. Revista Brasileira de Computação Aplicada, 18(1), 23-32. https://doi.org/10.5335/rbca.v18i1.16853
Vancouver
Neto RFDO, Filho EBDA, Ferreira ALDS, Carvalho DAP. QSAR Modeling of Analgesic Cannabinoids via Dual Feature Selection and Support Vector Machines: A Cheminformatics Case Study. Revista Brasileira de Computação Aplicada. 2026;18(1):23-32. doi:10.5335/rbca.v18i1.16853
BibTeX
@article{Neto2026,
author = {Neto, Rosalvo Ferreira De Oliveira and Filho, Edilson Beserra de Alencar and Ferreira, Allysson Layr dos Santos and Carvalho, Daniel Alencar Penha},
title = {QSAR Modeling of Analgesic Cannabinoids via Dual Feature Selection and Support Vector Machines: A Cheminformatics Case Study},
journal = {Revista Brasileira de Computação Aplicada},
year = {2026},
volume = {18},
number = {1},
pages = {23--32},
doi = {10.5335/rbca.v18i1.16853}
}
EUVIMED