Deep learning-based feature selection for lung adenocarcinoma classification and biomarker discovery
Bibliographic record
Abstract
Lung adenocarcinoma, a leading cause of cancer-related mortality, underscores the need for reliable diagnostic tools. This study proposes a robust multi-stage feature selection and classification framework for biomarker discovery, using the cancer genome atlas lung adenocarcinoma (TCGA-LUAD) as the primary dataset and GSE19188 for independent validation. The framework combines differential expression analysis (Wilcoxon rank-sum test), joint mutual information maximization (JMIM), and sparse autoencoder-based refinement to identify a compact and predictive set of five genes. These genes are involved in key lung cancer pathways, including epidermal growth factor receptor (EGFR) signaling, cell cycle regulation, and immune response, and include biomarkers such as surfactant protein A2 (SFTPA2), napsin an aspartic peptidase (NAPSA), and T-box transcription factor 4 (TBX4). The hybrid deep learning classifier achieved high accuracy (98.4%) and area under the receiver operating characteristic curve (AUC-ROC) (0.996) on TCGA-LUAD, with strong generalization on GSE19188 (accuracy: 96.7%, AUC-ROC: 0.993%). Overall, the framework offers an interpretable and effective solution for LUAD classification and biomarker identification.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".