Multi-Omics Fusion and Deep Feature Selection for Precision DrugDisease Association Prediction
International Journal of Drug Delivery Technology · 02.06.2026 · 16 (44s)
DOI: 10.25258/ijddt.16.44s.36 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Drug Delivery Technology, online erschienen am 02.06.2026. Verfasst von Kanyakumari K T und 1 weiteren Autor:innen.
Abstract (Originalsprache)
Drug repositioning offers a cost-effective strategy to accelerate therapeutic discovery by identifying new indications for existing compounds. In this study, we present a hybrid framework that integrates text-based biomedical features with swarm intelligence-driven dimensionality reduction and deep learning. A curated dataset of drug characteristics was processed using TF-IDF embeddings, followed by Binary Particle Swarm Optimization (PSO), which reduced the feature space from 592 to 377 dimensions. Comparative benchmarking of Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks demonstrated the superiority of CNN, achieving 74.40% accuracy, 74.77% precision, 74.62% recall, and 74.39% F1-score, compared to LSTM's 48.80% accuracy. These findings highlight the potential of swarm-based feature selection combined with deep learning for drug-disease association prediction, establishing a pathway toward multi-omics fusion in precision medicine.
Zitieren
APA
T, K. K., & Veerappa, B. N. (2026). Multi-Omics Fusion and Deep Feature Selection for Precision DrugDisease Association Prediction. International Journal of Drug Delivery Technology, 16(44s). https://doi.org/10.25258/ijddt.16.44s.36
Vancouver
T KK, Veerappa BN. Multi-Omics Fusion and Deep Feature Selection for Precision DrugDisease Association Prediction. International Journal of Drug Delivery Technology. 2026;16(44s). doi:10.25258/ijddt.16.44s.36
BibTeX
@article{T2026,
author = {T, Kanyakumari K and Veerappa, B N},
title = {Multi-Omics Fusion and Deep Feature Selection for Precision DrugDisease Association Prediction},
journal = {International Journal of Drug Delivery Technology},
year = {2026},
volume = {16},
number = {44s},
doi = {10.25258/ijddt.16.44s.36}
}
EUVIMED