Multiple sclerosis is an autoimmune disease that causes psychological impacts and severe physical disabilities, including motor disabilities and partial blindness. This work introduces an early detection method for multiple sclerosis disease by analyzing transcriptomic microRNA data. By transforming this phenotype classification problem into a text mining problem, multiple sclerosis disease biomarkers can be obtained. To our knowledge, text mining methods have not been introduced previously in transcriptomic data analysis of multiple sclerosis disease. Hence, this work presents a complete predictive model by combining consecutive transcriptomic data preprocessing procedures, followed by the proposed KmerFIDF method as a feature extraction method and linear discriminant analysis for dimensionality reduction. Predictive machine learning methods can then be obtained accordingly. This study describes experimental work on a transcriptomic dataset of noncoding microRNA sequences denoted from relapsing-remitting multiple sclerosis patients before fingolimod treatment and after six consecutive months of treatment. The experimental results of the predictive methods with the proposed model report sensitivity, specificity, F1-score, and average accuracy scores of 96.4, 96.47, 95.6, and 97% with random forest, 92.89, 92.78, 93.2, and 94% with support vector machine and 91.95, 92.2, 93.1, and 94% with logistic regression, respectively. These promising results support the introduced model and the proposed KmerFIDF method in transcriptomic data analysis. Moreover, comparative experiments are conducted with two referenced studies. The obtained results show that the average reported accuracy scores of the proposed model outperform the referenced literature work.

Thanks to high-throughput data technology, microRNA analysis studies have evolved in early disease detection. This work introduces two complete models to detect the biomarkers of two autoimmune diseases, multiple sclerosis and rheumatoid arthritis, via miRNA analysis. Based on work the authors published previously, both introduced models involve complete pipelines of text mining methods, integrated with traditional machine learning methods, and LSTM deep learning. This work also studies the fragmentation of miRNA sequences to reduce the needed processing time and computational power. Moreover, this work studies the impact of obtaining two different library preparation kits (NEBNEXT and NEXTFLEX) on the detection accuracy for rheumatoid arthritis. Additional experiments are applied to the proposed models based on three different transcriptomic datasets. The results denote that the transcriptomic fragmentation model reported a biomarker detection accuracy of 96.45% on a sequence fragment size of 0.2, indicating a significant reduction in execution power while retaining biomarker detection accuracy. On the other hand, the LSTM model obtained a promising detection accuracy of 72%, implying savings in feature engineering processing. Additionally, the fragmentation model and the LSTM model reported 22.4% and 87.5% less execution time than work in the literature, respectively, denoting a considerable execution power reduction.

Background: Graph attention networks (GATs) are increasingly applied to transcriptomic data because they integrate gene-network structure while producing attention weights that are often interpreted as indicators of biological importance. However, whether attention-derived explanations reliably reflect biologically meaningful signals has received little systematic evaluation, particularly in the small, heterogeneous cohorts common in psychiatric transcriptomics. Methods: We systematically re-evaluated a GAT using peripheral blood RNA-sequencing data from 76 individuals (39 ADHD, 37 controls), including 16 discordant monozygotic twin pairs. To maximize analytical rigor, we implemented a leakage-aware pipeline, incorporating twin-aware group-stratified cross-validation, fold-wise gene selection, corrected transcript-to-gene mapping, and validation through repeated cross-validation, permutation testing, three complementary feature-importance methods, orthogonal differential-expression and pathway analyses, and data-quality controls. Results: Across 20 repeated cross-validation splits, GAT achieved a slightly higher mean AUC than a graph convolutional network (mean AUC 0.624 vs. 0.599) and outperformed five classical machine-learning models on a prespecified split. However, GAT performance was not statistically distinguishable from a rigorously matched permutation-derived null distribution (p = 0.327), while an exploratory sample-size calculation indicated that roughly twice the current sample size would be needed to detect an effect this size at conventional power. Independent validation analyses converged on the same conclusion: attention-derived gene rankings were significantly negatively correlated with both SHAP and permutation importance, whereas differential-expression analyses---including discordant twin-pair comparisons---and pathway enrichment identified no reproducible biological signals after multiple-testing correction. Recovery of established co-expression modules and the absence of blood-cell marker differences supported pipeline validity. Conclusions: Graph-based models may show modest predictive gains, but predictive performance and biological interpretation are distinct scientific questions. Our findings demonstrate that attention-derived importance should be regarded as hypothesis-generating rather than mechanistic evidence unless independently validated, illustrating why rigorous, multi-level validation is essential before biological conclusions are drawn from graph neural networks in transcriptomic research.