{
  "abstract": "Background and Objective: The classification of RNA sequencing (RNA-seq) data presents a fundamental challenge in computational biomedicine: raw read counts are high-dimensional, over-dispersed, and heteroscedastic, requiring careful preprocessing before machine learning models can be applied. Existing deep learning approaches for RNA-seq classification have largely overlooked the tabular nature of genomic expression data and have offered limited embedded interpretability. This study proposes TabNet, an attentive interpretable tabular learning architecture, as a framework for miRNA-based disease classification and evaluates its performance and interpretability against three established baseline models.\n\nMethods: Two publicly available miRNA expression datasets were examined: a cervical cancer cohort (58 samples, 714 miRNAs) and an Alzheimer's disease cohort (70 samples, 503 miRNAs). Raw count data were preprocessed following the MLSeq framework, encompassing DESeq median-ratio normalisation, near-zero variance filtering, supervised gene ranking based on DESeq differential expression analysis, and the DESeq variance-stabilising transformation (vst). Gene subsets corresponding to 5%, 10%, and 30% of the post-filtering feature space were evaluated. TabNet was benchmarked against eight baselines spanning four learning paradigms: a 1D Convolutional Neural Network (CNN), a Long Short-Term Memory network (LSTM), Extreme Gradient Boosting (XGBoost), Random Forest, ElasticNet-regularised logistic regression, a Multi-Layer Perceptron (MLP), the prior-fitted transformer TabPFN, and the inherently interpretable Explainable Boosting Machine (EBM). Each configuration was assessed over 50 independent random train/test splits (70%/30%) under a strict leakage-free protocol in which all preprocessing, hyperparameter selection, and early stopping relied exclusively on inner validation subsets of the training partitions; all metrics are reported as mean ± ± SD.\n\nResults: Under the leakage-free protocol, a group of four methods reached a statistically indistinguishable accuracy ceiling: on the cervical cancer dataset, ElasticNet (95.06% ± ± 4.66), EBM (94.94% ± ± 4.60), TabPFN (94.71% ± ± 4.64), and Random Forest (94.35% ± ± 5.82); on the Alzheimer's disease dataset, TabPFN (70.86% ± ± 10.26), EBM (70.67% ± ± 12.67), and ElasticNet (70.48% ± ± 9.76) led. TabNet reached 85.18% ± ± 11.10 (cervical) and 64.38% ± ± 11.23 (Alzheimer's) at its respective best levels -- below the top tier, but with the distinctive property of producing sparse, instance-level attention explanations as part of its forward computation. Supplementary analyses showed that self-supervised pre-training conferred no significant benefit at these cohort sizes, that results were robust to the choice between supervised differential-expression and unsupervised variance feature ranking, and that instance-level attention patterns varied substantially across splits, supporting their use as illustrative rather than confirmatory evidence.\n\nConclusions: In rigorously leakage-controlled small-cohort miRNA classification, strongly regularised classical models, glass-box additive models, and prior-fitted transformers converge to the same accuracy ceiling, and no evaluated method -- including attention-based deep learning -- surpasses it. Within this landscape, TabNet remains distinctive as the only evaluated deep architecture whose sequential attention mechanism produces sparse instance-level miRNA attributions as an inherent part of prediction, offering a trade-off between embedded interpretability and a moderate accuracy cost that we quantify precisely. These results argue for protocol-first evaluation and calibrated claims when deep tabular models are applied to small transcriptomic cohorts.",
  "abstract_shown": true,
  "affiliations": [
    "Department of Computer Engineering, Hasan Kalyoncu University, Gaziantep, 27020 Turkey",
    "Department of Computer Engineering, Gaziantep University, Gaziantep, 27310 Turkey"
  ],
  "article_type": "research article",
  "arxiv": null,
  "author_total": 3,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Hilal Haznedar",
      "orcid": "0009-0002-2783-1210"
    },
    {
      "affs": [
        1
      ],
      "name": "Gözde Özsert Yiğit",
      "orcid": "0000-0002-8871-6024"
    },
    {
      "affs": [
        1
      ],
      "name": "Bülent Haznedar",
      "orcid": "0000-0003-0692-9921"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/3pv7jferkhz8a.bib",
  "cited_by": 0,
  "doi": "10.1186/s12859-026-06706-7",
  "fulltext_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC13737494/",
  "id": "3pv7jferkhz8a",
  "issns": [
    "1471-2105"
  ],
  "landing_url": "https://doi.org/10.1186/s12859-026-06706-7",
  "language": "en",
  "licence": "CC-BY-NC-ND-4.0",
  "licence_label": "CC BY-NC-ND 4.0",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by-nc-nd/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "heading",
      "Research"
    ],
    [
      "openalex",
      "1312|Gene expression and cancer classification"
    ]
  ],
  "openalex": "W7223948501",
  "pdf_url": null,
  "pmcid": "PMC13737494",
  "pmid": "42989092",
  "published": "2026-10-27",
  "publisher": "BMC",
  "ris": "https://research.draconitic.com/paper/3pv7jferkhz8a.ris",
  "sources": [
    {
      "first_seen": "2026-11-09T12:22:39Z",
      "native_id": "PMC13737494",
      "source": "pmc",
      "url": "https://doi.org/10.1186/s12859-026-06706-7"
    }
  ],
  "subjects": [
    {
      "field": "biochemistry",
      "origin": "openalex:1312|Gene expression and cancer classification",
      "subfield": "molecular-biology"
    }
  ],
  "title": "Attentive interpretable tabular learning (TabNet) for miRNA expression classification in cervical cancer and Alzheimer's disease",
  "title_text": "Attentive interpretable tabular learning (TabNet) for miRNA expression classification in cervical cancer and Alzheimer's disease",
  "type": "peer-reviewed",
  "updated_at": "2026-11-09T12:22:39Z",
  "url": "https://research.draconitic.com/paper/3pv7jferkhz8a",
  "venue": "BMC Bioinformatics",
  "versions": []
}