EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

In Silico Modeling of Transcriptomic Signatures in Alzheimer’s Disease: A Leakage-Controlled Machine Learning Framework for Candidate Biomarker Discovery

Emine Güven, Khalid Saad Alharbi, Sattam Khulaif Alenezi, Tariq G. Alsahli, Sümeyya Arıkan Akgün, Ayfer Koyuncu, Muhammad Afzal

Current Issues in Molecular Biology · 19.11.2026 · 48 (11) · 1251

DOI: 10.3390/cimb48111251 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Current Issues in Molecular Biology, online erschienen am 19.11.2026. Verfasst von Emine Güven und 6 weiteren Autor:innen. Die Arbeit nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Alzheimer’s disease (AD) presents a critical global health challenge requiring reliable candidate predictive features and molecular signatures. In this study, we established a leakage-controlled, transcriptomics-guided in silico machine learning framework using post-mortem brain RNA sequencing datasets. The GSE125583 dataset (N = 288) was partitioned into training (n = 231) and internal testing (n = 57) sets via a subject-aware split, while an independent external validation cohort, GSE153873 (RNA-seq, N = 30), served exclusively for external model validation. To directly evaluate classifier capacity and feature-space sensitivity, we also validated on microarray data from GSE109887 (N = 78), benchmarking models across candidate gene dimensions (top 30 and 300 DEGs). Differential expression analysis performed strictly within the training data of each outer cross-validation fold identified a compact 30-gene candidate signature. Six machine learning algorithms—GLMNET, Support Vector Machines (SVM), Partial Least Squares (PLS), Random Forest (RF), Gradient Boosting Machine (GBM), and Neural Networks (NNET)—were trained using subject-grouped 10-fold outer/5-fold inner nested cross-validation. On the primary external RNA-seq cohort, GLMNET achieved high discrimination (AUC = 0.954), while an equal-weighted GLMNET + GBM ensemble demonstrated consistent cross-cohort performance (AUC = 0.954) using frozen, out-of-fold Youden J-based decision thresholds. Cross-platform validation on the microarray cohort revealed that while regularized linear models and neural networks generalized robustly (AUC = 0.826–0.895), tree-based ensembles exhibited severe sensitivity to expanded feature spaces. Feature importance analysis consistently prioritized key candidate predictive features, including RIPOR3, PPEF1, PPARGC1A-AS1, GABRR2, and LOC100129316. Functional enrichment linked upregulated genes to extracellular matrix remodeling and focal adhesion, whereas downregulated genes mapped to mitochondrial ATP production, oxidative phosphorylation, and GABAergic neurotransmission. Overall, this leakage-controlled, biologically informed in silico framework provides a reproducible strategy for evaluating transcriptomic features for AD classification and identifies candidate predictive features that warrant validation in larger independent cohorts.

Zitieren

APA

Güven, E., Alharbi, K. S., Alenezi, S. K., Alsahli, T. G., Akgün, S. A., Koyuncu, A., & Afzal, M. (2026). In Silico Modeling of Transcriptomic Signatures in Alzheimer’s Disease: A Leakage-Controlled Machine Learning Framework for Candidate Biomarker Discovery. Current Issues in Molecular Biology, 48(11), 1251. https://doi.org/10.3390/cimb48111251

Vancouver

Güven E, Alharbi KS, Alenezi SK, Alsahli TG, Akgün SA, Koyuncu A, et al. In Silico Modeling of Transcriptomic Signatures in Alzheimer’s Disease: A Leakage-Controlled Machine Learning Framework for Candidate Biomarker Discovery. Current Issues in Molecular Biology. 2026;48(11):1251. doi:10.3390/cimb48111251

BibTeX
@article{Gven2026,
  author = {Güven, Emine and Alharbi, Khalid Saad and Alenezi, Sattam Khulaif and Alsahli, Tariq G. and Akgün, Sümeyya Arıkan and Koyuncu, Ayfer and Afzal, Muhammad},
  title = {In Silico Modeling of Transcriptomic Signatures in Alzheimer’s Disease: A Leakage-Controlled Machine Learning Framework for Candidate Biomarker Discovery},
  journal = {Current Issues in Molecular Biology},
  year = {2026},
  volume = {48},
  number = {11},
  pages = {1251},
  doi = {10.3390/cimb48111251}
}
Kostenlos starten →